Snow removal decision support system and program, road management method

The snow removal decision support system addresses the challenge of predicting future operational loads by integrating operation and environmental data, enabling efficient resource allocation and decision-making for snow removal operations.

JP7953984B1Active Publication Date: 2026-11-19葛西 章史
View PDF 8 Cites 0 Cited by

Patent Information

Application Number
JP2026082651
Authority / Receiving Office
JP · JP
Patent Type
Patents
Current Assignee / Owner
Filing Date
2026-05-15
Publication Date
2026-11-19
Estimated Expiration
2046-05-15

AI Technical Summary

Technical Problem

Existing snow removal and disposal systems lack a comprehensive system to derive operational load information by associating snow removal operation information with environmental information, leading to difficulties in predicting future operational loads and making informed decisions on vehicle deployment, timing, and resource allocation.

Method used

A snow removal decision support system that acquires and analyzes snow removal operation and environmental information, including location, travel history, and weather data, to predict future operational loads and generate decision support information for vehicle deployment and resource allocation.

Benefits of technology

Enables advanced prediction of snow removal operational loads, facilitating timely and efficient deployment of resources, adjusting to varying environmental conditions, and improving snow removal operations based on real-time data and AI models.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 0007953984000001_ABST
    Figure 0007953984000001_ABST
Patent Text Reader

Abstract

In snow removal operations in snowy, cold regions, snowfall amount and snow depth alone do not adequately reflect the relationship between snow removal operations and the snow removal environment. This makes it difficult to accurately grasp the future workload and resource constraints for each route, work section, road administrator, or municipality. As a result, decisions regarding deployment timing, target sections, vehicle deployment, and snow removal commencement timing may be delayed. [Solution] Snow removal operation information, including the operating status, dispatch history, or work performance of snow removal vehicles, is associated with snow removal environment information, including the amount of snowfall, snow depth, compacted snow condition, or reduction in road width during snow removal operations. Snow removal operation load information is derived for each management unit, and this load information is applied to future snow removal environment information to calculate future snow removal operation load prediction information. Furthermore, this prediction information is compared with a standard load level, and snow removal decision support information, snow removal decision support information, or snow removal work resource allocation adjustment decision support information is generated using AI or the like.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to a technology for supporting road snow removal and disposal responses in snowy and cold regions, and in particular, by associating snow removal and disposal operation information including position information, travel history, operation status, operation history, dispatch history, or work performance of snow removal and disposal vehicles with snow removal and disposal environment information including snowfall amount information, snow depth information, air temperature information, wind speed information, snow quality information, compacted snow condition information, road shoulder snow accumulation amount information, or road width reduction information associated with accumulated snow or snow cover, derives snow removal and disposal operation load information for each route, work section, snow removal and disposal operator, road administrator, or local government, and applies the snow removal and disposal operation load information to future snow removal and disposal environment conditions indicated by future snow removal and disposal environment information, thereby relating to a snow removal and disposal decision support system, program, and road management method for calculating future snow removal and disposal operation load prediction information.

Background Art

[0002] In snowy and cold regions, in order to maintain winter road traffic functions, citizen lives, logistics, public transportation, passage of emergency vehicles, and urban functions, it is necessary to appropriately determine snow removal, snow disposal, widening snow removal, road surface leveling, deployment of snow removal and disposal vehicles, dispatch requests to snow removal and disposal operators, support deployment, mutual adjustment, redeployment, or advance deployment, in consideration of snowfall conditions, snow cover conditions, road surface conditions, road width reduction, road shoulder snow accumulation amount, compacted snow conditions, traffic conditions, operation status of snow removal and disposal vehicles, and work capacity of each snow removal and disposal operator. Conventionally, in making decisions on snow removal and disposal responses, visual patrols by road administrators or local government staff, reports from snow removal and disposal operators, report information from residents via telephone or electronic means, weather information, traffic information, position information of snow removal and disposal vehicles, daily work reports, or empirical rules of road administrators have been used. In recent years, technologies have also been proposed, including a technology for analyzing images acquired by cameras mounted on patrol vehicles using AI (Artificial Intelligence), a sensing technology for estimating snow cover conditions based on optical fiber cables laid on roads, and a technology for analyzing the content of user messages acquired via SNS (Social Networking Service) or chat applications using AI (Artificial Intelligence). However, in snow removal operations, simply understanding current or past road conditions, snow accumulation, snow removal work status, traffic conditions, resident reports, or individual detection results may not adequately predict future snow removal operational workloads. For example, even with similar snowfall amounts or snow depths, the actual number of snow removal vehicles needed, working hours, deployment timing, target routes, target work areas, snow removal start time, need for support, need for flexibility, need for redeployment, or need for pre-deployment may differ depending on temperature, wind speed, snow quality, compaction status, amount of snow piled on road shoulders, road width reduction, traffic congestion, bus delays, snow disposal site utilization, snow removal transport route conditions, snow removal vehicle operation status, or the work capacity of the snow removal company. Therefore, in the practical implementation of snow removal and clearing operations, there is a need for a system that can organize the relationship between past and present snow removal and clearing operation information and snow removal environment information at the time of those operations, predict future snow removal and clearing operational loads in accordance with future snowfall, snow accumulation, compacted snow, snow pile-up, road width reduction, traffic impact, or the operating status of snow removal vehicles, and utilize this information for decision-making by road administrators or snow removal operators. [Prior art documents] [Patent Documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2025-031637 [Patent Document 2] Patent No. 7622875 [Patent Document 3] Japanese Patent Publication No. 2017-084366 [Overview of the Initiative] [Problems that the invention aims to solve]

[0004] In recent years, advanced technologies have been developed for snow removal and snow clearing decisions and work management, such as AI (artificial intelligence) technology that analyzes images acquired by cameras mounted on patrol vehicles to understand the conditions of snow accumulation and snow embankments (for example, Patent Document 1), and vibration sensing technology that estimates snow accumulation conditions based on optical fiber cables laid on roads (for example, Patent Document 2). Furthermore, interactive information provision systems (for example, Patent Document 3) have been proposed that use AI (artificial intelligence) to analyze the content of users' messages via SNS (Social Networking Service) or chat applications and present relevant information. However, while each of these technologies has its own merits, they often focus on understanding road conditions, snow conditions, resident reports, or individual detection results, or on presenting related information. Therefore, there has been a lack of a well-organized system that can derive snow removal operational load information corresponding to specific snow removal environmental conditions by associating snow removal operation information, including the location information, travel history, operating status, operation history, dispatch history, or work results of snow removal vehicles, with snow removal environmental information, including snowfall amount information, snow depth information, temperature information, wind speed information, snow quality information, compacted snow condition information, road shoulder snow accumulation amount information, or information on road width reduction due to snow accumulation or snow accumulation, with snow removal operational load information corresponding to specific snow removal environmental conditions. Furthermore, there has been a lack of a system that can predict future snow removal operational loads for each route, work section, snow removal company, road administrator, or municipality by applying this snow removal operational load information to future snow removal environmental conditions. In particular, in snow removal operations in snowy and cold regions, even with similar amounts of snowfall or snow depth, the actual number of snow removal vehicles required, working hours, deployment timing, target routes, target work areas, start time of snow removal, need for reinforcement, need for flexibility, need for redeployment, or need for advance deployment can vary greatly depending on temperature, wind speed, snow quality, compaction, amount of snow piled on road shoulders, reduction in road width, traffic congestion, delays in route buses, utilization of snow disposal sites, condition of snow removal transport routes, operating status of snow removal vehicles, work capacity of snow removal operators, or the management system of each local government. Furthermore, even if future snowfall forecasts, snow depth forecasts, temperature forecasts, wind speed forecasts, snow quality forecasts, compacted snow condition forecasts, road shoulder snow accumulation forecasts, or road width reduction forecasts are available, it is difficult to appropriately grasp which routes, construction sections, snow removal companies, road administrators, or local governments will experience a concentration of snow removal operational loads in the future, and how many snow removal vehicles, working hours, reinforcements, adjustments, redeployments, or pre-deployment arrangements will be necessary, unless these future snow removal environmental information are systematically correlated with past or present snow removal operational information and snow removal environmental information. As a result, in conventional snow removal operations, it was not easy to derive in advance, based on the future load of snow removal operations, and to reflect in the decisions of road administrators or snow removal operators, potential timings for dispatching snow removal, potential routes to be snow removed, potential work sections to be snow removed, potential start times for snow removal, potential routes to be snow removed, potential work sections to be snow removed, potential number of snow removal vehicles required, potential use of snow disposal sites, potential snow removal transport routes, potential deployment of support, potential flexibility, potential redeployment, or potential pre-deployment, either before or during snowfall. To solve these problems, the present invention aims to provide a snow removal decision support system, program, and road management method that can acquire snow removal operation information and snow removal environment information, associate them to derive snow removal operation load information for each route, work section, snow removal business operator, road administrator, or local government, and calculate future snow removal operation load prediction information by applying this snow removal operation load information to future snow removal environment conditions indicated by future snow removal environment information. Furthermore, the present invention aims to provide highly practical snow removal support tailored to future snowfall, snow accumulation, compacted snow, snow pileup, road width reduction, traffic impact, or the operating status of snow removal vehicles, by generating information on the start date of snow removal operations, the routes or work sections to be covered, the number of snow removal vehicles to be deployed, the deployment of snow removal vehicles, requests for dispatch to snow removal businesses, information used for decision-making by road administrators, snow removal decision support information, snow removal decision support information, or snow removal work resource allocation adjustment decision support information based on future snow removal operation load prediction information. [Means for solving the problem]

[0005] The above problems can be solved by the invention having the following configuration. The snow removal decision support system of the present invention is a snow removal decision support system for predicting the operational load of snow removal on roads, and may comprise: an information acquisition unit that acquires snow removal operation information, snow removal environment information, and future snow removal environment information; and an analysis unit that derives snow removal operation load information for each route, work section, snow removal business operator, road administrator, or local government by associating the snow removal operation information with the snow removal environment information, and calculates future snow removal operation load prediction information by applying the snow removal operation load information to future snow removal environment conditions indicated by the future snow removal environment information. Furthermore, the present invention may be implemented as a configuration that derives snow removal operation load information by classifying snow removal environmental conditions into a plurality of categories, a configuration that calculates future snow removal operation load prediction information by associating future snow removal environmental conditions with the above categories, a configuration that calculates snow removal operation evaluation information by comparing it with a standard load level, and a configuration that corrects snow removal operation load information or future snow removal operation load prediction information using traffic operation-related information or bus route delay information. Furthermore, the present invention may be implemented as a road snow removal unit that generates snow removal decision support information, including information used for decisions by road administrators, such as the start date of snow removal operations, the routes or work sections to be covered by snow removal operations, the number of snow removal vehicles to be deployed, the deployment of snow removal vehicles, the dispatch of snow removal businesses, or other information based on future snow removal operation load prediction information. Furthermore, the present invention may be implemented as a configuration that generates snow removal decision support information, snow removal decision support information, or snow removal work resource allocation adjustment decision support information based on the aforementioned future snow removal operation load prediction information. Furthermore, the present invention may be implemented as a configuration that generates snow removal work resource allocation adjustment support information, including candidates for support deployment, transfer of resources, reassignment, or pre-deployment, for snow removal work resources between multiple routes, multiple work sections, multiple snow removal businesses, multiple road administrators, or multiple municipalities. Furthermore, the present invention may be implemented as a configuration that compares the predicted future snow removal operational load information with a standard load level, determines whether or not to adjust the allocation of snow removal work resources if the future load exceeds or is likely to exceed the standard load level, and outputs or notifies the snow removal work resource allocation adjustment support information based on the determination result. Furthermore, the present invention may be implemented as a configuration that updates snow removal operation load information or future snow removal operation load prediction information to reflect information newly acquired or updated during the same snow removal season, a configuration that generates verification information regarding the difference between prediction information and actual information at the end or end of the snow removal season, and a configuration that generates information on on-site snow removal work challenges for the next snow removal season. Furthermore, the present invention may be implemented using at least one of the following: an AI (artificial intelligence) model, a machine learning model, a statistical model, a clustering model, a regression model, a time series prediction model, or a rule-based model. Alternatively, the present invention may be implemented as a configuration that analyzes image information to generate at least a portion of snow removal environment information, or generates or corrects future snow removal environment information based on changes in image information acquired over time. Furthermore, the present invention may be implemented not only as a snow removal decision support system, but also as a road management method that uses a computer to predict the operational load of snow removal on roads, or as a program that causes a computer to function as the snow removal decision support system. An example of the configuration of the present invention is shown below in accordance with the claims. [1] A snow removal decision support system for predicting the operational load of snow removal on roads, comprising: snow removal operation information, at least one of the following: location information, driving history, operating status, operation history, dispatch history, or work performance of snow removal vehicles; snow removal environment information, at least one of the following: snowfall amount information, snow depth information, temperature information, wind speed information, snow quality information, compacted snow condition information, road shoulder snow accumulation amount information, or road width reduction information due to snow accumulation or snowfall, as indicated by the snow removal operation information; and future snow removal environment information, snowfall amount prediction information, snow depth prediction information, temperature prediction information, wind speed prediction information, snow quality prediction information, compacted snow condition prediction information, road shoulder snow accumulation amount prediction information, and A snow removal decision support system comprising: an information acquisition unit that acquires at least one of the predicted road width reduction information due to snow accumulation or snow load; and an analysis unit that associates the snow removal operation information acquired by the information acquisition unit with the snow removal environment information to derive snow removal operation load information corresponding to the snow removal environment conditions indicated by the snow removal environment information for each route, work section, snow removal business operator, road administrator, or local government, and applies the snow removal operation load information to the future snow removal environment conditions indicated by the future snow removal environment information to calculate predicted future snow removal operation load information for each route, work section, snow removal business operator, road administrator, or local government. A snow removal decision support system as described in [2][1], wherein the analysis unit sets up a plurality of categories based on a single condition or a combination of multiple conditions for the snow removal environmental conditions included in the snow removal environmental information, associates the snow removal operation information with the snow removal environmental information for each of the plurality of categories, and derives the snow removal operation load information corresponding to the plurality of categories. A snow removal decision support system as described in [3][2], wherein the analysis unit associates the future snow removal environmental conditions indicated by the future snow removal environmental information with at least one of the plurality of categories, and calculates the future snow removal operational load prediction information using the snow removal operational load information corresponding to the associated categories. A snow removal decision support system as described in [4][1], wherein the analysis unit compares the predicted future snow removal operational load information with a standard load level determined based on the snow removal operational load information, and calculates snow removal operation evaluation information relating to at least one of the following for the route, the work section, the snow removal business operator, the road administrator, or the local government: the expected excess of the snow removal operational load, the expected increase in the snow removal operational load, or the expected strain on snow removal operations. A snow removal decision support system as described in [5][1], wherein the information acquisition unit further acquires traffic operation-related information including route bus operation information, and the analysis unit derives traffic impact information corresponding to the snow removal environment conditions indicated by the snow removal environment information by associating the snow removal environment information with the traffic operation-related information, and calculates future traffic impact prediction information by applying the traffic impact information to future snow removal environment conditions indicated by the future snow removal environment information. A snow removal decision support system as described in [6][1], wherein the information acquisition unit further acquires traffic operation-related information, including route bus operation information during or after snow removal operations, as indicated by the snow removal operation information; and the analysis unit generates bus route delay information based on the route bus operation information, associates the bus route delay information with the routes, and corrects the snow removal operation load information for each route based on the associated bus route delay information. A snow removal decision support system as described in [7][5], wherein the analysis unit corrects the future snow removal operation load prediction information based on the future traffic impact prediction information. A snow removal decision support system as described in [8][1], wherein the information acquisition unit further acquires traffic operation-related information including route bus operation information, and the analysis unit corrects the future snow removal operation load prediction information based on the current traffic operation status indicated by the traffic operation-related information. A snow removal decision support system as described in [9][6], wherein the route bus operation information includes location information and time information of the route bus, the analysis unit calculates the delay status of the bus route or the delay status of a section included in the bus route based on the location information and the time information, classifies the calculated delay status into a plurality of delay categories, and generates bus route delay information for each bus route or section by associating the plurality of delay categories with the bus route or the section. A snow removal decision support system as described in

[10] [1], wherein the snow removal decision support system further comprises a road snow removal unit, the road snow removal unit is characterized in that it generates snow removal decision support information that includes at least one of the following: the start date of snow removal response, the route or work section to be covered by snow removal response, the amount of snow removal vehicles to be deployed, the placement of snow removal vehicles, a request for dispatch to the snow removal business operator, or information used for decision-making by the road administrator, based on the future snow removal operation load prediction information calculated by the analysis unit. A snow removal decision support system as described in

[11]

[10] , wherein the road snow removal unit generates snow removal decision support information that includes at least one of the following based on the predicted future snow removal operation load information: a candidate timing for dispatching snow removal vehicles, a candidate route to be snow removed, a candidate work section to be snow removed, or a candidate priority for snow removal in the route or work section. A snow removal decision support system as described in

[12]

[10] , wherein the road snow removal unit generates snow removal decision support information that includes at least one of the following based on the predicted future snow removal operation load information: a candidate route to be snow removed from, a candidate work section to be snow removed from, a candidate snow removal start time, a candidate number of snow removal vehicles required for snow removal, a candidate use of a snow disposal site, or a candidate snow removal transport route. A snow removal decision support system as described in

[13]

[10] , wherein the road snow removal unit generates snow removal work resource allocation adjustment decision support information, which includes at least one of the following regarding snow removal work resources among multiple routes, multiple work sections, multiple snow removal businesses, multiple road administrators, or multiple municipalities: a candidate for support deployment, a candidate for sharing, a candidate for reassignment, or a candidate for pre-deployment. A snow removal decision support system as described in

[14]

[13] , wherein the road snow removal unit compares the predicted future snow removal operational load information with a standard load level determined based on the snow removal operational load information, determines whether or not to adjust the allocation of snow removal work resources if the future load indicated by the predicted future snow removal operational load information exceeds or is likely to exceed the standard load level, and outputs or notifies snow removal work resource allocation adjustment decision support information based on the determination result of whether or not to adjust the allocation. A snow removal decision support system as described in

[15] [1], wherein the information acquisition unit acquires at least one of the following information: newly generated or updated snow removal operation information, snow removal environment information, or future snow removal environment information during the same snow removal season; and the analysis unit updates the snow removal operation load information or future snow removal operation load prediction information by referring to the snow removal operation load information already derived or the future snow removal operation load prediction information already calculated, and reflecting the one or more of the information acquired by the information acquisition unit. A snow removal decision support system as described in

[16]

[15] , wherein the analysis unit, at the end or after the snow removal season, compares the predicted future snow removal operational load information calculated or updated during the snow removal season with the actual snow removal operational information obtained, and generates verification information regarding the difference between the snow removal operational load indicated by the predicted future snow removal operational load information and the actual snow removal operational load identified based on the snow removal operational information. A snow removal decision support system as described in

[17]

[16] , wherein the analysis unit refers to the verification information and the snow removal operation information obtained as actual results, and generates snow removal site work issue information for each route, work section, snow removal business operator, road administrator, or local government, relating to issues in snow removal site work during the snow removal season that are subject to improvement for the next snow removal season. A snow removal decision support system as described in

[18] [1], wherein the snow removal decision support system uses at least one of the following to derive the snow removal operation load information or calculate the future snow removal operation load prediction information: an AI (artificial intelligence) model, a machine learning model, a statistical model, a clustering model, a regression model, a time series prediction model, or a rule-based model. A snow removal decision support system as described in

[19]

[10] , wherein the snow removal decision support system generates the snow removal decision support information using at least one of the following: an AI (artificial intelligence) model, a machine learning model, a statistical model, a clustering model, a regression model, a time series forecasting model, or a rule-based model. A snow removal decision support system as described in

[20]

[13] , wherein the snow removal decision support system generates snow removal work resource allocation adjustment decision support information using at least one of the following: an AI (artificial intelligence) model, a machine learning model, a statistical model, a clustering model, a regression model, a time series forecasting model, or a rule-based model. A snow removal decision support system as described in

[21] [1], wherein the information acquisition unit acquires image information relating to at least one of the following: road, road surface, road shoulder, snow accumulation, snow deposits, compacted snow, snow dam, road width, or snow removal status; the snow removal decision support system analyzes the image information by image analysis processing including image analysis processing using an AI (artificial intelligence) model; generates at least a portion of the snow removal environment information based on the image information, or generates or corrects at least a portion of the future snow removal environment information based on changes in the image information acquired over time; and derives the snow removal operation load information or calculates the future snow removal operation load prediction information using the generated snow removal environment information or the generated or corrected future snow removal environment information.

[22] A road management method that uses a computer to predict the operational load of snow removal on a road, wherein the computer, via a network, provides, as snow removal operation information, at least one of the following: location information, driving history, operating status, operation history, dispatch history, or work performance of snow removal vehicles; as snow removal environment information, at least one of the following: snowfall amount information, snow depth information, temperature information, wind speed information, snow quality information, compacted snow condition information, road shoulder snow accumulation amount information, or road width reduction information due to snow accumulation or snow accumulation; and as future snow removal environment information, snowfall amount prediction information, snow depth prediction information, temperature prediction information, wind speed prediction information for the target of future snow removal operational load prediction. A road management method characterized by obtaining at least one of the following: snow quality prediction information, compacted snow condition prediction information, road shoulder snow accumulation prediction information, or road width reduction prediction information due to snow accumulation or snowfall; associating the obtained snow removal operation information with the snow removal environment information to derive snow removal operation load information corresponding to the snow removal environment conditions indicated by the snow removal environment information for each route, work section, snow removal business operator, road administrator, or local government; and applying the snow removal operation load information to the future snow removal environment conditions indicated by the future snow removal environment information to calculate future snow removal operation load prediction information for each route, work section, snow removal business operator, road administrator, or local government. A road management method as described in

[23]

[22] , wherein the computer sets up a plurality of classifications based on a single condition or a combination of multiple conditions for the snow removal environmental conditions included in the snow removal environmental information, associates the snow removal operation information with the snow removal environmental information for each of the plurality of classifications, and derives the snow removal operation load information corresponding to the plurality of classifications. A road management method as described in

[24]

[23] , characterized in that the computer associates the future snow removal environmental conditions indicated by the future snow removal environmental information with at least one of the plurality of categories, and calculates the future snow removal operational load prediction information using the snow removal operational load information corresponding to the associated categories. A road management method as described in

[25]

[22] , characterized in that the computer compares the predicted future snow removal and snow clearing operational load information with a standard load level determined based on the snow removal and snow clearing operational load information, and calculates snow removal and snow clearing operational evaluation information relating to at least one of the following for the route, the work section, the snow removal and snow clearing business operator, the road administrator, or the local government: the expected excess of the snow removal and snow clearing operational load, the expected increase in the snow removal and snow clearing operational load, or the expected strain on snow removal and snow clearing operations. A road management method as described in

[26]

[22] , characterized in that the computer further acquires traffic operation-related information including route bus operation information, associates the snow removal environment information with the traffic operation-related information to derive traffic impact information corresponding to the snow removal environment conditions indicated by the snow removal environment information, and calculates future traffic impact prediction information by applying the traffic impact information to future snow removal environment conditions indicated by the future snow removal environment information. A road management method as described in

[27]

[22] , wherein the computer further acquires traffic operation-related information, including route bus operation information during or after snow removal operations, as indicated by the snow removal operation information; generates bus route delay information based on the route bus operation information; associates the bus route delay information with the routes; and corrects the snow removal operation load information for each route based on the associated bus route delay information. A road management method as described in

[28]

[26] , characterized in that the computer corrects the future snow removal operation load prediction information based on the future traffic impact prediction information. A road management method as described in

[29]

[22] , characterized in that the computer further acquires traffic operation-related information including route bus operation information, and corrects the future snow removal operation load prediction information based on the current traffic operation status indicated by the traffic operation-related information. A road management method according to

[30]

[27] , wherein the route bus operation information includes location information and time information of the route bus, the computer calculates the delay status of the bus route or the delay status of a section included in the bus route based on the location information and the time information, classifies the calculated delay status into a plurality of delay categories, and associates the plurality of delay categories with the bus route or the section to generate bus route delay information for each bus route or section. A road management method as described in

[31]

[22] , characterized in that the computer generates snow removal decision support information that includes at least one of the following, based on the future snow removal operation load prediction information: the start date of snow removal response, the route or work section to be subject to snow removal response, the amount of snow removal vehicles to be deployed, the placement of snow removal vehicles, a request for dispatch to the snow removal business operator, or information used for decision-making by the road administrator. A road management method as described in

[32]

[31] , characterized in that the computer generates snow removal decision support information that includes at least one of the following based on the future snow removal operation load prediction information: a candidate timing for dispatching snow removal vehicles, a candidate route to be snow removed, a candidate work section to be snow removed, or a candidate priority for snow removal in the route or work section. A road management method according to

[33]

[31] , characterized in that the computer generates snow removal decision support information that includes at least one of the following based on the future snow removal operation load prediction information: a candidate route to be snow removed, a candidate work section to be snow removed, a candidate snow removal start time, a candidate number of snow removal vehicles to be used for snow removal, a candidate use of a snow disposal site, or a candidate snow removal transport route. A road management method according to

[34]

[31] , characterized in that the computer generates snow removal work resource allocation adjustment decision support information, which includes at least one of the following regarding snow removal work resources among a plurality of routes, a plurality of work sections, a plurality of snow removal businesses, a plurality of road administrators, or a plurality of municipalities: a candidate for support deployment, a candidate for sharing, a candidate for reassignment, or a candidate for pre-deployment. A road management method as described in

[35]

[34] , wherein the computer compares the predicted future snow removal and snow clearing operational load information with a standard load level determined based on the snow removal and snow clearing operational load information, determines whether or not to adjust the allocation of snow removal and snow clearing work resources if the future load indicated by the predicted future snow removal and snow clearing operational load information exceeds or is likely to exceed the standard load level, and outputs or notifies snow removal and snow clearing work resource allocation adjustment decision support information based on the determination result of whether or not to adjust the allocation. The road management method according to

[36] of

[22] , wherein the computer acquires at least one of the newly generated or updated snow removal and disposal operation information, the snow removal and disposal environment information, or the future snow removal and disposal environment information during the same snow removal and disposal season, refers to the already derived snow removal and disposal operation load information or the already calculated future snow removal and disposal operation load prediction information, reflects the acquired at least one piece of information, and updates the snow removal and disposal operation load information or the future snow removal and disposal operation load prediction information. The road management method according to

[37] of

[36] , wherein at the end of or after the end of the snow removal and disposal season, the computer compares the future snow removal and disposal operation load prediction information calculated or updated during the snow removal and disposal season with the snow removal and disposal operation information acquired as actual results, and generates verification information related to the difference between the snow removal and disposal operation load indicated by the future snow removal and disposal operation load prediction information and the actual snow removal and disposal operation load specified based on the snow removal and disposal operation information. The road management method according to

[38] of

[37] , wherein the computer refers to the verification information and the snow removal and disposal operation information acquired as actual results, and for each of the route, the work section, the snow removal and disposal operator, the road manager, or the local government, generates snow removal and disposal site work problem information related to problems that are targets for improvement for the next snow removal and disposal season, among the problems of snow removal and disposal site work in the snow removal and disposal season. The road management method according to

[39] of

[22] , wherein the computer derives the snow removal and disposal operation load information or calculates the future snow removal and disposal operation load prediction information using at least one of an AI (artificial intelligence) model, a machine learning model, a statistical model, a clustering model, a regression model, a time series prediction model, or a rule-based model. The road management method according to any one of

[40] and

[31] , wherein the computer generates the snow removal judgment support information using at least one of an AI (artificial intelligence) model, a machine learning model, a statistical model, a clustering model, a regression model, a time-series prediction model, or a rule-based model. The road management method according to any one of

[41] and

[34] , wherein the computer generates the snow removal work resource allocation adjustment judgment support information using at least one of an AI (artificial intelligence) model, a machine learning model, a statistical model, a clustering model, a regression model, a time-series prediction model, or a rule-based model. The road management method according to any one of

[42] and

[22] , wherein the computer acquires image information related to at least one of a road, a road surface, a road shoulder, accumulated snow, snow cover, compacted snow, a snow bank, road width, or snow removal status, analyzes the image information by image analysis processing including image analysis processing using an AI (artificial intelligence) model, generates at least part of the snow removal environment information based on the image information, or generates or corrects at least part of the future snow removal environment information based on a change in the image information acquired in time series, and derives the snow removal operation load information or calculates the future snow removal operation load prediction information using the generated snow removal environment information, or the generated or corrected future snow removal environment information.

