Snow removal decision support system and program, road management method

Abstract

We provide a highly practical snow removal decision support system, program, and road management method that can accurately and flexibly determine the need for snow removal by integrating and analyzing a variety of information such as patrol status, traffic conditions, weather information, and resident reports, and enables prioritization and the formulation and updating of dynamic implementation plans. [Solution] The snow removal decision support system comprises an information acquisition unit that acquires at least two types of information such as road surface, traffic, weather, driving, resident reports, and snow removal and disposal; an analysis unit that generates analysis results based on the acquired information; and a road snow removal and disposal unit that at least formulates dispatch orders to snow removal and disposal companies based on the analysis results and advance plans registered for each route or construction section (including the responsible snow removal and disposal company and snow removal and disposal standards).

Description

[Technical Field]

[0001] The present invention relates to technology that supports decisions on whether to perform snow removal work on snow-covered roads, and in particular to a snow removal decision support system that uses a variety of external information to dynamically determine and manage the necessity and priority of snow removal. [Background technology]

[0002] In cold, snowy regions, in order to maintain urban functions and ensure smooth road traffic during the winter, it is necessary to carry out appropriate snow removal work on roads when snow accumulates. This will minimize traffic disruptions and disruption to daily life. Traditionally, the main means of determining the need for snow removal was through visual patrols by local government officials and reports from residents via telephone, but issues included uneven distribution of information and subjectivity of judgment. In addition, while the use of AI (artificial intelligence) analysis and sensing technology has been increasing in recent years, these mainly rely on a few sensing methods and devices, and the reality is that they have not yet been implemented in a wide-area and planned manner across the entire municipality. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Laid-Open No. 2025-031637 [Patent Document 2] Patent No. 7622875 [Patent Document 3] JP 2017-084366 A Summary of the Invention [Problem to be solved by the invention]

[0004] In recent years, advanced technologies have been developed for the purposes of deciding whether to carry out snow removal and managing work, such as technology that uses AI (artificial intelligence) to analyze images taken by cameras mounted on patrol vehicles to grasp the state of snow accumulation and snow banks (e.g., Patent Document 1), and vibration sensing technology that estimates the state of snow accumulation based on optical fiber cables laid on roads (e.g., Patent Document 2). Also proposed is an interactive information providing system (for example, Patent Document 3) that uses AI (artificial intelligence) to analyze the contents of messages sent by users via SNS (Social Networking Service) or chat apps and presents related information. However, while each of these technologies is useful, they are limited to specific information sources and individual functions, and do not comprehensively support overall snow removal decisions, prioritization, or the development of dynamic implementation plans. The purpose of this invention is to provide a highly practical snow removal decision support system that can accurately and flexibly determine the need for snow removal by comprehensively analyzing a variety of information such as patrol status, traffic conditions, weather information, and reports from residents, and that enables prioritization and the formulation and updating of dynamic implementation plans. Furthermore, this invention embodies a new infrastructure management concept known as "self-improving snow removal decision support," which goes beyond the one-off task of snow removal and collects, analyzes, and judges the weather characteristics, traffic characteristics, and citizen needs of each region from multiple angles, and dynamically and continuously optimizes operational policies based on the results. [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 has the function of acquiring multiple pieces of information such as snow removal conditions, road conditions, traffic conditions, vehicle driving conditions, weather conditions, and resident report conditions, analyzing them in an integrated manner to determine the need for snow removal, and formulating a snow removal implementation plan. Furthermore, the present invention is configured with an analysis unit that comprehensively analyzes various information, a road snow removal unit that manages and controls actual snow removal work based on the results of the judgment, and an improvement unit that continuously improves the judgment model, and these are configured as core components. This enables flexible prioritization based on region and time of day, reflects diverse information sources, and improves learning through AI (artificial intelligence), resulting in efficient and accurate snow removal support. An example of the configuration of the present invention will be described below in accordance with the claims. [1] An information acquisition unit that acquires at least two or more pieces of information from among information on road surface conditions, information on traffic conditions, information on weather conditions, information on vehicle driving conditions, information on resident reports, and information on snow removal conditions; an analysis unit that analyzes the two or more pieces of information acquired by the information acquisition unit; and a route or construction section (including cases where at least a part of the route or construction section includes a road that may be designated as an emergency transportation route and / or a road clearance route, or a road leading to an emergency transportation route or a road clearance route), a responsible snow removal company, and a snow removal company. A snow removal decision support system comprising: a road snow removal unit that registers a pre-formulated snow removal plan including snow dispatch standards, and formulates a dispatch order to the snow removal company as part of a snow removal implementation plan (including, for example, dispatch orders, work type, work time period, and resource allocation) based on the analysis results analyzed by the analysis unit; and wherein the road snow removal unit formulates at least the dispatch order to the snow removal company for each route or work section based on the snow removal plan registered in the road snow removal unit and the analysis results analyzed by the analysis unit. [2] [1] A snow removal decision support system as described in [1], characterized in that the information acquisition unit acquires forecast information regarding future snowfall amount and temperature, as well as whether or not rain will fall, contained in short-term weather forecast information, and the analysis unit performs processing to derive the time to start preparatory work for snow removal or the time to carry out snow removal based on the forecast information acquired by the information acquisition unit. [3] [1] A snow removal decision support system as described in [1], wherein the information acquisition unit acquires forecast information regarding temperature, humidity, snow quality, moisture content or snow load contained in short-term weather forecast information, and the analysis unit performs a process to evaluate the level of workload in snow removal work based on the forecast information acquired by the information acquisition unit, and derive decision information for adjusting the start timing of preparatory work for snow removal or the implementation timing of snow removal based on the evaluation. [4] [1] A snow removal decision support system as described in [1], characterized in that the road snow removal unit predicts at least one of the following: the availability of snow removal vehicles or workers, the time required for snow removal work, and / or the necessary resources, and performs processing to optimize the snow removal implementation plan based on work efficiency. [5] [1] A snow removal decision support system as described in [1], wherein the information acquisition unit acquires at least one of information regarding the congestion status of a snow dumping site, information regarding the remaining capacity of the snow dumping site, information regarding the access distance to the snow dumping site, and information regarding the traffic congestion status of the access route to the snow dumping site, and the road snow removal and disposal unit performs route optimization processing for snow removal work based on the congestion status, remaining capacity, access distance, and traffic congestion status of the access route at the snow dumping site acquired by the information acquisition unit. [6] [1] A snow removal decision support system as described in [1], characterized in that the snow removal decision support system is equipped with a decision unit, and the analysis unit or the decision unit compares at least one item of the estimated implementation cost for each candidate snow removal response with the remaining budget, determines whether the response can be carried out within the budget, and performs priority adjustment processing or processing regarding requests for external support as necessary. [7] [1] A snow removal decision support system as described in [1], wherein the information acquisition unit acquires information on the operation status or availability of work vehicles and workers, and, if necessary, information on the usage status of snow dumping sites, from information sources shared via individual systems or networks managed by multiple local governments, multiple road managers, or the snow removal and disposal companies, and the road snow removal and disposal unit performs cross-border wide-area collaborative processing between multiple local governments, multiple road managers, or snow removal and disposal companies based on the information acquired by the information acquisition unit, and formulates the snow removal and disposal implementation plan, including mutual resource optimization and budget adjustment. [8] [1] A snow removal decision support system as described in [1], characterized in that the snow removal decision support system comprises a decision unit, and further comprises an improvement unit that continuously improves at least one of the processing logics used in the analysis unit, the road snow removal unit, or the decision unit based on learning data. [9] [1] A snow removal decision support system as described in [1], characterized in that the snow removal decision support system visually outputs at least one of the snow removal response priorities, work plans, operation forecasts, and snow removal route information based on the output of the analysis unit or the road snow removal unit in the form of a map display, a time series display, or a combination thereof.

[10] [1] A snow removal decision support system as described in [1], wherein the snow removal decision support system is equipped with an improvement unit, and the information acquisition unit acquires at least one of resident reporting trends, traffic congestion information, bus delay information, patrol results, and weather information, and the analysis unit or the improvement unit derives information on changes in road conditions based on the information acquired by the information acquisition unit, and evaluates the effectiveness of snow removal work by comparing the change information with actual information on snow removal responses that have been implemented, and analyzes the causal relationship between factors that change road conditions and trends in the occurrence of bad roads and at least one of weather conditions or snow removal response contents, and performs processing to optimize snow removal decision or processing logic based on the results of the analysis.

[11] [1] A snow removal decision support system as described in [1], characterized in that the snow removal decision support system is equipped with an improvement unit, and the snow removal decision support system analyzes the consistency between at least one of information on changes in road conditions after snow removal, traffic impact information, and weather information and the snow removal response content recorded by the snow removal decision support system, and performs feedback processing in the analysis unit or the improvement unit to continuously optimize the snow removal implementation plan or response logic based on the results of the analysis.

[12] A program for causing a computer to function as the snow removal decision support system described in any one of [1] to

[11] .

[13] A road management method using a computer, wherein the computer acquires at least two or more pieces of information from the group consisting of information on road surface conditions, information on traffic conditions, information on weather conditions, information on vehicle driving conditions, information on resident reports, and information on snow removal conditions via a network, analyzes the acquired two or more pieces of information, and registers a pre-formulated snow removal plan including the route or work section (including cases where at least a portion of the route or work section includes a road that may be designated as an emergency transportation route and / or road clearance route, or a road that leads to an emergency transportation route or road clearance route), the responsible snow removal company, and snow removal dispatch standards, and based on the registered snow removal plan and the analysis results, the computer executes a process to at least formulate a dispatch order to the snow removal company as part of a snow removal implementation plan (including, for example, a dispatch order, work type, work time period, and resource allocation) for each of the route or work section.

[14]

[13] A road management method as described in

[14]

[13] , characterized in that the computer acquires via a network at least one of the following: distribution information on vulnerable road users (including, for example, the elderly, people requiring care, school children, and physically disabled people) in a target area, location information on medical facilities, location information on welfare facilities, and location information on educational facilities; and using the acquired information, performs a priority weighting process to correct the priority of snow removal responses in the target area from the perspective of emphasizing welfare or the protection of human life.

[15]

[13] A road management method as described in

[13] , wherein the computer acquires management information for each route or construction section in a target area via a network, integrates the acquired management information with predicted values ​​for snow load contained in short-term weather forecast information, and distribution information for vulnerable road users (including, for example, the elderly, people requiring care, school-going children, and physically disabled people) in the target area to calculate a unique risk score, and performs a process to correct the priority of snow removal responses based on the risk score.

[16]

[13] A road management method as described in

[13] , characterized in that the computer predicts the availability of snow removal vehicles or workers, the time required for snow removal work, and the necessary resources, and performs a process to optimize the snow removal implementation plan based on work efficiency.

[17]

[13] A road management method as described in

[17]

[13] , characterized in that the computer acquires, via a network, at least one of the following information regarding the congestion status of a snow dumping site, information regarding the remaining capacity of the snow dumping site, information regarding the access distance to the snow dumping site, and information regarding the traffic congestion status of the access route to the snow dumping site, and performs route optimization processing for snow removal work, taking into account the acquired congestion status of the snow dumping site, the remaining capacity, the access distance, and the traffic congestion status of the access route.

[18]

[13] A road management method as described in

[13] , characterized in that the computer compares the estimated implementation cost for each snow removal candidate with the remaining budget, determines whether the candidate can be handled within the budget, and, if necessary, performs priority adjustment processing or processing related to requests for external assistance.

[19]

[13] A road management method as described in

[13] , wherein the computer acquires information on the operation status or availability of work vehicles and workers, and, if necessary, information on the usage status of snow dumping sites, from information sources or shared networks managed individually by multiple local governments, multiple road managers, or the snow removal companies via a network, and based on the acquired information, performs cross-border wide-area collaborative processing between multiple local governments, multiple road managers, or snow removal companies, and performs processing to formulate the snow removal implementation plan, including mutual resource optimization and budget adjustment.

[20]

[13] A road management method as described in

[13] , wherein the computer acquires at least one of resident reporting trends, traffic congestion information, bus delay information, patrol results, and weather information via a network, derives information on changes in road conditions based on the acquired information, compares the change information with actual information on snow removal and disposal measures implemented, evaluates the effectiveness of snow removal and disposal work, and analyzes the causal relationship between the factors that change road conditions and the tendency for bad roads to occur and at least one of weather conditions or snow removal and disposal measures, and performs processing to optimize snow removal decisions or processing logic based on the results of the analysis.

