Snow removal decision support system and program, road management method

Abstract

Snow removal operations in snowy, cold regions heavily rely on visual patrols and empirical rules, making it difficult to fully understand the relationship between snowfall and snow accumulation trends and the effectiveness of snow removal operations. This often leads to delays in initial response and inefficient resource allocation. Furthermore, conventional snow removal methods make it difficult to identify early on conditions where road surface recovery is unlikely. [Solution] The snow removal decision support system of the present invention includes an analysis unit that acquires multiple pieces of information including weather conditions and snow removal status, analyzes the temporal progression by causally relating the occurrence of snowfall, the formation or maintenance of snow accumulation, and the implementation status of snow removal work, and determines whether a condition in which road surface conditions are difficult to restore has continued for a predetermined period of time; and a road snow removal unit that generates an analysis result indicating the need for snow removal measures different from normal snow removal measures based on the determination result, and reflects this in the implementation plan and response instructions.

Description

Technical Field

[0001] The present invention relates to a technology for assisting in the implementation determination of snow removal and snow clearance operations on snow-covered roads, and particularly relates to a snow removal and clearance determination support system and its operation method for dynamically determining and managing the necessity and priority of snow removal and clearance using various external information.

Background Art

[0002] In snowy and cold regions, in order to maintain urban functions in winter and ensure smooth road traffic, it is necessary to appropriately carry out snow removal and clearance operations on roads during snowfall. This can minimize traffic disruptions and impacts on daily life. Conventionally, when determining the necessity of snow removal and clearance, visual patrols by local government staff and reported information such as phone calls from residents have been the main means, and the uneven distribution of information and the subjectivity of judgment have been issues. In recent years, the utilization of AI (artificial intelligence) analysis and sensing technologies has been promoted, but these mainly rely on some sensing means and devices, and the fact is that they have not reached a wide-area and planned operation across the entire local government.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Patent Document 2