[43] A program for causing a computer to function as the snow removal judgment support system according to any one of [1] to [2], [4] to [6], [8],

[10] ,

[15] ,

[18] , and

[21] .

[44] A program for causing a computer to function as the snow removal judgment support system according to [1], wherein the program includes an instruction sequence for causing the computer to execute at least one of the following processes (1) to (8). (1) A process to set up multiple categories based on a single condition or a combination of multiple conditions for the snow removal environmental conditions included in the snow removal environmental information, associate the snow removal operation information with the snow removal environmental information for each of the multiple categories, derive the snow removal operation load information corresponding to the multiple categories, associate the future snow removal environmental conditions indicated by the future snow removal environmental information with at least one of the multiple categories, and calculate the future snow removal operation load prediction information using the snow removal operation load information corresponding to the associated categories. (2) A process to obtain traffic operation-related information including route bus operation information, associate the snow removal environment information with the traffic operation-related information to derive traffic impact information corresponding to the snow removal environment conditions indicated by the snow removal environment information, apply the traffic impact information to the future snow removal environment conditions indicated by the future snow removal environment information to calculate future traffic impact prediction information, and correct the future snow removal operation load prediction information based on the future traffic impact prediction information. (3) Obtain route bus operation information during or after snow removal operations as indicated by the snow removal operation information, calculate the delay status on the bus route or the delay status in the section included in the bus route based on the location information and time information of the route bus included in the route bus operation information, classify the calculated delay status into a plurality of delay categories, associate the plurality of delay categories with the bus route or the section to generate bus route delay information for each bus route or section, associate the generated bus route delay information with the route, and correct the snow removal operation load information for each route based on the associated bus route delay information. (4) A process that generates snow removal decision support information based on the future snow removal operation load prediction information, including at least one of the following: candidate timing for dispatching snow removal vehicles, candidate routes to be snow removed, candidate work sections to be snow removed, or candidate snow removal priority in the routes or work sections. (5) A process that generates snow removal decision support information based on the future snow removal operation load prediction information, including at least one of the following: candidate routes to be snow removed, candidate work sections to be snow removed, candidate snow removal start dates, candidate number of snow removal vehicles required for snow removal, candidate use of snow disposal sites, or candidate snow removal transport routes. (6) A process that generates snow removal work resource allocation adjustment support information, based on the future snow removal operation load prediction information, which includes at least one of the following regarding snow removal work resources among multiple routes, multiple work sections, multiple snow removal businesses, multiple road administrators, or multiple municipalities: candidates for support deployment, candidates for sharing resources, candidates for reallocation, or candidates for pre-deployment deployment. (7) A process that, at the end of or after the snow removal season, compares the predicted future snow removal operational load information calculated or updated during the snow removal season with the actual snow removal operational information obtained, and generates verification information regarding the difference between the snow removal operational load indicated by the predicted future snow removal operational load information and the actual snow removal operational load identified based on the snow removal operational information. (8) A process that generates snow removal decision support information using at least one of the following, based on the future snow removal operation load prediction information: the start date of snow removal operations, the route or work section to be covered by snow removal operations, the number of snow removal vehicles to be deployed, the deployment of snow removal vehicles, the dispatch of snow removal businesses, or information used for decision-making by the road administrator.

[45] A program for causing a computer to function as the snow removal decision support system described in [1], the program comprising a sequence of instructions for causing the computer to perform at least one of the following processes (1) to (3). (1) Based on the future snow removal operation load forecast information, generate snow removal work resource allocation adjustment decision support information that includes at least one of the following regarding snow removal work resources among multiple routes, multiple work sections, multiple snow removal businesses, multiple road administrators, or multiple municipalities: a candidate for support deployment, a candidate for sharing, a candidate for reassignment, or a candidate for pre-deployment; compare the future snow removal operation load forecast information with a standard load level determined based on the snow removal operation load information; determine whether or not to adjust the allocation of snow removal work resources if the future load indicated by the future snow removal operation load forecast information exceeds or is likely to exceed the standard load level; and output or notify the snow removal work resource allocation adjustment decision support information based on the result of the determination of whether or not to adjust the allocation. (2) During the same snow removal season, acquire at least one of the following newly generated or updated snow removal operation information, snow removal environment information, or future snow removal environment information, refer to the snow removal operation load information already derived or the future snow removal operation load forecast information already calculated, and update the snow removal operation load information or the future snow removal operation load forecast information by reflecting the acquired one or more pieces of information, and at the end of or after the snow removal season, update the future snow removal operation load forecast information calculated or updated during the snow removal season The process involves comparing the snow removal operation information obtained as actual results with the snow removal operation information obtained as actual results, generating verification information regarding the difference between the snow removal operation load indicated by the future snow removal operation load prediction information and the actual snow removal operation load identified based on the snow removal operation information, and then, referring to the verification information and the snow removal operation information obtained as actual results, generating snow removal site work issue information for each route, section, snow removal business operator, road administrator, or local government, regarding issues in snow removal site work during the snow removal season that are subject to improvement for the next snow removal season. (3) Based on the predicted future snow removal operational load information, a process to generate snow removal resource allocation adjustment support information, which includes at least one of the following regarding snow removal resources among multiple routes, multiple work sections, multiple snow removal businesses, multiple road administrators, or multiple municipalities: candidates for support deployment, candidates for sharing resources, candidates for reallocation, or candidates for pre-deployment deployment, using at least one of the following: an AI (artificial intelligence) model, a machine learning model, a statistical model, a clustering model, a regression model, a time series forecasting model, or a rule-based model. [Effects of the Invention]

[0006] According to the present invention, it is possible not only to grasp the current or past snow removal work situation, but also to predict the future snow removal operational load based on future snowfall, snow accumulation, compacted snow, snow pile-up, road width reduction, traffic impact, or the operating status of snow removal vehicles. This makes it easier for road administrators or snow removal operators to make decisions in advance, before or during snowfall, regarding the start date of snow removal operations, the routes or work sections to be targeted, the number of snow removal vehicles to be deployed, their deployment, dispatch requests, reinforcement deployment, sharing, redeployment, or pre-deployment. Furthermore, according to the present invention, it is possible to grasp the future operational load of snow removal for each route, work section, snow removal company, road administrator, or municipality, making it easier to identify early on when the workload will be concentrated on a particular route, work section, snow removal company, road administrator, or municipality. This makes it easier to make adjustments in advance in response to shortages, uneven distribution, competition, or strain on snow removal vehicles, workers, snow disposal sites, snow removal transport routes, or snow removal work resources. Furthermore, according to the present invention, even with the same amount of snowfall or snow depth, it becomes easier to reflect the fact that the actual snow removal operational load differs depending on factors such as temperature, wind speed, snow quality, compaction, amount of snow piled on the roadside, reduction in road width, traffic congestion, delays in route buses, utilization of snow disposal sites, condition of snow removal and transport routes, operating status of snow removal vehicles, or the work capacity of snow removal operators. This makes it possible to realize practical snow removal support that takes into account the on-site load, which is difficult to grasp using only simple snowfall or snow depth criteria. Furthermore, according to the present invention, by using traffic operation-related information including route bus operation information, or bus route delay information, it becomes easier to provide support for decision-making that takes into account the impact of snow removal work on public transport and road traffic. This not only improves the efficiency of snow removal work, but also supports decisions regarding routes to be snow removed, routes to be cleared, target work areas, work order, or work timing, from the perspective of suppressing delays to route buses, traffic congestion, obstruction of traffic, or impact on citizens' lives. Furthermore, according to the present invention, when an increase in the operational load of snow removal is expected in the future, it is possible to suggest candidates for additional support, flexible deployment, reassignment, or pre-deployment. This not only allows for retrospective adjustment of snow removal resources to address shortages, but also supports operations that allow for prior allocation adjustments. This makes it easier to build a more flexible snow removal system in response to sudden snowfall, continuous snowfall, localized increases in snow accumulation, uneven distribution of snow removal vehicles, or conflicting work in multiple construction sections. Furthermore, according to the present invention, snow removal operational load information or future snow removal operational load forecast information can be updated to reflect information newly acquired or updated during the same snow removal season. This allows for continuous review of snow removal responses, taking into account discrepancies between initial forecasts and actual snowfall, snow accumulation, traffic impact, snow removal work performance, or the operating status of snow removal vehicles. Furthermore, according to the present invention, it is possible to verify the difference between the predicted snow removal operational load and the actual snow removal operational load at the end or after the snow removal season. This allows for the identification of challenges specific to each route, work section, snow removal company, road administrator, or local government for the next snow removal season, and can be used to improve snow removal plans, deployment of snow removal vehicles, work systems, snow disposal site operations, snow transport routes, or support systems. Furthermore, according to the present invention, by using AI (artificial intelligence) models, machine learning models, statistical models, clustering models, regression models, time series forecasting models, or rule-based models, it becomes easier to predict the operational load of snow removal that reflects regional characteristics, road characteristics, weather characteristics, traffic characteristics, work characteristics of each snow removal company, or past work performance. In addition, in configurations that use image information, it becomes easier to reflect the amount of snow accumulated on the road shoulder, reduction in road width, compacted snow conditions, snow levees, or the tendency for re-accumulation after snow removal, enabling snow removal support that is tailored to on-site conditions. [Brief explanation of the drawing]

[0007] [Figure 1] This is a system configuration diagram relating to the snow removal decision support system of the present invention. [Figure 2] This is a flowchart illustrating an example of a patrol procedure. [Figure 3] This is a flowchart illustrating an example of a fixed-point camera setup. [Figure 4] This is a diagram illustrating an example of road surface conditions. [Figure 5] This is a cross-sectional view showing an example of road surface conditions (unevenness of a snow-covered road surface). [Figure 6] This is a cross-sectional view showing an example of road surface conditions (thickness of compacted snow on the road surface). [Figure 7] This is a diagram illustrating an example of traffic conditions. [Figure 8] This is a diagram illustrating an example of road space conditions. [Figure 9] This figure shows an example of weather conditions. [Figure 10] This is a diagram illustrating an example of vehicle driving conditions. [Figure 11] This flowchart shows an example of the flow of the snow removal decision support system of the present invention. [Figure 12] This figure shows an example of the criteria used in the decision-making unit of the present invention. [Figure 13]This figure shows an example of the hardware configuration related to the snow removal decision support system of the present invention. Figure 1 is a schematic block diagram showing the basic configuration of the snow removal decision support system of the present invention. In this figure, the configuration of major functional modules such as the information acquisition unit and the analysis unit is shown, and the process of acquiring and analyzing various information such as road surface conditions, traffic conditions, weather conditions, and vehicle driving conditions is shown. On the other hand, the present invention also envisions embodiments that include components such as a road snow removal unit that manages resident notification information, snow removal information, and snow removal implementation plans, and an improvement unit that continuously improves the decision model. Figure 11 is a typical processing flow showing the flow of information acquisition, analysis, and decision processing, and is an auxiliary diagram for understanding embodiments of the present invention. Figure 12 is a table showing examples of decisions on whether or not snow removal is necessary when various types of information (road surface, traffic, road space, weather, and vehicle driving information) are combined in a complex manner, and should be understood as an example of the analysis process and decision criteria in the present invention. In addition, the present invention may include additional configurations not shown in the figures, such as: prioritizing snow removal and determining whether snow removal is necessary; deriving snow removal operation load information based on the correspondence between snow removal operation information and snow removal environment information; calculating future snow removal operation load prediction information by applying it to future snow removal environment conditions indicated by future snow removal environment information; classifying snow removal environment conditions; calculating snow removal operation evaluation information based on comparison with standard load levels; correction using traffic operation-related information or bus route delay information; generating snow removal decision support information, snow removal decision support information, snow removal decision support information, or snow removal work resource allocation adjustment decision support information; updating prediction information during the same snow removal season; generating verification information regarding the difference between prediction information and actual information; generating information on snow removal site work challenges for the next snow removal season; deriving, calculating, or generating information using AI (artificial intelligence) models, machine learning models, statistical models, clustering models, regression models, time series prediction models, or rule-based models; and generating or correcting snow removal environment information or future snow removal environment information based on image information. These are embodiments of the present invention and are configured as appropriate based on the functions claimed in Figures 1 to 13, although not necessarily explicitly shown. [Modes for carrying out the invention]

[0008] Hereinafter, an embodiment of the snow removal decision support system according to the present invention will be described in detail, with reference to drawings as necessary. The embodiments described below are merely examples to facilitate understanding of the present invention and do not unduly limit the technical scope of the invention. Each component and functional configuration described herein may be modified, substituted, deleted, or added as necessary, based on the gist of the invention as described in the claims, and are included within the technical scope insofar as they produce similar effects. Furthermore, the various components and means described herein can be considered as independent inventions, or they can be combined to form new inventive forms. In this specification, "core components" refers to the components that play a particularly central role in processing and coordinating functions within the overall configuration of the snow removal decision support system, and includes the information acquisition unit, the analysis unit, and the road snow removal unit. Furthermore, "core information" refers to information that is primarily acquired, analyzed, predicted, supported for decision-making, updated, or verified by these core components, and includes snow removal operation information, snow removal environment information, future snow removal environment information, snow removal operation load information, future snow removal operation load prediction information, and various decision-making support information generated based on these. Furthermore, the snow removal decision support system according to the present invention may be configured to generate decision support information including the amount of snow removal vehicles to be deployed, the deployment of snow removal vehicles, requests for deployment to snow removal businesses, candidates for routes or work sections to be snow-removed or cleared, candidates for support deployment, candidates for flexibility, candidates for relocation, or candidates for pre-deployment deployment. These configurations are embodiments implemented based on the technical ideas described in the claims, even if they are not explicitly shown in the drawings. Furthermore, the snow removal operation load information, future snow removal operation load prediction information, snow removal operation evaluation information, verification information, or snow removal site work issue information obtained by the analysis department may be recorded or managed in association with snow removal decision support information, snow removal decision support information, snow removal decision support information, or snow removal work resource allocation adjustment decision support information generated by the road snow removal department, or the status of responses implemented based on said decision support information. <Reference Guide> The main embodiments of the claims of this application are described in paragraph 0046 and subsequent paragraphs.

[0009] Figure 1 is a system configuration diagram relating to the snow removal decision support system 600 of the present invention. In the example shown in Figure 1, the snow removal decision support system 600 comprises an information acquisition unit 610 that acquires various types of information, an analysis unit 620 that analyzes the information acquired by the information acquisition unit 610, and a decision unit 630 that makes a decision based on the analysis results. In this embodiment, the snow removal decision support system 600 is connected to the road surface condition provision server 100, traffic condition provision server 200, road space condition provision server 300, weather condition provision server 400, and vehicle driving condition provision server 500 via a network NW. To understand the road surface conditions, Figure 1 shows only one vehicle Vh and terminal device TM, but multiple vehicles Vh and terminal devices TM may be connected to a network NW. Although Figure 1 shows only one fixed-point camera (CAM) to understand the road space conditions, multiple fixed-point cameras (CAM) may be connected to a network (NW). Furthermore, in the present invention, the snow removal decision support system 600 may be configured to acquire or process snow removal operation information, snow removal environment information, future snow removal environment information, snow removal operation load information, future snow removal operation load prediction information, traffic operation-related information, bus route delay information, image information, or various decision support information generated based on these, as core information. Furthermore, the snow removal decision support system 600 may be configured such that the analysis unit 620 associates snow removal operation information with snow removal environment information to derive snow removal operation load information, and then applies this snow removal operation load information to future snow removal environment conditions indicated by future snow removal environment information to calculate future snow removal operation load prediction information. Furthermore, in one embodiment of the present invention, the road snow removal unit may be configured to generate snow removal decision support information, snow removal decision support information, snow removal decision support information, or snow removal work resource allocation adjustment decision support information based on the analysis results or prediction results from the analysis unit 620. Note that the decision unit 630 shown in Figure 1 is a configuration that shows the decision processing in one embodiment of the present invention, and the present invention is not limited to cases where the decision processing by the decision unit 630 is essential.

[0010] The terminal device TM, fixed-point camera CAM, road surface condition server 100, traffic condition server 200, road space condition server 300, weather condition server 400, vehicle driving condition server 500, and snow removal decision support system 600 communicate via a network NW. The network NW includes some or all of the following: a WAN (Wide Area Network), a LAN (Local Area Network), the Internet, provider equipment, wireless base stations, dedicated lines, etc. Furthermore, data can be exchanged not only via the network (NW) but also via a memory card. Downloading and uploading data via the network (NW) is also acceptable. Furthermore, in the present invention, snow removal operation information, snow removal environment information, future snow removal environment information, traffic operation-related information, bus route delay information, image information, and various information generated or calculated based thereon may be acquired or processed as core or important information elements in the snow removal decision support system 600. This information may be acquired via a network (NW) from a vehicle (Vh), terminal device (TM), fixed-point camera (CAM), road surface condition server (100), traffic condition server (200), road space condition server (300), weather condition server (400), vehicle driving condition server (500), or equipment mounted on a snow removal vehicle. Alternatively, this information may be acquired via a network (NW) from road administrators, local governments, snow removal companies, transportation companies, or external information providers. Furthermore, in the present invention, the snow removal decision support system 600 may be configured to derive snow removal operation load information, calculate future snow removal operation load prediction information, and generate snow removal decision support information, snow removal decision support information, snow removal decision support information, or snow removal work resource allocation adjustment decision support information, not limited to information acquired via a network NW, but also using information acquired from memory cards or other recording media, manual input, data output from existing business systems, or batch import. On the other hand, road service information, fiber optic survey information, satellite survey information, etc., are positioned as optional extended information that can be acquired according to the operational purpose, and may be added to the snow removal decision support system 600 as needed. Even in this case, this information may be used as snow removal operation information, snow removal environment information, future snow removal environment information, traffic operation-related information, image information, or other auxiliary information in the present invention, and may be used to derive snow removal operation load information, calculate future snow removal operation load prediction information, or generate various decision support information.

[0011] Terminal devices TM are used by passengers riding in vehicles Vh. Terminal devices TM include mobile phones such as smartphones and tablet devices. Vehicles Vh are mainly road maintenance patrol vehicles / road patrol cars (patrol vehicles such as garbage trucks, packer trucks, and trash collection trucks are also acceptable). The terminal device TM may be a communication-type drive recorder mounted on the vehicle Vh, a stationary in-vehicle device, or it may be equipped with AI (artificial intelligence) image recognition capabilities. The vehicle Vh may also be equipped with a subsurface cavity detection function (a technology that irradiates electromagnetic waves from the road surface downwards and estimates the location of cavities and buried pipes from the reflected waves), and the vehicle Vh may be a subsurface cavity detection vehicle. The terminal device TM has a built-in road patrol application that works in conjunction with the road surface condition provision server 100. The terminal device™ includes a positioning device such as a GPS (Global Positioning System) receiver, a communication device for connecting to a network NW, input / output devices such as a G-sensor (accelerometer), camera, and touch panel, and a processor such as a CPU (Central Processing Unit).

[0012] Figure 2 is a flowchart illustrating an example of a patrol. The terminal device TM starts collecting location information, acceleration information, video, images, etc. when the patrol start button of the road patrol app is pressed (S1) (S2). After the patrol is completed, pressing the "end patrol" button on the road patrol app (S3) transmits the terminal device TM's location information, acceleration information, video, images, etc. to the road surface condition provision server 100 (S4). The road surface condition server 100 determines whether there are any bumps or unevenness on the road surface based on the measurement information transmitted from the terminal device TM, and identifies the location of the road surface that is determined to be uneven. Furthermore, the location information, acceleration information, video, images, etc. transmitted to the road surface condition server 100 may be measurement data from private cars, taxis, trucks, etc.

[0013] Fixed-point cameras (CAMs) are installed on roads (major arterial roads, roads with heavy traffic, major bus routes, roads important for transporting snow to disposal sites, roads connecting to schools, public facilities, and emergency hospitals, etc.) and on buildings, roadside pillars, poles, etc., around intersections. Fixed-point cameras (CAMs) include communication-enabled live cameras, web cameras, and network cameras. The fixed-point camera CAM may be a connected dashcam or a small unmanned aerial vehicle camera such as a drone, or it may be equipped with AI (artificial intelligence) image recognition capabilities. The fixed-point camera CAM has a built-in camera application that communicates with the road space condition provision server 300. A fixed-point camera (CAM) includes a lens, an image sensor, a positioning device such as a GPS (Global Positioning System) receiver, a communication device for connecting to a network (NW), and a processor such as a CPU (Central Processing Unit).

[0014] Figure 3 is a flowchart showing an example of the workflow for a fixed-point camera CAM. The fixed-point camera CAM collects road spatial conditions periodically or intermittently (S5), and periodically or intermittently automatically transmits video / images, location information, date and time information, etc. to the road spatial conditions provision server 300 (S6). The road space condition provision server 300 determines the height of snowdrifts (snow piles on the road shoulder, hereafter omitted) based on video and images transmitted from the fixed-point camera CAM, and identifies the location of road spaces that have been determined to be dangerous.

[0015] The road surface condition provision server 100 provides road surface conditions to the snow removal decision support system 600 via the network NW. The road surface conditions provided are road-specific information and include some or all of the following: unevenness of the snow-covered road surface, thickness of compacted snow on the road surface, quality of snow on the road surface, snow accumulation on the road surface, snowmelt on the snow-covered road surface, freezing of the road surface, bowl-shaped deformation of the snow-covered road surface, rutting of the snow-covered road surface, snow accumulation on the road surface, unevenness (flatness) of the road surface, cracks, rutting, cavities beneath the road surface, road damage, road collapse, flooding, and whether or not the road width has decreased due to snow accumulation. Figure 4 shows an example of road surface conditions, with areas 110, where the snow-covered road surface is severely uneven, indicated in black on the map. The provided road surface conditions are quantified in the analysis unit 620 as a traffic obstruction score, freezing risk, road surface damage risk, compacted snow condition, amount of snow accumulation on the road shoulder, or degree of road width reduction, and may be used to derive snow removal operation load information, calculate future snow removal operation load prediction information, or generate snow removal decision support information by the road snow removal unit.

[0016] Figure 5 is a cross-sectional view showing an example of road surface conditions (unevenness of a snow-covered road surface), where unevenness due to snow accumulation is indicated by a dashed line.

[0017] On snow-covered roads, snow melts easily near manholes, creating a step between the road surface and the compacted snow surface. Figure 6 is a cross-sectional view showing an example of road surface conditions (compacted snow thickness on the road surface). By determining the height of the step near the manhole from acceleration information from the terminal device TM, the compacted snow thickness of 130 can be determined.

[0018] The traffic information server 200 provides traffic information to the snow removal decision support system 600 via the network NW. The traffic information provided is road-specific information and includes some or all of the following: traffic volume, passing speed, average speed, and whether or not there is congestion or traffic jams. Figure 7 shows an example of traffic conditions, with areas 210 experiencing severe congestion indicated in black on the map. The provided traffic conditions may be converted and quantified in the analysis unit 620 as traffic flow score, congestion risk, traffic disruption trend, or traffic impact information, and integrated with weather conditions, vehicle driving conditions, road space conditions, snow removal operation information, or snow removal environment information to derive snow removal operation load information, calculate future snow removal operation load prediction information, or generate snow removal decision support information.

[0019] The road space condition provision server 300 provides road space conditions to the snow removal decision support system 600 via the network NW. The provided road space conditions are road-specific information and include some or all of the following: avalanches, snowdrifts, height of snow levees due to snow accumulation, presence or absence of poor visibility at intersections due to snow levees, presence or absence of road width reduction due to snow accumulation, presence or absence of stuck large vehicles, presence or absence of accident vehicles, etc. Figure 8 shows an example of road space conditions, with the dangerous locations 310, where snow dams are high, indicated in black on the map. The provided road space conditions are quantified in the analysis unit 620 as a traffic obstruction risk score, visibility impairment degree, road width reduction degree, snow accumulation impact degree, or road space obstruction information, and may be used as at least a part of the snow removal environment information or future snow removal environment information. Furthermore, this information may be used to derive snow removal operation load information, calculate future snow removal operation load prediction information, or generate snow removal decision support information in the road snow removal unit.

[0020] The weather information server 400 provides weather information to the snow removal decision support system 600 via the network NW. The weather information provided is regional information and includes some or all of the following: time, weather (sunny, rainy, snowy, etc.), temperature, humidity, snowfall amount, snow depth, snow density / weight, snow quality, moisture content, snow load, wind speed, forecast (snowfall amount / snow depth, etc.), presence or absence of warnings (blizzard, heavy snow, etc.) and advisories (heavy snow, windstorm, avalanche, etc.), record-breaking short-term heavy rain information, landslide disaster warning information, earthquake information, etc. Figure 9 shows an example of weather conditions, where snowfall amount 410 and warning 420 are displayed as numbers and letters. The weather conditions are processed in the analysis unit 620 as information regarding snowfall amount, snow depth, temperature, wind speed, snow quality, compacted snow condition, road shoulder snow accumulation, or road width reduction prediction, and may be used as at least part of the snow removal environment information or future snow removal environment information. The analysis unit 620 may also be configured to combine these weather conditions with other information to calculate snow removal operation load information or future snow removal operation load prediction information for each road, route, work section, snow removal business operator, road administrator, or local government.

[0021] The vehicle driving status provision server 500 provides vehicle driving status to the snow removal decision support system 600 via the network NW. The provided vehicle driving status is road and route-specific information obtained from vehicles such as route buses and loop buses, and includes some or all of the following: bus delay information (bus delay status) relative to the winter timetable (timetable that takes into account traffic conditions during the winter), bus route delay information, bus driving position (which lane out of three lanes on one side is the bus driving in, etc.), number of vehicles in front of the bus and number of vehicles alongside the bus, whether or not the road width has been reduced due to snow accumulation, skidding locations, tire slip locations, tire lock locations, and locations where sudden braking occurred. If there is no winter timetable, the bus delay time relative to the normal timetable may be used. Vehicle driving status can also be provided as open data in the Dynamic Bus Information Format (GTFS Realtime), including the latest route information (vehicle ID, route name, delay, estimated departure and arrival times, passing times, etc.), vehicle location information (vehicle latitude and longitude, approach information, congestion level, etc.), and operational information (service suspension, detour, accident, stuck, road obstruction, images of the front and rear of the bus, etc.). Furthermore, vehicle driving conditions may include data obtained from connected cars (private cars, taxis, trucks, garbage trucks, delivery vehicles, vehicles covered by auto insurance with drive recorders provided by insurance companies, etc.) from vehicle sensors such as temperature, locations of sudden braking, locations of skidding, locations of tire slippage, locations of tire lock-up, locations of ABS activation, unevenness of snowy road surfaces, ruts in snowy road surfaces, pits in snowy road surfaces, thickness of compacted snow on the road surface, reduction in road width due to snow accumulation, unevenness (flatness) of the road surface, locations of cavities under the road surface, avalanches, road obstacles, cracks, rutting, flooding, road damage, road collapses, road surface freezing, road surface snow accumulation, road surface snow quality, identification of impassable areas, traffic history, traffic volume, traffic congestion, passing speed, average speed, acceleration from probe information, and presence or absence of snowfall from wiper operation status. Figure 10 shows an example of vehicle driving conditions, where the area 510 where the tires are spinning is shown in black on the map. Various driving obstruction conditions or vehicle behavior abnormalities may be classified, weighted, or quantified in the analysis unit 620 using AI (artificial intelligence) models, machine learning models, statistical models, clustering models, regression models, time series prediction models, or rule-based models, and may be used to derive snow removal operation load information, calculate future snow removal operation load prediction information, derive traffic impact information, generate bus route delay information, or generate snow removal decision support information.