[21]

[13] A road management method as described in

[13] , characterized in that the computer analyzes the consistency between at least one of information on changes in road conditions after snow removal, traffic impact information, and weather information and the snow removal response content recorded by the computer, and performs feedback processing to continuously optimize the snow removal implementation plan or response logic based on the results of the analysis. [Effects of the Invention]

[0006] According to the present invention, by comprehensively analyzing a variety of information including road surface conditions, traffic conditions, weather information, vehicle driving conditions, and reports from residents, it is possible to determine the need for optimal snow removal and prioritize snow removal on snow-covered roads. This will prevent delays and duplication of work in snow removal, and enable planned and prompt snow removal on roads where it is necessary. It will also enable the formulation and notification of flexible snow removal implementation plans, including nighttime and disaster response, providing a safe and secure road traffic environment for road users and contributing to the improvement of work efficiency for local governments (road managers) and snow removal companies. Furthermore, this invention significantly improves the accuracy, flexibility, and citizen satisfaction of snow removal decisions by integrating information types (road surface, weather, vehicle traffic, resident reports, etc.) that were limited in conventional technology and using AI (artificial intelligence) to make decisions that take into account regional characteristics and temporal fluctuations. Furthermore, by reconfiguring and optimizing the decision model based on feedback such as road damage, traffic disruptions, and repeated reports, self-improving social infrastructure management becomes possible. [Brief explanation of the drawings]

[0007] [Figure 1] 1 is a system configuration diagram of a snow removal decision support system according to the present invention. [Figure 2] FIG. 10 is a flowchart illustrating an example of a patrol flow. [Figure 3] FIG. 10 is a flowchart illustrating an example of a flow of a fixed camera. [Figure 4] FIG. 2 is a diagram illustrating an example of a road surface condition. [Figure 5] FIG. 1 is a cross-sectional view showing an example of road surface conditions (unevenness of snow-covered road surface). [Figure 6] FIG. 2 is a cross-sectional view showing an example of road surface conditions (thickness of packed snow on the road surface). [Figure 7] FIG. 1 is a diagram illustrating an example of a traffic situation. [Figure 8] FIG. 1 is a diagram illustrating an example of a road space situation. [Figure 9] FIG. 10 is a diagram illustrating an example of weather conditions. [Figure 10]FIG. 2 is a diagram illustrating an example of a vehicle driving situation. [Figure 11] 1 is a flowchart illustrating an example of the flow of a snow removal decision support system according to the present invention. [Figure 12] FIG. 10 is a diagram showing an example of a determination criterion in a determination unit of the present invention. [Figure 13] FIG. 1 is a diagram illustrating an example of the hardware configuration of a snow removal decision-making support system according to the present invention. FIG. 1 is a block diagram showing a schematic diagram of the basic configuration of the snow removal decision-making support system according to the present invention. This diagram illustrates the configuration of major functional modules, such as an information acquisition unit, an analysis unit, and a decision unit, and shows the process of acquiring and analyzing various information, such as road surface conditions, traffic conditions, weather conditions, and vehicle driving conditions. However, the present invention also contemplates an embodiment that includes additional components, such as resident notification information, snow removal information, a road snow removal unit that manages snow removal implementation plans, and an improvement unit that continuously improves the decision-making model. FIG. 11 is a typical processing flow showing the flow of information acquisition, analysis, and decision-making processes, and is an auxiliary diagram for understanding an embodiment of the present invention. FIG. 12 is a table showing an example of a decision on the need for snow removal when various information (road surface, traffic, road space, weather, and vehicle driving information) is combined in a complex manner. This should be understood as an example of the analysis process and decision criteria of the present invention. In addition to analyzing the priority of snow removal and formulating an implementation plan, the present invention may also include additional components not shown, such as adjustment of implementation timing based on forecast information, workload evaluation, snow removal vehicle operation prediction, optimization of snow removal routes to snow dump sites, decision on whether to respond based on remaining budget, external support request processing, and weighting processing that takes into account the distribution of medical facilities, welfare facilities, educational facilities, and those with limited mobility. These are one embodiment of the present invention, and although not shown in Figures 1 to 12, they are configured as appropriate based on the functions claimed in the present application. DETAILED DESCRIPTION OF THE INVENTION

[0008] Hereinafter, an embodiment of a snow removal decision support system according to the present invention will be described in detail with reference to the drawings. The following embodiments are merely examples for the purpose of facilitating understanding of the present invention, and are not intended to unduly limit the technical scope of the present invention. The components and functional configurations described in this specification may be appropriately modified, substituted, deleted, or added as necessary based on the gist of the invention described in the claims, and are included in the technical scope as long as they achieve the same operational effects. Furthermore, the multiple components and means described in this specification can be considered as independent inventions, and can also be combined to form new forms of inventions. In this specification, "core components" refers to the following parts that are particularly responsible for central processing and coordination functions in the overall configuration of the snow removal decision support system: analysis part, improvement part, and road snow removal part. Furthermore, "core information" refers to information that is primarily subject to analysis, judgment, and control by these core components, and includes a variety of information such as snow removal information, road surface information, traffic information, weather information, vehicle driving information, and resident notification information. In addition, the snow removal decision support system of the present invention may be configured to include functions such as workload evaluation, operation prediction and reallocation of snow removal resources, optimization of snow removal routes, priority adjustment based on budget consistency, and decision processing for requests for external support; although these are not necessarily explicitly shown in the drawings, they are embodiments implemented based on the technical ideas described in the claims. Furthermore, the priority analysis results obtained by the analysis unit may be recorded or managed in association with the snow removal implementation plan formulated by the road snow removal unit or the response status implemented based on the plan. This allows the consistency between the analysis and the implementation results to be evaluated and reflected in the optimization of the decision model by the improvement unit.

[0009] 1 is a system configuration diagram of a snow removal decision support system 600 of the present invention. Snow removal decision support system 600 includes an information acquisition unit 610 that acquires information on road surface conditions, traffic conditions, road space conditions, weather conditions, and vehicle driving conditions, an analysis unit 620 that analyzes the road surface conditions, traffic conditions, road space conditions, weather conditions, and vehicle driving conditions obtained from the information acquired by the information acquisition unit 610, and a decision unit 630 that determines the need for snow removal based on the results of the analysis by analysis unit 620. In the embodiment, the snow removal decision support system 600 is communicatively connected to a road surface condition providing server 100, a traffic condition providing server 200, a road space condition providing server 300, a weather condition providing server 400, and a vehicle driving condition providing server 500 via a network NW. Although FIG. 1 shows only one vehicle Vh and one terminal device TM for grasping road surface conditions, a plurality of vehicles Vh and terminal devices TM may be connected to the network NW. Although only one fixed camera CAM is shown in FIG. 1 to grasp the road space situation, multiple fixed cameras CAM may be connected to the network NW. Furthermore, in the present invention, the snow removal decision support system 600 is configured to include a road snow removal unit that formulates and manages the resident report status and snow removal status, which are core information in the system, as well as a snow removal implementation plan, which is a core component, and an improvement unit that continuously improves the decision model. On the other hand, components such as the function of acquiring road service status, optical fiber survey status, and satellite survey status, as well as the infrastructure maintenance section, road clearance section, prediction section, and information provision section may be provided as an expandable configuration that can be added to the system as needed.

[0010] The terminal device TM, fixed camera CAM, road surface condition providing server 100, traffic condition providing server 200, road space condition providing server 300, weather condition providing server 400, vehicle traveling condition providing server 500, and snow removal decision support system 600 communicate via a network NW. The network NW includes, for example, some or all of a WAN (Wide Area Network), LAN (Local Area Network), the Internet, a provider device, a wireless base station, a dedicated line, etc. The communication method is not limited to the network NW, but data can also be sent and received via a memory card. Data can also be downloaded and uploaded via the network NW. In addition, in the present invention, snow removal information and resident notification information are core information elements in the snow removal decision support system 600, and the function of acquiring and processing this information is an essential component of the system. This information is acquired via the network NW through a dedicated server, an in-vehicle terminal device, a fixed camera, a resident notification server, etc. On the other hand, road service information, optical fiber survey information, satellite survey information, etc. are positioned as extended information that can be acquired arbitrarily depending on the operational purpose, and may be additionally provided in the snow removal decision support system 600 as needed.

[0011] The terminal device TM is used by a user riding in the vehicle Vh. The terminal device TM is a mobile phone such as a smartphone, a tablet device, or the like. The vehicle Vh is mainly a road management patrol vehicle or road patrol car (it may also be a patrol vehicle such as a garbage truck, compactor truck, or refuse collection truck). The terminal device TM may be a communication-type drive recorder or a stationary in-vehicle device mounted on the vehicle Vh, or may have an image recognition function using AI (artificial intelligence).The vehicle Vh may also have an under-road cavity detection function (technology that irradiates electromagnetic waves from above the road toward below the road and estimates the locations of cavities and buried pipes from the reflected waves), or the vehicle Vh may be an under-road cavity detection vehicle. The terminal device TM has a road patrol application installed therein that cooperates with the road surface condition providing server 100 . The terminal device TM has a positioning device such as a GPS (Global Positioning System) receiver, a communication device for connecting to the network NW, an input / output device such as a G sensor (acceleration sensor), a camera, and a touch panel, and a processor such as a CPU (Central Processing Unit).

[0012] 2 is a flowchart showing an example of the flow of patrol. When the terminal device TM presses a patrol start button on the road patrol app (S1), it starts collecting location information, acceleration information, video, images, etc. (S2). After the patrol is completed, the user presses the patrol end button in the road patrol application (S3), and the terminal device TM transmits the location information, acceleration information, video, images, etc. to the road surface condition providing server 100 (S4). The road surface condition providing server 100 determines whether or not there are irregularities 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. The position information, acceleration information, video, images, etc. transmitted to the road surface condition providing server 100 may be measurement information from a private car, taxi, truck, etc.

[0013] Fixed camera CAMs are installed on roads (major arterial roads, roads with heavy traffic, major bus routes, roads important for transporting and clearing snow to snow dumps, roads connecting to schools, public facilities, and emergency hospitals), buildings around intersections, and roadside posts and poles. Fixed camera CAMs include live cameras, web cameras, and network cameras that can communicate. The fixed camera CAM may be a communication-type drive recorder or a small unmanned aerial vehicle such as a drone, or it may be equipped with image recognition capabilities using AI (artificial intelligence). The fixed camera CAM has a built-in camera application that communicates with the road space situation providing server 300 . The fixed 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 the network NW, and a processor such as a CPU (Central Processing Unit).

[0014] 3 is a flowchart showing an example of the flow of the fixed camera CAM. The fixed camera CAM periodically or intermittently collects road space conditions (S5), and periodically or intermittently automatically transmits video / images, location information, date / time information, etc. to the road space condition providing server 300 (S6). The road space situation providing server 300 determines the height of snow banks (mountains of snow on the roadside, omitted below) based on the video and images transmitted from the fixed camera CAM, and identifies the location of road spaces determined to be dangerous areas.

[0015] The road surface condition providing server 100 provides the road surface conditions to the snow removal decision support system 600 via the network NW. The road surface conditions provided are information for each road, and may include some or all of the following: unevenness of the snow-covered road surface, thickness of packed snow on the road surface, snow quality on the road surface, accumulated snow on the road surface, snow melting on the snow-covered road surface, frozen road surface, bowl-shaped deformation of the snow-covered road surface, ruts on the snow-covered road surface, snow accumulation on the road surface, unevenness of the road surface (flatness), cracks, ruts, cavities under the road surface, road damage, road sinkholes, flooding, and whether or not the road width has been reduced due to accumulated snow. FIG. 4 is a diagram showing an example of road surface conditions, where a portion 110 where the snow-covered road surface is extremely uneven is displayed in black on the map. The provided road surface conditions may be quantified by the analysis unit 620 as a traffic obstruction score, freezing risk, road surface damage risk, etc., and may be used as input information for the priority determination process. In addition, the infrastructure maintenance unit may evaluate the risk of long-term deformation such as cracks and cavities, and determine whether repairs are necessary or not, and reflect the results in the road maintenance plan.

[0016] FIG. 5 is a cross-sectional view showing an example of road surface conditions (unevenness of a snow-covered road surface), and unevenness 120 of the road surface caused by snow is shown by a wavy line.

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

[0018] The traffic condition providing server 200 provides traffic conditions via the network NW to the snow removal decision support system 600. The traffic conditions provided are information for each road, and include some or all of the following: traffic volume, passing speed, average speed, and whether or not there is congestion or congestion. FIG. 7 is a diagram showing an example of traffic conditions, with locations 210 with heavy traffic congestion displayed in black on the map. The provided traffic conditions may be converted and quantified in the analysis unit 620 into traffic fluidity scores, congestion risks, traffic blockage tendencies, etc., and integrated with other information (weather information, vehicle driving information, road space conditions, etc.) to be used to determine snow removal priorities.