Patent Document 3

Summary of the Invention

Problems to be Solved by the Invention

[0004] In recent years, advanced technologies have been developed for snow removal and snow clearing decisions and work management, such as AI (artificial intelligence) technology that analyzes images acquired by cameras mounted on patrol vehicles to understand the conditions of snow accumulation and snow embankments (for example, Patent Document 1), and vibration sensing technology that estimates snow accumulation conditions based on optical fiber cables laid on roads (for example, Patent Document 2). Furthermore, interactive information provision systems (for example, Patent Document 3) have been proposed that use AI (artificial intelligence) to analyze the content of users' messages via SNS (Social Networking Service) or chat applications and present relevant information. However, while each of these technologies has its own merits, they are limited to specific information sources and individual functions, and do not comprehensively support the overall assessment and prioritization of snow removal and clearing, or the development of dynamic implementation plans. The present invention aims to provide a highly practical snow removal decision support system that enables accurate and flexible determination of the need for snow removal by integrating and analyzing diverse information such as patrol status, traffic conditions, weather information, and resident reports, thereby facilitating prioritization and the formulation and updating of dynamic implementation plans. Furthermore, this invention goes beyond the one-time task of snow removal and clearing, embodying a new infrastructure management concept called "self-improving snow removal and clearing decision support," which involves comprehensively collecting, analyzing, and judging regional weather characteristics, traffic characteristics, and citizen needs, and dynamically and continuously optimizing 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 acquires multiple pieces of information, such as snow removal status, road surface conditions, traffic conditions, vehicle movement conditions, weather conditions, and resident reports, and has the function of integrating and analyzing these to determine the necessity of snow removal and formulating a snow removal implementation plan. The implementation plan may include instruction information regarding snow removal responses that specifically indicate dispatch, allocation of materials and equipment, and priority of target routes or work sections. Furthermore, the analysis unit of the present invention analyzes the temporal progression of information on the occurrence of snowfall, the state of snow accumulation formed or maintained by snowfall, and the status of snow removal work on said snowfall or snow accumulation, based on acquired information on weather conditions and snow removal status, by causally relating the information on snowfall occurrence, the state of snow accumulation formed or maintained by snowfall, and determines whether a condition in which road surface conditions are difficult to restore by snow removal work continues for a predetermined period of time. Based on the determination result, it can also generate an analysis result indicating that it is necessary to carry out snow removal measures different from normal snow removal measures. Furthermore, the present invention may include at least an analysis unit that comprehensively analyzes various types of 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, with these being the core components. This enables flexible prioritization based on region and time of day, incorporation of diverse information sources, and learning improvement through AI (artificial intelligence), resulting in efficient and highly accurate snow removal support. An example of the configuration of the present invention is shown below in accordance with the claims. [1] A snow removal decision support system for managing snow removal operations on roads, comprising: an information acquisition unit that acquires information on weather conditions and information on snow removal status; and an analysis unit that, based on the information on weather conditions and snow removal status acquired by the information acquisition unit, analyzes the temporal progression by causally relating information on the occurrence of snowfall, the state of snow accumulation formed or maintained by said snowfall, and the status of snow removal operations on said snowfall or said snow accumulation, determines whether a state in which it is difficult to restore the road surface condition by snow removal operations continues for a predetermined period of time, and generates an analysis result indicating that it is necessary to perform snow removal operations different from normal snow removal operations based on the determination result, A snow removal and clearing decision support system characterized by comprising the following features. A snow removal decision support system according to [2][1], wherein the snow removal decision support system comprises a road snow removal unit, and the road snow removal unit generates a snow removal response command that includes at least one of the following based on the analysis results: a dispatch command, an instruction for the allocation of snow removal vehicles or equipment, or an instruction regarding the priority of the target route or work section. A snow removal decision support system as described in [3][2], wherein the road snow removal unit issues the snow removal response command via confirmation or approval by an operator. A snow removal decision support system as described in [4][2], characterized in that the snow removal response command is output as a request or notification to a snow removal business operator or an external related organization. A snow removal decision support system as described in [5][2], wherein the road snow removal unit generates the snow removal response command by referring to at least one of the following: a snow removal plan, route information, work section information, or information on a snow removal business operator that has been registered in advance. A snow removal decision support system as described in [6][1], wherein the analysis unit further uses information regarding the status of resident reports to evaluate or correct the validity of the analysis results. A snow removal decision support system as described in [7][1], wherein the analysis unit, when it is determined that it is difficult to restore the road surface conditions by snow removal work, identifies at least one of the following as factors contributing to the condition: whether or not snow removal work is being dispatched, the frequency of work, the amount of work, the efficiency of movement to the snow disposal site, the allocation status of snow removal vehicles or equipment, the availability of personnel, or work conflicts on the route or construction section. A snow removal decision support system as described in [8][1], characterized in that it generates the analysis results using information on resident notification status in order to estimate local weather conditions or road surface conditions in the target route or work section. A snow removal decision support system as described in [9][2], wherein the road snow removal unit optimizes the snow removal response command, taking into consideration constraints including the availability of personnel associated with the snow removal vehicle or equipment.

[10] A program comprising a sequence of instructions for causing a computer to perform at least one of the following (A) or (B): (A) a function of a snow removal decision support system as described in any one of [1] or [2], [6] or [8]; (B) at least one of the following functions (1) through (4): (1) a function as described in [3] for issuing snow removal response orders via confirmation or approval by an operator; (2) a function as described in [4] for outputting snow removal response orders as requests or notifications to snow removal businesses or external relevant organizations; (3) a function as described in [5] for generating snow removal response orders by referring to at least one of pre-registered snow removal plans, route information, work section information, or information concerning snow removal businesses; (4) a function as described in [9] for optimizing snow removal response orders, taking into account constraints including the availability of personnel associated with snow removal vehicles or equipment.

[11] A computer-based road management method, The road management method is characterized in that the computer acquires information on weather conditions and snow removal status via a network, analyzes the temporal progression of information on the occurrence of snowfall, the state of snow accumulation formed or maintained by said snowfall, and the status of snow removal work carried out on said snowfall or said snow accumulation by causally relating them based on the acquired information on weather conditions and snow removal status, determines whether a condition in which it is difficult to restore the road surface condition by snow removal work continues for a predetermined period of time, and generates an analysis result indicating that it is necessary to carry out snow removal measures different from normal snow removal measures based on the determination result. A road management method as described in

[12]

[11] , characterized in that the computer implements the snow removal and clearing measures based on the analysis results through confirmation or approval by an operator. A road management method as described in

[13]

[11] , wherein the computer optimizes the snow removal response based on the analysis results, taking into account constraints including the availability of personnel associated with snow removal vehicles or equipment. [Effects of the Invention]