[0022] As a method for assessing road width reduction due to snow accumulation, in addition to using camera functions and image recognition functions of smartphones, connected dashcams, and fixed-point cameras installed in vehicles to determine the snow accumulation situation, it is also acceptable to use the same functions to determine road width reduction from the number of lanes and the number of vehicles side by side. Furthermore, it is also acceptable to determine the lane position (which lane it is traveling in out of three lanes on one side, or which lane it is traveling in out of two lanes on one side, etc.) from the latitude and longitude of a moving route bus, etc., and to determine road width reduction due to snow accumulation. The results of the road width reduction determination may be integrated with traffic conditions, driving abnormalities, lane driving patterns, weather conditions, snow removal operation information, or snow removal environment information, and used by the analysis unit 620 to derive snow removal operation load information, calculate future snow removal operation load prediction information, correct road width reduction prediction information, or generate decision support information by the road snow removal unit.

[0023] The road service status provision server provides road service status to the snow removal decision support system 600 via the network NW. The information regarding road service status is road-specific information and is mainly managed by road service providers (such as the Japan Automobile Federation), and includes some or all of the following: rescue requests (date, time, location, rescue details, etc.), rescue requests due to abnormal weather (date, time, location, rescue details, etc.), rescue requests due to disasters (date, time, location, rescue details, etc.), dead batteries, locked-out keys, running out of gas, flat tires, wheels coming off / falling off, flooding / submersion, recovery from snowy / mud roads, accidents, slips, disaster / damage situations, vehicle towing / transportation, removal / towing / transportation of abandoned vehicles, removal / towing / transportation of damaged vehicles, removal / towing / transportation of accident vehicles, location information of stuck vehicles, situation of stuck vehicles, road conditions, traffic conditions, EV charging availability, vehicle inspection results, etc. The frequency of vehicle jamming and abnormal rescue requests are quantified by the analysis unit 620 as supplementary information for traffic difficulty index, traffic impact information, driving obstruction information, or snow removal environment information, and may be used to derive snow removal operation load information, calculate future snow removal operation load prediction information, or generate snow removal decision support information.

[0024] The optical fiber survey status provision server utilizes optical fiber sensing technology, which uses optical fibers as sensors. It receives backscattered light from communication optical fibers contained in cables laid on roads, etc., and detects vibration patterns corresponding to the vehicle driving conditions on the road, etc., based on the backscattered light. From the detected vibration patterns and the learned model, it is possible to understand road conditions such as the presence or absence of snow, changes in road surface conditions, the presence of compacted snow or bumps, frozen areas, vehicle congestion or lagging, underground cavities, and impassable areas. Furthermore, by analyzing the intensity, frequency changes, and continuous abnormal patterns of waveforms of minute vibrations propagating through the ground, it is possible to detect the risk of underground cavities and signs of ground deformation. If necessary, the sensing results can be corroborated and supplemented by images acquired from fixed-point cameras connected to optical fibers. The fiber optic survey status provision server provides fiber optic survey status to the snow removal decision support system 600 via the network NW. The information provided includes snow accumulation, compaction, and freezing conditions for each road, unevenness of the snow-covered road surface, vehicle traffic history, traffic volume, traffic congestion, sudden vehicle stops, accident trends, history of freezing and slipping, road surface unevenness, road damage, road collapses, and the possibility of voids under the road surface. This information is used to identify areas where passage is difficult due to snow accumulation and areas with high snow removal priority. This enables fiber optic sensing to continuously and widely monitor road conditions even during times when ground patrols cannot be conducted, contributing to more accurate and immediate decisions regarding snow removal and clearing. The obtained waveforms or sensing results may be analyzed by an AI (artificial intelligence) model, machine learning model, statistical model, time series prediction model, or rule-based model, and visualized or quantified as information regarding road surface abnormalities, freezing risk, snow accumulation conditions, compacted snow conditions, vehicle congestion, traffic congestion, difficulty of passage, or reduction in road width, and input into the analysis unit 620. Furthermore, this information may be used as at least part of the snow removal environment information or future snow removal environment information, and may be used to derive snow removal operation load information, calculate future snow removal operation load prediction information, or generate various decision support information.

[0025] The satellite survey status server uses satellite remote sensing technology with artificial satellites equipped with SAR (Synthetic Aperture Radar), optical sensors, microwave sensors, etc., to detect snow cover, compacted snow, snowdrifts, road surface freezing, unevenness of snow-covered road surfaces, areas where snow removal has been completed and not, impassable areas, cavities under the road surface, road damage, road collapses, and flooding. This uses satellite-acquired data such as optical images, SAR images, temperature data, scattering intensity values, polarization information, and phase information to detect time-series changes in snow cover conditions and abnormalities in road surface conditions with high accuracy. Furthermore, by applying interferometric analysis techniques such as InSAR (Interferometric SAR) and DInSAR (Differential Interferometric SAR), it is possible to comprehensively understand subtle height changes due to compacted snow and freezing, changes after snow removal, and areas where snow has accumulated. This allows for the detection of snow depth, remaining compacted snow, and areas where snow removal has been insufficient. The satellite survey status provision server transmits snow accumulation data, estimated snow removal requirements, snow removal completion evaluations, and traffic impact indicators to the snow removal decision support system 600 via the network (NW). This information is compiled and organized by route, work section, or local road, and used in conjunction with other information sources to make decisions regarding snow removal. Information regarding whether snow removal has been completed or not, snow accumulation data, traffic impact index, or abnormalities in road surface conditions is integrated and evaluated in the analysis unit 620 and may be used as at least part of the snow removal environment information or future snow removal environment information. Furthermore, this information may be used to derive snow removal operation load information, calculate future snow removal operation load prediction information, generate snow removal decision support information, snow removal decision support information, or snow removal work resource allocation adjustment decision support information.

[0026] The resident reporting status server collects and manages information regarding complaints, requests, and reports from residents. It supports multiple communication methods, including AI (artificial intelligence) voice reporting, reporting via SNS (e.g., LINE), web form reporting, email reporting, smartphone app reporting, voice assistant reporting, and traditional telephone reporting with input of interview results by staff. The resident reporting status server provides information regarding resident reporting status to the snow removal decision support system 600 via the network. "AI-based voice notification reception" refers to a system that automatically analyzes voice notification content transmitted via telephone or other voice input means using AI (artificial intelligence) technologies such as speech recognition and natural language processing. This enables quantitative understanding of notification content and automatic storage and learning of notification information without the need for human intervention by operators. The AI-powered voice notification system analyzes the content of the notification (e.g., uncleared snow, snowdrifts, ice, road obstruction, etc.) obtained through dialogue with the caller, as well as the location of the notification (address, facility name, landmark, etc.), using speech recognition and natural language processing, and automatically registers it in the notification database. In addition to SNS notifications and web notifications, citizen-participation notification platforms (e.g., FixMyStreet Japan) also handle posted data, including notification content and location information, in the same way. This data includes text entered by the caller, photos, GPS coordinates, and multiple-choice items, and is handled together with notification information entered by local government officials. The collected report information is classified by location, content, and method of reporting, and organized into report density maps and complaint histories by route or work section. This information may be used in the analysis unit 620 to derive snow removal operation load information, correct future snow removal operation load prediction information, or generate information to support snow removal decisions by the road snow removal unit. Furthermore, by considering this information in conjunction with the local population or number of households, it becomes possible to make decisions that balance the number of reports with the scope of impact. Resident notification status information may be automatically sorted by AI (artificial intelligence) to extract only notifications related to snow removal. After extraction, the urgency (road impassable, important route, in front of hospital facilities, etc.), geographical characteristics of the target area (main roads / local roads, width, traffic volume, etc.), notification density, and population or household distribution may be evaluated and organized as information regarding the necessity of snow removal, snow removal operational load, or traffic impact. This information will be subject to integrated analysis by the analysis unit 620 and may be used to derive snow removal operational load information, calculate or correct future snow removal operational load prediction information, and generate snow removal decision support information, snow removal decision support information, or snow removal work resource allocation adjustment decision support information by the road snow removal unit. In particular, it functions as a source of information that supports highly accurate decisions that affect the necessity, timing, and method (daytime / nighttime, etc.) of snow removal. Furthermore, the resident reporting status information may be configured to evaluate its reliability by cross-referencing it with external sensing information such as satellite survey data and fiber optic survey data, and then weighting and prioritizing it accordingly. This makes it possible to improve the reliability and reproducibility of decisions by mutually complementing multiple information sources, without relying on subjective judgment.

[0027] The snow removal status provision server provides snow removal status to the snow removal decision support system 600 via the network NW. The information regarding snow removal status may be road-specific information, route-specific information, work section-specific information, snow removal contractor-specific information, road administrator-specific information, or local government-specific information, and may primarily be information managed by road administrators. The aforementioned information regarding snow removal status may include, in whole or in part, information regarding snow removal routes (main roads, etc.) or work sections (local roads, etc.), road conditions, traffic conditions, information regarding snow removal businesses, types or number of snow removal vehicles (excavators, graders, rotary snowplows, dozers, dump trucks, spreaders), prior snow removal plans or work guidelines, snow removal implementation standards, snow removal completion standards, snow removal work plans, dispatch orders to snow removal businesses, snow removal implementation status, snow removal work status (including the current location of snow removal vehicles and video / images from snow removal vehicles), snow removal operational records, snow removal performance information (operating hours, location information, history, etc.), snow removal work daily reports, patrol results, budget management, settlement management, complaints and requests, and information regarding snow disposal sites or snow storage areas. Furthermore, information regarding snow removal status may be used as at least part of snow removal operation information. For example, information regarding snow removal status may include location information, travel history, operating status, operation history, dispatch history, work results, work time, work volume, target area, work sequence, work report, or information regarding the work capacity of each snow removal company. Information regarding snow removal status may also include snow removal work information and snow removal transport status information. Snow removal work information may include at least one of the following: snow removal schedule information, snow removal work command information, snow removal progress information, or snow removal results information. Snow removal transport status information may include at least one of the following: snow removal vehicle operating status information, snow disposal site utilization status information, snow removal transport route status information, or snow removal target section status information. Furthermore, road administrators may formulate snow removal plans and snow removal work guidelines in advance, and the following may be planned: snow removal implementation system (organization, implementation system, patrols, snow-related consultation desk, snow removal contractors, snow removal vehicles, snow removal work evaluation, snow removal dispatch orders, public awareness activities, etc.), snow removal classification (main roads, auxiliary main roads, suburban main roads, fully contracted work areas, designated contracted work areas, local roads, important routes, etc.), snow removal implementation methods (snow removal standards, snow removal dispatch standards, snow removal methods, snow removal length, snow removal time, snow removal time, routes, snow disposal sites, slip prevention measures by applying de-icing agents, etc.), and types of snow removal work (normal snow removal work, fresh snow removal work, road surface leveling work, widening snow removal work, transport snow removal work, intersection snow removal work, bottleneck work, narrow road snow removal work, snow peeling work, de-icing agent application work, etc.). In snow removal operations, after patrols by road administrators or snow removal companies, a snow removal implementation plan or work plan may be formulated, dispatch orders may be issued to snow removal companies, snow removal operations may be carried out, and patrols may be conducted after the snow removal operations are completed. This information may be used as information or data for prioritizing and deciding on the implementation of snow removal. In addition, information regarding snow removal operations may be acquired or recorded in the snow removal decision support system 600 as information regarding the snow removal operation schedule, instructions, progress, actual results, target area, work time, work volume, number of transports, amount of material brought in, daily work reports, or work reports. Furthermore, information regarding snow removal and transport may include the current location, operating status, standby status, loading status, number of transports, transport time, waiting time for delivery to the snow disposal site, acceptance status of the snow disposal site, remaining capacity of the snow disposal site, traffic congestion on the snow removal and transport route, obstruction of traffic on the snow removal and transport route, status of loading work in the snow removal target section, amount of snow to be removed, or information regarding the completion status of pre-snow removal processes. This information may be used to derive or generate information on snow removal operation load, snow removal and transport load, candidate snow disposal site use, candidate snow removal and transport route, or candidate snow removal start time. Furthermore, among these, information corresponding to the details of snow removal work and responses (work status, operational performance, daily work reports, patrol results, etc.) may be recorded or managed within the system as information on snow removal status, snow removal operation information, snow removal work information, or snow removal transport status information. This allows the snow removal decision support system 600 to associate past or present snow removal operation information with snow removal environment information at the time of the snow removal operation, and to use this as basic information for deriving snow removal operation load information corresponding to the snow removal environment conditions. This information regarding snow removal status may be used in the analysis unit 620 for correlation analysis between work performance and road surface changes, evaluation of the relationship between working time and finish accuracy, confirmation of spatiotemporal consistency with complaint locations, evaluation of snow removal progress, evaluation of the operational load of snow removal vehicles, evaluation of the snow removal transport load, evaluation of snow disposal site utilization, evaluation of traffic impact of snow removal transport routes, or evaluation of the work capacity of each snow removal business operator. Furthermore, the analysis unit 620 may derive snow removal operational load information for each route, work section, snow removal business operator, road administrator, or local government based on this information, and calculate future snow removal operational load prediction information by applying this snow removal operational load information to future snow removal environment information. Furthermore, the snow removal decision support system 600 may be configured to evaluate differences from work guidelines and implementation standards, surpluses or shortages in snow removal response, workload or work capacity of each snow removal business operator, uneven distribution of snow removal vehicles, congestion at snow disposal sites, congestion on snow removal transport routes, or work conflicts in multiple work sections. This makes it possible to provide decision support, including the amount of snow removal vehicles to be deployed, the placement of snow removal vehicles, requests for dispatch to snow removal businesses, candidates for support deployment, candidates for flexibility, candidates for redeployment, or candidates for pre-deployment deployment, based on snow removal operational load information or future snow removal operational load forecast information. In addition, the Road Snow Removal Unit may be configured to generate snow removal decision support information, snow removal decision support information, snow removal decision support information, or snow removal work resource allocation adjustment decision support information based on snow removal operation load information, future snow removal operation load prediction information, snow removal operation evaluation information, traffic impact information, bus route delay information, snow removal transport load information, snow disposal site utilization status, or snow removal transport route status derived or calculated by the Analysis Unit 620. For example, the Road Snow Removal Unit may generate information including the start time of snow removal response, the route or work section to be covered by snow removal response, the number of snow removal vehicles to be deployed, the deployment of snow removal vehicles, the dispatch request to snow removal businesses, candidate timing for snow removal deployment, candidate routes or work sections to be covered by snow removal, candidate start time for snow removal, candidate number of vehicles required, candidate use of snow disposal sites, candidate snow removal transport routes, candidate support deployment, candidate flexibility, candidate re-deployment, or candidate pre-deployment. Furthermore, patrol results and on-board video / image evaluation information may be used as evaluation information after snow removal work, snow removal environment information, or snow removal operation information. In addition, this information may be used to revise judgment conditions, prediction conditions, models, or operation rules, and may be configured to contribute to improving the accuracy of processing by AI (artificial intelligence) models, machine learning models, statistical models, clustering models, regression models, time series prediction models, or rule-based models. In addition, images, videos, acceleration sensor data, location information, or date and time information regarding road surface conditions after snow removal collected by patrol vehicles may also be used for evaluating the quality of work, understanding changes in road surface conditions, verifying snow removal operational load information, verifying the difference between predicted and actual snow removal operational load information for the future, or generating information on on-site work challenges for the next snow removal season. Furthermore, this information, along with information on the status of snow removal and clearing, reflects changes in road surface conditions and the finished state. In this specification, information on snow removal and clearing status or snow removal and clearing operation information may be configured to partially include elements of road surface information, traffic information, road space information, or work performance information. This information may be used by the road snow removal department to generate snow removal decision support information, snow removal decision support information, snow removal decision support information, or snow removal work resource allocation adjustment decision support information, and may be configured to be integrated and analyzed with other information as needed.

[0028] The information acquisition unit 610, which operates in the snow removal decision support system 600, acquires road surface conditions from the road surface condition provision server 100, traffic conditions from the traffic condition provision server 200, road space conditions from the road space condition provision server 300, weather conditions from the weather condition provision server 400, vehicle driving conditions from the vehicle driving conditions provision server 500, road service conditions from the road service conditions provision server, fiber optic survey conditions from the fiber optic survey conditions provision server, satellite survey conditions from the satellite survey conditions provision server, resident notification conditions from the resident notification conditions provision server, and snow removal conditions from the snow removal conditions provision server via the network NW. Road surface conditions provided by the road surface condition provision server 100 are stored as road surface information 640. Traffic conditions provided by the traffic condition provision server 200 are stored as traffic information 650. Road space conditions provided by the road space condition provision server 300 are stored as road space information 660. Weather conditions provided by the weather condition provision server 400 are stored as weather information 670. Vehicle driving conditions provided by the vehicle driving conditions provision server 500 are stored as vehicle driving information 680. Road service conditions provided by the road service condition provision server are stored as road service information. Fiber optic survey conditions provided by the fiber optic survey condition provision server are stored as fiber optic survey information. Satellite survey conditions provided by the satellite survey condition provision server are stored as satellite survey information. Resident notification conditions provided by the resident notification condition provision server are stored as resident notification information. Snow removal conditions provided by the snow removal condition provision server are stored as snow removal information. Furthermore, the information acquisition unit 610 may acquire snow removal operation information, snow removal work information, or snow removal transport status information based on snow removal status, snow removal information, snow removal implementation plan, work plan, work order, work progress, work results, work report, location information of snow removal vehicles, driving history, operating status, operating history, dispatch history, vehicle operation information, snow disposal site utilization information, snow removal transport route information, or snow removal target section information. Snow removal work information may include at least one of the following: snow removal schedule information, snow removal work order information, snow removal progress information, or snow removal results information. Snow removal transport status information may include at least one of the following: snow removal vehicle operating status information, snow disposal site utilization status information, snow removal transport route status information, and snow removal target section status information. Furthermore, the information acquisition unit 610 may acquire or generate snow removal environment information based on snowfall amount information, snow depth information, temperature information, wind speed information, snow quality information, compacted snow condition information, road shoulder snow accumulation amount information, road width reduction information due to snow accumulation or snow, traffic conditions, road space conditions, vehicle driving conditions, resident report status, road service status, optical fiber survey status, satellite survey status, or image information. In addition, the information acquisition unit 610 may acquire or generate future snow removal environment information based on snowfall amount forecast information, snow depth forecast information, temperature forecast information, wind speed forecast information, snow quality forecast information, compacted snow condition forecast information, road shoulder snow accumulation amount forecast information, road width reduction forecast information due to snow accumulation or snow, traffic impact forecast information, or snow removal transport load forecast information. The information acquired by the information acquisition unit 610 may include some or all of the following, depending on the embodiment: road surface conditions, traffic conditions, road space conditions, weather conditions, vehicle driving conditions, road service status, fiber optic survey status, satellite survey status, resident notification status, snow removal status, snow removal operation information, snow removal environment information, future snow removal environment information, snow removal work information, and snow removal transport status information. The configuration is not limited to acquiring all of this information. Furthermore, in one embodiment of the present invention, the information acquisition unit 610 may be configured to acquire snow removal operation information, snow removal work information, and snow removal transport status information. In this case, the information acquisition unit 610 may acquire this information from a snow removal status provision server, or from an in-vehicle terminal, a reception terminal at a snow disposal site, a work management system for snow removal businesses, a management system for road administrators, a traffic status provision server 200, a road space status provision server 300, a weather status provision server 400, a vehicle driving status provision server 500, or other external systems. This information may be passed to the analysis unit 620, the decision unit 630, the road snow removal unit, or, if necessary, the improvement unit, and used for analysis, decision support, updating, verification, or learning by each unit. The information acquisition unit 610 may also be configured to manage information by adding metadata such as the type of information, source, acquisition frequency, acquisition time, related route information, related work section information, snow removal target section, snow removal transport route, snow disposal site, vehicle identification information, snow removal business operator information, road administrator information, or local government information, enabling dynamic and real-time information utilization. Furthermore, the information acquisition unit 610 may be configured to acquire information from administrative agencies, transportation operators, snow removal and clearing companies, construction and civil engineering companies, infrastructure operators, tourist facility operators, or other external related organizations. This information may include information on snow removal, snow clearing, road obstruction, facility status, traffic conditions, snow disposal site utilization, traffic conditions on snow removal and transport routes, operating status of snow removal and clearing vehicles, available work resources, or road usage conditions for each region. Furthermore, the information acquisition unit 610 may be configured to dynamically select or limit the types of information to be acquired depending on the system's purpose, status, load, target period, target route, target work section, target snow removal business operator, target road administrator, or target municipality. For example, if there is a concentration of resident reports, the system may prioritize acquiring highly relevant information such as resident report information, traffic information, road surface information, road space information, and information on population or the number of households. Also, if an increase in the load of snow removal operations is expected in the future, the system may prioritize acquiring snow removal operation information, snow removal environment information, future snow removal environment information, operating status of snow removal vehicles, snow disposal site utilization status, snow removal transport route status, traffic operation-related information, bus route delay information, or image information. The information acquired by the information acquisition unit 610 may be used by the analysis unit 620 for the following purposes: associating snow removal operation information with snow removal environment information; deriving snow removal operation load information; calculating future snow removal operation load prediction information based on future snow removal environment information; making corrections using traffic operation-related information or bus route delay information; generating or correcting snow removal environment information or future snow removal environment information based on image information; and generating snow removal decision support information, snow removal decision support information, snow removal decision support information, or snow removal work resource allocation adjustment decision support information by the road snow removal unit.

[0029] The analysis unit 620, which operates within the snow removal decision support system 600, analyzes various types of information acquired by the information acquisition unit 610, including road surface information 640, traffic information 650, road space information 660, weather information 670, vehicle travel information 680, road service information, fiber optic survey information, satellite survey information, resident notification information, and snow removal information, for each type of information, and stores the analysis results 690. The analysis unit 620 is one of the core components of the snow removal decision support system 600 and performs individual and integrated analysis based on the acquired information. The analysis results 690 may be visualized in the form of a map display, tabular format, time-series display, graph, etc., and may be configured to contribute to subsequent decision-making processes and decisions. The analysis unit 620 may also have an integrated analysis function that cross-references or compares multiple pieces of information in addition to individual analysis. For example, optical fiber vibration data, satellite image data, vehicle driving anomaly data, resident report information, traffic information, weather information, or snow removal information may be associated with the same area, same route, same work section, same road section, or same time period, and the anomaly score, degree of traffic obstruction, degree of traffic impact, road surface condition, snow accumulation condition, or snow removal implementation status of each piece of information may be cross-referenced or aggregated to evaluate the snow removal environmental conditions, snow removal operation status, or the need for snow removal response at that location or management unit. This complements the limitations of individual information and enables decision support based on the consistency of multiple pieces of information. Furthermore, in one embodiment of the present invention, the analysis unit 620 may be configured to associate snow removal operation information acquired by the information acquisition unit 610 with snow removal environment information during snow removal operations indicated by the snow removal operation information. For example, the analysis unit 620 may associate the location information, driving history, operating status, operation history, dispatch history, work results, snow removal work information, or snow removal transport status information of snow removal vehicles with snowfall amount information, snow depth information, temperature information, wind speed information, snow quality information, compacted snow status information, road shoulder snow accumulation amount information, road width reduction information, traffic conditions, road space conditions, vehicle driving conditions, or resident report status. Furthermore, the analysis unit 620 may be configured to derive snow removal operational load information corresponding to the snow removal environmental conditions indicated by the snow removal environmental information for each route, work section, snow removal business operator, road administrator, or local government, based on the aforementioned correspondence. The snow removal operational load information may include information on the operating load of snow removal vehicles, working hours, workload, work delays, number of dispatches, snow removal transport load, snow disposal site utilization load, traffic impact of snow removal transport routes, workload for each snow removal business operator, or the amount of resources required for snow removal. Furthermore, the analysis unit 620 may be configured to calculate future snow removal operational load prediction information for each route, work section, snow removal business operator, road administrator, or local government by applying snow removal operational load information to future snow removal environmental conditions indicated by future snow removal environmental information. This makes it possible to apply the relationship between operational load and environmental conditions during past or present snow removal operations to future snowfall, snow accumulation, compacted snow, snow pileup, road width reduction, traffic impact, or operating status of snow removal vehicles, and predict the load required for future snow removal operations. Furthermore, snow removal work information and snow removal transport status information may be used as part of snow removal operation information. The analysis unit 620 may derive snow removal operation load information or snow removal transport load information related to snow removal based on the progress of snow removal work, the operating status of snow removal vehicles, the waiting status of snow removal vehicles, the number of transports by snow removal vehicles, the waiting time for transport to the snow disposal site, the acceptance status of the snow disposal site, the traffic status of the snow removal transport route, the status of loading work in the snow removal target section, or the amount of snow to be removed. Furthermore, the road snow removal unit may be configured to generate snow removal decision support information, snow removal decision support information, snow removal decision support information, or snow removal work resource allocation adjustment decision support information based on snow removal operation load information, future snow removal operation load prediction information, snow removal transport load information, snow disposal site utilization status, or snow removal transport route status derived or calculated by the analysis unit 620. This makes it possible to provide decision support including the start date of snow removal response, the target route or work section, the amount of snow removal vehicles to be deployed, the deployment of snow removal vehicles, the dispatch request to snow removal businesses, candidate snow removal start dates, candidate snow disposal site utilization, candidate snow removal transport routes, candidate support deployment, candidate flexibility, candidate re-deployment, or candidate pre-deployment when an increase in snow removal operation load is expected.

[0030] Furthermore, the analysis unit 620 may be configured to use at least one of the following as inputs: an AI (artificial intelligence) model, a machine learning model, a statistical model, a clustering model, a regression model, a time series forecasting model, or a rule-based model, to take multiple pieces of information as input and output information used to generate snow removal operation load information, future snow removal operation load forecast information, snow removal operation evaluation information, traffic impact information, future traffic impact forecast information, bus route delay information, snow removal transport load information, or snow removal decision support information. For example, the analysis unit 620 may estimate the snow removal operational load for each route, work section, snow removal business operator, road administrator, or municipality using a neural network, decision tree-based machine learning model, random forest, gradient boosting, regression analysis, Bayesian inference, clustering, time series forecasting model, or rule-based model. Alternatively, the analysis unit 620 may estimate the snow removal operational load corresponding to future snow removal environmental conditions indicated by future snow removal environmental information, based on the correspondence between past or present snow removal operational information and snow removal environmental information. The output scores, classification results, estimation results, or prediction results may be stored as analysis results 690 and may be used to generate snow removal decision support information, snow removal decision support information, snow removal decision support information, or snow removal work resource allocation adjustment decision support information in the road snow removal unit. Furthermore, in a configuration in which a decision unit 630 is provided, these analysis results 690 may be used as decision criteria or decision processing in the decision unit 630. Furthermore, the analysis unit 620 may be configured to contribute to updating judgment conditions, prediction conditions, models, or operational rules using the information to be analyzed, the analysis results 690, prediction results, actual information, or verification information. Specifically, the model weights or judgment conditions may be adjusted using effectiveness indicators obtained after snow removal, such as a decrease in resident complaints, improvement in traffic speed, change in the number of complaints, reduction in the turnaround time of snow removal vehicles, reduction in waiting time for transport to snow disposal sites, increase in transport volume per unit time, reduction in travel time on snow removal transport routes, or the recovery status of road width after snow removal, as training signals or evaluation indicators. The data to be learned or updated may include date and time, location, report content, report density, complaint classification, congestion occurrence, traffic volume, snow accumulation, snow removal history, snow removal operation history, snow removal vehicle operation status, snow disposal site utilization status, snow removal transport route status, snow removal target section status, work performance for each snow removal company, workload for each route or work section, and weather conditions or road width reduction status. This enables adaptive prediction or decision support tailored to regional characteristics and seasonal trends. In addition, resident report information may be subjected to AI (artificial intelligence)-based content sorting, urgency assessment, report density aggregation, geographical characteristic assessment of the target area, and integration processing with the local population or number of households. The analysis unit 620 may be configured to synthesize these multi-stage evaluation results and use them to correct information regarding the necessity of snow removal, traffic impact, snow removal operational load, or future snow removal operational load predictions. Furthermore, the analysis unit 620 may be configured to focus on the time or period of information acquisition and perform weighting processing according to the reliability, immediacy, and impact on traffic of the information. In addition, the analysis unit 620 may be configured to weight the reliability or priority of various information obtained by the information acquisition unit 610, such as road surface information, traffic information, road space information, weather information, vehicle driving information, road service information, fiber optic survey information, satellite survey information, resident notification information, snow removal information, snow removal work information, snow removal transport status information, etc., according to the time of acquisition, and perform analysis processing based on said weighting. Such weighting processing according to time of day may also be utilized in deciding whether to carry out daytime or nighttime snow removal, deciding when to start snow removal operations, or correcting future snow removal operation load prediction information. Furthermore, the analysis unit 620 may be configured to analyze the relationship between factors influencing changes in road conditions and trends in the occurrence of bad roads, and weather conditions, traffic conditions, snow removal response measures, operating status of snow removal vehicles, or work performance of each snow removal business operator, using statistical or machine learning methods. This makes it possible to understand trends in the occurrence of bad roads, the effectiveness of snow removal responses, factors that increase the operational load of snow removal, or factors that will affect the future operational load of snow removal, contributing to improved preventative dispatch decisions, selection of target routes or work sections, resource allocation, and priority evaluation.