[0019] The road space condition providing server 300 provides the road space condition via the network NW to the snow removal decision support system 600. The road space condition provided is information for each road, and includes some or all of the following: avalanches, snowdrifts, height of snow banks caused by accumulated snow, poor visibility at intersections caused by snow banks, narrowing of road width caused by accumulated snow, whether large vehicles are stuck, whether there are any accident vehicles, etc. FIG. 8 is a diagram showing an example of road space conditions, where dangerous areas 310 with high snow banks are displayed in black on the map. The provided information may be quantified by the analysis unit 620 as a traffic obstruction risk score, a degree of visibility obstruction, or the like, and used to evaluate the necessity of snow removal work by the road snow removal unit.

[0020] The weather condition providing server 400 provides weather conditions via the network NW to the snow removal decision support system 600. The weather conditions provided are information for each region, and include some or all of the following: time, weather (sunny, rainy, snowy, etc.), temperature, humidity, snowfall amount, snow depth, snow density and 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, wind and snow, avalanches, etc.), information on record-breaking short-term heavy rain, landslide warning information, earthquake information, etc. FIG. 9 shows an example of weather conditions, where snowfall amount 410 and warning 420 are displayed in numbers and letters. The weather conditions are used by the determination unit 630 for short-term snow removal forecast processing, and are used by the prediction unit for medium- to long-term snowfall risk prediction. Furthermore, the analysis unit 620 may be configured to process wind speed, snowfall amount, temperature, etc. from multiple factors to calculate a snow removal difficulty score for each road.

[0021] The vehicle driving status providing server 500 provides vehicle driving status information to the snow removal decision support system 600 via the network NW. The provided vehicle driving status information is information for each road and route obtained from vehicles such as route buses and circular buses, and includes some or all of the following: bus delay information (bus delay status) and bus route delay information based on the winter schedule (a timetable that takes winter traffic conditions into account), the bus's driving position (which lane out of three lanes in each direction the bus is driving in, etc.), the number of vehicles ahead of the bus, the number of vehicles lined up next to the bus, whether the road width has narrowed due to snow accumulation, areas of skidding, areas of tire spinning, areas of tire locking, and areas of sudden braking. Note that if there is no winter schedule, bus delay times based on the regular schedule may also be used. Vehicle driving conditions can be the latest route information (vehicle ID, route name, delays, predicted departure and arrival times, passing, etc.) in the open data dynamic bus information format (GTFS real-time), vehicle location information (vehicle latitude and longitude, approach information, congestion level, etc.), and operation information (service suspensions, detours, accidents, stuck buses, traffic obstructions, images before and after the bus, etc.). Furthermore, the vehicle driving conditions may be obtained from connected cars (private cars, taxis, trucks, garbage trucks, delivery vehicles, cars covered by automobile insurance with dashcams provided by insurance companies, etc.), and may include information such as temperature, locations of sudden braking, locations of skidding, locations of tire spinning, locations of tire lock, locations of ABS activation, unevenness of the snow-covered road surface, ruts on the snow-covered road surface, mortar-like structures on the snow-covered road surface, thickness of packed snow on the road surface, reduction in road width due to snow accumulation, unevenness of the road surface (flatness), and locations of cavities under the road surface from vehicle sensors, avalanches, obstacles on the road, cracks, ruts, flooding, road damage, potholes, frozen road surfaces, snow accumulation on the road surface, snow quality on the road surface, and identification of impassable areas from camera footage and images, and travel history, traffic volume, traffic congestion, passing speed, average speed, acceleration, and whether or not snow is falling from wiper operation status from probe information, etc. FIG. 10 is a diagram showing an example of a vehicle driving situation, where a location 510 where the tires are spinning is displayed in black on the map. Various driving impediments or vehicle behavior abnormalities may be automatically classified and weighted by an AI (artificial intelligence) model in the analysis unit 620, and locations where tires are spinning or skidding frequently may be strongly reflected in snow removal priorities. In addition, the delay data may be used by the improvement unit to re-learn the judgment model.

[0022] As a method for understanding the narrowing of road width due to snow accumulation, it is acceptable to use camera and image recognition functions of smartphones, communication-type drive recorders, fixed-point cameras, etc. installed in vehicles to determine the snow accumulation situation, or to use the same functions to determine the narrowing of road width from the number of lanes and the number of vehicles side by side.It is also acceptable to determine the lane driving position of a route bus or other vehicle from the latitude and longitude (which lane out of three lanes on each side the bus is driving in, or which lane out of two lanes on each side the bus is driving in, etc.) and determine the narrowing of road width due to snow accumulation. The result of the determination of the narrowing of road width may be integrated with the traffic conditions, driving abnormalities, lane driving patterns, etc., and may be used for the obstacle evaluation by the analysis unit 620 and the weight adjustment process by the improvement unit.

[0023] The road service status providing server provides the road service status via the network NW to the snow removal decision support system 600. The information on the road service status is information for each road 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 content, etc.), rescue requests due to abnormal weather (date, time, location, rescue content, etc.), rescue requests due to disasters (date, time, location, rescue content, etc.), dead battery, locked-in car, running out of gas, flat tire, wheel off / falling off, flooding / submersion, recovery from snowy roads / mud, accident, slip and fall, disaster / damage status, towing / transportation of vehicle, removal / towing / transportation of abandoned vehicle, removal / towing / transportation of damaged vehicle, removal / towing / transportation of accident vehicle, location information of stranded vehicle, status of stranded vehicle occurrence, road conditions, traffic conditions, EV charging support, vehicle inspection results, etc. The frequency of stuck vehicles and emergency rescue requests may be quantified by the analysis unit 620 as an index of impassability and used as information for determining the priority of the judgment.

[0024] The optical fiber survey status providing server utilizes optical fiber sensing technology that uses optical fiber as a sensor, and receives backscattered light from communication optical fibers included in cables laid on roads, etc., and detects vibration patterns based on the backscattered light according to the vehicle's driving status on the road, etc. From the detected vibration patterns and learning models, it is possible to grasp road conditions such as the presence or absence of snow accumulation, changes in road surface conditions, the presence of packed snow or unevenness, frozen areas, vehicle backlogs or traffic jams, cavities under the road surface, and impassable areas. Furthermore, by analyzing the strength and frequency changes of minute vibrations propagating underground, as well as continuous abnormal patterns in the waveforms, it is possible to detect the risk of underground cavities and signs of deformation in the ground. If necessary, the sensing results can be corroborated and supplemented by linking them with images acquired from fixed cameras connected to optical fiber. The optical fiber survey status providing server provides the optical fiber survey status via the network NW to the snow removal decision support system 600. The provided information includes the snow accumulation, packed snow, and icy conditions for each road, unevenness of the snow-covered road surface, vehicle traffic history, traffic volume, traffic congestion, sudden vehicle stops, accident occurrence tendency, history of ice slippage, unevenness of the road surface, road damage, road cave-ins, possibility of subsurface cavities, etc., and this information is used to extract areas where road passage is difficult due to snow accumulation and areas where snow removal is a high priority. As a result, optical fiber sensing makes it possible to continuously and widely grasp road conditions even during times when ground patrols are not possible, contributing to more accurate and immediate decisions on snow removal. The obtained waveform may be analyzed by AI (artificial intelligence), visualized and quantified as the spatiotemporal distribution of road surface abnormalities and freezing risk, and input to the analysis unit 620 and the decision unit 630.

[0025] The satellite survey status server uses satellite remote sensing technology using artificial satellites equipped with SAR (Synthetic Aperture Radar), optical sensors, microwave sensors, etc. to detect snow accumulation, packed snow, snowdrifts, frozen road surfaces, unevenness of snow-covered road surfaces, areas that have been cleared or not, impassable areas, cavities under the road surface, road damage, road sinkholes, flooding, etc. It 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 accumulation and abnormal road surface conditions with high accuracy. In addition, by applying interference analysis techniques such as InSAR (Interferometric SAR) and DInSAR (Differential Interferometric SAR), it is possible to grasp on a surface level minute changes in height due to compacted snow or freezing, changes after snow removal, snowdrift locations, etc. This makes it possible to detect snow thickness, remaining compacted snow, and areas where snow removal is insufficient. The satellite survey status providing server transmits snow accumulation data, estimated snow removal necessity, snow removal completion assessment, indicators regarding traffic impact, etc. to the snow removal decision support system 600 via the network NW. This information is compiled and organized by route, work section, or community road, and used in conjunction with other information sources as information for making decisions about snow removal. The determination of whether snow removal has been completed or not and the traffic impact index may be integrated and evaluated in the analysis unit 620 and may be used for priority determination in the determination unit 630 and disaster risk assessment in the prediction unit.

[0026] The resident report status providing server collects and manages information on complaints, requests, and reports from residents, and supports multiple communication methods, such as voice report reception by AI (artificial intelligence), report reception by SNS (e.g., LINE), report reception by web form, report reception by email, report reception by smartphone app, voice report by voice assistant, or traditional telephone reception and input of interview results by staff. The resident report status providing server provides information on the status of resident reports to the snow removal decision support system 600 via the network NW. "AI-based voice call reception" refers to a system that automatically analyzes the content of voice calls sent via telephone or other voice input means using AI (artificial intelligence) technology such as voice recognition and natural language processing. This makes it possible to quantitatively grasp the content of calls and automatically accumulate and learn call information without the need for human intervention such as an operator. AI voice reporting uses voice recognition and natural language processing to analyze the report content (e.g., unspent snow removal, snowdrifts, ice, road obstructions, etc.) and the location of the report (address, facility name, landmark, etc.) obtained through dialogue with the caller, and automatically registers them in a reporting database. Social media reports, web reports, and citizen participation reporting platforms (e.g., FixMyStreet Japan) also handle posted data, including the report content and location information, in the same way. This data includes text, photos, GPS coordinates, multiple-choice options, and other information entered by the caller, and is handled together with the report information entered by local government officials. The collected report information is categorized by the location of the incident, the content of the report, the method of reporting, etc., and organized as a report density map and complaint history for each route or work section. This information is used as basic information when the Road Snow Removal Department assigns priorities to snow removal, and by linking it to the population or number of households in the area, it becomes possible to make decisions that strike a balance between the number of reports and the scope of impact. The content of resident report status information is automatically sorted using AI (artificial intelligence), and only reports related to snow removal are extracted. After extraction, the urgency (impassable roads, road clearance routes, in front of hospital facilities, etc.), the geographic characteristics of the target area (main roads / community roads, width, traffic volume, etc.), report density, and population or household distribution are evaluated to derive a priority order. This information is subject to integrated analysis by the analysis unit 620 and used as decision-making information by the decision unit 630. In particular, it functions as a source of information that supports high-precision decisions that affect the necessity of snow removal, the timing of implementation, and the implementation method (daytime / nighttime, etc.). Furthermore, the reliability of the resident report status information can be evaluated by comparing it with external sensing information such as satellite survey information and optical fiber survey information, and weighting and priority adjustments can be performed. This makes it possible to improve the reliability and reproducibility of judgments by having multiple information sources complement each other without relying on personal judgment.

[0027] The snow removal status providing server provides the snow removal status via the network NW to the snow removal decision support system 600. The information on snow removal status is road-specific information, is mainly managed by road administrators, and includes some or all of the following: information on snow removal routes (such as main roads) and work areas (such as residential roads), road conditions, traffic conditions, information on snow removal companies, type and number of snow removal vehicles (shovels, graders, rotary dozers, dump trucks, spreaders), advance snow removal plans and work guidelines, implementation standards for snow removal, standards for completion of snow removal, snow removal work plans, dispatch orders to snow removal companies, implementation status of snow removal, work status of snow removal (including the current location of snow removal vehicles and video and images from snow removal vehicles), snow removal operation results and snow removal performance information (operating hours, location information, history, etc.), daily snow removal work reports, patrol results, budget management, settlement management, complaints and requests, and information on snow dumping sites and snow storage areas. In addition, road administrators formulate snow removal plans and guidelines in advance, which include the snow removal implementation structure (organization, implementation structure, patrols, snow consultation desk, snow removal contractors, snow removal vehicles, snow removal work evaluation, snow removal dispatch orders, public relations and awareness activities, etc.), snow removal classification (main roads, secondary main roads, suburban main roads, fully outsourced construction sections, designated outsourced construction sections, residential roads, road clearance routes, etc.), snow removal implementation methods (snow removal standards, snow removal dispatch standards, snow removal methods, snow removal extensions, snow removal times, snow removal times, routes, snow dump sites, anti-freeze spraying to prevent slipping, etc.), and types of snow removal work (regular snow removal, new snow removal, road surface leveling, widening snow removal, snow transportation and removal, intersection snow removal, bottleneck area response, alley snow removal, snow removal, anti-freeze spraying, etc.). In snow removal work, after patrols by road managers and snow removal companies, implementation plans and work plans for snow removal are drawn up, snow removal work is carried out, and patrols are also carried out after the snow removal work has been completed. This information may be used as information and data for evaluating snow removal priorities and making decisions about implementation. Furthermore, information corresponding to the snow removal work content and response content (work status, operation results, daily work report, patrol results, etc.) may be configured to be stored in the system as snow removal information. This information about the snow removal situation may be used by the analysis unit 620 for correlation analysis between work performance and road surface changes, evaluation of the relationship between operation time and finishing accuracy, and confirmation of spatiotemporal consistency with the location of complaints. Furthermore, the improvement department may readjust and optimize decision-making logic and allocation policies by detecting deviations from work guidelines and implementation standards, evaluating whether snow removal responses are excessive or insufficient, and comparing the performance of each snow removal company. In addition, the road snow removal department may be configured to be able to review snow removal implementation plans, redesign work sequences, dynamically adjust resource allocation, and optimize snow dump site utilization based on these analysis results and performance evaluations. In addition, patrol results and finish evaluation information from in-vehicle video and images can also be used as feedback learning data, contributing to improving the accuracy of judgment models and AI (artificial intelligence) processing. In addition, images, videos, acceleration sensor data, etc. relating to road surface conditions after snow removal collected by patrol vehicles may also be included as information used for finish evaluation and feedback learning. In addition, this information reflects changes in road surface conditions and the state of completion, along with information regarding the status of snow removal and clearance, and in this specification, snow removal and clearance information may be configured to include some road surface information elements. This information can be used by the road snow removal department to formulate snow removal implementation plans, assign priorities, and decide whether to remove snow during the day or at night, and can be configured to be analyzed in an integrated manner with other information as needed.