[0006] According to the present invention, by integrating and analyzing various information including road surface conditions, traffic conditions, weather information, vehicle driving conditions, and resident reports, it is possible to determine and prioritize the optimal need for snow removal on snow-covered roads. In particular, according to the present invention, by analyzing the relationship between the progression of snowfall and snow accumulation and the status of snow removal operations in a time-trackable, causal manner, and by determining whether a condition in which road surface conditions are difficult to restore through snow removal operations continues for a predetermined period, it is possible to identify situations where normal snow removal measures are insufficient and generate analysis results indicating the need for snow removal measures different from normal ones. This will prevent delays and duplication of snow removal work, enabling planned and rapid snow removal on necessary roads. Furthermore, it will allow for the development and notification of flexible snow removal plans, including nighttime and disaster response, providing a safe and secure road traffic environment for road users, while also contributing to increased efficiency for local governments (road administrators) and snow removal companies. Furthermore, this invention significantly improves the accuracy, flexibility, and citizen satisfaction of snow removal decisions by comprehensively integrating information types (such as road surface, weather, vehicle movement, and resident reports) that were limited in conventional technology, and by using AI (artificial intelligence) to make decisions that take into account regional characteristics and temporal variations. In addition, by reconstructing and optimizing the decision model based on feedback such as road damage, traffic disruptions, and repeated reports, it is possible to realize self-improving social infrastructure management. [Brief explanation of the drawing]

[0007] [Figure 1] This is a system configuration diagram relating to the snow removal decision support system of the present invention. [Figure 2] It is a flowchart showing an example of the flow of patrol. [Figure 3] It is a flowchart showing an example of the flow of a fixed-point camera. [Figure 4] It is a diagram showing an example of road surface conditions. [Figure 5] It is a cross-sectional view showing an example of road surface conditions (undulations of a snow-covered road surface). [Figure 6] It is a cross-sectional view showing an example of road surface conditions (snow depth on the road surface). [Figure 7] It is a diagram showing an example of traffic conditions. [Figure 8] It is a diagram showing an example of the road space conditions. [Figure 9] It is a diagram showing an example of weather conditions. [Figure 10] It is a diagram showing an example of vehicle driving conditions. [Figure 11] It is a flowchart showing an example of the flow of the snow removal and snow clearing judgment support system of the present invention. [Figure 12] It is a diagram showing an example of the judgment criteria in the decision-making unit of the present invention. [Figure 13]This figure shows an example of the hardware configuration related to the snow removal decision support system of the present invention. Figure 1 is a schematic block diagram showing the basic configuration of the snow removal decision support system of the present invention. In this figure, the configuration of major functional modules such as the information acquisition unit, analysis unit, and decision unit is shown, and the process of acquiring and analyzing various information such as road surface conditions, traffic conditions, weather conditions, and vehicle driving conditions is shown. On the other hand, the present invention also envisions embodiments that include components such as a road snow removal unit that manages resident notification information, snow removal information, and snow removal implementation plans, and an improvement unit that continuously improves the decision model. Figure 11 is a typical processing flow showing the flow of information acquisition, analysis, and decision processing, and is an auxiliary diagram for understanding embodiments of the present invention. Figure 12 is a table showing examples of decisions on whether or not snow removal is necessary when various types of information (road surface, traffic, road space, weather, and vehicle driving information) are combined in a complex manner, and should be understood as an example of the analysis process and decision criteria in the present invention. In addition to snow removal priority analysis and implementation plan formulation, the present invention may also include additional configurations not shown, such as adjustment processing of implementation timing based on predictive information, workload evaluation, snow removal vehicle operation prediction, optimization of snow removal routes to snow disposal sites, feasibility determination based on remaining budget, processing of requests for external support, and weighting processing that takes into account the distribution of medical facilities, welfare facilities, educational facilities, and vulnerable road users. These are embodiments of the present invention and are not shown in Figures 1 to 12, but can be appropriately configured based on the functions claimed in this application. [Modes for carrying out the invention]