[0031] These analysis results 690 may be transmitted to the decision unit 630 and used as information to help determine the necessity of snow removal. Furthermore, the analysis results 690 may be distributed to the road snow removal unit or improvement unit as needed and used to generate snow removal decision support information, snow removal decision support information, snow removal decision support information, snow removal work resource allocation adjustment decision support information, verification information, or snow removal site work issue information. In addition, the analysis results 690 may be visualized in conjunction with a GIS (Geographic Information System) and configured to contribute to reviewing decision conditions, prediction conditions, models, or operational rules through comparison with snow removal implementation history, comparative analysis with snow removal method selection history, evaluation of implementation effectiveness, or difference verification between prediction results and actual information. The system may also be configured to analyze past weather information, traffic information, road space information, vehicle movement information, resident report information, snow removal information, snow removal work information, or snow removal transport status information to grasp the trends in fluctuations of snow accumulation, road conditions, traffic impact, snow removal work status, or snow removal operational load. Furthermore, the system may be configured to analyze the relationship between factors influencing changes in road conditions, trends in the occurrence of bad roads, and weather conditions, traffic conditions, snow removal measures, or the operational status of snow removal vehicles using statistical or machine learning methods. This will enable a more accurate understanding of the mechanisms of bad road occurrence and the effectiveness of countermeasures, and will contribute to the derivation of snow removal operational load information, the calculation of future snow removal operational load prediction information, priority evaluation, or preventive decision-making. These analysis results can be used as information regarding the necessity, urgency, traffic impact, workload, snow removal and transportation workload, operating workload of snow removal vehicles, or the allocation and adjustment of snow removal work resources. They may also be used to generate information to support snow removal decisions by the road snow removal department, snow removal decisions, snow removal decisions, or snow removal work resource allocation and adjustment decisions. Furthermore, in one embodiment of the present invention, the analysis result 690 may include analysis results derived based on snow removal work information or snow removal transport status information, and may be used to generate snow removal decision support information by the road snow removal unit, candidate snow disposal site utilization, candidate snow removal transport route, candidate snow removal start time, candidate number of snow removal vehicles required for snow removal, or snow removal work resource allocation adjustment decision support information. The output scores, evaluation results, prediction results, or decision-making support information may be displayed on a GIS (Geographic Information System) for each road section or area on the map, and may be color-coded according to the level of the score, the magnitude of the load, the degree of traffic impact, or the presence or absence of potential countermeasures. This allows operators and decision-makers to intuitively understand areas with high snow removal operational loads, routes or work sections requiring attention, sections targeted for snow removal, or areas requiring resource allocation adjustments, thereby supporting quick decision-making. The information to be analyzed is not limited to all information; analysis may be performed using any combination depending on the target area, operational system, processing purpose, target period, target route, target work section, or target snow removal business operator. Furthermore, the system may be configured to provide decision support that does not rely on a single sensor by performing processes such as matching image data with non-image data (for example, comparing image analysis results with optical fiber data), spatiotemporal interpolation processing for areas with frequent anomalies, information interpolation processing for nighttime or severe weather conditions, and multifaceted evaluation processing using AI (artificial intelligence) models, machine learning models, statistical models, time series prediction models, or rule-based models. Furthermore, the system may be configured to obtain distribution information regarding the population or number of households in a region from statistical information databases or administrative information, and to integrate and evaluate this information with the density and urgency of resident reports, thereby enabling snow removal decisions that are appropriate to the population size and density of the region. In addition, the system may be configured to dynamically adjust the weighting coefficients of each analysis indicator based on regional attributes. For example, by giving a higher value to the urgency of reports in areas with a large elderly population and increasing the weight of traffic impact near main roads, it becomes possible to perform evaluations that are more in line with the actual circumstances of each region. Furthermore, the analysis unit 620 may be configured to perform weighting processing of evaluation indicators using distribution information on vulnerable road users (elderly people, people requiring care, schoolchildren, people with disabilities) in the target area, as well as location information of medical facilities, welfare facilities, and educational facilities, and to correct the priority of snow removal and clearing responses for each road, snow removal and clearing operational load information, or snow removal and clearing decision support information from the perspective of prioritizing welfare and the protection of human life. Conventionally, decisions have been primarily based on empirical rules and rules, making it difficult to integrate and analyze large amounts of unstructured information (resident reports, images, social media, vibration data, etc.). In contrast, this invention uses AI (artificial intelligence) models, machine learning models, statistical models, clustering models, regression models, time series prediction models, or rule-based models to learn or estimate the nonlinear relationships and time series trends between this information, enabling the derivation of snow removal operation load information, the calculation of future snow removal operation load prediction information, or the generation of decision-making support information. Furthermore, the score generation process performed by the analysis unit 620 may consist of multivariate analysis or machine learning methods that take multiple pieces of information as input. For example, variables such as resident report density, traffic speed reduction rate, number of days without snow removal, snow depth, temperature, snowfall forecast, past snow removal history, operating status of snow removal vehicles, status of snow removal transport routes, or utilization status of snow disposal sites may be used as features, and these may be normalized or categorized to construct an input vector. The learning model may employ decision tree-based classification and regression models such as Random Forest or XGBoost (eXtreme Gradient Boosting), or numerical regression models using neural networks. The model's training data may include past snow removal results, dispatch status, priority, regional population composition, number of complaints, snow removal vehicle operation records, snow transport records, or snow disposal site usage records, and weight optimization may be performed using supervised learning. The output may be defined as a score, load level, rank, category, candidate information, or predicted value for each target area. This information, stored as analysis results 690, may be used by the decision unit 630 to determine whether or not action is necessary through threshold determination, etc., or it may be used by the road snow removal unit to generate snow removal decision support information, snow removal decision support information, snow removal decision support information, or snow removal work resource allocation adjustment decision support information. This configuration enables the analysis unit 620 to integrate and analyze both standardized information (such as sensor data) and non-standardized information (such as resident reports and video analysis results), achieving flexible decision-making support that goes beyond conventional rule-based processing.

[0032] The analysis unit 620 may evaluate indicators related to the necessity, urgency, traffic impact, difficulty of work, workload, operational load of snow removal vehicles, snow removal transport load, snow disposal site utilization load, or the degree of strain on snow removal work resources for each road, route, work section, snow removal business operator, road administrator, local government, or other management unit, based on multiple pieces of information obtained from the information acquisition unit 610, and derive integrated evaluation information including these. The evaluation information may be expressed as numerical scores, hierarchical ranks, classifications, candidate information, or predicted values, and may be used to derive snow removal operation load information, calculate future snow removal operation load prediction information, or generate various decision support information by the road snow removal unit. Furthermore, the analysis unit 620 may evaluate the workload for each route or each work section based on snowfall amount, snow depth, temperature, wind speed, snow quality, compaction condition, amount of snow piled on the road shoulder, reduction in road width, traffic impact, delays in route buses, utilization status of snow disposal sites, condition of snow removal and transport routes, operating status of snow removal vehicles, or the work capacity of each snow removal and transport company. The workload may be converted into indicators such as required working time, required number of snow removal and transport vehicles, heavy equipment load, number of workers, number of snow removal and transport trips, waiting time for transport to snow disposal sites, or work costs, and expressed as snow removal and transport operation load information or load score. Furthermore, the analysis unit 620 may acquire predictive information such as future snowfall, snow depth, temperature fluctuations, wind speed, snow quality, compacted snow conditions, road shoulder snow accumulation, road width reduction, traffic impact, and other predictive information in a time series based on short-term weather forecast information included in future snow removal environment information, or other future snow removal environment information, and calculate future snow removal operational load prediction information based on this predictive information. This makes it possible to provide support for making prior decisions regarding sudden snowfall, continuous snowfall, freezing, deterioration of compacted snow, increase in snow accumulation, reduction in road width, or expansion of traffic impact. Furthermore, predictive information regarding snow load may be used to evaluate the impact of said load on traffic, road structure, road width, road surface conditions, or snow removal work load. If the predicted value of snow load exceeds a predetermined standard, it may be evaluated as a high future snow removal operational load in the target route or work section, and this may be used to generate snow removal decision support information, snow removal decision support information, snow removal decision support information, or snow removal work resource allocation adjustment decision support information that takes this risk into consideration. Regarding the evaluation of workload, a load conversion coefficient may be set for each management unit based on information such as past snow removal daily reports, snow clearing daily reports, operational records, snow depth, operating hours, fuel consumption, road length, road width, number of vehicles, type of snow removal vehicle, operational records for each snow removal company, or unit cost of work. Specifically, the required workload may be calculated according to the length, width, snow depth, amount of snow piled on the road shoulder, reduction in road width, amount of snow to be cleared, or traffic impact of the target section, and the time, number of vehicles, number of workers, or cost required to process that workload may be estimated. This makes it easier to compare the workload relative to other sections, level out operational plans, or adjust the allocation of snow removal resources. Furthermore, regarding the use of short-term weather forecast information included in future snow removal environment information, time-series data on the probability of snowfall, snowfall amount, snow depth, temperature, wind speed, humidity, presence or absence of rainfall, snow quality, compacted snow condition, amount of snow accumulated on the road shoulder, or predicted reduction in road width may be obtained for each region, and the future snow removal operational load may be estimated based on statistical weather pattern analysis, machine learning, regression analysis, Bayesian inference, random forest, time-series forecasting model, or rule-based model. For example, if snow removal was frequently required in the past when certain weather and road condition conditions were met, then when these conditions are predicted to occur in the future, it may be evaluated as an increase in the future snow removal operational load. The evaluation score may be calculated as a comprehensive score by weighting and averaging various factors such as the necessity of snow removal, urgency, traffic impact, difficulty of work, workload, operational load of snow removal vehicles, snow removal and transportation load, snow disposal site utilization load, or the degree of strain on snow removal work resources, or by inputting these factors into a predetermined model. If the comprehensive score exceeds or is likely to exceed a predetermined standard, it may be provided to the road snow removal department as a candidate for priority response, pre-emptive response, deployment preparation, reassignment of snow removal vehicles, deployment of support, flexibility, redeployment, or pre-deployment. Furthermore, in a configuration in which a decision unit 630 is provided, the comprehensive score or evaluation information may be used in the decision processing in the decision unit 630. The analysis unit 620 may use past performance information regarding changes in priority in the target area, operating hours of snow removal vehicles, snow removal unit cost, number of snow removal transports, snow disposal site utilization status, traffic conditions on snow removal transport routes, or operational performance for each snow removal business operator to evaluate the consistency between future snow removal operational load and budget, work system, number of vehicles, or working hours. Alternatively, the system may be configured to calculate estimated implementation costs based on the required working hours, number of vehicles, number of personnel, amount of snow disposal site utilization, number of snow removal transports, or transport time for each snow removal response candidate, and to determine feasibility or the need for allocation adjustments based on a comparison with the budget or available work resources. Furthermore, the evaluation information may be structured to derive an integrated score by applying predetermined weights to multiple indicators. For example, a comprehensive evaluation may be performed using at least one of the following: traffic impact, workload, operational load of snow removal vehicles, snow removal and transport load, snow disposal site utilization load, density of resident reports, bus route delay information, or road width reduction. The evaluation may also include a process to classify the data into categories such as priority response, normal response, postponed response, pre-emptive response, candidate for support deployment, candidate for redeployment, or candidate for advance deployment, based on the score. This clarifies the basis for generating snow removal decision support information, snow removal decision support information, snow removal decision support information, or snow removal work resource allocation adjustment decision support information in the road snow removal department, thereby increasing its practicality. Furthermore, in one embodiment of the present invention, the analysis unit 620 may use information regarding workload, future snow removal environment information including short-term weather forecast information, operational performance, number of vehicles, working hours, costs, snow removal and transport load, snow disposal site utilization status, snow removal and transport route status, or the work capacity of each snow removal and transport business operator to generate snow removal decision support information, candidate snow disposal site utilization, candidate snow removal and transport route, candidate snow removal start time, candidate number of snow removal and transport vehicles required for snow removal, or snow removal work resource allocation adjustment decision support information.

[0033] In this specification, "evaluation information" refers to analysis results derived for each road, route, work section, snow removal business operator, road administrator, local government, or other management unit based on multiple pieces of information acquired by the information acquisition unit 610, and may include indicators regarding the necessity, urgency, traffic impact, difficulty of work, workload, operational load of snow removal vehicles, snow removal transport load, snow disposal site utilization load, degree of strain on snow removal work resources, or future snow removal operational load. Specifically, the evaluation information may include various indicators based on snow depth, snowfall, temperature, wind speed, snow quality, compaction status, road shoulder snow accumulation, road width reduction, freezing risk, traffic history, resident report density, bus route delay information, traffic impact, traffic status of snow removal routes, snow disposal site utilization, snow removal vehicle operation status, work performance for each snow removal company, remaining budget, distribution of vulnerable road users, and the locational relationship of medical facilities, welfare facilities, and educational facilities. These indicators may be weighted according to regional attributes, road type, facility distribution, traffic impact, or the degree of snow removal operational burden. Furthermore, these evaluation indicators may be integrated with weather, traffic, vehicle movement, resident reports, snow removal status, image information, fiber optic survey information, satellite survey information, or road service information using AI (artificial intelligence) models, machine learning models, statistical models, clustering models, regression models, time series forecasting models, or rule-based models, and may be configured as evaluation information that includes predictions of short-term or medium-term snow removal operational load. Furthermore, the evaluation information may be expressed as numerical scores, hierarchical ranks, classifications, candidate information, predicted values, or map display information, and may be used to generate snow removal decision support information, snow removal decision support information, snow removal decision support information, or snow removal work resource allocation adjustment decision support information by the road snow removal unit. In addition, patrol results, in-vehicle images, fixed-point camera images, post-snow removal finish evaluation information, or snow removal operation information acquired as actual results may be used to verify, correct, or update the evaluation information. Furthermore, in one embodiment of the present invention, the evaluation information may include indicators derived based on snow removal work information or snow removal transport status information. In this case, the evaluation information may include indicators based on the progress of snow removal work, the operating status of snow removal vehicles, the waiting status of snow removal vehicles, the number of snow removal transports, the waiting time for transport to the snow disposal site, the acceptance status of the snow disposal site, the remaining capacity of the snow disposal site, traffic congestion on the snow removal transport route, obstruction of traffic on the snow removal transport route, or the status of loading work in the snow removal target section. In this specification, "evaluation information" is a broad concept that includes evaluations in general derived from various information acquired by the information acquisition unit 610 or analysis results obtained by the analysis unit 620, and "snow removal operation evaluation information" is one form of evaluation information that includes information on the expected excess, increase, or shortage of snow removal operation load, calculated based on a comparison of future snow removal operation load prediction information with a standard load level.

[0034] In this specification, "decision information" means information derived or generated by the analysis unit 620 or the road snow removal unit regarding the necessity of snow removal, urgency, priority, timing of response, feasibility of work, preparation for dispatch, quantity of snow removal vehicles to be deployed, deployment of snow removal vehicles, dispatch requests to snow removal businesses, candidate routes or work sections to be snow removed, candidate routes or work sections to be cleared, candidate start dates for snow removal, candidate use of snow disposal sites, candidate snow removal transport routes, candidate support deployment, candidate flexibility, candidate relocation, or candidate pre-deployment. The decision information may be generated based on various information obtained from the information acquisition unit 610, evaluation information derived by the analysis unit 620, snow removal operation load information, future snow removal operation load prediction information, snow removal operation evaluation information, traffic impact information, future traffic impact prediction information, bus route delay information, snow removal transport load information, snow disposal site utilization status, or snow removal transport route status. The decision information may also be used as snow removal decision support information, snow removal decision support information, snow removal decision support information, or snow removal work resource allocation adjustment decision support information. The judgment information may be expressed in the form of a score, judgment categories, candidate lists, map displays, time-series displays, tables, notification information, or information used by road administrators for decision-making. Furthermore, the judgment information may be structured to be used in processes related to snow removal implementation plans, snow clearing plans, work plans, work sequences, snow removal vehicle deployment plans, contact with snow removal contractors, requests for assistance, adjustments, redistribution adjustments, or preliminary deployment. Furthermore, in one embodiment of the present invention, the decision information may include snow removal decision support information or decision support information related to snow removal and transportation. In this case, the decision information may include a candidate snow removal start time, a candidate route or work section to be snow removed, a candidate number of snow removal vehicles required for snow removal, a candidate use of a snow disposal site, a candidate snow removal and transportation route, the number of snow removal and transportation trips, the time of day for transporting snow to the snow disposal site, or a candidate change to the snow removal and transportation route.

[0035] The analysis unit 620 may perform analysis based on road conditions, road surface conditions, road space conditions, traffic conditions, vehicle driving conditions, weather conditions, resident reporting status, or snow removal status in order to evaluate the necessity of snow removal, snow removal operational load, future snow removal operational load, or priority of snow removal response. For example, the analysis unit 620 may perform analysis based on a specific definition of so-called bad roads. Here, a bad road refers to road conditions in which vehicle driving is difficult due to unevenness of the snow-covered road surface, compacted snow thickness, snow quality, snow accumulation, freezing, snowmelt, bowl-shaped deformation, rutting, snow accumulation on the road shoulder, snow dikes, reduction in road width, or other obstructions to traffic. The analysis unit 620 may be configured to perform a bad road evaluation for each target section using one or more of these indicators and calculate a bad road score that is used for snow removal operational load information, future snow removal operational load prediction information, or snow removal decision support information. For example, in evaluating unevenness, amplitude values ​​and variability can be calculated based on vertical fluctuation values ​​obtained from the vehicle's acceleration sensor, and these can be quantitatively expressed as an unevenness index. Alternatively, a configuration that sets thresholds and evaluates in stages is also possible, which contributes to the standardization of on-site judgment. Furthermore, compacted snow thickness can be evaluated using directly measured values, values ​​estimated through image analysis, or step differences estimated from acceleration information as a guideline for thickness. In addition, regarding road surface conditions, image data obtained from fixed-point cameras, in-vehicle cameras, drones, smartphones, connected drive recorders, or patrol vehicles may be used to perform object detection, image segmentation, feature extraction, or image analysis processing using AI (artificial intelligence) models to recognize snow accumulation, snow piles, compacted snow, freezing, snowmelt, snow levees, road shoulder snow accumulation, road width reduction, or snow removal status, and convert this into a bad road index, snow removal environment information, or future snow removal environment information. The analysis unit 620 may include a process that uses these poor road indicators to calculate the percentage of poor road sections exceeding a predetermined standard for each management unit, which is a division of the road into route units or work sections. The system may then perform scoring based on a step-by-step evaluation according to the percentage and reflect this in snow removal operation load information, snow removal operation evaluation information, future snow removal operation load prediction information, or various decision support information. Furthermore, the analysis unit 620 may be configured to manage road information using a GIS (Geographic Information System) at the branch number level, route level, work section level, road section level, or management level, and to perform detailed evaluations of individual sections on main roads and local roads. This configuration makes it possible to identify local problem areas, such as between intersections, at points of gradient change, near bus stops, along routes to snow disposal sites, or at locations where road width reduction is likely to occur, in addition to the entire route, thereby contributing to the prioritization and efficiency of snow removal and clearing operations. Furthermore, the system may be configured to evaluate the reliability of the information for the section based on the patrol vehicle's mileage, frequency of travel, acquisition time, acquisition location, image clarity, frequency of fixed-point camera shooting, or reliability of the information source, and to perform correction processing, weighting reduction processing, re-acquisition request, or matching with other information processing if the reliability falls below a predetermined standard. In addition, the analysis unit 620 may use multiple pieces of information, such as bad road information, traffic information, weather information, vehicle driving information, road service information, resident notification information, snow removal information, snow removal work information, snow removal transport status information, fiber optic survey information, satellite survey information, or image information, to perform processing to correct or calculate snow removal operation load information, future snow removal operation load prediction information, or various decision support information using rule-based models, statistical models, machine learning models, clustering models, regression models, time series prediction models, or AI (artificial intelligence) models. With such a configuration, consistent decision support becomes possible from both rule and actual measurement data perspectives. Furthermore, the analysis unit 620 in this embodiment may be configured to comprehensively analyze distribution information regarding vulnerable road users in the target area, location information of medical facilities, welfare facilities, and educational facilities, weather forecast values ​​regarding snow load, snow removal response history for each management unit, regional characteristics, road type, or traffic impact, and generate a score that numerically represents the urgency of snow removal response, snow removal operation load, or future snow removal operation load for each road, route, work section, or management unit. This score may be used for snow removal operation load information, snow removal operation evaluation information, snow removal decision support information, or correction processing of response priority. Furthermore, when generating various decision-making support information for road snow removal departments, the system may be configured to group target areas by priority or load level based on evaluation information, snow removal operation load information, future snow removal operation load prediction information, traffic impact information, bus route delay information, bad road score, snow removal transport load information, snow disposal site utilization status, or snow removal transport route status, and to generate response candidates for each time period, work method, snow removal vehicle, snow removal business operator, or target route or work section. For example, routes or work sections requiring emergency response may be extracted as early response candidates, and decision-making support information that takes into account the time of day may be generated, such as utilizing time periods with low traffic volume. Furthermore, the results of the poor road conditions evaluation may be used not only for prioritizing snow removal and clearing operations, but also for deriving snow removal and clearing operational load information, calculating future snow removal and clearing operational load prediction information, understanding the condition of snow removal target sections or snow removal and transport routes, and generating candidate snow removal target routes, snow removal target routes, snow removal start times, snow disposal site utilization candidates, snow removal and transport route candidates, support deployment candidates, flexible deployment candidates, relocation candidates, or pre-deployment candidates.

[0036] The decision unit 630 operating in the snow removal decision support system 600 may be configured to make an integrated and comprehensive decision on the necessity of snow removal based on some or all of the analysis results 690 of various information analyzed by the analysis unit 620, namely road surface information 640, traffic information 650, road space information 660, weather information 670, vehicle driving information 680, road service information, fiber optic survey information, satellite survey information, resident notification information, and snow removal information, and store the decision result 695. The judgment result 695 may include information regarding the necessity of snow removal at each location, route, work section, snow removal business operator, road administrator, local government, or other management unit, snow removal priority, work necessity score, snow removal operational load, future snow removal operational load, recommended time slots for snow removal response, candidate timings for snow removal dispatch, candidate timings for snow removal start, or information regarding the allocation and adjustment of snow removal work resources. The judgment result 695 may be displayed in a format that visualizes it on a map, displays it in a list, displays it chronologically, in a table format, or on a monitoring screen such as a dashboard. Furthermore, the decision unit 630 may be configured to use an AI (artificial intelligence) model, machine learning model, statistical model, clustering model, regression model, time series forecasting model, or rule-based model to support or automate decision-making based on the analysis results 690, snow removal operation load information, future snow removal operation load forecast information, snow removal operation evaluation information, traffic impact information, future traffic impact forecast information, bus route delay information, snow removal transport load information, or snow disposal site utilization status. Furthermore, the decision unit 630 may be configured to cooperate with the road snow removal unit and, based on the judgment result 695, support decisions regarding the necessity, priority, implementation time, amount of snow removal vehicles to be deployed, deployment of snow removal vehicles, dispatch requests to snow removal businesses, candidates for routes or work sections to be snow removed, candidates for routes or work sections to be cleared, candidates for the start time of snow removal, candidates for use of snow disposal sites, candidates for snow removal transport routes, candidates for deployment of support vehicles, candidates for flexibility, candidates for re-deployment, or candidates for pre-deployment. This makes it easier to ensure consistency with the analysis result 690, future snow removal operation load prediction information, and various decision support information generated by the road snow removal unit. Furthermore, the decision unit 630 may be configured to determine the necessity of snow removal or the possibility of increased snow removal operational load in the near future based on weather forecasts, future snow removal environment information, snow removal operation information, snow removal environmental information, snow removal performance, snow removal work information, snow removal transport status information, resident reporting trends, traffic operation-related information, bus route delay information, image information, or analysis results 690. In addition to weather forecast information, various information obtained by the information acquisition unit 610 may be used in an integrated manner in the decision processing of the decision unit 630. The decision result 695 may be handed over to the road snow removal unit and used to consider the start time of snow removal response, candidate timing for snow removal dispatch, candidate start time for snow removal, candidate priority, response time period, or to generate information to support decision-making regarding the allocation of snow removal work resources. Furthermore, the judgment result 695 may be used to generate snow removal decision support information, snow removal decision support information, snow removal decision support information, or snow removal work resource allocation adjustment decision support information by the road snow removal department. For example, the judgment result 695 may be used as auxiliary information to determine whether or not to adjust the allocation of snow removal work resources when the predicted future snow removal operational load information exceeds or is likely to exceed a predetermined standard load level. In addition, the judgment result 695 may be compared with actual information obtained after snow removal and used to generate verification information or snow removal site work issue information. Note that the decision unit 630 shown in Figure 1 is a configuration that shows the decision processing in one embodiment of the present invention, and the present invention is not limited to those in which the decision processing by the decision unit 630 is essential. For example, the present invention may be configured such that the road snow removal unit generates snow removal decision support information, snow removal decision support information, snow removal decision support information, or snow removal work resource allocation adjustment decision support information based on snow removal operation load information, future snow removal operation load prediction information, snow removal operation evaluation information, traffic impact information, future traffic impact prediction information, bus route delay information, or snow removal transport load information derived or calculated by the analysis unit 620. Thus, the decision unit 630 may function as a component that comprehensively evaluates the diverse information acquired or analyzed by the analysis unit 620 and supports snow removal decision-making. On the other hand, the calculation of future snow removal operational load prediction information, snow removal decision support information, snow removal decision support information, snow removal decision support information, or snow removal work resource allocation adjustment decision support information in the present invention may be implemented by the analysis unit 620 and the road snow removal unit, and is not limited by the presence or absence or name of the decision unit 630.

[0037] Figure 11 is a flowchart showing an example of the flow of the snow removal decision support system 600. The information acquisition unit 610 periodically acquires information on road surface conditions from the road surface condition provision server 100 (for example, every few minutes) (S10). The information acquisition unit 610 periodically acquires information on traffic conditions from the traffic condition provision server 200 (for example, every few minutes) (S11). The information acquisition unit 610 periodically acquires information on road space conditions from the road space condition provision server 300 (for example, every few minutes) (S12). The information acquisition unit 610 periodically acquires information on weather conditions from the weather condition provision server 400 (for example, every few minutes) (S13). The information acquisition unit 610 periodically acquires information on vehicle driving conditions from the vehicle driving condition provision server 500 (for example, every few minutes) (S14). The analysis unit 620 then extracts areas where the road width has been significantly reduced due to snow accumulation from the road surface information 640 (S15). The analysis unit 620 extracts sections where traffic congestion is continuously occurring from the traffic information 650 (S16). The analysis unit 620 extracts dangerous areas where snowdrifts are high (for example, about 1m or more) and visibility is poor from the road space information 660 (S17). The analysis unit 620 extracts areas where the amount of snowfall since the start of the snowfall has reached 10cm or more from the weather information 670 (S18). The analysis unit 620 extracts sections where bus delays have continued for 30 minutes or more from the vehicle driving information 680 (S19). Next, based on the results of the above analysis, the decision unit 630 makes a comprehensive determination of the necessity of snow removal and, if necessary, makes a decision to execute the appropriate action (S20). Figure 11 shows an example of a typical processing flow, and the present invention is not limited thereto. In this embodiment, various types of information not shown, such as snow removal information, resident notification information, optical fiber survey information, satellite survey information, road service information, snow removal operation information, snow removal environment information, future snow removal environment information, snow removal work information, snow removal transport status information, traffic operation-related information, bus route delay information, and image information, can also be acquired by the information acquisition unit 610 and become the subject of analysis processing by the analysis unit 620. Furthermore, the analysis unit 620 may be configured to use this information to perform the following: matching snow removal operation information with snow removal environment information, deriving snow removal operation load information, calculating future snow removal operation load prediction information based on future snow removal environment information, making corrections using traffic impact information or bus route delay information, and generating or correcting snow removal environment information or future snow removal environment information based on image information. Furthermore, these analysis results may be used in the decision unit 630 to determine the necessity or priority of snow removal and clearing operations, and may also be used to generate snow removal and clearing decision support information, snow removal decision support information, snow clearing decision support information, or snow removal and clearing work resource allocation adjustment decision support information by the road snow removal and clearing unit. In addition, the system may be configured to be used, as necessary, to update decision conditions, prediction conditions, models, or operational rules, to generate verification information, or to generate information on on-site snow removal and clearing work challenges for the next snow removal and clearing season.