[0028] The information acquisition unit 610 operating in the snow removal decision support system 600 acquires, via the network NW, road surface conditions from the road surface condition providing server 100, traffic conditions from the traffic condition providing server 200, road space conditions from the road space condition providing server 300, weather conditions from the weather condition providing server 400, vehicle driving conditions from the vehicle driving condition providing server 500, road service conditions from the road service status providing server, optical fiber investigation conditions from the optical fiber investigation status providing server, satellite investigation conditions from the satellite investigation status providing server, resident report conditions from the resident report status providing server, and snow removal conditions from the snow removal status providing server. The road surface conditions provided by the road surface condition providing server 100 are stored as road surface information 640. The traffic conditions provided by the traffic condition providing server 200 are stored as traffic information 650. The road space conditions provided by the road space condition providing server 300 are stored as road space information 660. The weather conditions provided by the weather condition providing server 400 are stored as weather information 670. The vehicle driving conditions provided by the vehicle driving condition providing server 500 are stored as vehicle driving information 680. The road service status provided by the road service status providing server is stored as road service information. The optical fiber inspection status provided by the optical fiber inspection status providing server is stored as optical fiber inspection information. The satellite inspection status provided by the satellite inspection status providing server is stored as satellite inspection information. The resident report status provided by the resident report status providing server is stored as resident report information. The snow removal and removal status provided by the snow removal and removal status providing server is stored as snow removal and removal information. The information acquired by the information acquisition unit 610 may be two or more pieces of information including at least resident notification status information from among road surface conditions, traffic conditions, road space conditions, weather conditions, vehicle driving conditions, road service status, optical fiber survey status, satellite survey status, resident notification status, and snow removal status, and it is not necessary to be configured to acquire all information. This information is also passed on to the analysis unit 620, decision unit 630, road snow removal unit, improvement unit, etc., and is used for the decisions, analyses, learning, etc. of each unit. The information acquisition unit 610 may be configured to add and manage metadata such as the type of information, source, acquisition frequency, acquisition time, related route information, etc., enabling dynamic and real-time information utilization. Furthermore, the information acquisition unit 610 may be configured to acquire information from external related organizations such as government agencies (police, fire department, Self-Defense Forces, etc.), infrastructure operators (communications, electricity, gas, water, sewerage, etc.), transportation operators (railroads, buses, etc.), snow removal companies, construction and civil engineering companies, tourist facility operators, etc. This information includes information on requests regarding disasters, recovery, and snow removal, road obstructions, facility status, evacuation support needs, etc. Furthermore, the information acquisition unit 610 may be configured to dynamically select and limit the types of information to be acquired depending on the purpose, situation, load, etc. of the system. For example, when there is a concentration of resident reports, it may be configured to prioritize the acquisition of highly relevant information such as report information, traffic information, and population density.

[0029] The analysis unit 620 operating in the snow removal decision support system 600 analyzes each type 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 driving information 680, road service information, optical fiber survey information, satellite survey information, resident notification information, and snow removal information, and stores the results as 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 analyses based on the acquired information. The analysis results 690 may be visualized in the form of a map, table, time series, graph, or the like, to contribute to subsequent judgment processing and decision-making. In addition to individual analysis, the analysis unit 620 may also have an integrated analysis function that cross-checks and compares multiple pieces of information. For example, by mapping optical fiber vibration data, satellite image data, and vehicle driving abnormality data in the same area and cross-checking and aggregating the abnormality scores of each piece of information, it becomes possible to evaluate the overlap and accuracy of abnormality occurrences at that location and derive the need for snow removal with high accuracy. This makes it possible to compensate for the limitations of individual information and make decisions based on the consistency of multiple pieces of information.

[0030] The analysis unit 620 may also incorporate an AI (artificial intelligence) model, such as a neural network or decision tree-based machine learning model, which takes multiple pieces of information as input and generates a score (numerical value or classification) of the snow removal necessity for each location as output. The output score is used as a decision criterion by the determination unit 630 and for prioritizing road snow removal units. Furthermore, the analysis unit 620 may be configured to provide the analyzed information to the improvement unit as learning data or update data, contributing to improving the accuracy of the judgment model and relearning processing. Specifically, effectiveness indicators obtained after snow removal operations (such as a reduction in resident reports, improved traffic speeds, and changes in the number of complaints) are used as training signals to perform online learning that successively adjusts the model weights, enabling adaptive judgments based on regional characteristics and seasonal trends. Learning targets include date and time, location, report content, report density, complaint classification, congestion occurrence, traffic volume, snow accumulation, and snow removal history, making it possible to build statistical trends and reproducible judgment logic for snow removal decisions. Additionally, the analysis unit 620 may be configured to detect signs of a disaster, and may be configured to perform disaster screening analysis different from snow removal judgment using multiple abnormal information (sudden increase in reports, traffic disruptions, weather warnings, abnormal vibrations in optical fiber, surface abnormalities in satellite images, etc.). Disaster analysis is performed in parallel with normal processing based on indicators and models specialized for disaster judgment. In addition, the information reported by residents is sorted by AI (artificial intelligence), its content is assessed, its urgency is evaluated, the density of reports is tallied, the geographical characteristics of the target area are evaluated, and the data is integrated with the local population or number of households. The analysis unit 620 has the function of integrating the results of these multi-stage evaluations and evaluating with high accuracy the necessity and priority of snow removal for each area. Furthermore, the analysis unit 620 may be configured to weight the information based on its reliability, immediacy, impact on traffic, etc., by focusing on the time or time period when the information was acquired. The analysis unit 620 may also be configured to weight the reliability or priority of each piece of information (e.g., 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, etc.) acquired by the information acquisition unit 610 according to the time period when the information was acquired, and perform analysis based on the weighting. Such weighting according to time period may also be used in determining whether to perform daytime or nighttime snow removal. For example, if resident notifications tend to be concentrated in the morning, the analysis unit 620 may be configured to place more importance on the density of notifications during that time period, or to adjust the weighting by distinguishing satellite data provided at night from daytime information, thereby enabling more reliable decisions based on the time axis. The analysis unit 620 may also be configured to use statistical or machine learning techniques to analyze the causal relationships between factors that change road conditions or trends in the occurrence of bad roads, and weather conditions or snow removal measures. This makes it possible to accurately understand the mechanisms by which bad roads occur and the effectiveness of snow removal measures, contributing to more advanced preventative dispatch decisions and priority assessments.

[0031] These analysis results 690 are sent to the decision unit 630 and used as information to help determine the need for snow removal. Furthermore, they are distributed as needed to each component, such as the road snow removal unit, road clearance unit, infrastructure maintenance unit, improvement unit, and prediction unit, contributing to improving the accuracy of decisions and management for the entire system. Furthermore, the analysis results 690 may be visualized in conjunction with a GIS (geographic information system), and may be configured to contribute to feedback learning of the decision model through cross-checking with snow removal implementation history, comparative analysis with snow removal method selection history, and evaluation of implementation effectiveness. The system may be configured to ascertain trends in snow accumulation and road conditions by collating and analyzing past weather information, traffic information, and the like. In addition, the causal relationship between factors that change road conditions or trends in the occurrence of bad roads and weather conditions or snow removal measures may be analyzed using statistical or machine learning techniques. This allows for a more accurate understanding of the mechanisms behind the occurrence of bad roads and the effectiveness of measures, which can be useful for priority assessment and preventive decisions. These analysis results may be utilized as information on changes in road conditions regarding the need for snow removal and the urgency of the situation, and may be used to assist in priority assessment and work decisions. The output scores can be displayed on a GIS (geographic information system) map for each road section or area, and can be color-coded (e.g., in a heat map format) according to the score. This allows operators and decision makers to intuitively grasp high-priority areas and supports quick response decisions. Note that the information to be analyzed is not limited to all information, and any combination of information can be analyzed depending on the target area, operational system, processing purpose, etc. Furthermore, by performing processes such as matching image data with non-image data (e.g., matching image analysis results with optical fiber data), spatiotemporal interpolation of areas where abnormalities frequently occur (interpolation at night or during bad weather), and improving the responsiveness of disaster response decisions (multifaceted risk assessment using AI / XAI), the configuration can be made to provide advanced decision-making support that does not rely on a single sensor. Furthermore, by acquiring distribution information on the population or number of households in a region from a statistical information database or administrative information and evaluating it in conjunction with the density and urgency of reports from residents, snow removal decisions can be made based on the population size and concentration of the population in the region. Furthermore, the weighting coefficients for each analysis index can be dynamically adjusted based on the regional attributes. For example, by giving a higher weight to the urgency of reports in regions with a large elderly population and increasing the weighting of traffic impact near major roads, priority assessments tailored to the actual conditions of each region can be realized. Furthermore, the analysis unit 620 may be configured to perform a priority weighting process using distribution information on vulnerable road users (elderly people, people requiring care, school-going children, and physically disabled people) in the target area, as well as location information on medical facilities, welfare facilities, and educational facilities, and to perform a process to correct the priority of snow removal responses for each road from the perspective of emphasizing welfare and the protection of human life. Previously, decisions were mainly based on experience or rules, making it difficult to make integrated decisions on a large amount of non-standard information (resident reports, images, SNS, vibration data, etc.) In contrast, this invention uses AI (artificial intelligence) to learn and estimate the non-linear relationships and time-series trends between this information, enabling advanced and reproducible decision-making processing. The process of generating the snow removal necessity score executed by the analysis unit 620 is performed using multivariate analysis or machine learning techniques that use multiple pieces of information as input. For example, variables such as the density of resident reports, the rate of traffic speed reduction, the number of days without snow removal, the amount of snow, the temperature, snowfall forecast, and past snow removal history are used as feature quantities, and these are normalized or categorically converted to form an input vector. The learning model may be a decision tree-based classification / regression model such as Random Forest or XGBoost (eXtreme Gradient Boosting), or a numerical regression model using a three-layer deep neural network. The model's learning data uses past snow removal results (whether or not a snow removal dispatch was made, priority, local population composition, number of complaints, etc.), and weights are optimized using supervised learning. The output is defined as a score between 0 and 100 for each target area, with a higher score indicating a higher urgency for snow removal. This score, stored as the analysis result 690, is used by the decision unit 630 to determine whether or not action is required, using threshold judgment or the like. This configuration enables the analysis unit 620 to perform integrated analysis of standardized information (sensor information, etc.) and non-standardized information (resident reports, video analysis results, etc.), thereby realizing flexible decision support that goes beyond conventional rule-based processing.