[0008] Hereinafter, with reference to the drawings, one embodiment of the snow removal decision support system according to the present invention will be described in detail. The embodiments described below are merely examples to facilitate understanding of the present invention and do not unduly limit the technical scope of the invention. Each component and functional configuration described herein may be modified, substituted, deleted, or added as necessary, based on the gist of the invention as described in the claims, and are included within the technical scope insofar as they produce similar effects. Furthermore, the various components and means described herein can be considered as independent inventions, or they can be combined to form new forms of invention. In this embodiment, the process described will focus on acquiring information on weather conditions and snow removal status, analyzing the temporal progression of information on the occurrence of snowfall, the state of snow accumulation formed or maintained by snowfall, and the status of snow removal work against snowfall or snow accumulation by causally relating them based on this information, determining whether a state in which road surface conditions are difficult to restore through snow removal work continues for a predetermined period of time, and generating analysis results indicating the need for snow removal measures different from normal snow removal measures based on the determination result. In this specification, "core components" refers to the parts that are responsible for particularly central processing and coordination functions in the overall configuration of the snow removal decision support system, and includes, for example, the analysis unit, the road snow removal unit, and the improvement unit depending on the embodiment. Furthermore, "core information" refers to information that is primarily subject to analysis, judgment, and control based on these core components, and includes a variety of information such as snow removal information, road surface information, traffic information, weather information, vehicle movement information, and resident report information. Furthermore, "snow removal response orders" refer to information that specifically instructs or notifies regarding the implementation of snow removal work, including dispatch of personnel, allocation of equipment and materials, and priority of target routes or work sections. Furthermore, the snow removal decision support system according to the present invention may also include functions such as work load evaluation, forecasting and reallocating snow removal resources, optimizing snow removal routes, prioritizing based on budget alignment, and processing decisions for requesting external assistance. These are not necessarily explicitly shown in the drawings, but are embodiments implemented based on the technical ideas described in the claims. Furthermore, the priority analysis results obtained by the analysis department may be recorded or managed in conjunction with the snow removal implementation plan formulated by the road snow removal department or the status of the response implemented based on that plan. This configuration may allow for evaluation of the consistency between the analysis and the implementation results, and reflect this in the optimization of the decision model by the improvement department.

[0009] Figure 1 is a system configuration diagram relating to the snow removal decision support system 600 of the present invention. The 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 necessity of snow removal based on the results analyzed by the analysis unit 620. In this embodiment, the snow removal decision support system 600 is connected to the road surface condition provision server 100, traffic condition provision server 200, road space condition provision server 300, weather condition provision server 400, and vehicle driving condition provision server 500 via a network NW. To understand the road surface conditions, Figure 1 shows only one vehicle Vh and terminal device TM, but multiple vehicles Vh and terminal devices TM may be connected to a network NW. Although Figure 1 shows only one fixed-point camera (CAM) to understand the road space conditions, multiple fixed-point cameras (CAM) may be connected to a network (NW). Furthermore, the present invention includes a road snow removal unit that formulates and manages the snow removal implementation plan, which is a core component of the snow removal decision support system 600, as well as the status of resident reports and the snow removal status, and an improvement unit that continuously improves the decision model. On the other hand, functions for acquiring road service status, fiber optic survey status, and satellite survey status, as well as components such as infrastructure maintenance, road clearing, forecasting, and information provision units, may be provided as expandable configurations that can be added to the system as needed.

[0010] The terminal device TM, fixed-point camera CAM, road surface condition server 100, traffic condition server 200, road space condition server 300, weather condition server 400, vehicle driving condition server 500, and snow removal decision support system 600 communicate via a network NW. The network NW includes some or all of the following: a WAN (Wide Area Network), a LAN (Local Area Network), the Internet, provider equipment, wireless base stations, dedicated lines, etc. Furthermore, data can be exchanged not only via the network (NW) but also via a memory card. Downloading and uploading data via the network (NW) is also acceptable. Furthermore, in this invention, snow removal information and resident notification information are core information elements in the snow removal decision support system 600, and functions for acquiring and processing them are provided as an essential component of the system. This information is acquired via a network NW through a dedicated server, an in-vehicle terminal device, a fixed-point camera, a resident notification server, etc. On the other hand, road service information, fiber optic survey information, satellite survey information, etc., are positioned as optional extended information that can be acquired according to the operational purpose, and may be additionally provided to the snow removal decision support system 600 as needed.