[0038] Figure 12 shows an example of the criteria used by the decision unit 630. The decision unit 630 can determine the necessity of snow removal measures based on triggers such as: heavy snowfall of 10 cm / h or more (1st element) 631; road width reduced by snow accumulation resulting in bus delays of 30 minutes or more (2nd element) 632; snow melting due to sunny weather, causing severe unevenness on snow-covered roads and worsening traffic congestion (3rd element) 633; ​​heavy snow warning issued, causing vehicles to slip and skid, as well as congestion due to vehicles getting stuck in the snow (4th element) 634; and frequent tire lock-ups on icy roads at -10°C, resulting in self-inflicted accidents and congestion (5th element) 635. Furthermore, some or all of the judgment results 695 determined by the decision unit 630, the analysis results 690 derived by the analysis unit 620, snow removal operation load information, future snow removal operation load prediction information, snow removal operation evaluation information, traffic impact information, bus route delay information, or various information acquired by the information acquisition unit 610 may be provided to road administrators, snow removal operators, transportation operators, government agencies, road users, or residents. This information may be provided by email to snow removal operators, data provision to road administrator GIS (Geographic Information System), linkage to autonomous driving systems and MaaS (Mobility as a Service), information provision to government agencies or media organizations, information disclosure functions for road users or residents, and transmission to homepages, smartphone applications, car navigation systems, digital signage, or other terminal devices. It should be noted that this information provision does not necessarily require a specific information provision unit and may be performed via the snow removal decision support system 600, the road snow removal unit, external systems, or existing business systems. As an example of the function of disclosing information to road users or residents, information may be provided regarding unevenness of snow-covered road surfaces, thickness of compacted snow on the road surface, traffic congestion status, camera images, height of snow levees around routes or intersections, future snowfall forecasts or snow depth, bus route delay information, locations where vehicles are stuck, snow removal orders or implementation status, snow removal orders or implementation status, patrol results, snow removal and snow removal schedules, progress of snow removal and snow removal work, information on traffic obstruction, or information on reduction of road width. Furthermore, this information, analysis results 690, judgment results 695, snow removal and snow removal judgment support information, snow removal judgment support information, snow removal judgment support information, or snow removal and snow removal work resource allocation adjustment judgment support information may be configured to be transmitted to mobile terminal devices, fixed terminal devices, in-vehicle terminal devices, road administrator terminals, snow removal and snow removal business operator terminals, or external systems. Figure 12 shows an example of typical judgment criteria, and the present invention is not limited thereto. In this embodiment, various types of information not shown, such as snow removal information, resident notification information, optical fiber survey information, satellite survey information, road service information, snow removal operation information, snow removal environment information, future snow removal environment information, snow removal work information, snow removal transport status information, traffic operation-related information, bus route delay information, and image information, may also be used for analysis processing by the analysis unit 620, judgment processing by the decision unit 630, or generation of judgment support information by the road snow removal unit. Furthermore, these judgment results or analysis results may be used by the road snow removal unit to generate snow removal judgment support information, snow removal judgment support information, snow removal judgment support information, or snow removal work resource allocation adjustment judgment support information, and may be used, if necessary, to update judgment conditions, prediction conditions, models, or operation rules, generate verification information, or generate information on snow removal site work challenges for the next snow removal season.

[0039] The snow removal decision support system 600 may also be configured to include an improvement unit that continuously verifies or updates some or all of the analysis results 690 obtained by the analysis unit 620, the decision results 695 output by the decision unit 630, and the snow removal decision support information, snow removal decision support information, snow removal decision support information, or snow removal work resource allocation adjustment decision support information generated by the road snow removal unit. The improvement unit may be a component that forms a loop of learning, verification, updating, or reconstruction within a series of processes in the snow removal decision support system 600, such as acquiring, analyzing, predicting, supporting decisions, executing, evaluating, and verifying various types of information, in order to improve the accuracy of snow removal operation load prediction, the validity of decision support information, the effectiveness of snow removal response, or resident satisfaction. The improvement unit may be configured to verify or update analytical methods, prediction conditions, decision conditions, weighting conditions, thresholds, features, input information selection criteria, or operational rules using AI (artificial intelligence) models, machine learning models, statistical models, clustering models, regression models, time series forecasting models, or rule-based models. For example, the improvement unit may detect overestimation, underestimation, prediction errors, or biases in decision conditions based on comparisons with actual data regarding snow removal operation load information, future snow removal operation load prediction information, snow removal operation evaluation information, traffic impact information, bus route delay information, snow removal transport load information, snow disposal site utilization status, snow removal transport route status, or snow removal work resource allocation adjustment decision support information. Furthermore, the improvement unit may be configured to use road surface information, traffic information, road space information, weather information, vehicle driving information, road service information, optical fiber survey information, satellite survey information, resident notification information, snow removal information, snow removal operation information, snow removal environment information, future snow removal environment information, snow removal work information, or snow removal transport status information acquired by the information acquisition unit 610 as input data, and to use the analysis results 690 from the analysis unit 620, the judgment results 695 from the decision unit 630, various judgment support information from the road snow removal unit, and actual snow removal response performance information as learning targets or verification targets. Furthermore, the improvement unit may collect or analyze traffic congestion information, changes in traffic speed, delays of route buses, recurrence of resident reports and complaints, road conditions obtained by patrol vehicles, road surface conditions after snow removal, remaining snow conditions, ruts, steps, reduction in road width, remaining snow embankments, or re-snow accumulation conditions after snow removal, and evaluate their consistency with future snow removal operational load prediction information, snow removal decision support information, snow removal decision support information, or snow removal work resource allocation adjustment decision support information generated before snow removal operations. The Improvement Unit may review the conditions for updating snow removal operational load information or future snow removal operational load prediction information using information newly acquired or updated during the snow removal season. Furthermore, towards the end of or after the end of the snow removal season, the Improvement Unit may compare the future snow removal operational load prediction information calculated or updated during the season with the actual snow removal operational information acquired, and generate verification information regarding the difference between the predicted snow removal operational load and the actual snow removal operational load. In addition, the Improvement Unit may refer to the verification information and actual information to organize the information used to generate information on snow removal site work issues that are subject to improvement for the next snow removal season, for each route, work section, snow removal business operator, road administrator, or local government. The improvement unit may use performance information after snow removal operations, such as the operating time of snow removal vehicles, the number of dispatches, the time of completion of work, work delays, the work area, the amount of work, the number of snow removal transports, the waiting time for transport to the snow disposal site, the amount of transported per unit time, the travel time on the snow removal transport route, the recovery status of road width after snow removal, the change in the number of resident reports, or the improvement status of traffic speed, as training signals or evaluation indicators. This makes it possible to update the conditions for deriving snow removal operation load information, the conditions for calculating future snow removal operation load prediction information, the conditions for calculating snow removal operation evaluation information, or the conditions for generating various decision support information according to the actual operational results. Furthermore, the improvement department may analyze resident complaint information, including the content of the complaint, the density of complaints, the location of the complaint, the time of the complaint, whether or not there were repeat complaints, the increase or decrease in complaints, the status of snow removal and clearing after the complaint, or the recurrence of complaints after snow removal and clearing, and revise the weighting conditions used for snow removal and clearing operational load information, traffic impact information, snow removal and clearing operational evaluation information, or decision support information. For example, if complaints continue at the same location or on the same route even after snow removal and clearing, the evaluation conditions for road width reduction, snow compaction, insufficient snow removal, traffic disruption, or workload related to that location or route may be revised. Furthermore, the improvement department may update the weighting conditions according to the time of day by referring to traffic volume by time of day, the time of day when snow removal work is carried out, the time of day when resident reports occur, the time of day when bus delays occur, weather conditions, the operating status of snow removal vehicles, or the work performance of each snow removal company. This will enhance the support for snow removal decisions according to daytime snow removal, nighttime snow removal, commuting hours, school hours, public transport operating hours, or times of low traffic volume. Furthermore, the improvement unit may evaluate the correlation between the integrated analysis results from the analysis unit 620 and actual traffic disruptions, bus delays, the number of resident complaints, sections where snow removal and clearing were not handled, delays in snow removal and transport, congestion at snow disposal sites, or the strain on snow removal and clearing vehicles, and dynamically adjust the confidence coefficient or weighting coefficient for each information source. For example, among image information, fiber optic survey information, satellite survey information, resident complaint information, vehicle travel information, or snow removal and clearing performance information, the weight of information sources that are highly consistent with actual results in a specific region or time period may be increased, and the weight of information sources that are less consistent may be decreased. Furthermore, in score generation or prediction processing using AI (artificial intelligence) models, the results of XAI (explainable AI) analysis may be used in conjunction to evaluate the validity or transparency of the basis for judgment. For models with poor explainability, models that are overly dependent on specific features, or models that deviate significantly from actual results, the configuration may involve augmenting the training data, re-selecting features, resetting thresholds, changing the training data period, or modifying the model structure. Furthermore, the Improvement Unit may, in cooperation with the Analysis Unit 620 or the Road Snow Removal Unit, use snow removal operation load information, future snow removal operation load prediction information, snow removal operation evaluation information, verification information, or snow removal field work issue information to revise the judgment conditions, prediction conditions, models, or operational rules for future snow removal responses. This allows the snow removal decision support system 600 to continuously improve the accuracy of its snow removal response support while reflecting regional characteristics, road characteristics, traffic characteristics, weather characteristics, snow disposal site operational characteristics, snow removal transport route characteristics, or work characteristics of each snow removal business operator. Furthermore, these improvement processes are not limited to being executed by the improvement unit, but may also be executed by the analysis unit 620, the road snow removal unit, or an external learning processing system. The timing of the improvement processes may also be batch processing at night, periodic processing at regular intervals, sequential processing during the same snow removal season, verification processing after the end of the snow removal season, trigger processing during abnormal weather conditions, trigger processing when there is a surge in resident reports, or processing based on arbitrary execution instructions from the road administrator.

[0040] In this specification, "management information" refers to attribute information associated with roads, routes, work sections, snow removal businesses, road administrators, local governments, snow disposal sites, snow removal and transport routes, or other management units in the target area. Management information may also include information on the type of management unit, the managing entity, past snow removal performance, snow removal operation information, snow removal environment information, future snow removal environment information, road width, route type, road type, traffic volume, route bus routes, snow removal target sections, snow removal target sections, snow disposal sites, snow removal and transport routes, vehicle bases, budget limits, the location of available snow removal businesses or construction companies, the number of operational snow removal vehicles or work machines, the type of snow removal vehicle, the work capacity of each snow removal business, snow removal dispatch criteria, work standards, work guidelines, or information on past trends in resident complaints. This management information may be used in the analysis unit 620 as basic information for deriving snow removal operational load information for each route, work section, snow removal business operator, road administrator, or municipality. Furthermore, the management information may be used to predict which routes, work sections, snow removal business operators, road administrators, or municipalities will experience a concentration of snow removal operational load in response to future snow removal environmental conditions indicated by future snow removal environmental information. Furthermore, the management information may be used by the road snow removal department to generate snow removal decision support information, snow removal decision support information, snow removal decision support information, or snow removal work resource allocation adjustment decision support information. For example, based on the number of snow removal vehicles, vehicle types, work capacity of each snow removal business operator, location or acceptance capacity of snow disposal sites, snow removal transport routes, vehicle bases, budget limits, route types, road widths, traffic volume, or route bus routes included in the management information, the amount of snow removal vehicles to be deployed, the deployment of snow removal vehicles, requests for deployment to snow removal businesses, candidate snow removal start dates, candidate routes or work sections to be targeted for snow removal, candidate use of snow disposal sites, candidate snow removal transport routes, candidate support deployments, candidate flexibility, candidate re-deployment, or candidate pre-deployment may be generated. Furthermore, management information may be updated during the same snow removal season. For example, management information may be updated in response to changes in the operational status of snow removal vehicles, the operational capacity of snow removal operators, the remaining capacity of snow disposal sites, the traffic conditions on snow removal routes, traffic conditions, weather conditions, snow removal performance, or resident reports. The updated management information may be reflected in updating snow removal operational load information or future snow removal operational load forecast information, as well as in generating various decision-making support information.

[0041] The snow removal decision support system 600 may be configured to include a prediction unit that evaluates future road conditions, impacts on traffic functions, impacts on the wide-area snow removal system, or snow damage risks in the medium to long term or on a wide-area basis, in preparation for special events such as extreme snowfall, continuous snowfall, widespread traffic disruption, or snow damage. The prediction unit may be configured to estimate the possibility of future large-scale snowfall, widespread traffic paralysis, snow damage risks exceeding the normal snow removal system, or the need for emergency response, based on the analysis results 690 accumulated by the analysis unit 620, the history of decision results 695 output by the decision unit 630, past snow removal implementation history, snow removal operation information, snow removal environment information, resident reporting trends, traffic impact, weather change trends, topography, road structure, snow disposal site utilization trends, snow removal transport route utilization trends, or past heavy snow response history. The prediction unit may be configured to quantitatively or probabilistically predict, for example, the possibility of extreme snowfall, continuous snowfall, widespread traffic disruptions, concentrated reporting areas, difficulties in snow removal across multiple regions, or the possibility of snow damage exceeding the normal snow removal capacity, from several days in advance through the snow removal season. This makes it possible to generate auxiliary information that can be used for wide-area preventative measures, emergency response policies, information sharing with related organizations, consideration of medium- to long-term snow removal systems, or consideration of operational policies in preparation for snow damage, separate from individual dispatch decisions, decisions regarding individual routes or work sections, or decisions regarding the allocation of individual snow removal resources during normal snow removal operations. Furthermore, the prediction unit may use AI (artificial intelligence) models, machine learning models, statistical models, clustering models, regression models, time series prediction models, or rule-based models to learn or estimate time series fluctuations, geographical distribution, similarity to past heavy snow response patterns, trends in expanding traffic impact, trends in concentration of resident reports, or trends in the occurrence of conditions where wide-area snow removal is difficult. Input factors may include past snow accumulation history, snowfall amount, snow depth, temperature trends, wind direction, wind speed, snow density, past snow removal delays, resident report volume, complaint density, trends in declining traffic flow, history of snow-stuck incidents, route bus delay information, snow removal implementation history, snow transport record, snow disposal site usage history, traffic conditions on snow transport routes, or road surface images. Furthermore, the prediction unit may be configured to work in conjunction with the analysis unit 620 or the improvement unit to improve the reliability of prediction results, evaluate prediction errors, verify discrepancies with actual performance information, or retrain the model. For example, the prediction conditions, weighting conditions, model, or operational rules may be reviewed by comparing the snow damage risk, the risk of widespread traffic disruption, the possibility of exceeding the normal snow removal system, or the possibility of concentrated reporting areas evaluated by the prediction unit with actual snow removal operation information, traffic impact information, resident reporting information, snow removal performance information, or snow removal and transport performance information. The prediction results from the prediction unit are provided to the analysis unit 620 and may be used as supplementary information for evaluating snow removal operations, traffic impact information, risk scores, the need for wide-area snow removal responses, or for considering emergency response policies. Furthermore, the prediction results from the prediction unit are provided to the road snow removal unit and may be used to generate decision-making support information regarding wide-area or emergency responses, distinct from individual decisions made under normal circumstances. The main embodiments relating to the claims of this application are primarily described in paragraph 0046 and subsequent paragraphs. The prediction unit described in this paragraph is an optional auxiliary configuration distinct from the configuration in which the analysis unit 620 derives snow removal operation load information based on the correspondence between snow removal operation information and snow removal environment information, and calculates future snow removal operation load prediction information by applying the said snow removal operation load information to future snow removal environment conditions indicated by future snow removal environment information. In other words, the prediction unit is not limited to the main embodiments of this application and may be provided as an extended configuration for performing medium- to long-term or wide-area risk assessments regarding extreme snowfall, widespread snow damage, traffic disruption, or snow removal systems in emergencies.

[0042] The snow removal decision support system 600 may also be configured to include a road snow removal unit that generates snow removal decision support information, snow removal decision support information, snow removal decision support information, or snow removal work resource allocation adjustment decision support information based on future snow removal operational load prediction information, snow removal operational load information, snow removal operational evaluation information, traffic impact information, bus route delay information, snow removal transport load information, snow disposal site utilization status, snow removal transport route status, or various information acquired by the information acquisition unit 610. The road snow removal unit is configured to generate information to support decisions on snow removal responses by road administrators or snow removal operators, and is not limited to a configuration that directly formulates snow removal implementation plans or snow removal implementation plans, but may also be configured to generate information used in the formulation, updating, review, or operational decisions of such plans. Local governments or road administrators may formulate snow removal plans and snow removal work guidelines in advance, which may include the snow removal implementation system (organization, implementation system, patrols, snow-related consultation desk, snow removal contractors, snow removal vehicles, snow removal work evaluation, snow removal dispatch orders, public awareness activities, etc.), snow removal classifications (main roads, auxiliary main roads, suburban main roads, fully contracted work areas, designated contracted work areas, local roads, important routes, etc.), snow removal implementation methods (snow removal standards, snow removal dispatch standards, snow removal methods, snow removal duration, snow removal time, snow removal time, routes, snow disposal sites, anti-slip measures by applying de-icing agents, etc.), and types of snow removal work (normal snow removal work, fresh snow removal work, road surface leveling work, widening snow removal work, transport snow removal work, intersection snow removal work, bottleneck work, narrow road snow removal work, snow peeling work, de-icing agent application work, etc.). This information may be registered in advance with the road snow removal department and referenced when the department generates various decision-making support information. The Road Snow Removal Department may generate snow removal decision support information that includes at least one of the following, based on the future snow removal operational load prediction information calculated by the Analysis Department 620: the start date of snow removal response, the routes or work sections to be addressed, the number of snow removal vehicles to be deployed, the deployment of snow removal vehicles, the dispatch of snow removal businesses, or information used for decision-making by road administrators. The Road Snow Removal Department may also generate response candidates for each target area, route, work section, or snow removal business based on the future snow removal operational load prediction information, road width reduction prediction, traffic impact prediction, route bus delay information, snow removal vehicle operating status, or the work capacity of each snow removal business. The Road Snow Removal Department may generate snow removal decision support information that includes at least one of the following as decision support information regarding snow removal: candidate timing for dispatching snow removal vehicles, candidate routes to be snow removed, candidate work sections to be snow removed, or candidate snow removal priority for routes or work sections. For example, the Road Snow Removal Department may generate candidate start times for snow removal, target routes, target work sections, working hours, or vehicles to be deployed based on short-term snowfall forecasts, snow depth forecasts, compaction condition forecasts, road shoulder snow accumulation forecasts, road width reduction forecasts, traffic impact forecasts, or the operating status of snow removal vehicles. The road snow removal unit may generate snow removal decision support information that includes at least one of the following as decision support information regarding snow removal: candidate routes to be snow removed, candidate work sections to be snow removed, candidate start times for snow removal, candidate number of snow removal vehicles required for snow removal, candidate use of snow disposal sites, or candidate snow removal and transport routes. For example, the road snow removal unit may generate candidate start times for snow removal, candidate use of snow disposal sites, candidate snow removal and transport routes, candidate delivery time slots, or candidate number of vehicles required based on snow removal work information, snow removal and transport status information, snow removal vehicle operating status, snow disposal site acceptance status, snow disposal site remaining capacity, traffic congestion on snow removal and transport routes, loading work status in the snow removal target section, or the amount of snow to be snow removed. The Road Snow Removal Department may generate information to support decisions regarding the allocation of snow removal work resources, including at least one of the following: candidates for support deployment, candidates for resource sharing, candidates for reallocation, or candidates for pre-deployment, relating to snow removal work resources across multiple routes, multiple work sections, multiple snow removal contractors, multiple road administrators, or multiple municipalities. For example, the Road Snow Removal Department may compare future snow removal operational load forecast information with a standard load level determined based on the snow removal operational load information, and if the future load exceeds or is likely to exceed the standard load level, it may determine whether or not to adjust the allocation of snow removal work resources, and based on the determination result, it may output or notify information to support decisions regarding the allocation of snow removal work resources. Furthermore, when generating information to support decisions regarding the allocation of snow removal work resources, the Road Snow Removal Department may refer to the number of snow removal vehicles, vehicle types, number of workers, work teams, vehicle bases, available capacity for each snow removal business operator, travel time, standby status, utilization status of snow disposal sites, status of snow removal and transport routes, location relationship of snow removal target routes or work sections, traffic conditions, weather conditions, or past snow removal performance. When multiple municipalities or snow removal businesses cooperate, they may organize the supply-demand relationship using work vehicles, workers, snow disposal sites, vehicle bases, snow removal and transport routes, or target work sections as management units, and generate candidates for support deployment, resource sharing, redeployment, or pre-deployment. Furthermore, the snow removal implementation plan in this specification is distinct from the annual snow removal plan predetermined by the local government or road administrator, and may include implementation plans that are formulated, updated, reviewed, or referenced daily or at predetermined intervals based on information obtained or calculated by the snow removal decision support system 600. In addition, the snow removal implementation plan in this specification includes plans related to snow removal work or snow removal and transportation, and may include at least one of the following: snow removal target section, snow removal time slot, vehicles used, snow disposal site, snow removal and transportation route, time slot for transporting snow to the disposal site, order of transport, order of work, requests for assistance, or responses to obstacles in snow removal and transportation. Various decision support information generated by the road snow removal department may be used in formulating, updating, reviewing, approving, or operational decisions regarding these snow removal implementation plans or snow removal implementation plans. The areas targeted for snow removal may be linked to predefined routes or work sections, and the road snow removal department may be configured to generate, for each of these management units, the start date for snow removal, target candidates, priority candidates, work type, implementation timing, candidate vehicles to be deployed, or candidate allocation adjustments for snow removal work resources. By associating route codes or work section IDs with notification density, snow removal history, snow removal history, complaint history, traffic impact information, bus route delay information, operating status of snow removal vehicles, snow disposal site utilization status, or snow transport route status, the accuracy of generating decision support information for each management unit can be improved. Furthermore, the road snow removal unit may use AI (artificial intelligence) models, machine learning models, statistical models, clustering models, regression models, time series forecasting models, or rule-based models to generate snow removal decision support information, snow removal decision support information, snow removal decision support information, or snow removal work resource allocation adjustment decision support information. For example, the road snow removal unit may use snow accumulation conditions, road shoulder snow volume, road width reduction, compacted snow conditions, snow removal conditions, past snow removal performance, operating status of snow removal vehicles, or traffic impact information obtained through image analysis as input information to generate the start time for snow removal, candidate target routes, candidate target work sections, candidate number of vehicles required, candidate snow disposal site use, candidate snow removal transport routes, candidate support deployment, candidate flexibility, candidate relocation, or candidate pre-deployment. Furthermore, the road snow removal unit may generate decision support information using integrated evaluation processing that is not based on AI (artificial intelligence). For example, it may integrate resident notification density, notification methods, traffic delay information, snow depth, snowfall amount, presence or absence of visibility obstruction, location information of snow removal vehicles, congestion status of snow disposal sites, traffic status of snow removal transport routes, or the available work capacity of each snow removal business operator, and generate snow removal decision support information, snow removal decision support information, snow removal decision support information, or snow removal work resource allocation adjustment decision support information through predetermined weighting processing or rule-based processing. Furthermore, the road snow removal department may generate information to support decisions regarding feasibility, priority, timing, or necessity of adjustments to the workforce by referring to the implementation cost, required number of vehicles, required working hours, amount of snow disposal site usage, number of snow removal and transport operations, snow removal and transport time, or the current remaining budget for each candidate response. If there is a possibility of exceeding the budget, information may be generated regarding adjustments to the priority of responses, changes to the timing of implementation, adjustments to the target routes or work sections, generation of candidates for additional support, or registration of candidates for external support requests. This enables support for snow removal decisions that take into account financial constraints or work resource constraints. The Road Snow Removal and Clearing Department may, in cooperation with the Analysis Department 620 or the Improvement Department, verify the validity and effectiveness of the generated decision support information by referring to images from patrol vehicles obtained after snow removal and clearing, acceleration data, road surface conditions after snow removal and clearing, the occurrence of complaints or repeat reports, changes in traffic speed, changes in bus delays, snow removal and transport records, snow disposal site usage records, or snow removal and clearing vehicle operation records. Alternatively, the system may be configured to adjust the decision support information according to time periods with high report rates, high traffic volume, significant impacts on public transportation, or times when snow removal and clearing operations are easier to carry out, by utilizing the results of applying time-based weighting analyzed by the Analysis Department 620. Furthermore, the road snow removal department may have a function to manage or record the status of snow removal (work time, work duration, vehicle history, etc.) and the road surface condition after snow removal (remaining snow, ruts, unevenness, road width recovery status, etc.). This information may be used for explaining to residents, evaluating work, settling accounts with snow removal contractors, visualizing snow removal results, verifying differences between predicted and actual information, or generating information on on-site work challenges for the next snow removal season. In addition, decision support information, snow removal schedules, implementation status, or work progress generated by the road snow removal department may be provided to road administrators, snow removal contractors, related organizations, road users, or residents. Thus, the road snow removal unit is a core component that generates snow removal decision support information, snow removal decision support information, snow removal decision support information, or snow removal work resource allocation adjustment decision support information based on future snow removal operation load prediction information, snow removal operation load information, snow removal operation evaluation information, traffic impact information, bus route delay information, snow removal transport load information calculated by the analysis unit 620, or various information acquired by the information acquisition unit 610. It should be noted that the road snow removal unit is not limited to operating based on the decision results of the decision unit 630, but may also operate based on the analysis results of the analysis unit 620, future snow removal operation load prediction information, various information acquired by the information acquisition unit 610, input information from road administrators or personnel, or existing snow removal plans or work guidelines.