[0032] The analysis unit 620 evaluates indicators such as the necessity of snow removal, urgency, traffic impact, and work difficulty for each road or management unit based on the multiple pieces of information acquired from the information acquisition unit 610, and derives integrated evaluation information including these. The evaluation information is expressed in the form of a numerical score or hierarchical ranking, and is used to formulate a snow removal implementation plan. The analysis unit 620 also evaluates the workload for each work section based on predicted snow quality, moisture content, snow load, etc. The workload is converted into indicators such as required work time, heavy equipment load, and number of workers, and expressed as a workload score. If a high workload is predicted, adjustments are made by bringing the work schedule forward or reallocating resources. Furthermore, the analysis unit 620 acquires future snowfall amounts, temperature fluctuations, whether or not there will be rainfall, and other forecast information (temperature, humidity, snow quality, moisture content, snow load) in chronological order based on short-term weather forecast information, and based on this forecast information, extracts the start time for preparations for snow removal work and work sections that require advance action. This improves the ability to respond to sudden snowfall and freezing, and increases the accuracy of planning. In addition, the system may use the predicted snow load information to evaluate the risk that the load poses to traffic or road structures. If the predicted snow load exceeds a threshold, the work priority for the target section is increased, and a snow removal implementation plan is developed that takes the risk into account. To evaluate workload, the system uses past daily snow removal reports and operational records (snow depth, operating hours, fuel consumption, road length, number of vehicles, etc.) to set a load conversion coefficient linked to the average operating speed (km / h) of each piece of heavy equipment and the unit fuel and labor costs, and then converts the workload of each section into a numerical score. Specifically, the system calculates the required workload (t / km or cubic meters / km) based on the length, width, and snow volume of the target section, and estimates the time or cost required to complete that workload. This makes it possible to compare the workload relative to other sections and to level out operational plans. In addition, when utilizing short-term weather forecast information, time-series data such as snowfall probability, temperature, wind speed, humidity, and rainfall for each region is obtained from a WebAPI or data published by the Japan Meteorological Agency, and predictive snow removal decisions are made based on statistical weather pattern analysis. For example, if it is found that snow removal has been frequently required in the past when the conditions of "temperature below -2°C" and "snowfall probability 70% or higher" are met, the system will be configured to increase the pre-deployment decision when these conditions are met. Regression analysis, Bayesian inference, random forest, or a time-series forecasting model (such as LSTM) can be used as the model. The evaluation score is calculated as a weighted average of factors such as the necessity of snow removal, urgency, traffic impact, and task difficulty, and if the score exceeds a predetermined threshold, the item is notified to the decision unit 630 as a candidate for priority response or pre-dispatch. The score calculation logic and threshold may be configured to be externally editable as a parameter setting file according to regional characteristics and administrative policies. The analysis unit 620 may perform a process to evaluate the consistency with the budget using information on past performance, such as trends in changes in priority in the target area, operating hours, and unit prices for snow removal and disposal. Alternatively, the estimated implementation costs may be calculated based on the work time, number of vehicles, number of personnel, etc. required for each snow removal candidate, and the feasibility of the operation may be determined based on a comparison with the budget. Furthermore, the evaluation information may be configured to derive an integrated score by applying a predetermined weighting to multiple indicators, for example, a weighted average score such as "traffic impact 70 points, workload 30 points." It may also include processing to classify the results into categories such as "priority response," "normal response," and "postponed response" based on the score. This clarifies the basis for decisions on the snow removal implementation plan formulation by the road snow removal department, improving its practicality.

[0033] In this specification, "evaluation information" refers to analysis results derived for each road or management unit based on multiple pieces of information acquired by the information acquisition unit 610, and includes at least the priority of snow removal responses. Specifically, it includes various indicators based on the necessity of snow removal, urgency, traffic impact, difficulty of work, amount of snow, risk of freezing, traffic history, density of resident reports, remaining budget, distribution of vulnerable road users (elderly people, people requiring care, school-going children, physically disabled people), and the relative locations of medical, welfare, and educational facilities, and the weighting of these indicators may be dynamically adjusted according to the attributes of the area and the distribution of facilities. These evaluation indicators can also be integrated with AI (artificial intelligence) weather and traffic forecast models and urgency assessments of resident reports to create evaluation information that includes predictions of the need for short-term response. Furthermore, the evaluation information can be expressed in the form of a numerical score or hierarchical ranking and used in the planning process by the road snow removal department. Patrol results and evaluation information from in-vehicle images can also be incorporated as feedback learning data and used to create the evaluation information.

[0034] In this specification, "determination information" refers to information derived by the analysis unit 620 or the improvement unit regarding the determination of whether snow removal is necessary, the urgency, priority, response timing, whether the work is possible, etc. The determination information is generated based on various information and evaluation information obtained from the information acquisition unit 610, and may be configured to be used for formulating snow removal implementation plans, assisting local government decisions, determining whether external support is necessary, dynamic resource reallocation processing, etc. The determination information is expressed in the form of a score or a judgment category, and is used as the basis for decision-making in subsequent processing.

[0035] The analysis unit 620 may perform an analysis process based on a specific definition of a "bad road" to evaluate the necessity and priority of snow removal. A bad road here refers to road conditions that make vehicle travel difficult due to unevenness of the snow-covered road surface, packed snow thickness, snow quality, snow accumulation, freezing, snow melting, bowl-shaped deformation, rutting, etc. The analysis unit 620 may be configured to use one or more of these indicators to evaluate the bad road conditions for each target section and calculate a bad road score that contributes to determining the priority of snow removal. For example, when evaluating unevenness, amplitude values ​​and variations are calculated based on the vertical fluctuation values ​​obtained from the vehicle's acceleration sensor, and this is quantitatively expressed as an unevenness index. In addition, by setting thresholds and configuring a step-by-step evaluation (e.g., an amplitude of 5mm or more is a caution level, and 15mm or more is a level requiring snow removal), this contributes to the standardization of on-site judgment. Furthermore, the thickness of packed snow can be evaluated using directly measured values ​​or the amount of step difference estimated from acceleration, etc. As for road surface conditions, image data obtained from fixed cameras, in-vehicle cameras, drones, smartphones, etc. can be used to perform image analysis such as object detection and image segmentation to recognize snow accumulation, snow accumulation, freezing, melting snow, etc., and convert them into a rough road index. The analysis unit 620 may use these road roughness indicators to calculate the percentage of road roughness sections that exceed a predetermined standard for each management unit obtained by dividing a road into routes or construction sections. The analysis unit 620 may then perform a scoring process based on a graded evaluation (e.g., 0-20% = low, 21-50% = medium, over 51% = high) according to the percentage, and reflect this in the priority of snow removal. The analysis unit 620 may also be configured to manage road information by branch number using a GIS (geographic information system) and perform detailed evaluations of individual sections of main roads and community roads. This configuration makes it possible to identify local danger points, such as between intersections and at points where gradients change, in addition to the entire route, contributing to the prioritization and efficiency of snow removal efforts. Furthermore, the reliability of information for the section may be evaluated based on the distance traveled and frequency of patrol vehicles, and correction and exclusion processing may be performed if the reliability falls below a predetermined threshold. Additionally, the analysis unit 620 may use multiple pieces of information (bad roads, traffic, weather, vehicle operation, road service, etc.) to perform a process of correcting or weighting the snow removal priority score using pre-set rule-based logic. This configuration enables consistent judgment based on both rules and actual measurement data. The analysis unit 620 in this embodiment may also be configured to perform an integrated analysis of the distribution information of vulnerable road users (elderly people, people requiring care, school children, physically disabled people, etc.) in the target area, weather forecast values ​​for snow load, and snow removal response history and regional characteristics for each management unit, and generate a unique risk score that numerically expresses the urgency of snow removal response for each road or work section. This score is used for priority assessment and response order correction processing. Furthermore, when formulating a snow removal implementation plan for the road snow removal department, it is possible to group target areas by priority based on the evaluation information and create a schedule for each time period and work method. For example, by arranging work in a timetable format, such as prioritizing work around routes and areas that require emergency response in the early morning and utilizing times with low traffic volume, it is possible to achieve a configuration that achieves both efficiency and reliability.

[0036] The decision unit 630 operating in the snow removal decision support system 600 makes an integrated and comprehensive decision on the necessity of snow removal based on some or all of the analysis results 690 of the various information (road surface information 640, traffic information 650, road space information 660, weather information 670, vehicle driving information 680, road service information, optical fiber survey information, satellite survey information, resident notification information, and snow removal information) analyzed by the analysis unit 620, and stores the decision result 695. The determination result 695 may include the snow removal priority for each location, a work necessity score, a recommended time period for snow removal (daytime or nighttime), the need for disaster response, etc. The determination result 695 may be visualized on a map, displayed as a list, displayed over time, or displayed on a real-time monitoring screen such as a dashboard. In addition, the decision unit 630 may be configured to support or automate decisions using machine learning or rule-based AI (artificial intelligence) models, learning statistical trends, thresholds, correlations, etc. of the analysis results 690 to improve and speed up snow removal decisions. Furthermore, the decision unit 630 may be configured to execute a process to determine whether or not disaster response is necessary (access to disaster prevention centers, road clearance, securing emergency transportation routes, etc.) when a disaster occurs or its signs are detected, in addition to determining whether or not snow removal is necessary. In the event of a disaster, the decision unit 630 switches from the normal snow removal decision logic to disaster response criteria, and prioritizes and formulates a response policy appropriate for the disaster. The decision unit 630 may also be configured to cooperate with the road snow removal unit to determine the necessity of snow removal for the target road, the priority, the implementation time (daytime / nighttime), etc. based on the determination result 695, and to support the process of formulating and updating a snow removal implementation plan based on that information. This ensures consistency between the determination and the plan, improving the efficiency of on-site response. Furthermore, the determination unit 630 may be configured to forecast the likelihood of snow removal becoming necessary in the near future (e.g., several hours to the next day) based on information such as weather forecasts, snow removal performance, and resident reporting trends. The future forecast processing by the determination unit 630 may also use, in addition to weather forecast information, various information obtained by the information acquisition unit 610 (e.g., road surface information, traffic information, road space information, vehicle driving information, road service information, optical fiber survey information, satellite survey information, etc.). This forecast function is functionally different from the prediction unit, which targets medium- to long-term risks related to extreme snowfall and snow damage, and is intended for short-term operational decisions and notifications. The forecast results are passed on to the road snow removal unit and used for advance snow removal preparations, provisional prioritization, and consideration of response time periods. In addition, the judgment result 695 is shared with components such as the road clearance department, infrastructure maintenance department, and improvement department, and is used as input information for processing by each department and for formulating implementation plans. Furthermore, the judgment result 695 may be configured to be notified and provided to external parties (municipal government officials, snow removal companies, residents, etc.) via the information providing unit, and the information providing unit may be configured to have a function to notify in real time the judgment results by the decision unit 630 (necessity of snow removal, priority, forecast results, etc.) and the medium- to long-term risk prediction results by the prediction unit via a web dashboard, notification email, smartphone push notification, administrative system integration API, etc. In addition, the judgment result 695 may be used to optimize and re-learn the judgment logic in the improvement department, thereby supporting self-improvement of the system. This enables feedback learning with actual snow removal results and complaint information, contributing to improving the accuracy of snow removal. In this way, the decision unit 630 functions as a component that comprehensively evaluates the various information acquired and analyzed by the analysis unit 620, and executes snow removal decisions, disaster response decisions, and short-term snow removal forecasts. This enables comprehensive and flexible decision support that goes beyond snow removal and includes infrastructure maintenance and disaster response. Furthermore, the snow removal decision support system 600 may be configured with a function to dynamically reevaluate and reconfigure analysis results and response plans when information about disasters, damage, recovery, etc. changes, enabling flexible decision support that can respond quickly to sudden changes in on-site conditions.

[0037] 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 (e.g., every few minutes) from the road surface condition providing server 100 (S10). The information acquisition unit 610 periodically acquires information on traffic conditions (e.g., every few minutes) from the traffic condition providing server 200 (S11). The information acquisition unit 610 periodically acquires information on road space conditions (e.g., every few minutes) from the road space condition providing server 300 (S12). The information acquisition unit 610 periodically acquires information on weather conditions (e.g., every few minutes) from the weather condition providing server 400 (S13). The information acquisition unit 610 periodically acquires information on vehicle driving conditions (e.g., every few minutes) from the vehicle driving condition providing server 500 (S14). The analysis unit 620 then extracts, from the road surface information 640, locations where road width has been significantly reduced due to snow accumulation (S15). The analysis unit 620 extracts, from the traffic information 650, sections where congestion is occurring continuously (S16). The analysis unit 620 extracts, from the road space information 660, dangerous locations where snow banks are high (for example, approximately 1 meter or more) and visibility is reduced, etc. (S17). The analysis unit 620 extracts, from the weather information 670, areas where the amount of snowfall since the start of snowfall has been 10 cm or more (S18). The analysis unit 620 extracts, from the vehicle travel information 680, sections where bus delays are continuing for 30 minutes or more (S19). Next, based on the results of the above analysis, the decision unit 630 comprehensively determines the necessity of snow removal measures, and makes a decision to execute the measures as necessary (S20). 11 shows an example of a typical processing flow, and is not limited to this. In this embodiment, various information not shown, such as snow removal information, resident notification information, optical fiber survey information, satellite survey information, and road service information, can also be acquired by the information acquisition unit 610 and subjected to analysis processing by the analysis unit 620. The results of these analyses are used by the decision unit 630 to make snow removal decisions and set priorities, and this information may also be used by the road snow removal unit to formulate a snow removal implementation plan, or by the improvement unit to optimize decision logic.