[0043] In this embodiment, the information acquisition unit 610 may acquire operational status and availability information regarding snow removal vehicles, workers, work teams, vehicle bases, snow disposal sites, snow removal transport routes, or other snow removal work resources from multiple local governments, multiple road administrators, multiple snow removal businesses, or information sources shared through systems or networks individually owned by them. The term "availability information" as used herein may include information on currently operating snow removal resources, as well as information on their availability within a certain period in the future, including availability schedules, deployment locations, mobility, responsiveness, service areas, operating hours, shift status, reservation status, allocation schedules, overlap with other operations, communication availability, contractual constraints, or operational constraints. Availability information may be managed for each route, work section, snow removal company, road administrator, or local government, and may be used in conjunction with future snow removal operational load forecast information. The information acquisition unit 610 may also acquire information regarding the utilization status of snow disposal sites or snow storage areas. Information regarding the utilization status of snow disposal sites or snow storage areas may include information regarding the current congestion status of deliveries, remaining acceptance capacity, delivery schedule, delivery waiting time, planned number of deliveries, available acceptance time slots, planned closures, delivery restrictions, access routes to the snow disposal sites, traffic congestion on snow removal and transport routes, or acceptance capacity for each snow disposal site. This information may be used to generate snow removal decision support information, candidate snow disposal sites, candidate snow removal and transport routes, candidate snow removal start times, or candidate numbers of snow removal vehicles required for snow removal. Furthermore, in this embodiment, availability information may be used as information indicating the available capacity of a candidate support source to provide snow removal vehicles or other snow removal vehicles, workers, work teams, or other snow removal work resources. In this case, the information acquisition unit 610 may acquire or refer to information relating to the candidate support source, such as work schedules, work progress, vehicle operating status, standby status, type of snow removal vehicle, minimum number of vehicles remaining, travel time to the support destination, travel route to the support destination, predicted snowfall amount, future snow removal operational load prediction information, contractual or operational feasibility of providing support, and information regarding the impact on the candidate support source's normal operations. The Road Snow Removal and Clearing Unit may generate snow removal and clearing resource allocation adjustment support information, which includes at least one of the following for snow removal and clearing resources among multiple routes, multiple work sections, multiple snow removal and clearing businesses, multiple road administrators, or multiple municipalities: candidates for support deployment, candidates for sharing resources, candidates for reallocation, or candidates for pre-deployment deployment, based on availability information obtained by the Information Acquisition Unit 610, information on the utilization status of snow disposal sites, information on snow removal and clearing transport routes, operating status of snow removal and clearing work resources, future snow removal and clearing operational load prediction information calculated by the Analysis Unit 620, or snow removal and clearing operation evaluation information. Furthermore, the Road Snow Removal Unit may compare future snow removal operational load prediction information with a standard load level determined based on the snow removal operational load information, and determine whether or not to adjust the allocation of snow removal work resources if the future load exceeds or is likely to exceed the standard load level. Based on the determination of whether or not to adjust the allocation, the Road Snow Removal Unit may output or notify information regarding candidates for support deployment, candidates for sharing resources, candidates for re-allocation, candidates for advance deployment, candidates for use of snow disposal sites, candidates for snow removal transport routes, or requests for dispatch to snow removal businesses. In this process, the road snow removal department may consider the mutual snow removal plans, work schedules, budgets, contract terms, working hours, types of snow removal vehicles, the work capacity of each snow removal company, the utilization status of snow disposal sites, the status of snow removal and transport routes, the impact on the snow removal response of potential support sources, travel time to the support location, or imbalances in snow removal operational loads between regions. This will help to mitigate snow removal delays, uneven distribution of snow removal vehicles, congestion at snow disposal sites, strain on snow removal and transport routes, and disparities in response between regions, making it possible to support wide-area snow removal responses spanning multiple municipalities, multiple road administrators, or multiple snow removal companies.

[0044] The snow removal and clearing decision support system 600 may be configured to include an infrastructure maintenance unit that supports the assessment of the soundness of road infrastructure or the decision regarding maintenance and management. The infrastructure maintenance unit may be an optional auxiliary configuration that grasps road surface abnormalities, road damage, subsurface cavities, road collapses, shoulder damage, gutter damage, or structural deformations that may occur or become apparent due to snow accumulation, freezing, compaction of snow, snow removal work, snow clearing work, or reduction in road width, and supports decisions regarding road maintenance and management. The Infrastructure Maintenance Department may use at least one of the following information acquired by the Information Acquisition Unit 610 to analyze road surface abnormalities, changes in vehicle behavior, abnormalities in video footage, vibration patterns, report content, or changes in road surface conditions after snow removal. The Infrastructure Maintenance Department may also combine this information to calculate a risk score related to subsurface cavities, road damage, road collapses, shoulder damage, ditch damage, or structural damage. The risk score may be calculated using at least one of the following: an AI (artificial intelligence) model, a machine learning model, a statistical model, a clustering model, a regression model, a time series forecasting model, or a rule-based model. Input information may include past traffic history, vehicle driving history, acceleration information, vibration information, weather information, snow cover conditions, freezing conditions, snow removal work history, road surface images after snow removal, resident reports, or optical fiber sensing results. Furthermore, for areas deemed to be at high risk, information regarding the presence or absence of cavities, the presence or absence of damage, the location, extent, depth, or shape of damage may be obtained through on-site surveys, ground-penetrating radar surveys, camera image acquisition, vibration measurements, visual inspections, or reacquisition of vehicle driving data. The obtained on-site survey results may be used as training data, validation data, or correction data for AI (artificial intelligence) models or machine learning models. Furthermore, the infrastructure maintenance department may use XAI (Explainable AI) technology to visualize the basis for calculating the risk score. In addition, active learning may be used to efficiently select learning targets from limited field survey data, and data augmentation processing may be used to improve the accuracy of image or sensor data analysis during snowfall, nighttime, blizzards, icy roads, or poor visibility. The road damage covered by this Infrastructure Maintenance Department may include uneven road surfaces, cracks, rutting, subsurface cavities, road collapses, road damage, damaged gutters, damaged road shoulders, tilting structures, deformation of structures, or changes in road surface conditions that become apparent after snow removal work. Based on this information, the Infrastructure Maintenance Department may record, classify, and manage damaged areas, identify candidates for inspection, calculate repair priorities, or generate information to support decisions regarding road maintenance. Furthermore, risk scores, inspection candidates, repair priorities, or decision-making support information related to road maintenance generated by the Infrastructure Maintenance Department may be provided to the Analysis Department 620 and used as supplementary information for snow removal operation evaluation information, traffic impact information, road space obstruction information, or snow removal environment information. For example, in areas with a high risk of road surface damage, subsurface cavities, road collapses, or shoulder damage, this information may be used as supplementary information when considering the travel routes of snow removal vehicles, snow removal transport routes, working hours, or snow removal work methods. Furthermore, the Infrastructure Maintenance Department may collaborate with the Analysis Department 620 or the Improvement Department to verify or update the conditions for determining the necessity of road surface repair, identifying candidates for inspection, evaluating road damage risk, or understanding trends in changes in road surface conditions. For example, the risk score, weighting conditions, judgment conditions, or models may be reviewed using image information, acceleration information, vehicle travel information, resident report information, or on-site survey results obtained after snow removal work. It should be noted that the infrastructure maintenance unit in this embodiment is not limited to the main embodiments claimed in this application, but is an optional auxiliary configuration that supports the assessment of the soundness of road infrastructure or the decision on maintenance and management. The main embodiments claimed in this application are mainly described in paragraph 0046 and later, and the information obtained by the infrastructure maintenance unit may be used as auxiliary information for deriving snow removal operation load information, calculating future snow removal operation load prediction information, or generating various decision support information by the road snow removal unit, as needed. In this specification, "processes related to infrastructure maintenance" includes recording, classifying, and managing damaged areas, identifying candidates for inspection, formulating inspection plans, calculating repair priorities, proposing repairs, assisting with contractor arrangements, assisting with decision-making regarding road maintenance, or similar processes.

[0045] The snow removal decision support system 600 may be configured to include a road clearing unit to support road clearing operations during disasters or heavy snowfall of disaster magnitude. The road clearing unit may be an optional auxiliary configuration that supports decision support regarding road clearing, confirmation of road clearing routes, prioritization of road clearing operations, or formulation or updating of road clearing implementation plans, based on various information acquired by the information acquisition unit 610, analysis results 690 obtained by the analysis unit 620, decision results 695 output by the decision unit 630, decision support information generated by the road snow removal unit, or disaster-related information acquired from external organizations. Road clearing refers to the process of identifying obstacles on roads, such as snow, snowdrifts, stuck vehicles, fallen trees, rubble, uneven surfaces, road damage, flooding, or other impediments to traffic, and taking the minimum necessary measures quickly to secure a passable route in order to enable life-saving, rescue operations, emergency supplies transport, recovery support, medical transport, movement of support units, or the passage of emergency vehicles. In large-scale disasters, torrential snowfall of disaster magnitude, widespread traffic paralysis, or abnormal situations where normal snow removal systems are insufficient, road clearing may be carried out as an initial response prior to emergency restoration. Local governments or road administrators may formulate road clearing plans in advance, including road clearing bases, disaster prevention bases, support unit bases, supply depots, medical facilities, evacuation facilities, critical facilities, or road clearing routes connecting them. These road clearing plans may also include information on wide-area travel routes, access routes, routes within disaster-stricken areas, emergency transport routes, critical routes, work timelines, prioritization of road clearing operations, communication systems with relevant organizations, or work resources used for road clearing operations. This information may be pre-registered with the road clearing department and referenced when supporting decisions regarding road clearing or when formulating implementation plans. The Road Clearing Unit may, after a disaster occurs or during a disaster-level heavy snowfall, evaluate areas that are difficult to pass, locations where vehicles frequently get stuck, locations where road width is reduced, locations blocked by snow or snow accumulation, locations with road damage, locations with a risk of subsurface cavities, locations with a risk of building collapse, locations with flooding, or locations that obstruct traffic, based on road surface information, traffic information, road space information, weather information, vehicle travel information, road service information, fiber optic survey information, satellite survey information, resident notification information, snow removal information, snow removal operation information, snow removal environment information, image information, or disaster-related information from external organizations. Furthermore, the Road Clearing Unit may refer to the analysis results 690 obtained by the Analysis Unit 620, future snow removal operation load prediction information, snow removal operation evaluation information, traffic impact information, bus route delay information, risk score, road space obstruction information, or information on road damage risk generated by the Infrastructure Maintenance Unit, to generate auxiliary information used in formulating a road clearing implementation plan, such as the passability of the road clearing route, the necessity of road clearing work, and the priority of road clearing work. Furthermore, the road clearing unit may use AI (artificial intelligence) models, machine learning models, statistical models, clustering models, regression models, time series prediction models, or rule-based models to analyze disaster images, traffic disruption information, satellite images, fiber optic sensing information, patrol camera images, SNS reports, resident reports, vehicle travel information, road service information, or information regarding snow removal status. This may enable the system to compare traffic obstruction, potential blockage, snow removal workload, road damage risk, or the passability of emergency vehicles along multiple candidate routes, and generate or evaluate candidate road clearing routes. The Road Clearing Department may formulate or update a Road Clearing Implementation Plan by comparing pre-registered information on road clearing bases, road clearing routes, work timelines, emergency transport routes, critical facilities, disaster response plans, or communication systems with relevant organizations with the latest information obtained after the disaster. The Road Clearing Implementation Plan may include information on the start time of road clearing work, target routes, target sections, processing order, priorities, required time, work resources, notifications to relevant organizations, or confirmation of implementation status. Furthermore, the road clearing implementation plan in this specification differs from the static road clearing plans established by local governments or road administrators during normal times. It may include a dynamic implementation plan that is formulated, updated, corrected, or referenced after a disaster or during a disaster-level heavy snowfall, based on the latest information obtained by the snow removal decision support system 600. The road clearing implementation plan may also include a work timeline that chronologically organizes the sequence of road clearing operations, or, in lieu of or in conjunction with this, information regarding the priority of road clearing operations, target routes, target sections, work resources, or target times for road reopening. Furthermore, the Road Clearing Department may, in cooperation with the Road Snow Removal Department, refer to snow removal decision support information, snow removal decision support information, snow removal decision support information, or snow removal work resource allocation adjustment decision support information during times of disaster-level heavy snowfall or widespread disruption of traffic functions. For example, the Road Clearing Department may use information generated by the Road Snow Removal Department regarding the start date of snow removal response, the target routes or work sections, the number of snow removal vehicles to be deployed, the deployment of snow removal vehicles, candidates for support deployment, candidates for flexibility, candidates for redeployment, or candidates for pre-deployment, as auxiliary information regarding the feasibility of road clearing work, the order of work, or the adjustment of work resources. Furthermore, the Road Clearing Department may collaborate with the Infrastructure Maintenance Department to refer to information regarding road damage risks, subsurface cavity risks, road collapse risks, bridge or structure damage risks, shoulder damage, ditch damage, or road width reductions along the road clearing route. This allows for the identification of impassable sections, difficult-to-work-in sections, sections requiring repair coordination, or sections affecting passability along the road clearing route, which can then be used to adjust the road clearing route or prioritize road clearing operations. Furthermore, the Road Clearing Unit may collaborate with the Forecasting Unit to refer to medium- to long-term or wide-area risk assessments regarding extreme snowfall, widespread snow damage, traffic disruption, or emergency snow removal systems. In this case, the forecasting results from the Forecasting Unit may be used as supplementary information, distinct from forecasts of the load on individual snow removal operations or decisions on individual resource allocation during normal times, for prior identification of areas where road clearing is difficult, for considering emergency response policies, or for sharing information with relevant organizations. The Road Clearing Department may obtain or refer to patrol results after road clearing, traffic records, road surface conditions, resident reports, traffic information, vehicle travel information, road service information, or reports from relevant organizations to evaluate the effectiveness of the road clearing route, the results of the road clearing work, the achievement status of making the road passable, or the appropriateness of the road clearing implementation plan. The evaluation results may be provided to the Improvement Department, Analysis Department 620, the Road Snow Removal Department, or an external business system and used to review future road clearing responses, snow removal responses, road maintenance, or emergency response policies. Thus, the Road Clearing Department may be configured to support the formulation or updating of road clearing decisions and road clearing implementation plans during disasters or heavy snowfall of disaster magnitude, using registered road clearing bases, road clearing routes, work timelines, disaster action plans, or communication systems with related organizations as basic information, in cooperation with the Information Acquisition Department 610, Analysis Department 620, Decision Department 630, Road Snow Removal Department, Improvement Department, Prediction Department, or Infrastructure Maintenance Department. It should be noted that the road clearing unit in this embodiment is not limited to the main embodiments claimed in this application, but is an optional auxiliary configuration to support road clearing operations during disasters or heavy snowfall of disaster magnitude. The main embodiments claimed in this application are mainly described in paragraph 0046 and later, and the information obtained by the road clearing unit may be used as auxiliary information for deriving snow removal operation load information, calculating future snow removal operation load prediction information, or generating various decision support information by the road snow removal unit, as needed.

[0046] The following describes how each configuration and function described in the claims of this application can be specifically realized as one embodiment of the snow removal and clearing decision support system 600 according to the present invention. The embodiments described below are merely examples for realizing the technical concept of the claimed invention, and the present invention is not limited thereto. Furthermore, the present invention can be realized not only as the snow removal decision support system 600 described below, but also as a program for causing a computer to execute each function of the system, and as a road management method including the processing performed by the system.

[0047] The snow removal decision support system 600 according to this embodiment is a system for predicting the operational load of snow removal on roads. The snow removal decision support system 600 comprises at least an information acquisition unit 610 and an analysis unit 620. The information acquisition unit 610 acquires snow removal operation information, snow removal environment information, and future snow removal environment information. The analysis unit 620 associates the snow removal operation information and snow removal environment information acquired by the information acquisition unit 610 to derive snow removal operational load information corresponding to the snow removal environment conditions indicated by the snow removal environment information for each route, work section, snow removal business operator, road administrator, or local government, and calculates future snow removal operational load prediction information by applying the snow removal operational load information to future snow removal environment conditions indicated by the future snow removal environment information.

[0048] In this embodiment, snow removal operation information refers to information indicating the actual state of past or present snow removal operations, and includes at least one of the following: location information, travel history, operating status, operation history, dispatch history, or work results for snow removal vehicles. Snow removal vehicles may include snow removal vehicles, snow removal vehicles, dump trucks, graders, rotary snowplows, wheel loaders, de-icing agent spreaders, sidewalk snowplows, or other vehicles used for snow removal work. Location information may include GPS information, current location transmitted from an in-vehicle terminal, work start location, work end location, travel trajectory, or location information associated with the target route or work area for snow removal. Travel history may include travel time, travel distance, travel speed, travel route, stopping time, waiting time, detour route, or transport route to the snow disposal site.

[0049] The operational status may include information indicating whether snow removal vehicles are dispatched, working, on standby, moving, transporting, unloading at snow disposal sites, broken down, idle, or returning to depot. The operational history may include the start time of operation, end time of operation, working hours, non-working hours, standby time, transport time, time spent at snow disposal sites, travel time within work sections, or utilization rate for each snow removal vehicle. The dispatch history may include the date and time of dispatch, destination, route or work section to be dispatched, reason for dispatch, dispatch order, dispatch request, dispatched snow removal company, number of dispatched vehicles, or frequency of dispatch. The work performance may include performance information related to snow removal work, snow clearing work, road widening work, compacted snow removal work, shoulder treatment, intersection treatment, sidewalk snow removal, de-icing agent application, snow levee treatment, or transport to snow disposal sites.

[0050] In this embodiment, snow removal environment information refers to information indicating the environmental conditions of the road or surrounding area during snow removal operations as indicated by snow removal operation information, and includes at least one of the following: snowfall amount information, snow depth information, temperature information, wind speed information, snow quality information, compacted snow condition information, road shoulder snow accumulation information, or road width reduction information due to snow accumulation or snow. Snowfall amount information may include hourly snowfall amount, cumulative snowfall amount, daily snowfall amount, information on the occurrence of short-term heavy snow, or snowfall amount before and after snow removal work. Snow depth information may include snow depth at observation points, estimated snow depth associated with routes or work sections, snow thickness on roads, amount of snow on road shoulders, or the snow condition remaining after snow removal. Temperature information may include temperature, road surface temperature, possibility of freezing, possibility of snow melting, or temperature change trend. Wind speed information may include wind speed, wind direction, possibility of snowdrifts, reduced visibility, or possibility of ground blizzards.

[0051] Snow quality information may include information indicating the properties of snow that affect snow removal operations, such as fresh snow, wet snow, granular snow, compacted snow, frozen snow, ice sheets, heavy snow, light snow, etc. Compacted snow condition information may include the thickness of compacted snow on the road surface, the hardness of the compacted snow, unevenness of the compacted snow, ruts, ice formation, compaction due to vehicle traffic, or the condition of the road surface. Road shoulder snow accumulation information may include the height, width, volume, continuous length of snow accumulated on the road shoulder, the snow accumulation condition near intersections or bus stops, or the amount of snow accumulation that requires removal. Road width reduction information due to snow accumulation or snowfall may include the amount of reduction in carriageway width, remaining road width, sections where passing is difficult, reduction in the number of lanes, reduction in sidewalk width, difficulty of stopping near bus stops, or difficulty of passage for emergency vehicles.

[0052] In this embodiment, future snow removal environment information refers to information indicating future snow removal environmental conditions in the time period, route, work section, road management area, area of ​​responsibility of a snow removal business operator, area of ​​management of a road administrator, or municipal area that are subject to future snow removal operational load prediction. Future snow removal environment information includes at least one of the following: snowfall amount prediction information, snow depth prediction information, temperature prediction information, wind speed prediction information, snow quality prediction information, compacted snow condition prediction information, road shoulder snow accumulation amount prediction information, or road width reduction prediction information due to snow accumulation or snow. Future snow removal environment information may be generated or acquired based on weather forecast data, road weather observation data, past snow removal performance, current snow accumulation conditions, image analysis results, traffic conditions, operating status of snow removal vehicles, or work schedule information held by the road administrator.

[0053] The period covered by the forecast of future snow removal operational load may be a few hours later, the next day, a few days later, during a snowfall event, on a weekly, monthly, or any period during the snow removal season. The analysis unit 620 may calculate future snow removal operational load forecast information used to generate candidate timings for snow removal deployment based on short-term snowfall forecasts, or it may calculate future snow removal operational load forecast information used to generate candidate start times for snow removal, candidate routes to be snow removed, candidate work sections to be snow removed, candidate number of snow removal vehicles required, or candidate pre-deployment of snow removal work resources based on forecasts of snow depth, road shoulder snow accumulation, road width reduction, compacted snow conditions, traffic impact, or snow removal transport load on a daily or weekly basis.

[0054] Snow removal and clearing operational load information refers to information that indicates the operational load on snow removal and clearing operations that arises in response to snow removal and clearing environmental conditions. Snow removal and clearing operational load information may include information such as workload, working time, required time, number of snow removal and clearing vehicles required, vehicle utilization rate, dispatch frequency, working distance, number of transports, snow removal and transport load, number of routes or work sections to be snow removed or cleared, load on the processing capacity of snow removal and clearing operators, response load at the road administrator or municipal level, possibility of work delays, degree of urgency in snow removal and clearing response, reserve capacity indicator, required working volume, required working time, required number of vehicles, work density, standby load, transport load, or load ratio on processing capacity. The analysis unit 620 correlates snow removal operation information with snow removal environment information to calculate or aggregate, for example, the number of vehicles, working hours, number of dispatches, number of transports, waiting time, work delays, or load ratios that actually occurred under predetermined snowfall amounts, snow depths, temperatures, snow quality, compacted snow conditions, road shoulder snow accumulation, or road width reduction conditions, and derives the results of such calculation or aggregation as snow removal operation load information.

[0055] Snow removal and clearing operational load information is not limited to being generated as explicit tabular data, numerical data, score data, or judgment results. Snow removal and clearing operational load information may also be expressed as load score, load coefficient, features, hidden variables, cluster classification results, load level judgment results, severity, reserve index, required workload, required working hours, required number of vehicles, work density, standby load, transport load, or load ratio relative to processing capacity within the prediction model. The analysis unit 620 may generate this information for each route, work section, road section, management section, snow removal target area, snow removal business operator, road administrator, local government, or any management unit.

[0056] The snow removal and clearing operation load information may include snow removal and transport load information that indicates the load related to snow removal and transport. The snow removal and transport load information may include the travel history of snow removal vehicles, the number of transports, transport time, waiting time, actual delivery to snow disposal sites, waiting time at snow disposal sites, snow disposal site utilization load, travel time on snow removal and transport routes, traffic congestion on snow removal and transport routes, obstruction of traffic on snow removal and transport routes, round-trip travel time from the snow removal target section to the snow disposal site, or demand for snow removal vehicles. The analysis unit 620 may predict future snow removal and transport load, snow disposal site utilization load, transport route load, or demand for snow removal vehicles based on future snow removal and clearing environment information, snow removal and clearing operation information, information on snow disposal sites, information on snow removal and transport routes, or traffic operation-related information. As a result, the snow removal and clearing decision support system 600 can not only extract snow removal target routes or snow removal target work sections, but also obtain information for generating the number of vehicles required for snow removal and transport, transport routes, candidate snow disposal sites, transport time slots, or candidate snow removal start times.

[0057] The analysis unit 620 associates snow removal operation information and snow removal environment information for each route, work section, snow removal business operator, road administrator, or local government. Here, "for each route, work section, snow removal business operator, road administrator, or local government" refers to a management unit used for aggregating, evaluating, predicting, displaying, or supporting decision-making regarding the snow removal operation load. The route or work section is not limited to the route name or work section name predetermined by the road administrator. The route or work section may include road sections, management sections, snow removal target areas, sections including intersections, sections corresponding to bus routes, sections corresponding to transport routes to snow disposal sites, meshes, areas, blocks, management units, or any area set as an aggregation unit for snow removal work. The analysis unit 620 may associate, aggregate, evaluate, or display snow removal operation information, snow removal environment information, future snow removal environment information, snow removal operation load information, or future snow removal operation load prediction information for each of these units.

[0058] The analysis unit 620 associates, for example, the amount of snowfall, snow depth, road width reduction, operating hours of snow removal vehicles, number of operations, and time to completion of work for a specific route or work section. The analysis unit 620 may also associate the work sections assigned to each snow removal company, the number of vehicles owned, the number of vehicles actually in operation, working hours, waiting time, and work delays. Furthermore, the analysis unit 620 may aggregate the snow removal operational load for routes or work sections within the management area for each road administrator or local government. Through these associations, the analysis unit 620 learns, records, aggregates, or evaluates the relationship between snow removal environmental conditions and the actual snow removal operational load that occurs.

[0059] The analysis unit 620 calculates future snow removal operation load prediction information by applying snow removal operation load information to future snow removal environmental conditions indicated by future snow removal environmental information. Here, application includes associating, fitting, referencing, interpolating, estimating, or using in model calculations the snow removal operation load information derived in response to past or present snow removal environmental conditions with future snow removal environmental conditions indicated by future snow removal environmental information. The future snow removal operation load prediction information may include the number of snow removal vehicles required at a future target time or period, working hours, routes or work sections to be worked on, workload, dispatch frequency, snow removal transport load, load for each snow removal business operator, response load for each road administrator or local government, or information indicating the expected strain on snow removal operations.

[0060] The analysis unit 620 may set up multiple categories based on a single condition or a combination of multiple conditions for the snow removal environmental conditions included in the snow removal environmental information. The multiple categories may be set up based on, for example, snowfall amount categories, snow depth categories, temperature categories, wind speed categories, snow quality categories, compacted snow condition categories, road shoulder snow accumulation categories, road width reduction categories, or combinations thereof. For each of the multiple categories, the analysis unit 620 associates snow removal operation information with snow removal environmental information and derives snow removal operation load information corresponding to each category. For example, if the snowfall amount is within a predetermined range, the snow depth is within a predetermined range, and the road width reduction is within a predetermined range, the analysis unit 620 may derive the work time, number of vehicles, number of operations, number of transports, waiting time, or work delays that were required based on past or present results as snow removal operation load information corresponding to that category.

[0061] Multiple classifications are not limited to those set based on predetermined fixed thresholds. Multiple classifications may also be classifications based on numerical ranges, classifications based on state classifications, classifications set by statistical processing, classifications set by machine learning, clusters generated by clustering processing, classifications on the feature space, classifications according to load levels, or classifications set by rule-based processing. For example, the analysis unit 620 may use snowfall amount, snow depth, temperature, wind speed, snow quality, compacted snow condition, amount of snow piled on the road shoulder, reduction in road width, vehicle utilization rate, traffic impact information, or bus route delay information as features, and set a group of conditions with similar snow removal operation loads as a single classification.

[0062] The analysis unit 620 may associate the future snow removal environmental conditions indicated by the future snow removal environmental information with at least one of several categories, and use the snow removal operational load information corresponding to the associated categories to calculate future snow removal operational load prediction information. For example, if the future snow removal environmental information predicts that the amount of snowfall within a predetermined time period, the snow depth, and the amount of snow accumulation on the road shoulder or reduction in road width will fall within a predetermined range on the target route or target work section, the analysis unit 620 may associate the future snow removal environmental conditions with the corresponding categories and calculate future workload, work time, required number of vehicles, required operating load, transport load, or degree of urgency based on the snow removal operational load information corresponding to those categories.

[0063] The analysis unit 620 may compare future snow removal operational load forecast information with a standard load level determined based on snow removal operational load information, and calculate snow removal operational evaluation information regarding at least one of the following for a route, work section, snow removal business operator, road administrator, or local government: the expected excess of the snow removal operational load, the expected increase in the snow removal operational load, or the expected strain on snow removal operations. The standard load level may be determined based on past normal snow removal operational load, the processing capacity of the snow removal business operator, the expected response capacity of the road administrator or local government, the contractual or operational standard workload, the number of vehicles owned, the number of workers, the acceptance capacity of snow disposal sites, or the standard working hours for each target route or work section. The snow removal operational evaluation information may include information indicating the possibility that future loads will exceed the standard load level, the possibility that they will exceed the range that can be handled by the normal system, the need to start snow removal operations earlier, the need to deploy additional snow removal vehicles or snow removal work resources, or the need for prior judgment by the road administrator.

[0064] The information acquisition unit 610 may further acquire traffic operation-related information, including route bus operation information. Traffic operation-related information is information used to analyze the impact that snow removal environmental conditions, indicated by snow removal environmental information, have on road traffic or public transport operations. In addition to route bus operation information, traffic operation-related information may also include traffic flow information, road traffic information, vehicle driving status information, traffic congestion information, traffic restriction information, travel time information, driving speed information, traffic volume information, probe traffic information, vehicle congestion information based on road surveillance cameras or AI image analysis, slow driving information, stopped information, information on difficulty in passing, information on obstruction of traffic, information on impassable roads, public transport operation status, cancellations, delays, route changes, stops, or information on disruptions to bus operations.

[0065] Route bus operation information may include current location information, past location information, location history information, acquisition time information, service information, route information, operating time, scheduled operation information, actual operation information, scheduled departure and arrival time information, actual departure and arrival time information, scheduled stop passage time information, actual stop passage time information, departure and arrival time forecast information, detour information, service suspension information, approach information, delay time, delayed section, congestion near stop, reduced punctuality, or GTFS real-time information. Traffic operation-related information may also include information indicating traffic operation status corresponding to the time or period indicated by snow removal environment information. The information acquisition unit 610 may acquire traffic operation-related information or route bus operation information from road administrators, transportation operators, bus operators, traffic information providers, external traffic information systems, road surveillance cameras, in-vehicle terminals, or bus location systems.