[0038] 12 is a diagram showing an example of the determination criteria used by the determination unit 630. The determination unit 630 can determine the necessity of snow removal measures based on the following triggers: heavy snowfall of 10 cm / h or more (element 1) 631; snow accumulation reducing road width and causing bus delays of 30 minutes or more (element 2) 632; snow melting on clear skies, making the snow-covered road surface more uneven and worsening traffic congestion (element 3) 633; ​​heavy snow warnings being issued, causing cars to skid and get stuck in the snow, resulting in congestion (element 4) 634; frequent tire locks on frozen roads at -10°C, causing self-inflicted accidents and resulting in congestion (element 5) 635; etc. In addition, some or all of the judgment result 695 determined by the decision unit 630, the analysis result 690 derived by the analysis unit 620, and the various information acquired by the information acquisition unit 610 (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) can be sent via an information provision unit, etc. to snow removal companies via email, data provided to a GIS (Geographic Information System) for road managers, linked to an autonomous driving system or MaaS (Mobility as a Service), information provided to government agencies (police, fire department, Self-Defense Forces, etc.) and the media, and information disclosure functions for road users and residents (websites, smartphone apps, etc.). Note that this information provision does not necessarily have to go through the information provision unit, allowing for structural flexibility. Examples of information disclosure functions for road users and residents include providing the following information: unevenness of snow-covered road surfaces, thickness of packed snow on road surfaces, traffic congestion, camera images, height of snow banks around routes and intersections, future snowfall forecasts and snow depths, bus route delay information, stuck vehicle locations, snow removal orders and implementation status, snow removal orders and implementation status, and patrol results. This snow removal decision support system is also characterized by being configured to be able to transmit this information, analysis results, decision results, snow removal implementation plans, etc. to mobile terminal devices (such as mobile phones, smartphones, tablets, laptops, and game consoles) or fixed terminal devices (such as desktop computers, smart TVs, set-top boxes, digital signage, kiosks, car navigation systems, and car display audio systems). 12 shows an example of a typical judgment criterion, and the present invention is not limited to this. In this embodiment, various information not shown, such as snow removal information, resident notification information, optical fiber survey information, satellite survey information, and road service information, is also used as judgment material by the decision unit 630. Furthermore, these judgment results may also be used in the formulation of a snow removal implementation plan by the road snow removal unit, the optimization of judgment logic by the improvement unit, and notification processing by the information provision unit.

[0039] Snow removal decision support system 600 is configured to include an improvement unit that continuously improves the analysis results 690 (including the analysis method) obtained by analysis unit 620, the decision results 695 output by decision unit 630, and some or all of the decision criteria. The improvement unit is a core component that realizes the "continuous improvement" of snow removal decision support system 600, and forms a loop of learning, verification, and reconstruction within the series of steps of acquiring, analyzing, deciding, executing, and evaluating various types of information, with the aim of improving decision accuracy, execution validity, resident satisfaction, etc. The Improvement Department is equipped with a re-evaluation and re-learning function, including the AI ​​(artificial intelligence) analysis method itself, and uses statistical processing, machine learning, deep learning, and other technologies to improve information acquisition methods, analysis logic, judgment criteria, and prioritization algorithms, etc. Examples include optimizing threshold settings, redefining evaluation items, and revising input information selection criteria. Furthermore, the improvement unit may have a function for analyzing the causal relationship between factors that change road conditions or the tendency of bad roads to occur, and weather conditions or snow removal measures, which allows for understanding the effectiveness of measures and the mechanisms that cause problems, and contributes to improving the accuracy of decision-making logic and prioritization. The improvement unit uses 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, and snow removal information acquired by the information acquisition unit 610 as input data, and performs learning processing and model improvement based on the accumulated history of analysis results 690 and judgment results 695 obtained from these. Note that the improvement unit may be configured to use various information (e.g., 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, etc.) acquired by the information acquisition unit 610 as learning targets, in addition to the analysis results by the analysis unit 620, the judgment results by the decision unit 630, and the implementation status of the road snow removal unit. In particular, the improvement unit may be configured to dynamically reconfigure the priority criteria and the timing of snow removal implementation using triggers such as the recurrence of reports or an increase in complaints after snow removal in cooperation with a resident notification status providing server. Furthermore, the improvement unit may be configured to collect and analyze information on traffic congestion that occurs after snow removal is carried out, the recurrence of reports and complaints, and road conditions (remaining snow, ruts, steps, narrowing of road width, etc.) obtained by patrol vehicles (including not only road managers but also snow removal companies, etc.), and provide feedback to future decisions and implementation plans, thereby enabling a highly accurate evaluation and improvement of the consistency between actual results and decisions. The Improvement Department will be responsible for optimizing the formulation of future snow removal plans by analyzing the correlation between the snow removal implementation plans and prioritization results formulated by the Road Snow Removal Department and the implementation history after snow removal, snow removal quality, time of completion of snow removal, remaining snow conditions, and feedback from residents (complaints and re-reports). Furthermore, the improvement unit may be configured to cooperate with the infrastructure maintenance unit to continuously improve the prediction model for road damage, subsurface cavities, etc., and to cooperate with the road clearance unit to optimize the algorithm for determining road clearance routes and priority bases. Also, the improvement unit may be configured to cooperate with the prediction unit to improve the prediction accuracy of the model to be improved according to the results of future snowfall, traffic, and disaster predictions. The timing of learning in the improvement unit is selected appropriately according to the operational situation, such as nighttime batch processing, periodic learning at regular intervals, trigger processing when an exceptional increase in complaints occurs or abnormal weather is detected, etc. Furthermore, the learning model can be configured to apply multiple methods such as deep learning, decision trees, random forests, and reinforcement learning depending on the application. Furthermore, the improvement unit may be configured to evaluate the relationship between the application result of the time-of-day weighting by the analysis unit 620 and the actual snow removal results, resident satisfaction, repeat reporting status, etc., and optimize the weighting parameters for the next time onwards. This makes it possible to optimize the judgment system taking into account reporting trends according to time of day, differences in traffic volume, difficulty of snow removal, etc. In this invention, the relationship between changes in road conditions (e.g., the occurrence and resolution of bad roads), the implementation details, weather conditions, etc. is analyzed as a causal model using regression analysis, correlation analysis, etc., to quantitatively evaluate the effectiveness of snow removal. The improvement department accumulates learning data such as past snow removal results, weather conditions, road conditions, and resident reporting trends, and continuously improves the evaluation results and output of the judgment model through supervised learning. Particular emphasis is placed on error feedback through consistency analysis. The improvement unit may also have a function to statistically analyze the error or deviation from the actual snow removal results for the snow removal necessity score, workload score, predicted snowfall amount, priority correction information based on population density, etc. output by the analysis unit 620. This allows for a configuration that detects deficiencies or excesses (overestimation or underestimation) in the score design logic and allows for the refinement of the entire analysis logic, such as by resetting thresholds or reviewing weighting parameters. Furthermore, a mechanism may be provided that evaluates the correlation between the integrated analysis results (e.g., aggregated value of anomaly scores of multiple pieces of information) in the analysis unit 620 and actual traffic disruptions, number of complaints, sections where snow removal has not been completed, etc., and dynamically adjusts the reliability coefficient for each information source. Furthermore, when generating scores using an AI (artificial intelligence) model, the analysis results of XAI (explainable AI) can be used in conjunction with the model to evaluate the validity and transparency of the basis for judgment, and for models that lack explanatory power, training data can be supplemented or feature selection can be reviewed. Furthermore, the improvement unit may be configured to analyze the consistency between information on changes in road conditions, traffic impact information, and weather information after snow removal is performed and the snow removal response details automatically recorded by the system. This allows for a quantitative understanding of the relationship between actual road changes and response results, enabling feedback processing to continuously refine and optimize snow removal implementation plans or response logic. These processes may be configured to be performed by either the analysis unit or the improvement unit.

[0040] In this specification, "management information" refers to attribute information associated with road sections in the target area, and includes information such as the type of management unit (by route, by construction section, etc.), management entity (by city, ward, town, village, prefecture, road administrator, etc.), past snow removal performance, road width, route type (by arterial road, by community road, etc.), budget, location of available construction companies, and number of operating machines. This information is used by the analysis unit 620 or the improvement unit to determine whether snow removal can be performed, adjust response policies, or correct priorities.

[0041] The snow removal decision support system 600 may be configured to include a prediction unit that predicts future road conditions and disaster risks over the medium to long term in preparation for unusual events such as extreme snowfall and snow damage. The prediction unit estimates future risks of large-scale snowfall, traffic paralysis, and disasters based on the analysis results 690 accumulated by the analysis unit 620, the history of judgment results 695 output by the decision unit 630, the history of past snow removal operations, trends in complaint occurrence, weather change trends, topography, road structure, etc. The prediction unit may be configured to quantitatively or probabilistically predict, for example, traffic disruptions, simultaneous traffic jams at multiple locations, the possibility of a high-volume call area, or the possibility of snow damage reaching a disaster level when snowfall of 100 cm or more is expected within 24 hours. This makes it possible to formulate advance wide-area countermeasures, emergency resource deployment, road clearance preparations, etc., in addition to making decisions about normal snow removal and disposal. Furthermore, the prediction unit can use an AI (artificial intelligence) model to learn time-series fluctuations, geographical distribution, similarities with past disaster patterns, etc., and output high-resolution future predictions. Input factors may include past snow accumulation history, temperature trends, wind direction and speed, snow accumulation density, snow removal delays, number of resident reports and complaints, traffic flow attenuation trends, stuck road occurrence history, road surface images, etc. Furthermore, the prediction unit may be configured to work in cooperation with the analysis unit 620 and the improvement unit to improve the reliability of the prediction results and perform model re-learning, and may also have a function to periodically evaluate prediction errors and verify deviations from reality, thereby enabling continuous improvement of prediction accuracy. The prediction results are provided to the infrastructure maintenance department or road clearance department and are reflected in the advance identification of areas where snow removal is difficult and in plans to secure road clearance routes.In addition, information based on the prediction results is integrated and evaluated as a risk score through the analysis department 620, and may be used by the improvement department to tune the prediction model and decision logic. In this embodiment, the prediction unit is functionally distinct from the short-term snow removal "forecast" based on weather forecasts executed by the decision unit, and is configured to prepare for medium- to long-term risks such as large-scale snow damage and complex disasters.