[0066] The analysis unit 620 may derive traffic impact information corresponding to the snow removal environmental conditions indicated by the snow removal environmental information by associating the snow removal environmental information with traffic operation-related information. The traffic impact information is information that shows the impact that snowfall amount, snow depth, temperature, wind speed, snow quality, compacted snow condition, amount of snow piled on the road shoulder, or reduction in road width have had on road traffic or public transport operations. The traffic impact information may include, for example, the delay time, degree of delay, delay category, decrease in operating speed, increase in travel time between stops, congestion length, average travel time, difficulty stopping near bus stops, occurrence of detours, occurrence of service cancellations, decrease in traffic flow, difficulty passing, obstruction of traffic, impassability, or the degree of improvement in traffic conditions after snow removal. The analysis unit 620 may associate snow removal environment information with traffic operation-related information for each route, work section, road section, bus route, between bus stops, management section, snow removal target area, snow removal business operator, road administrator, or local government.

[0067] The analysis unit 620 may calculate future traffic impact prediction information by applying traffic impact information to future snow removal environmental conditions indicated by future snow removal environmental information. Future traffic impact prediction information is information that indicates the impacts that are expected to occur on road traffic or public transport due to future snowfall amount, snow depth, compacted snow conditions, amount of snow piled on the road shoulder, reduction in road width, or other snow removal environmental conditions. Future traffic impact prediction information may include expected future bus delays, expected changes in delay categories, expected reductions in operating speed, expected increases in travel time between stops, expected occurrence of detours or cancellations, expected difficulty in stopping near bus stops, expected occurrence of traffic congestion, expected expansion of traffic disruptions, expected occurrence of difficulty in passing, or expected occurrence of road closures. The analysis unit 620 may correct future snow removal operational load prediction information based on the future traffic impact prediction information. For example, even with the same snowfall amount or snow depth, the snow removal operational load may be corrected to be higher for routes or work sections with a high expected delay of buses, expected traffic congestion, or expected road closures.

[0068] The analysis unit 620 may correct the future snow removal operation load prediction information based on the current traffic conditions indicated by traffic operation-related information. The current traffic conditions may include current driving speed, travel time, traffic volume, congestion, stagnation, slow driving, stopping, obstruction of traffic, difficulty in passing, impassable roads, delays of route buses, suspension of public transport, detours, stagnation near bus stops, or traffic obstruction conditions obtained by road surveillance cameras or AI image analysis. For example, even if the future snowfall amount or snow depth indicated by future snow removal environment information is similar, the analysis unit 620 may correct the future snow removal operation load prediction information to a higher value for routes or work sections where congestion, bus delays, slow driving, difficulty in passing, or obstruction of traffic have already occurred in the current traffic conditions.

[0069] The information acquisition unit 610 may further acquire traffic operation-related information, including route bus operation information during or after snow removal operations, as indicated by the snow removal operation information. Here, "during snow removal operations" includes the time period when snow removal vehicles are dispatched, the time period when snow removal work is being carried out, the time period when snow removal is being carried out on the target route or work section, or the time period when the snow removal work may affect road traffic. "After snow removal operations" includes the time period after snow removal work is completed, the time period after snow removal vehicles have left the target route or work section, the time period when the road conditions after snow removal may affect traffic operations, or the time period set up to evaluate the traffic conditions after snow removal.

[0070] The analysis unit 620 may generate bus route delay information based on route bus operation information. The bus route delay information may include delay status for each bus route, delay status for each section, delay status between stops, delay category, delay time, delay degree, congestion status, delay in progress, detour status, service suspension status, or service disruption status. The analysis unit 620 may associate the generated bus route delay information with routes, work sections, road sections, management sections, snow removal target areas, road sections near bus stops, or sections to which the work performance of snow removal vehicles is associated. This allows the analysis unit 620 to use delay status in public transport not merely as traffic information, but to correct snow removal operation load information, correct future snow removal operation load prediction information, or generate snow removal decision support information.

[0071] Route bus operation information may include location information and time information of route buses. Location information may include the current location, past location, location history, bus stop location, location on the route, planned location, actual location, or location obtained by a bus location system. Time information may include acquisition time, planned departure time, actual departure time, planned arrival time, actual arrival time, planned bus stop passage time, actual bus stop passage time, section entry time, section exit time, departure and arrival time prediction information, or time information for each service. Based on this location information and time information, the analysis unit 620 may calculate the delay status on the bus route or the delay status in the section included in the bus route. Here, the section may be between bus stops, between intersections, road sections, part of a route subject to snow removal, a section corresponding to a snow removal work area, a management section, or a section on the bus route that has been arbitrarily divided.

[0072] The analysis unit 620 may calculate the delay status based on the difference between the planned operating status and the actual operating status. For example, the analysis unit 620 may calculate the delay status based on the difference between the planned departure and arrival times and the actual departure and arrival times, the difference between the planned time to pass a bus stop and the actual time to pass a bus stop, the difference between the planned location and the actual location, the difference between the planned time and the actual time, the difference between the planned route and the actual route, the difference between the predicted departure and arrival time information and the actual arrival time, or the difference between the normal time between bus stops and the time between bus stops during snow damage. The analysis unit 620 may also calculate the delay status of the route bus based on the normal timetable, winter timetable, temporary timetable, planned route during detours, or operating schedule information provided by the operating company.

[0073] The analysis unit 620 may calculate the delay status based on the difference between before and after the acquisition of route bus operation information acquired in a time series. For example, the analysis unit 620 may use the location information and time information of route buses acquired at predetermined intervals to calculate the delay status for each bus route or section based on the difference between the previously acquired location information and the currently acquired location information, the difference between the previously acquired time and the currently acquired time, the distance traveled within the predetermined time, the speed traveled within the predetermined time, the amount traveled from the previous location to the current location, the amount traveled compared to the planned amount traveled, the actual time required between stops or for each section, the difference from the normal time required for the same section, or the stopping time within the predetermined time. This makes it possible to calculate the delay status for each bus route or section based on the time series changes in the location and time of route buses, even in cases of snow damage where there is already a significant delay at the time of departure, where there is a large delay compared to the normal timetable or winter timetable, where the bus is detouring off the normal route, or where it is difficult to grasp the traffic disruption for each section by simply comparing it with the scheduled departure and arrival times.

[0074] The analysis unit 620 may classify the calculated delay status into several delay categories. These delay categories may include no delay, minor delay, moderate delay, major delay, significant delay, congestion, difficulty in operation, detour operation, or a state equivalent to cancellation. The delay categories may also be set according to the delay time, degree of delay, delay in progress, reduction in travel speed, time required between stops, comparison value with normal conditions, or degree of improvement before and after snow removal work. The delay categories may be two, three, five, nine, or any other set of multiple levels. For example, the analysis unit 620 may classify the delay status for each bus route or section into nine delay categories and generate information that can be displayed in association with bus routes, road sections, routes, work sections, or snow removal target areas on a map.

[0075] The analysis unit 620 may generate bus route delay information for each bus route or section by associating multiple delay categories with bus routes or sections included in said bus routes. The analysis unit 620 may associate the generated bus route delay information with routes, work sections, road sections, management sections, or snow removal target areas, and correct the snow removal operation load information for each route based on the associated bus route delay information. The correction of the snow removal operation load information may include, for example, a process to increase the snow removal operation load for routes or sections with large delays indicated by the bus route delay information, a process to increase the snow removal operation load for routes or sections where delays persist even after snow removal work, or a process to decrease the snow removal operation load for routes or sections where delays have improved after snow removal work. Furthermore, the analysis unit 620 may evaluate the impact of snow removal operations on the bus route delay state by comparing bus route delay information at at least one of the following points in time: before snow removal operations, during snow removal operations, and after snow removal operations. For example, if the delay category improves after snow removal operations, the analysis unit 620 may generate information indicating the improvement in traffic impact due to the snow removal operations. On the other hand, if the delay category does not improve even after snow removal operations, the analysis unit 620 may generate information indicating compacted snow, snow accumulation on the road shoulders, reduction in road width, delays in transporting snow to disposal sites, congestion on snow removal and transport routes, or the need for additional snow removal.

[0076] The snow removal decision support system 600 according to this embodiment may further include a road snow removal unit. The road snow removal unit generates snow removal decision support information based on future snow removal operational load prediction information calculated by the analysis unit 620. The snow removal decision support information includes at least one of the following: the start date of snow removal response, the route or work section to be covered by snow removal response, the number of snow removal vehicles to be deployed, the placement of snow removal vehicles, the dispatch request to snow removal businesses, or information used for decision-making by road administrators. For example, if the future snow removal operational load prediction information predicts a higher-than-normal snow removal operational load for a given route, work section, snow removal business, road administrator, or local government, the road snow removal unit generates snow removal decision support information to address that load.

[0077] The start time of snow removal and clearing operations included in the snow removal decision support information may include the planned start time of work, candidate start time of work, start time of dispatch preparation, dispatch request time, snow removal start time, candidate for earlier start, or the start time of pre-deployment before the start of snowfall or before snowfall intensifies. The routes or work sections targeted for snow removal and clearing operations may include routes or work sections where high loads are predicted based on future snow removal and clearing operation load forecast information, routes or work sections where the amount of snow accumulation on the road shoulders is predicted to increase, routes or work sections where the reduction in road width is predicted to progress, routes or work sections determined to have a significant traffic impact based on route bus delay information or future traffic impact forecast information, or routes or work sections where snow removal and clearing operations should be prioritized. The amount of snow removal and clearing vehicles deployed may include the number of vehicles deployed, deployment time, vehicle type, deployment order, deployment destination, or allocation amount to multiple routes or work sections. The deployment of snow removal and clearing vehicles may include current deployment, planned deployment, pre-deployment deployment, waiting area, base deployment, deployment around snow disposal sites, or pre-deployment to high-load predicted areas.

[0078] The information used by road administrators to make decisions may include information used to determine whether or not to dispatch personnel, the timing of dispatch, the target of work, the priority of work, the amount of personnel to be deployed, deployment, requests for support, requests for flexibility, redeployment, pre-deployment, transition to snow removal, traffic restrictions, public notification, contact with snow removal contractors, revision of snow removal plans or implementation plans, or adjustment of snow removal work resources. The Road Snow Removal Department may generate this information as a management screen, map screen, report, notification message, draft work order, draft dispatch request, or data linkage information. The Road Snow Removal Department may not only present the generated snow removal decision support information to road administrators, but may also output or notify snow removal contractors, work order personnel, site supervisors, or external systems.

[0079] Snow removal decision support information, snow disposal decision support information, and snow removal work resource allocation adjustment decision support information may be generated as part of the snow removal decision support information, or they may be generated as separate decision support information from the snow removal decision support information. The road snow removal unit may generate this decision support information individually or in association with each other based on future snow removal operation load prediction information, snow removal operation evaluation information, traffic impact information, future traffic impact prediction information, bus route delay information, information on snow removal work resources, or standard load levels.

[0080] The road snow removal unit may generate snow removal decision support information based on future snow removal operational load prediction information. The snow removal decision support information includes at least one of the following: candidate timing for snow removal dispatch for snow removal vehicles, candidate routes to be snow removed, candidate work sections to be snow removed, or candidate snow removal priority for routes or work sections. For example, the road snow removal unit generates candidate timing for snow removal dispatch for routes or work sections where future snow removal environment information predicts an increase in snowfall, an increase in snow depth, deterioration of compacted snow conditions, an increase in road shoulder snow accumulation, a decrease in road width, or an expansion of traffic impact within a predetermined time period. The road snow removal unit may also generate candidate routes to be snow removed, candidate work sections to be snow removed, or candidate snow removal priority based on future snow removal operational load prediction information, snow removal operation evaluation information, traffic impact information, future traffic impact prediction information, bus route delay information, or current traffic conditions.

[0081] Candidate timings for snow removal deployment may be set before snowfall begins, after snowfall begins, before snowfall reaches a predetermined value, before snow depth reaches a predetermined value, before compacted snow conditions deteriorate, before shoulder snow accumulation exceeds a predetermined value, before road width reduction exceeds a predetermined value, before bus delays exceed a predetermined level, or before deterioration of traffic conditions is predicted. Candidate routes or work sections to be snow removed may be selected based on predicted snow removal operational load, traffic impact, road width reduction, bus route delays, accessibility for emergency vehicles, impact on public transport, impact on local roads, or past work delay history. Candidate snow removal priorities may be calculated using predicted load, traffic impact, available resources, estimated completion time for each route or work section, or conflicts with other snow removal responses.

[0082] The road snow removal unit may generate snow removal decision support information based on future snow removal operation load prediction information. The snow removal decision support information includes at least one of the following: candidate routes to be snow removed, candidate work sections to be snow removed, candidate snow removal start dates, candidate number of snow removal vehicles required, candidate use of snow disposal sites, or candidate snow removal transport routes. The road snow removal unit extracts routes or work sections to be snow removed based, for example, on information such as road shoulder snow accumulation amount, road width reduction information, future road shoulder snow accumulation amount prediction information, future road width reduction prediction information, traffic impact information, future traffic impact prediction information, snow removal transport load information, snow disposal site usage load, or snow removal transport route load.

[0083] The Road Snow Removal and Clearing Department may, based on future snow removal and clearing operational load forecasts, generate candidate snow removal start times, candidate snow removal vehicles required for snow removal, candidate snow disposal site usage, or candidate snow removal and clearing routes if a shortage of snow removal vehicles, an increase in snow removal and transport load, congestion at snow disposal sites, insufficient acceptance capacity at snow disposal sites, traffic congestion on snow removal and transport routes, obstruction of traffic on snow removal and transport routes, an increase in round-trip travel time from the snow removal target section to the snow disposal site, or delays in snow removal operations are predicted. Candidate snow disposal site usage may include the snow disposal site to be used, the time of use, the amount to be brought in, the acceptance capacity, waiting time, the priority of arrival, or alternative snow disposal sites. Candidate snow removal and clearing routes may include transport routes from the snow removal target route or work section to the snow disposal site, alternative transport routes, transport time slots, routes to avoid traffic congestion, or transport routes that are modified according to the allocation of snow removal and clearing work resources.

[0084] In this embodiment, snow removal and clearing resources refer to human, vehicle, equipment, managerial, or operational resources used to implement, support, or supplement snow removal and clearing operations. Snow removal and clearing resources may include at least one of the following: snow removal vehicles, snow removal machines, snow removal vehicles, construction machinery, dump trucks, rotary snowplows, snow graders, wheel loaders, de-icing agent spreaders, sidewalk snowplows, workers, drivers, operators, work teams, the operational capacity of snow removal and clearing businesses, support personnel, the acceptance capacity of snow disposal sites, the available hours of snow disposal sites, work bases, waiting areas, fuel, materials, communication equipment, in-vehicle terminals, work command systems, or reserve work resources that can be deployed for snow removal and clearing operations.

[0085] Snow removal and clearing resources are not limited to pre-registered snow removal vehicles, workers, or snow removal businesses. Snow removal and clearing resources may also include additional vehicles, heavy machinery, personnel, work teams, cooperating businesses, support systems from neighboring municipalities, work capacity that can be coordinated among road administrators, or reserve work resources that can be deployed in response to snowfall conditions, snow accumulation conditions, reduction in road width, strain on snow removal and transport, occurrence of traffic disruptions, or anticipated increase in snow removal and clearing operational load. As a result, the snow removal and clearing decision support system 600 can treat not only pre-registered resources, but also work resources not pre-registered, or additionally identified work resources, as snow removal and clearing resources in cases of disaster-level heavy snowfall, localized heavy snowfall, strain on snow removal and transport, or when coordination of support among multiple municipalities is required.

[0086] Information regarding snow removal and clearing resources may include at least one of the following: type of snow removal and clearing resource, affiliation, location, assigned routes, assigned work sections, service area, operational status, operational history, availability, work capacity, types of work that can be handled, number of vehicles owned, number of operational vehicles, number of workers, number of operators, available operating hours, contract scope, availability for support, flexibility, redeployment, pre-deployment, travel time, access to snow disposal sites, fuel supply availability, or contact information. Availability may include not only whether the resource is currently operational, but also its availability within a certain period in the future, available schedules, deployment location, mobility, responsiveness, coverage area, operating hours, shift status, booking status, assignment schedule, overlap with other work, or communication availability. The Road Snow Removal Department may refer to this information and generate data to determine which snow removal resources should be deployed, shared, reallocated, or pre-deployed for routes, work sections, snow removal companies, road administrators, or local governments where high loads are predicted based on future snow removal operational load forecasts.

[0087] The Road Snow Removal Department may generate information to support decisions regarding the allocation of snow removal work resources, based on future snow removal operational load forecast information, including at least one of the following regarding snow removal work resources among multiple routes, multiple work sections, multiple snow removal companies, multiple road administrators, or multiple municipalities: candidates for support deployment, candidates for resource sharing, candidates for reallocation, or candidates for pre-deployment deployment. Candidates for support deployment may include candidates for additional snow removal work resources from other routes, work sections, snow removal companies, road administrators, or municipalities to routes, work sections, snow removal companies, road administrators, or municipalities where high loads are predicted. Candidates for resource sharing may include candidates for sharing vehicles, heavy machinery, workers, work teams, working hours, snow disposal site usage slots, work bases, or waiting areas from entities or areas with surplus snow removal work resources to entities or areas with insufficient snow removal work resources.

[0088] The reassignment candidates may include candidates to move snow removal resources that are already in place to routes or work sections where high loads are expected. The pre-placement candidates may include candidates to pre-place snow removal resources before snowfall, snow accumulation, compacted snow, snow pileup on the road shoulders, reduction in road width, snow removal and transport load, or significant traffic impact occurs. The snow removal resource allocation adjustment decision support information may include at least one of the following: candidates for support deployment, flexible deployment, reassignment, pre-placement, waiting location, relocation destination, deployment timing, deployment order, support request destination, allocation adjustment source, allocation adjustment destination, or expected load reduction after allocation adjustment.

[0089] The Road Snow Removal Department may compare future snow removal operational load forecast information with a standard load level determined based on the snow removal operational load information. The Road Snow Removal Department will determine whether it is necessary to adjust the allocation of snow removal work resources if the future load indicated by the future snow removal operational load forecast information exceeds, or is likely to exceed, the standard load level. The standard load level may be determined based on the workload under normal conditions, standard working hours, the usual number of snow removal vehicles deployed, the processing capacity of each snow removal business operator, the standard response capacity of the road administrator or local government, the acceptance capacity of snow disposal sites, past performance during high load periods, contractual or operational standard processing capacity, or the availability of snow removal work resources. For example, the Road Snow Removal Department may determine that an adjustment in allocation is necessary if it determines that the required number of vehicles, required working hours, required number of transports, number of target routes, number of target work sections, load per snow removal business operator, load per road administrator, or load per local government, as indicated by the future snow removal operational load forecast information, exceeds the standard load level.

[0090] The Road Snow Removal Department may output or notify information to support decisions regarding the allocation of snow removal work resources based on the determination result of whether or not allocation adjustment is necessary. The recipients of the output or notification may include road administrators, local government officials, snow removal businesses, work commanders, site supervisors, snow removal vehicle operators, snow removal vehicle operators, external cooperation systems, departments in neighboring municipalities, cooperation systems between road administrators, or disaster response systems. The form of output or notification may include display on the management screen, overlay on the map screen, display as a list, generation of a priority list, sending of a notification message, generation of a work command draft, generation of a dispatch request draft, generation of an allocation change draft, generation of a support request draft, or sending of information for data linkage. The Road Snow Removal Department may generate information as information to support decisions regarding the allocation of snow removal work resources, including support destinations, candidate support sources, snow removal work resources to be shared, redeployment destinations, preliminary deployment destinations, reasons for allocation adjustment, predicted load overload details, difference from the standard load level, candidate times for implementing allocation adjustment, or expected load reduction after allocation adjustment.

[0091] The information acquisition unit 610 may acquire at least one of the following information during the same snow removal season: newly generated or updated snow removal operation information, snow removal environment information, or future snow removal environment information. Here, the same snow removal season includes the same fiscal year, the same winter, the same snowfall season, the same heavy snow response period, or the period designated by the road administrator or local government as the snow removal response period. Newly generated or updated information may be acquired based on new snowfall, changes in snow depth, changes in temperature or wind speed, changes in snow quality, deterioration of compacted snow conditions, increase in road shoulder snow accumulation, progress of road width reduction, changes in the operating status of snow removal vehicles, addition of work results, addition of dispatch history, changes in traffic operation-related information, changes in route bus operation information, updates of image information, or changes in work schedules by the road administrator or snow removal business operator.

[0092] The analysis unit 620 may update the snow removal operation load information or the future snow removal operation load forecast information by referring to the snow removal operation load information already derived or the future snow removal operation load forecast information already calculated, and by reflecting one or more pieces of information acquired by the information acquisition unit 610. For example, the analysis unit 620 may recalculate, correct, or re-evaluate the snow removal operation load information already derived or the future snow removal operation load forecast information already calculated if, during the same snow removal season, the amount of snowfall increases compared to the initial forecast, the snow depth increases, the amount of snow piled up on the roadside increases, the road width decreases, the compacted snow condition deteriorates, the operating rate of snow removal vehicles increases, delays in work occur, the usage load of snow disposal sites increases, traffic congestion occurs on snow removal transport routes, or the traffic impact expands.

[0093] The analysis unit 620 may update multiple categories, snow removal operational load information, standard load levels, calculation conditions for future snow removal operational load prediction information, or generation conditions for snow removal decision support information using newly acquired snow removal operational information, snow removal environmental information, traffic operation-related information, route bus operation information, image information, or actual work results during the same snow removal season. For example, the analysis unit 620 may update thresholds for snowfall amount categories, snow depth categories, road shoulder snow accumulation categories, road width reduction categories, bus route delay categories, or high load categories based on results accumulated during the same season. Furthermore, even if a condition was not previously judged as high load, if the actual snow removal operational load increased during the same season, the analysis unit 620 may update the calculation conditions for snow removal operational load information or future snow removal operational load prediction information corresponding to that condition.

[0094] The analysis unit 620 may record the information before and after the update in association when updating snow removal operation load information or future snow removal operation load forecast information. For example, the analysis unit 620 may record the snow removal operation load information before the update, the snow removal operation load information after the update, the future snow removal operation load forecast information before the update, the future snow removal operation load forecast information after the update, the new information used for the update, the date and time of the update, the reason for the update, the load level that changed due to the update, the snow removal decision support information generated after the update, or the snow removal work resource allocation adjustment decision support information generated after the update in association with each other. By managing the update history in this way, it is possible to confirm in subsequent verification processing which forecast was updated and based on which information.

[0095] The analysis unit 620 may compare the predicted future snow removal operational load information calculated or updated during the snow removal season with the actual snow removal operational information obtained at the end or end of the snow removal season. The actual snow removal operational information obtained may include the actual operating time of snow removal vehicles, the number of dispatches, the number of operations, the time of completion of operations, the routes or work sections covered, the number of snow removal transports, the number of transports to snow disposal sites, the waiting time at snow disposal sites, the travel time on snow removal transport routes, the work performance of each snow removal company, the response performance of each road administrator or local government, work delays, work cancellations, whether or not support was deployed, whether or not flexibility was provided, whether or not redeployment was done, whether or not advance deployment was done, or the status of shortages of snow removal operational resources. Based on this actual snow removal operational information obtained, the analysis unit 620 identifies the actual snow removal operational load.

[0096] The analysis unit 620 may generate verification information regarding the difference between the snow removal operational load indicated by the future snow removal operational load prediction information and the actual snow removal operational load identified based on the snow removal operational information. The verification information may include the difference between the predicted workload and the actual workload, the difference between the predicted working time and the actual working time, the difference between the predicted number of snow removal vehicles needed and the actual number deployed, the difference between the predicted dispatch frequency and the actual dispatch frequency, the difference between the predicted snow removal and transport load and the actual snow removal and transport load, the difference between the predicted snow disposal site utilization load and the actual snow disposal site utilization load, the difference between the predicted snow removal and transport route load and the actual snow removal and transport route load, the difference between the predicted load for each snow removal business operator and the actual load, or the difference between the predicted response load for road administrators or municipalities and the actual response load.

[0097] Verification information may include routes or work sections where the prediction was overestimated, routes or work sections where the prediction was underestimated, snow removal operators with large discrepancies from actual results, road administrators or local governments with large discrepancies from actual results, the difference between the snow removal environmental conditions used for prediction and the actual snow removal environmental conditions, whether or not actions based on snow removal decision support information were taken, whether or not support was provided, adjusted, reallocated, or pre-allocated based on snow removal work resource allocation adjustment decision support information was taken, the load reduction effect after implementation, or the degree of improvement in prediction accuracy after updating. Based on the verification information, the analysis unit 620 may reflect the calculation conditions for future snow removal operation load prediction information, standard load levels, multiple categories, or setting conditions for AI (artificial intelligence) models, statistical models, time series prediction models, or rule-based models in subsequent processing.

[0098] The analysis unit 620 may refer to the verification information and the snow removal operation information obtained as actual results, and generate snow removal site operation issue information for each route, work section, road section, snow removal target area, snow removal business operator, road administrator, or local government, regarding issues in snow removal site operations during the snow removal season that are subject to improvement for the next snow removal season. The snow removal site operation issue information may include a shortage of snow removal vehicles, a shortage of workers, a shortage of operators, uneven distribution of load among snow removal business operators, uneven workload in work sections, work delays on each route, concentration of snow removal transport load, congestion at snow disposal sites, traffic disruption on snow removal transport routes, insufficient pre-deployment, delays in deploying support, insufficient understanding of available snow removal work resources, delays in redeployment, delays in starting work, inappropriate setting of snow removal priority or snow removal priority, or targets for improvement extracted based on the discrepancy between future snow removal operation load forecast information and actual results.

[0099] The snow removal and clearing site work issue information may include information such as routes or work sections prone to delays in snow removal work, time periods when snow removal and clearing resources are likely to be insufficient, sections where snow removal and transport are likely to be strained, areas where snow disposal sites are likely to be heavily utilized, snow removal and clearing businesses that are likely to require additional support, road administrators or local governments, locations where the forward placement of snow removal and clearing vehicles should be considered, routes or work sections where the start of snow removal should be brought forward, snow removal and clearing resources that should be considered for pre-placement or forward placement in the next snow removal and clearing season, or information indicating targets for reviewing the standard load level in the snow removal and clearing decision support system 600. The generated snow removal and clearing site work issue information may be used for snow removal and clearing plans for the next snow removal and clearing season, contracts with snow removal and clearing businesses, work section settings, snow disposal site operations, vehicle placement, support systems, forward placement rules, snow removal and transport route settings, cooperation with transportation operators, or reviewing the standard load level or forecast conditions in the snow removal and clearing decision support system 600.

[0100] The snow removal decision support system 600 may use at least one of the following to derive snow removal operational load information or calculate future snow removal operational load prediction information: an AI (artificial intelligence) model, a machine learning model, a statistical model, a clustering model, a regression model, a time series forecasting model, or a rule-based model. These models or processes may be executed by the analysis unit 620, or by an external server, cloud processing platform, road administrator's management system, snow removal business operator's business system, traffic information provision system, image analysis system, or external AI processing platform that can communicate with the snow removal decision support system 600. Even in this case, the snow removal decision support system 600 may acquire the output results of the model or process and use them to generate snow removal operational load information, future snow removal operational load prediction information, snow removal decision support information, or snow removal work resource allocation adjustment decision support information.

[0101] An AI (artificial intelligence) model or machine learning model may use at least one of the following as input: snow removal operation information, snow removal environment information, future snow removal environment information, traffic operation-related information, route bus operation information, bus route delay information, image information, past snow removal operation load information, past and future snow removal operation load prediction information, snow removal decision support information, snow removal work resource allocation adjustment decision support information, verification information, or snow removal on-site work issue information. Based on the input information, the AI ​​(artificial intelligence) model or machine learning model may output the workload, working hours, required number of vehicles, vehicle utilization rate, dispatch frequency, snow removal transport load, snow disposal site utilization load, snow removal transport route load, load per snow removal operator, load per road administrator or municipality, or the expected strain on snow removal operations.

[0102] Machine learning models may include supervised learning models, unsupervised learning models, semi-supervised learning models, deep learning models, neural networks, convolutional neural networks, recurrent neural networks, decision trees, random forests, gradient boosting, support vector machines, anomaly detection models, time series forecasting models, or clustering models. These models may use snow removal operation information, snow removal environment information, future snow removal environment information, traffic operation-related information, bus route delay information, image information, validation information, or snow removal field work problem information as training data, explanatory variables, features, evaluation targets, inference targets, or update data.

[0103] Statistical models, regression models, time-series forecasting models, or rule-based models may be used to numerically or systematically represent the correspondence between snow removal environmental conditions and snow removal operational load. For example, a regression model may estimate working time, required number of vehicles, number of dispatches, number of snow removal and transport operations, snow disposal site utilization load, snow removal and transport route load, or snow removal operational load, using snowfall amount, snow depth, temperature, wind speed, snow quality, compaction status, road shoulder snow accumulation, road wi...

Claims

1. A snow removal decision support system that predicts the operational load of snow removal on roads, Snow removal operation information includes at least one of the following for snow removal vehicles: location information, travel history, operating status, operation history, dispatch history, or work performance. As snow removal environment information, at least one of the following is included: snowfall amount information, snow depth information, temperature information, wind speed information, snow quality information, compacted snow condition information, road shoulder snow accumulation information, or road width reduction information due to snow accumulation or snow cover, as indicated in the snow removal operation information: As future snow removal environment information, at least one of the following will be included in the future snow removal operational load prediction: snowfall amount prediction information, snow depth prediction information, temperature prediction information, wind speed prediction information, snow quality prediction information, compacted snow condition prediction information, road shoulder snow accumulation prediction information, or road width reduction prediction information due to snow accumulation or snow cover. Information acquisition unit that acquires information, The snow removal operation information, snow removal environment information, and future snow removal environment information acquired by the information acquisition unit are associated with each route, work section, snow removal business operator, road administrator, or local government. Regarding the snow removal environmental conditions included in the aforementioned snow removal environmental information, multiple categories are set based on a single condition or a combination of multiple conditions. Based on the snow removal operation information and snow removal environment information associated with each of the aforementioned routes, work sections, snow removal businesses, road administrators, or local governments, the snow removal operation results indicated by the snow removal operation information are calculated or aggregated for each of the multiple categories. The results obtained by the above calculation or aggregation are derived as snow removal operation load information indicating the operational load of snow removal corresponding to the above-mentioned multiple categories. Of the aforementioned multiple categories, identify at least one category to which the future snow removal environmental conditions indicated by the future snow removal environmental information correspond, Using the snow removal operation load information corresponding to one or more of the identified categories, An analysis unit calculates future snow removal operational load prediction information that shows the future snow removal operational load for each of the aforementioned routes, work sections, snow removal operators, road administrators, or local governments, A snow removal and clearing decision support system characterized by comprising the following features.

2. A snow removal and clearing decision support system according to Claim 1, The snow removal operation load information is characterized in that it shows at least one of the following: workload, working hours, number of snow removal vehicles, vehicle utilization rate, dispatch frequency, working distance, number of transports, waiting time, work delay, load rate, load score, load coefficient, or load level determination result obtained by the calculation or aggregation.

3. A snow removal and clearing decision support system according to Claim 1, The snow removal decision support system is characterized in that the analysis unit sets at least one of the following as the multiple classifications for the snow removal environmental conditions: classification by numerical range, classification by state classification, classification using one or more pieces of information included in the snow removal environmental information as features, classification by statistical processing, classification by machine learning, clusters generated by clustering processing, classification according to the load level in snow removal operations, or classification by rule-based processing.

4. A snow removal and clearing decision support system according to claim 1, The analysis unit compares the predicted future snow removal and snow clearing load information with the standard load level determined based on the snow removal and snow clearing load information. A snow removal decision support system characterized by calculating snow removal operation evaluation information relating to at least one of the following: the expected excess of snow removal operation load, the expected increase in snow removal operation load, or the expected strain on snow removal operations, for the aforementioned route, the aforementioned work section, the aforementioned snow removal business operator, the aforementioned road administrator, or the aforementioned local government.

5. A snow removal and clearing decision support system according to claim 1, The aforementioned information acquisition unit further acquires traffic operation-related information, including route bus operation information. The analysis unit associates the traffic operation-related information with the snow removal environment information for each route, work section, snow removal business operator, road administrator, or local government. Based on the traffic operation-related information and snow removal environment information associated with each of the aforementioned routes, work sections, snow removal operators, road administrators, or local governments, the traffic operation status indicated by the traffic operation-related information is calculated or aggregated for each of the multiple categories. The results obtained by the above calculation or aggregation are derived as traffic impact information corresponding to the above multiple categories, showing the impact that the snow removal environmental conditions had on road traffic or public transport operations. Using the traffic impact information corresponding to one or more of the identified categories, A snow removal decision support system characterized by calculating future traffic impact prediction information that shows the impact of the future snow removal environmental conditions on future road traffic or public transport operations for each of the aforementioned routes, work sections, snow removal operators, road administrators, or local governments.

6. A snow removal and clearing decision support system according to claim 1, The information acquisition unit further acquires traffic operation-related information, including route bus operation information during or after snow removal operations, as indicated by the snow removal operation information. The analysis unit generates bus route delay information based on the route bus operation information, The aforementioned bus route delay information is associated with the aforementioned route, Based on the associated bus route delay information, the degree or change in the delay status on the route is evaluated. A snow removal decision support system characterized by correcting the snow removal operation load information for each route so that the snow removal operation load is shown as high or low, according to the results of the evaluation.

7. A snow removal and clearing decision support system according to claim 5, Based on the future traffic impact prediction information, the analysis unit performs the following: A snow removal decision support system characterized by correcting the aforementioned future snow removal operation load prediction information.

8. A snow removal and clearing decision support system according to claim 1, The aforementioned information acquisition unit further acquires traffic operation-related information, including route bus operation information. The analysis unit associates the traffic operation-related information with the route or the work section. In the current traffic conditions indicated by the associated traffic operation-related information, for the aforementioned route or section where at least one of the following is occurring: congestion, delays in route buses, slow speeds, difficulty in passing vehicles, or obstruction of traffic, A snow removal decision support system characterized by correcting the future snow removal operation load prediction information so that the future snow removal operation load is indicated as high.

9. A snow removal and clearing decision support system according to claim 6, The aforementioned route bus operation information includes location information and time information of route buses, The analysis unit calculates the delay status on the bus route, or the delay status in the section included in the bus route, based on the location information and the time information. The calculated delay state is classified into multiple delay categories, A snow removal decision support system characterized by generating bus route delay information for each bus route or section by associating the plurality of delay categories with the bus route or section.

10. A snow removal and clearing decision support system according to claim 1, The aforementioned snow removal and clearing decision support system further comprises a road snow removal and clearing unit, Based on the predicted future snow removal operation load information calculated by the analysis unit, the road snow removal unit shall A snow removal decision support system characterized by generating snow removal decision support information that includes at least one of the following: the start date of snow removal operations, the aforementioned route or work section to be covered by snow removal operations, the number of snow removal vehicles to be deployed, the deployment of snow removal vehicles, the dispatch of snow removal businesses, or information used for decision-making by the road administrator.

11. A snow removal and clearing decision support system according to claim 10, Based on the predicted future snow removal and snow clearing load information, the road snow removal unit shall A snow removal decision support system characterized by generating snow removal decision support information that includes at least one of the following: a candidate timing for dispatching snow removal vehicles, a candidate route to be snow removed, a candidate work section to be snow removed, or a candidate priority for snow removal in the route or work section.

12. A snow removal and clearing decision support system according to claim 10, Based on the predicted future snow removal and snow clearing load information, the road snow removal unit shall A snow removal decision support system characterized by generating snow removal decision support information that includes at least one of the following: candidates for the aforementioned routes to be snow removed, candidates for the aforementioned work sections to be snow removed, candidates for the start date of snow removal, candidates for the required number of snow removal vehicles to be used for snow removal, candidates for the use of snow disposal sites, or candidates for snow removal transport routes.

13. A snow removal and clearing decision support system according to claim 10, Based on the predicted future snow removal and snow clearing load information, the road snow removal unit shall Regarding snow removal work resources among multiple routes, multiple work sections, multiple snow removal operators, multiple road administrators, or multiple municipalities, A snow removal decision support system characterized by generating snow removal work resource allocation adjustment decision support information that includes at least one of the following: candidates for support deployment, candidates for flexible deployment, candidates for reassignment, or candidates for pre-deployment deployment.

14. A snow removal and clearing decision support system according to claim 13, The road snow removal unit compares the predicted future snow removal operational load information with the standard load level determined based on the snow removal operational load information, If the future load indicated by the aforementioned future snow removal operation load prediction information exceeds, or is likely to exceed, the standard load level, Determine whether or not it is necessary to adjust the allocation of the aforementioned snow removal and clearing resources. A snow removal decision support system characterized by outputting or notifying snow removal work resource allocation adjustment decision support information based on the determination result of whether or not the allocation adjustment is necessary.

15. A snow removal and clearing decision support system according to claim 1, The information acquisition unit acquires at least one of the following information during the same snow removal season: newly generated or updated snow removal operation information, snow removal environment information, or future snow removal environment information. The snow removal decision support system is characterized in that the analysis unit updates the snow removal operation load information or the future snow removal operation load prediction information by referring to the snow removal operation load information already derived or the future snow removal operation load prediction information already calculated and reflecting one or more pieces of information acquired by the information acquisition unit.

16. A snow removal and clearing decision support system according to claim 15, The analysis unit, at the end or after the snow removal season, The predicted future snow removal operational load information, calculated or updated during the aforementioned snow removal season, is compared with the snow removal operational information obtained as actual data. A snow removal decision support system characterized by generating verification information regarding the difference between the snow removal operation load indicated by the predicted future snow removal operation load information and the actual snow removal operation load identified based on the snow removal operation information.

17. A snow removal and clearing decision support system according to claim 16, The analysis unit refers to the verification information and the snow removal operation information obtained as actual results, A snow removal decision support system characterized by generating information on on-site work challenges for the next snow removal season, which includes at least one of the following as targets for improvement extracted based on the differences shown by the verification information: shortage of snow removal vehicles, uneven distribution of workload among snow removal businesses, uneven workload in construction sections, work delays on each route, concentration of snow removal and transport load, delays in the start of work, etc., during the aforementioned snow removal season.

18. A snow removal and clearing decision support system according to claim 1, The aforementioned snow removal decision support system uses at least one of the following: an AI (artificial intelligence) model, a machine learning model, a statistical model, a clustering model, a regression model, a time series forecasting model, or a rule-based model. A snow removal decision support system characterized by deriving the aforementioned snow removal operation load information or calculating the aforementioned future snow removal operation load prediction information.

19. A snow removal and clearing decision support system according to claim 10, The aforementioned snow removal decision support system uses at least one of the following: an AI (artificial intelligence) model, a machine learning model, a statistical model, a clustering model, a regression model, a time series forecasting model, or a rule-based model. A snow removal decision support system characterized by generating the aforementioned snow removal decision support information.

20. A snow removal and clearing decision support system according to claim 13, The aforementioned snow removal decision support system uses at least one of the following: an AI (artificial intelligence) model, a machine learning model, a statistical model, a clustering model, a regression model, a time series forecasting model, or a rule-based model. A snow removal decision support system characterized by generating information to support decisions regarding the allocation of snow removal work resources.

21. A snow removal and clearing decision support system according to claim 1, The information acquisition unit acquires image information relating to at least one of the following: road, road surface, road shoulder, snow accumulation, snow deposits, compacted snow, snow levees, road width, or snow removal conditions. The snow removal decision support system analyzes the image information by image analysis processing including image analysis processing using an AI (artificial intelligence) model, generates at least a portion of the snow removal environment information based on the image information, or generates or corrects at least a portion of the future snow removal environment information based on changes in the image information acquired over time. A snow removal decision support system characterized by deriving snow removal operation load information or calculating future snow removal operation load prediction information using the generated snow removal environment information or the generated or corrected future snow removal environment information.

22. A road management method that uses a computer to predict the operational load of snow removal and clearing on roads, The aforementioned computer, via the network, Snow removal operation information includes at least one of the following for snow removal vehicles: location information, travel history, operating status, operation history, dispatch history, or work performance. As snow removal environment information, at least one of the following is included: snowfall amount information, snow depth information, temperature information, wind speed information, snow quality information, compacted snow condition information, road shoulder snow accumulation information, or road width reduction information due to snow accumulation or snow cover, as indicated in the snow removal operation information: As future snow removal environment information, at least one of the following will be included in the future snow removal operational load prediction: snowfall amount prediction information, snow depth prediction information, temperature prediction information, wind speed prediction information, snow quality prediction information, compacted snow condition prediction information, road shoulder snow accumulation prediction information, or road width reduction prediction information due to snow accumulation or snow cover. Obtain, The acquired snow removal operation information, snow removal environment information, and future snow removal environment information are mapped to each route, work section, snow removal business operator, road administrator, or local government. Regarding the snow removal environmental conditions included in the aforementioned snow removal environmental information, multiple categories are set based on a single condition or a combination of multiple conditions. Based on the snow removal operation information and snow removal environment information associated with each of the aforementioned routes, work sections, snow removal businesses, road administrators, or local governments, the snow removal operation results indicated by the snow removal operation information are calculated or aggregated for each of the multiple categories. The results obtained by the above calculation or aggregation are derived as snow removal operation load information indicating the operational load of snow removal corresponding to the above-mentioned multiple categories. Of the aforementioned multiple categories, identify at least one category to which the future snow removal environmental conditions indicated by the future snow removal environmental information correspond, Using the snow removal operation load information corresponding to one or more of the identified categories, A road management method characterized by calculating future snow removal operational load prediction information that indicates the future snow removal operational load for each of the aforementioned routes, work sections, snow removal operators, road administrators, or local governments.

23. A road management method according to claim 22, A road management method characterized in that the computer derives snow removal operation load information that shows at least one of the following obtained by calculation or aggregation: amount of work, working time, number of snow removal vehicles, vehicle utilization rate, dispatch frequency, working distance, number of transports, waiting time, work delay, load rate, load score, load coefficient, or load level determination result.

24. A road management method according to claim 22, A road management method characterized in that the computer sets at least one of the following as the plurality of classifications for the snow removal environmental conditions: classification by numerical range, classification by state classification, classification using one or more pieces of information included in the snow removal environmental information as features, classification by statistical processing, classification by machine learning, clusters generated by clustering processing, classification according to the load level in snow removal operations, or classification by rule-based processing.

25. A road management method according to claim 22, The computer compares the predicted future snow removal and snow clearing load information with the standard load level determined based on the snow removal and snow clearing load information. A road management method characterized by calculating snow removal operation evaluation information relating to at least one of the following: the expected excess of snow removal operation load, the expected increase in snow removal operation load, or the expected strain on snow removal operations, for the aforementioned route, the aforementioned work section, the aforementioned snow removal business operator, the aforementioned road administrator, or the aforementioned local government.

26. A road management method according to claim 22, The aforementioned computer further acquires traffic operation-related information, including route bus operation information. The aforementioned traffic operation-related information and the aforementioned snow removal environment information are associated with each of the aforementioned routes, work sections, snow removal businesses, road administrators, or local governments. Based on the traffic operation-related information and snow removal environment information associated with each of the aforementioned routes, work sections, snow removal operators, road administrators, or local governments, the traffic operation status indicated by the traffic operation-related information is calculated or aggregated for each of the multiple categories. The results obtained by the above calculation or aggregation are derived as traffic impact information corresponding to the above multiple categories, showing the impact that the snow removal environmental conditions had on road traffic or public transport operations. Using the traffic impact information corresponding to one or more of the identified categories, A road management method characterized by calculating future traffic impact prediction information that shows the impact of the future snow removal environmental conditions on future road traffic or public transport operations for each of the aforementioned routes, work sections, snow removal operators, road administrators, or local governments.

27. A road management method according to claim 22, The computer further acquires traffic operation-related information, including route bus operation information during or after snow removal operations, as indicated by the snow removal operation information. Based on the aforementioned bus route operation information, bus route delay information is generated. The aforementioned bus route delay information is associated with the aforementioned route, Based on the associated bus route delay information, the degree or change in the delay status on the route is evaluated. A road management method characterized by correcting the snow removal operation load information for each route so that the snow removal operation load is shown as high or low, according to the results of the evaluation.

28. A road management method according to claim 26, Based on the future traffic impact prediction information, the computer, A road management method characterized by correcting the predicted future snow removal and snow clearing operational load information.

29. A road management method according to claim 22, The aforementioned computer further acquires traffic operation-related information, including route bus operation information. The aforementioned traffic operation-related information is associated with the aforementioned route or the aforementioned work section. In the current traffic conditions indicated by the associated traffic operation-related information, for the aforementioned route or section where at least one of the following is occurring: congestion, delays in route buses, slow speeds, difficulty in passing vehicles, or obstruction of traffic, A road management method characterized by correcting the future snow removal operation load prediction information so that the future snow removal operation load is indicated as higher.

30. A road management method according to claim 27, The aforementioned route bus operation information includes location information and time information of route buses, The computer calculates the delay status on the bus route or the delay status in the section included in the bus route based on the location information and the time information. The calculated delay state is classified into multiple delay categories, A road management method characterized by generating bus route delay information for each bus route or section by associating the plurality of delay categories with the bus route or section.

31. A road management method according to claim 22, Based on the future snow removal operation load prediction information, the computer, A road management method characterized by generating snow removal decision support information that includes at least one of the following pieces of information used for decision-making by the road administrator: the start date of snow removal operations, the aforementioned route or work section to be covered by snow removal operations, the amount of snow removal vehicles to be deployed, the deployment of snow removal vehicles, the dispatch of snow removal businesses, or other information used for decision-making by the road administrator.

32. A road management method according to claim 31, Based on the future snow removal operation load prediction information, the computer, A road management method characterized by generating snow removal decision support information that includes at least one of the following: a candidate timing for dispatching snow removal vehicles, a candidate route to be snow removed, a candidate work section to be snow removed, or a candidate priority for snow removal in the route or work section.

33. A road management method according to claim 31, Based on the future snow removal operation load prediction information, the computer, A road management method characterized by generating snow removal decision support information that includes at least one of the following: candidates for the aforementioned routes to be snow removed, candidates for the aforementioned work sections to be snow removed, candidates for the start date of snow removal, candidates for the required number of snow removal vehicles to be used for snow removal, candidates for the use of snow disposal sites, or candidates for snow removal transport routes.

34. A road management method according to claim 31, Based on the future snow removal operation load prediction information, the computer, Regarding snow removal work resources among multiple routes, multiple work sections, multiple snow removal operators, multiple road administrators, or multiple municipalities, A road management method characterized by generating information to support decisions regarding the allocation of snow removal and clearing work resources, which includes at least one of the following: candidates for support deployment, candidates for flexible deployment, candidates for reassignment, or candidates for pre-deployment deployment.

35. A road management method according to claim 34, The computer compares the predicted future snow removal and snow clearing load information with the standard load level determined based on the snow removal and snow clearing load information. If the future load indicated by the aforementioned future snow removal operation load prediction information exceeds, or is likely to exceed, the standard load level, Determine whether or not it is necessary to adjust the allocation of the aforementioned snow removal and clearing resources. A road management method characterized by outputting or notifying information supporting the decision on the allocation adjustment of snow removal work resources based on the result of determining whether or not the allocation adjustment is necessary.

36. A road management method according to claim 22, The computer acquires at least one of the following pieces of information during the same snow removal season: newly generated or updated snow removal operation information, snow removal environment information, or future snow removal environment information. A road management method characterized by updating the snow removal operation load information or the future snow removal operation load prediction information by referring to the snow removal operation load information already derived or the future snow removal operation load prediction information already calculated and reflecting the acquired information.

37. A road management method according to claim 36, The computer, at the end of or after the snow removal season, The predicted future snow removal operational load information, calculated or updated during the aforementioned snow removal season, is compared with the snow removal operational information obtained as actual data. A road management method characterized by generating verification information regarding the difference between the snow removal operation load indicated by the predicted future snow removal operation load information and the actual snow removal operation load identified based on the snow removal operation information.

38. A road management method according to claim 37, The computer refers to the verification information and the snow removal operation information obtained as actual results, A road management method characterized by generating information on on-site snow removal work challenges for the next snow removal season, which includes at least one of the following as targets for improvement extracted based on the differences shown by the verification information: a shortage of snow removal vehicles, uneven distribution of workload among snow removal businesses, uneven workload in construction sections, delays in work on each route, concentration of snow removal and transport load, delays in the start of work, or the aforementioned snow removal season.

39. A road management method according to claim 22, The computer uses at least one of the following: AI (artificial intelligence) models, machine learning models, statistical models, clustering models, regression models, time series forecasting models, or rule-based models. A road management method characterized by deriving the aforementioned snow removal operation load information or calculating the aforementioned future snow removal operation load prediction information.

40. A road management method according to claim 31, The computer uses at least one of the following: AI (artificial intelligence) models, machine learning models, statistical models, clustering models, regression models, time series forecasting models, or rule-based models. A road management method characterized by generating the aforementioned snow removal decision support information.

41. A road management method according to claim 34, The computer uses at least one of the following: AI (artificial intelligence) models, machine learning models, statistical models, clustering models, regression models, time series forecasting models, or rule-based models. A road management method characterized by generating information to support decisions regarding the allocation of snow removal and clearing work resources.

42. A road management method according to claim 22, The computer acquires image information relating to at least one of the following: road, road surface, road shoulder, snow accumulation, snow deposits, compacted snow, snow levees, road width, or snow removal conditions. The image information is analyzed by image analysis processing, including image analysis processing using an AI (artificial intelligence) model, and at least a portion of the snow removal environment information is generated based on the image information, or at least a portion of the future snow removal environment information is generated or corrected based on changes in the image information acquired over time. A road management method characterized by deriving snow removal operation load information or calculating future snow removal operation load prediction information using the generated snow removal environment information or the generated or corrected future snow removal environment information.

43. A program for causing a computer to function as a snow removal decision support system according to any one of claims 1 to 6, 8, 10, 15, 18, or 21.

44. A program for causing a computer to function as a snow removal decision support system according to claim 1, The program is characterized by including a sequence of instructions that causes the computer to perform at least one of the following processes (1) to (7). (1) A process to acquire traffic operation-related information including route bus operation information, associate the traffic operation-related information with the snow removal environment information for each route, work section, snow removal business operator, road administrator, or local government, calculate or aggregate the traffic operation status indicated by the traffic operation-related information for each of the multiple categories based on the traffic operation-related information and snow removal environment information associated for each route, work section, snow removal business operator, road administrator, or local government, derive the results obtained from the calculation or aggregation as traffic impact information corresponding to the multiple categories and showing the impact that the snow removal environment conditions have had on road traffic or public transport operations, calculate future traffic impact prediction information for each route, work section, snow removal business operator, road administrator, or local government showing the impact that future snow removal environment conditions will have on future road traffic or public transport operations based on the future traffic impact prediction information. (2) Obtain route bus operation information during or after snow removal operations as indicated by the snow removal operation information, calculate the delay status on the bus route or the delay status in the section included in the bus route based on the location information and time information of the route bus included in the route bus operation information, classify the calculated delay status into a plurality of delay categories, associate the plurality of delay categories with the bus route or the section to generate bus route delay information for each bus route or section, associate the generated bus route delay information with the route, evaluate the degree or change of the delay status on the route based on the associated bus route delay information, and correct the snow removal operation load information for each route so that the load on snow removal operations is indicated as high or low according to the result of the evaluation. (3) A process that generates snow removal decision support information, based on the predicted future snow removal operation load information, including at least one of the following: candidate timing for dispatching snow removal vehicles, candidate routes to be snow removed, candidate work sections to be snow removed, or candidate snow removal priority in the routes or work sections. (4) A process that generates snow removal decision support information, based on the future snow removal operation load prediction information, which includes at least one of the following: candidate routes to be snow removed, candidate work sections to be snow removed, candidate snow removal start dates, candidate number of snow removal vehicles required for snow removal, candidate use of snow disposal sites, or candidate snow removal transport routes. (5) A process that generates snow removal work resource allocation adjustment support information, based on the future snow removal operation load prediction information, which includes at least one of the following regarding snow removal work resources among multiple routes, multiple work sections, multiple snow removal businesses, multiple road administrators, or multiple municipalities: a candidate for support deployment, a candidate for sharing resources, a candidate for reallocation, or a candidate for pre-deployment deployment. (6) A process that, at the end of or after the snow removal season, compares the predicted future snow removal operational load information calculated or updated during the snow removal season with the actual snow removal operational information obtained, and generates verification information regarding the difference between the snow removal operational load indicated by the predicted future snow removal operational load information and the actual snow removal operational load identified based on the snow removal operational information. (7) A process that generates snow removal decision support information using at least one of the following, based on the future snow removal operation load prediction information: the start date of snow removal operations, the route or work section to be covered by snow removal operations, the amount of snow removal vehicles to be deployed, the deployment of snow removal vehicles, the dispatch of snow removal businesses, or information used for decision-making by the road administrator.

45. A program for causing a computer to function as a snow removal decision support system according to claim 1, The program is characterized by including a sequence of instructions that causes the computer to perform at least one of the following processes (1) to (3). (1) Based on the future snow removal operation load forecast information, generate snow removal work resource allocation adjustment decision support information that includes at least one of the following regarding snow removal work resources among multiple routes, multiple work sections, multiple snow removal businesses, multiple road administrators, or multiple municipalities: a candidate for support deployment, a candidate for sharing, a candidate for reassignment, or a candidate for pre-deployment; compare the future snow removal operation load forecast information with a standard load level determined based on the snow removal operation load information; determine whether or not to adjust the allocation of snow removal work resources if the future load indicated by the future snow removal operation load forecast information exceeds or is likely to exceed the standard load level; and output or notify the snow removal work resource allocation adjustment decision support information based on the determination result of whether or not to adjust the allocation. (2) During the same snow removal season, acquire at least one of the following newly generated or updated snow removal operation information, snow removal environment information, or future snow removal environment information, refer to the snow removal operation load information already derived or the future snow removal operation load forecast information already calculated, and update the snow removal operation load information or the future snow removal operation load forecast information by reflecting the acquired one or more pieces of information, and at the end or end of the snow removal season, compare the future snow removal operation load forecast information calculated or updated during the snow removal season with the snow removal operation information acquired as actual results. The process involves generating verification information regarding the difference between the predicted snow removal and snow clearing operational load indicated by the future snow removal and snow clearing operational load information and the actual snow removal and snow clearing operational load identified based on the snow removal and snow clearing operational information, and referencing the verification information and the snow removal and snow clearing operational information obtained as actual results to generate information on on-site snow removal and snow clearing operational challenges for the next snow removal and snow clearing season, which includes at least one of the following as targets for improvement extracted based on the difference indicated by the verification information during the snow removal and snow clearing season: a shortage of snow removal and snow clearing vehicles, uneven distribution of load among snow removal and snow clearing businesses, uneven distribution of work volume in construction sections, work delays for each route, concentration of snow removal and snow transport load, delays in the start of work, or information on on-site snow removal and snow clearing operational challenges for the next snow removal and snow clearing season. (3) Based on the predicted future snow removal operational load information, a process to generate snow removal resource allocation adjustment support information, which includes at least one of the following regarding snow removal work resources among multiple routes, multiple work sections, multiple snow removal businesses, multiple road administrators, or multiple municipalities: candidates for support deployment, candidates for sharing resources, candidates for reallocation, or candidates for pre-deployment deployment, using at least one of the following: an AI (artificial intelligence) model, a machine learning model, a statistical model, a clustering model, a regression model, a time series forecasting model, or a rule-based model.

Citation Information

Patent Citations

  • Cordless telephone system

    JP1991001637A

  • Outer side handle structure of door for automobile

    JP1996004366A

  • Snowfall amount estimation system and snowfall amount estimation method

    JP7622875B2

  • JPP7721032B

  • JPP7776925B