[0042] The snow removal decision support system 600 is configured to include a road snow removal unit that is activated when the decision unit 630 determines that snow removal is necessary and that formulates and manages a snow removal implementation plan for the target road. The road snow removal unit is configured to be able to flexibly respond not only to everyday snow removal in normal times, but also to wide-area responses that arise from disaster-level heavy snowfall, etc. Local governments (road administrators) formulate snow removal plans and work guidelines in advance, which include the following: snow removal implementation structure (organization, implementation structure, patrols, snow consultation desk, snow removal contractors, snow removal vehicles, snow removal work evaluation, snow removal dispatch orders, public relations and awareness activities, etc.), snow removal classification (main roads, secondary main roads, suburban main roads, fully outsourced work sections, designated outsourced work sections, residential roads, road clearance routes, etc.), snow removal implementation methods (snow removal standards, snow removal dispatch standards, snow removal methods, snow removal extensions, snow removal times, snow removal times, routes, snow dumps, slip prevention measures such as spraying antifreeze), and types of snow removal work (regular snow removal, new snow removal, road surface leveling, widening snow removal, transportation and snow removal, intersection snow removal, bottleneck area response, alley snow removal, snow removal, antifreeze spraying, etc.). This information is registered in advance with the Road Snow Removal Department and used as reference information when the system formulates implementation plans. The road snow removal unit is primarily responsible for formulating and updating dynamic snow removal implementation plans. It determines the priority, work time periods (day / night), and work categories for each target area and route based on various information acquired from the information acquisition unit 610, the analysis results 690 from the analysis unit 620, and the judgment results 695 from the decision unit 630. The road snow removal unit may also determine the most appropriate work time periods for snow removal based on the analysis results of the acquired information, and formulate and update snow removal implementation plans based on this determination. For example, in determining the appropriate work time periods, nighttime, when traffic volume is low, is often the most suitable for snow removal under normal circumstances. However, in the event of traffic disruptions due to disaster-level heavy snowfall, snow removal may be performed during the day, prioritizing lifesaving efforts. This improves the safety, efficiency, and satisfaction of the work. Furthermore, priority adjustments and reevaluations are performed by integrating multiple information, including resident report status information. The snow removal implementation plan in this specification is distinct from the annual snow removal plan determined in advance by the local government, and refers to a dynamic implementation plan that is formulated and updated daily or in real time based on the latest information acquired by the snow removal decision support system 600. Similarly, the prioritization is also configured to be constantly updated and reevaluated. Areas subject to snow removal are linked to predefined "route" or "work section" units, and the Road Snow Removal Department is configured to set and update the priority, work type, and implementation timing for each of these management units. Linking route codes and work section IDs with various information (report density, snow removal history, complaint history, etc.) enables the formulation of highly accurate work plans. Furthermore, the road snow removal unit may incorporate an analysis and judgment model using AI (artificial intelligence), and it can build a model that estimates snow accumulation trends and the risk of traffic disruptions using various sensor information, camera images, past snow removal records, etc. as learning data. For example, it may be configured to input snow accumulation conditions obtained through image recognition into a learning model, output the degree of snow removal necessity that should be corrected, and adjust the implementation plan based on that. In addition, conventional integrated evaluation processing that is not based on AI (artificial intelligence) can also be carried out in parallel, including a configuration that integrates resident reporting density, reporting methods (SNS, telephone, etc.), traffic delay information, snow depth, presence or absence of visibility obstructions, snowplow location information, etc., and performs prioritization using non-AI weighting processing. The analysis unit 620 or the determination unit 630 may also be configured to compare the implementation cost of each candidate action with the current remaining budget, automatically adjust the response order if the budget is exceeded, and register the action as a candidate for an external support request (wide-area collaboration). This makes it possible to implement a flexible and sustainable snow removal plan even under financial constraints. The road snow removal unit may be configured to work in cooperation with the improvement unit to continuously evaluate and improve the validity and effectiveness of the snow removal implementation plan based on images and acceleration data obtained from patrol vehicles after snow removal, and the occurrence of complaints and repeat reports.The road snow removal unit may also be configured to utilize the results of applying weighting by time period analyzed by the analysis unit 620 to dynamically adjust the work plan according to time periods with a high number of reports, time periods with a high volume of traffic, etc. Furthermore, by coordinating with the infrastructure maintenance department and road clearance department, road damage discovered during snow removal work and areas where road clearance is difficult can be shared, and it can be configured to be able to coordinate with repair and clearance work.In addition, by coordinating with the prediction department, it is possible to grasp in advance the locations where snow removal is expected to be difficult in the future and areas where snow damage is expected, and to incorporate preventative measures. In a resource sharing network formed by multiple local governments or snow removal companies working together, a clustering process is introduced to optimally match resource demand and supply, with resources such as work vehicles, workers, and snow dumping sites as nodes. The Road Snow Removal Department also has the function of managing and recording the status of snow removal (work time, work duration, vehicle history, etc.) and the road surface condition after snow removal (remaining snow, ruts, unevenness, etc.), and this information is used for explaining to residents, work evaluation, and settlement processing with snow removal companies.In addition, the information provision department can also make the plans and implementation status public and notify residents, businesses, and related organizations. In this way, the Road Snow Removal Department is activated based on the decision results from the decision unit 630, dynamically and flexibly formulates and updates prioritized snow removal implementation plans, and is a core component that realizes highly efficient snow removal operations that provide high levels of citizen satisfaction through collaboration with other departments. In addition, the road snow removal unit may be configured to record information regarding the snow removal company's performance (date and time of performance, amount of snow removed, distance covered, response time, etc.) and use this information for settlement processing based on the contract and visualization of business performance. In addition, the road snow removal unit may be configured to predict the efficiency of each work section, taking into account the number of operational snow removal vehicles and workers, travel time, waiting status, etc., and dynamically formulate and update a snow removal schedule using the most efficient combination. Furthermore, for snow removal, a route selection algorithm may be implemented that minimizes a cost function that takes into account the remaining capacity and real-time congestion status of each snow dump site, access distance, and road (access route) congestion status. The cost function is configured to include parameters such as time, fuel consumption, congestion rate, and response time. The road snow removal unit may also be configured to dynamically adjust the work order, resource allocation, and response time period for each management unit by comprehensively referencing information such as the snow removal necessity score, workload score, and predicted snowfall output by the analysis unit 620. For example, the unit may compare scores across multiple management units and immediately raise the priority of sections with scores above a threshold, or automatically generate a preventative deployment plan when disaster-level snowfall is predicted. Furthermore, based on the spatial distribution and temporal transition of scores, priority areas may be defined as zones, and a scheduling process may be performed to implement concentrated snow removal in those zones. This allows the analysis unit 620's advanced judgment results to be reflected in the snow removal plan in a prompt and flexible manner.

[0043] In this embodiment, the information acquisition unit 610 can acquire information regarding the operating status of work vehicles and workers, as well as their availability, from information sources shared via systems or networks individually owned by multiple local governments, multiple road administrators (e.g., the Ministry of Land, Infrastructure, Transport and Tourism, prefectures, cities, towns, and villages), or snow removal companies. "Availability information" here refers to information about resources currently in operation, including availability and free schedules for a certain period of time in the future. Availability information can also include deployment location and relocation possibility (responsiveness and coverage area), operating hours and shift status (available hours), reservation status and allocation schedule (avoiding overlap with other work), and communication availability (a prerequisite for remote collaboration). Additionally, the information acquisition unit 610 acquires information on the usage status of snow dump sites, such as the current congestion status, remaining capacity, and delivery schedule, as needed. This information is used for resource reallocation and regional coordination optimization processing in the road snow removal department. Based on the information acquired above, the Road Snow Removal Department dynamically executes the reallocation of snow removal resources across borders (wide-area collaboration) among multiple local governments and road administrators. In this process, optimization, including mutual budget adjustments and consistency of implementation plans, is sought, minimizing snow removal delays and disparities between regions.

[0044] The snow removal decision support system 600 may be configured to include an infrastructure maintenance unit that is responsible for evaluating the soundness of road infrastructure and making maintenance management decisions. The infrastructure maintenance unit is configured to quickly detect and manage the impact on road surfaces caused by snow removal and road damage that is easily exacerbated by snow accumulation, freezing, snow removal work, etc., and rationally determine repair priorities. In addition, in the event of a disaster, damage assessment results for affected roads can be linked to the road clearance unit and decision unit 630, allowing for integrated operation with disaster response processing. The infrastructure maintenance unit may be configured to perform correlation analysis of road surface abnormalities (vibration intensity, changes in vehicle behavior, abnormalities in video footage, report content, etc.) using at least two or more types of information acquired by the information acquisition unit 610, including satellite survey information, optical fiber survey information, vehicle driving information, road space information, and resident report information, and calculate a risk score for subsurface cavities, structural damage, etc. An AI (artificial intelligence) model such as a neural network may be used to calculate the risk score, and accumulated traffic history and weather data may also be used as learning data. In this detection process, any combination of various information acquired by the information acquisition unit 610 (e.g., road surface information, traffic information, road space information, vehicle driving information, optical fiber survey information, satellite survey information, resident report information, etc.) may be used. Furthermore, for locations determined to be high risk, on-site ground surveys (such as underground radar surveys, camera image acquisition, and vibration measurements) can be conducted to obtain information such as the presence, depth, and shape of cavities, and this information can then be re-input as training data into an AI (artificial intelligence) model to continuously improve prediction accuracy.Furthermore, XAI (Explainable AI) technology can be used to visualize the basis for score calculation, active learning can be used to efficiently learn from limited data, and data augmentation processing using GAN (Generative Adversarial Network) and other techniques can be used to improve model performance. The road damage covered by this Infrastructure Maintenance Department includes unevenness of the road surface, cracks, rutting, cavities under the road, road sinkholes, road damage, tilting and deformation of structures, damage to gutters and road shoulders, etc. It has the function of making repair decisions or proposing countermeasures for these. It is also responsible for the overall maintenance support process, including recording, classifying, prioritizing, proposing inspections, and supporting repair contractors for damaged areas. Furthermore, the infrastructure maintenance unit may cooperate with the improvement unit to improve the accuracy of the assessment of the need for road surface repairs, and may also be configured to contribute to the detection of real-time damage trends by utilizing road spatial information and changes in vehicle driving patterns provided by the analysis unit 620. If necessary, by cooperating with the prediction unit, it may also be possible to make preventative repair proposals based on predictions of future road damage risks. In this way, the Infrastructure Maintenance Department has the functions to contribute to both repair support in peacetime and rapid response decisions in the event of a disaster, and through organic collaboration with other components, it achieves more efficient infrastructure maintenance and reduced risks. In this specification, "response processing related to infrastructure maintenance" includes recording, classifying, and managing damaged areas, developing inspection plans, assigning priorities, proposing repairs, assisting in arranging contractors, or similar processing.

[0045] The snow removal decision support system 600 may be configured to include a road clearance unit that supports road clearance work in the event of a disaster. The road clearance unit is configured to dynamically formulate and update a road clearance implementation plan based on various information acquired when a disaster occurs and the judgment and analysis results provided by each component. Road clearance involves quickly taking minimum measures such as removing debris and repairing uneven surfaces to ensure a passable route (a clear road route) so that emergency vehicles can pass through for the purposes of life-saving and rescue operations, transporting emergency supplies, and supporting recovery. In the event of an emergency such as a large-scale disaster or disaster-level heavy snowfall, this is the initial response that is carried out prior to emergency restoration. Local governments (road administrators) have been formulating road clearance plans in peacetime, including road clearance bases (disaster prevention bases, support unit bases, supply depots, etc.), road clearance routes connecting them (wide-area travel routes, access routes, routes within disaster-stricken areas, etc.), and action plans (work timelines) for when a disaster occurs. This information is registered in advance in the road clearance department. After a disaster occurs, the road clearance unit comprehensively evaluates areas that are difficult to pass, locations where vehicles are frequently stuck, risks of building collapse, etc. based on the disaster, traffic, and report-related information collected by the information acquisition unit 610, the integrated analysis results of the analysis unit 620, and the disaster judgment results of the decision unit 630, and identifies feasible road clearance routes. Furthermore, the road clearance unit may be configured to analyze disaster images and traffic obstruction scores using an AI (artificial intelligence) model and select the optimal road clearance route from multiple candidate routes. Optical fiber sensing, satellite images, traffic delay data, patrol cameras, and SNS reports are used as input information, and the process of correcting abnormal values ​​and false positives is realized in cooperation with the improvement unit. After determining the road clearance route, the road clearance unit automatically creates an implementation plan (road clearance implementation plan) including the road clearance implementation sequence (work timeline) and presents and notifies it to the road administrator. The work timeline indicates the order of road clearance work to be carried out and a chronological action plan. Alternatively, or in addition to this, a road clearance implementation plan may be created based on the priority of each road. The road clearance implementation plan here includes as one component a work timeline that chronologically organizes the start time, processing sequence, required time, etc. of road clearance work based on information on pre-registered road clearance bases and road clearance routes. This implementation plan may also be configured to include optimization processing of priorities and implementation sequences to ensure a rapid initial response in the event of a disaster. If necessary, this implementation plan is also distributed to fire departments, police, medical institutions, and related businesses via the information provision unit for use in initial response. In this specification, the road clearance implementation plan is different from the static road clearance plans established by local governments in peacetime, and refers to a dynamic implementation plan that is formulated and updated daily or in real time after a disaster occurs based on the latest information obtained by the snow removal decision support system 600. The Road Clearance Department also works with the Improvement Department to analyze the results of patrols after road clearance (traffic record, road surface conditions, complaints, etc.) and reflect them in evaluating the effectiveness of the road clearance route and in future improvements. It can also be configured to work with the Prediction Department to identify risk areas where road clearance will be difficult in the future and incorporate countermeasures into plans. Additionally, by working with the Infrastructure Maintenance Department, it is possible to adjust routes and coordinate repairs that take into account the risk of road damage along the road clearance route. In this way, the road clearance unit uses road clearance base stations, road clearance routes, work timelines, etc. registered during normal times as basic information to accurately and quickly formulate and update road clearance implementation plans in cooperation with the decision unit 630, analysis unit 620, prediction unit, improvement unit, infrastructure maintenance unit, etc. As a result, the snow removal decision support system 600 is configured to be able to flexibly respond to road clearance decisions and their execution during disasters in addition to normal snow removal decisions. The road clearance department may be configured to plan and manage road clearance implementation plans, including road clearance bases (disaster prevention warehouses, support unit bases, etc.), road clearance routes (wide-area connecting roads, emergency access roads, etc.), and timelines for the order in which work will be carried out, based on the results of decisions made by the decision department, and to support rapid disaster response through cooperation with other departments (infrastructure maintenance department, road snow removal department, improvement department, etc.).

[0046] <Hardware configuration> FIG. 13 illustrates an example of the hardware configuration of a terminal device TM, a fixed camera CAM, a road surface condition providing server 100, a traffic condition providing server 200, a road space condition providing server 300, a weather condition providing server 400, a vehicle driving condition providing server 500, and a snow removal decision support system 600. This diagram illustrates an example in which the terminal device TM is a mobile phone such as a smartphone. The terminal device TM includes, for example, a CPU 701, a RAM 702, a ROM 703, a secondary storage device 704 such as a flash memory, a touch panel 705, and a wireless communication module 706, all interconnected via an internal bus or a dedicated communication line. Application programs such as a road patrol app are downloaded via a network NW and stored in the secondary storage device 704. The fixed camera CAM includes, for example, a CPU 901, a RAM 902, a ROM 903, a secondary storage device 904 such as a flash memory, a lens / image sensor 905, and a communication device 906, all interconnected via an internal bus or a dedicated communication line. Application programs such as a camera application are downloaded via the network NW and stored in the secondary storage device 904 . Each server includes, for example, a NIC 801, a CPU 802, a RAM 803, a ROM 804, a secondary storage device 805 such as a flash memory or a HDD, and a drive device 806, all interconnected via an internal bus or a dedicated communication line. A portable storage medium such as an optical disk is attached to the drive device 806. A program stored in the secondary storage device 805 or the portable storage medium attached to the drive device 806 is loaded into the RAM 803 by a DMA controller (not shown) or the like, and executed by the CPU 802, thereby realizing the functional units of each server. Road surface information 640, traffic information 650, road space information 660, weather information 670, vehicle driving information 680, analysis results 690, and judgment results 695 are stored in the secondary storage device 805. Note that each server may be implemented using cloud computing. In addition, the snow removal decision support system 600 may be configured to be able to communicate with various servers corresponding to snow removal information, resident notification information, road service information, optical fiber survey information, satellite survey information, etc. when acquiring and processing these. Meanwhile, the overall configuration of the snow removal decision support system 600 is comprised of a computing environment (cloud or on-premise) equipped with the memory, processors and storage areas necessary for the processing of each component, such as the information acquisition unit 610, analysis unit 620, decision unit 630, improvement unit, prediction unit, road snow removal unit, road clearance unit, infrastructure maintenance unit, and information provision unit. Furthermore, the system may be configured with computing resources including a GPU (Graphics Processing Unit), TPU (Tensor Processing Unit) or AI accelerator to execute the AI ​​(artificial intelligence) models used in each component. Furthermore, this configuration is an example of the hardware configuration shown in FIG. 13, and other configurations (edge ​​device configuration, IoT node configuration, etc.) may be used depending on the embodiment.

[0047] Although the embodiments of the present invention have been described above with reference to the drawings, the present invention is not limited to these embodiments or the illustrated configurations. For example, aspects including components described in this specification, such as information on snow removal status, information on resident notification status, road snow removal units, improvement units, prediction units, road clearance units, infrastructure maintenance units, and information provision units, which are not illustrated, are also included within the technical scope of the present invention. Therefore, various modifications, alterations, and substitutions can be made to the present invention without departing from the spirit and scope of the present invention. [Explanation of symbols]

[0048] 100: Road surface condition server 200: Traffic information server 300: Road space situation providing server 400: Weather information server 500: Vehicle driving status server 600: Snow removal decision support system 610: Information acquisition department 620: Analysis Department 630: Decision Section 640: Road surface information 650: Traffic information 660: Road spatial information 670: Weather information 680: Vehicle driving information 690:Analysis results 695: Judgment result

Claims

1. an information acquisition unit that acquires at least two or more pieces of information among information on road surface conditions, information on traffic conditions, information on weather conditions, information on vehicle driving conditions, information on resident notification conditions, and information on snow removal conditions; an analysis unit that analyzes the two or more pieces of information acquired by the information acquisition unit; Register a pre-established snow removal plan including the route or construction section (including cases where at least a portion of the route or construction section includes a road that may be designated as an emergency transportation route and / or a road clearance route, or a road that leads to an emergency transportation route or a road clearance route), the responsible snow removal company, and snow removal dispatch standards; and a road snow removal unit that formulates a dispatch command to the snow removal business operator as part of a snow removal implementation plan (including, for example, a dispatch command, a work type, a work time period, and resource allocation) according to the analysis results obtained by the analysis unit. Based on the snow removal plan registered in the road snow removal unit and the analysis results analyzed by the analysis unit, A snow removal decision support system characterized in that the road snow removal unit at least formulates the dispatch command to the snow removal business operator for each route or each work section.

2. The snow removal decision support system according to claim 1, the information acquisition unit acquires forecast information regarding the amount of snowfall and temperature in the future, and whether or not rain will fall, which is included in short-term weather forecast information; A snow removal decision-making support system characterized in that the analysis unit performs processing to derive the time to start preparatory work for snow removal or the time to carry out snow removal based on the prediction information acquired by the information acquisition unit.

3. The snow removal decision support system according to claim 1, the information acquisition unit acquires forecast information on temperature, humidity, snow quality, moisture content, or snow load included in short-term weather forecast information; The analysis unit evaluates the level of the workload in the snow removal work based on the prediction information acquired by the information acquisition unit, This snow removal decision support system is characterized by performing a process that derives decision information for adjusting the start date of preparatory work for snow removal or the implementation date of snow removal based on the evaluation.

4. The snow removal decision support system according to claim 1, The road snow removal unit predicts at least one of the following: the availability of snow removal vehicles or workers, the time required for snow removal work, and / or the required resources; A snow removal decision support system characterized by performing processing to optimize the snow removal implementation plan based on work efficiency.

5. The snow removal decision support system according to claim 1, The information acquisition unit acquires at least one of information regarding the congestion status of a snow dumping site, information regarding the remaining capacity of the snow dumping site, information regarding the access distance to the snow dumping site, and information regarding the traffic congestion status of an access route to the snow dumping site, The road snow removal unit determines whether the snow dumping site is congested, the remaining capacity, the access distance, and the traffic congestion status of the access route, which are acquired by the information acquisition unit. A snow removal decision support system that performs route optimization processing for snow removal work.

6. The snow removal decision support system according to claim 1, The snow removal decision support system includes a decision unit, The analysis unit or the determination unit compares at least one item of the estimated implementation cost for each snow removal candidate with the remaining budget, A snow removal decision support system that determines whether or not a project can be handled within the budget, and if necessary, adjusts priorities or processes requests for external assistance.

7. The snow removal decision support system according to claim 1, The information acquisition unit acquires information on the operation status or availability of work vehicles and workers, and, if necessary, information on the usage status of snow dumping sites, from information sources shared via individual systems or networks managed by multiple local governments, multiple road managers, or the snow removal and disposal companies; The road snow removal and disposal unit performs cross-border wide-area collaborative processing between multiple local governments, multiple road managers, or snow removal and disposal companies based on the information acquired by the information acquisition unit, and formulates the snow removal and disposal implementation plan, which includes mutual resource optimization and budget adjustment.

8. The snow removal decision support system according to claim 1, The snow removal decision support system includes a decision unit, The snow removal decision-making support system is characterized in that it further includes an improvement unit that continuously improves at least one of the processing logics used in the analysis unit, the road snow removal unit, or the decision unit based on learning data.

9. The snow removal decision support system according to claim 1, The snow removal decision support system uses at least one of the following information: a priority order for snow removal response, a work plan, an operation forecast, and snow removal route information based on the output of the analysis unit or the road snow removal unit. A snow removal decision support system that visually outputs data in the form of a map display, a time series display, or a combination of these.

10. The snow removal decision support system according to claim 1, The snow removal decision support system includes an improvement unit, The information acquisition unit acquires at least one of resident reporting trends, traffic congestion information, bus delay information, patrol results, and weather information, the analysis unit or the improvement unit derives information on changes in road conditions based on the information acquired by the information acquisition unit; By comparing the change information with the actual information on snow removal operations, the effectiveness of snow removal operations can be evaluated. Analyze the causal relationship between factors that change road conditions and the tendency for road conditions to become bad and at least one of weather conditions or snow removal measures, A snow removal decision support system characterized by performing processing to optimize snow removal decisions or processing logic based on the analyzed results.

11. The snow removal decision support system according to claim 1, The snow removal decision support system includes an improvement unit, The snow removal decision support system receives at least one of information on changes in road conditions after snow removal, traffic impact information, and meteorological information. Analyze the consistency with the snow removal response details recorded by the snow removal decision support system, A snow removal decision support system characterized in that the analysis unit or the improvement unit performs feedback processing to continuously optimize the snow removal implementation plan or response logic based on the analyzed results.

12. A program for causing a computer to function as the snow removal decision support system according to any one of claims 1 to 11.

13. A road management method using a computer, comprising: The computer communicates with the network via Acquire at least two pieces of information from among information on road conditions, information on traffic conditions, information on weather conditions, information on vehicle driving conditions, information on resident reports, and information on snow removal conditions; Analyzing the two or more pieces of information obtained; Register a pre-established snow removal plan including the route or construction section (including cases where at least a portion of the route or construction section includes a road that may be designated as an emergency transportation route and / or a road clearance route, or a road that leads to an emergency transportation route or a road clearance route), the responsible snow removal company, and snow removal dispatch standards; Based on the registered snow removal plan and the analyzed analysis results, A road management method characterized in that the computer executes a process of at least formulating a dispatch order to the snow removal company as part of a snow removal implementation plan (including, for example, a dispatch order, work type, work time period, and resource allocation) for each route or work section.

14. 14. The road management method according to claim 13, The computer communicates with the network via Obtain at least one of the following information: distribution information on vulnerable road users (including, for example, the elderly, those requiring care, school-going children, and physically disabled people) in the target area; location information on medical facilities; location information on welfare facilities; and location information on educational facilities; performing a priority weighting process using the acquired information; A road management method characterized by carrying out a process for correcting the priority of snow removal responses in the target area from the perspective of prioritizing welfare or the protection of human life.

15. 14. The road management method according to claim 13, The computer communicates with the network via Acquire management information for each of the routes or construction sections in the target area; Calculating a unique risk score by integrating the acquired management information, the predicted snow load value included in the short-term weather forecast information, and distribution information of vulnerable road users (including, for example, elderly people, people requiring care, school children, and people with disabilities) in the target area; A road management method characterized by executing a process for correcting the priority of snow removal responses based on the risk score.

16. 14. The road management method according to claim 13, The computer predicts the availability of snow removal vehicles or workers, the time required for snow removal work, and the resources required; A road management method characterized by executing a process for optimizing the snow removal implementation plan based on work efficiency.

17. 14. The road management method according to claim 13, The computer communicates with the network via Obtaining at least one of information regarding the congestion status of a snow dumping site, information regarding the remaining capacity of the snow dumping site, information regarding the access distance to the snow dumping site, and information regarding the traffic congestion status of an access route to the snow dumping site; Considering the congestion status of the snow dumping site, the remaining capacity, the access distance, and the traffic congestion status of the access route, A road management method characterized by executing route optimization processing for snow removal work.

18. 14. The road management method according to claim 13, The computer compares the estimated implementation cost for each snow removal candidate with the remaining budget, A road management method characterized by determining whether or not a problem can be handled within the budget, and, if necessary, correcting the priority or processing a request for external support.

19. 14. The road management method according to claim 13, The computer acquires, via a network, information on the operation status or availability of work vehicles and workers, and, if necessary, information on the usage status of snow dumping sites, from information sources or shared networks managed individually by multiple local governments, multiple road managers, or the snow removal business operators; A road management method characterized by performing cross-border wide-area collaborative processing between multiple local governments, multiple road managers, or snow removal companies based on the acquired information, and performing processing to formulate the snow removal implementation plan, including mutual resource optimization and budget adjustment.

20. 14. The road management method according to claim 13, The computer communicates with the network via Obtain at least one of the following information: resident reporting trends, traffic congestion information, bus delay information, patrol results, and weather information. deriving information on changes in road conditions based on the acquired information; By comparing the change information with the actual information on snow removal operations, the effectiveness of snow removal operations can be evaluated. Analyze the causal relationship between factors that change road conditions and the tendency for road conditions to become bad and at least one of weather conditions or snow removal measures, A road management method characterized by performing a process to optimize snow removal decisions or processing logic based on the analyzed results.

21. 14. The road management method according to claim 13, The computer receives at least one of information on changes in road conditions after snow removal, traffic impact information, and meteorological information. Analyze the consistency with the snow removal response recorded by the computer, A road management method characterized by performing feedback processing to continuously optimize snow removal implementation plans or response logic based on the analyzed results.

Images