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

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

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

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

[0015] The road surface condition provision server 100 provides road surface conditions to the snow removal decision support system 600 via the network NW. The road surface conditions provided are road-specific information and include some or all of the following: unevenness of the snow-covered road surface, thickness of compacted snow on the road surface, quality of snow on the road surface, snow accumulation on the road surface, snowmelt on the snow-covered road surface, freezing of the road surface, bowl-shaped deformation of the snow-covered road surface, rutting of the snow-covered road surface, snow accumulation on the road surface, unevenness (flatness) of the road surface, cracks, rutting, cavities beneath the road surface, road damage, road collapse, flooding, and whether or not the road width has decreased due to snow accumulation. Figure 4 shows an example of road surface conditions, with areas 110, where the snow-covered road surface is severely uneven, indicated in black on the map. The provided road surface conditions may be quantified in the analysis unit 620 as traffic obstruction score, freezing risk, road surface damage risk, etc., and used as input information for priority determination processing. In addition, the infrastructure maintenance unit may evaluate the long-term deformation risk such as cracks and cavities, and perform processing to determine whether repairs are necessary and to reflect this in the road maintenance plan.

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

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

[0018] The traffic information server 200 provides traffic information to the snow removal decision support system 600 via the network NW. The traffic information provided is road-specific information and includes some or all of the following: traffic volume, passing speed, average speed, and whether or not there is congestion or traffic jams. Figure 7 shows an example of traffic conditions, with areas 210 experiencing severe congestion indicated in black on the map. The traffic conditions provided may be converted and quantified in the analysis unit 620 into traffic flow scores, congestion risk, traffic disruption trends, etc., and integrated with other information (weather information, vehicle driving information, road space conditions, etc.) for use in determining the priority of snow removal.

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

[0020] The weather information server 400 provides weather information to the snow removal decision support system 600 via the network NW. The weather information provided is regional information and includes some or all of the following: time, weather (sunny, rainy, snowy, etc.), temperature, humidity, snowfall amount, snow depth, snow density / weight, snow quality, moisture content, snow load, wind speed, forecast (snowfall amount / snow depth, etc.), presence or absence of warnings (blizzard, heavy snow, etc.) and advisories (heavy snow, windstorm, avalanche, etc.), record-breaking short-term heavy rain information, landslide disaster warning information, earthquake information, etc. Figure 9 shows an example of weather conditions, where snowfall amount 410 and warning 420 are displayed as numbers and letters. Weather conditions are used in the short-term snow removal forecast processing by the determination unit 630, and are utilized in the forecasting unit for medium- to long-term snowfall risk forecasting. Furthermore, the analysis unit 620 may be configured to process wind speed, snowfall amount, temperature, etc., in a multifactorial manner to calculate a snow removal difficulty score for each road.

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

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

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

[0024] The optical fiber survey status provision server utilizes optical fiber sensing technology, which uses optical fibers as sensors. It receives backscattered light from communication optical fibers contained in cables laid on roads, etc., and detects vibration patterns corresponding to the vehicle driving conditions on the road, etc., based on the backscattered light. From the detected vibration patterns and the learned model, it is possible to understand road conditions such as the presence or absence of snow, changes in road surface conditions, the presence of compacted snow or bumps, frozen areas, vehicle congestion or lagging, underground cavities, and impassable areas. Furthermore, by analyzing the intensity, frequency changes, and continuous abnormal patterns of waveforms of minute vibrations propagating through the ground, it is possible to detect the risk of underground cavities and signs of ground deformation. If necessary, the sensing results can be corroborated and supplemented by images acquired from fixed-point cameras connected to optical fibers. The fiber optic survey status provision server provides fiber optic survey status to the snow removal decision support system 600 via the network NW. The information provided includes snow accumulation, compaction, and freezing conditions for each road, unevenness of the snow-covered road surface, vehicle traffic history, traffic volume, traffic congestion, sudden vehicle stops, accident trends, history of freezing and slipping, road surface unevenness, road damage, road collapses, and the possibility of voids under the road surface. This information is used to identify areas where passage is difficult due to snow accumulation and areas with high snow removal priority. This enables fiber optic sensing to continuously and widely monitor road conditions even during times when ground patrols cannot be conducted, contributing to more accurate and immediate decisions regarding snow removal and clearing. The obtained waveforms may be analyzed by AI (artificial intelligence), visualized and quantified as a spatiotemporal distribution of road surface abnormalities and freezing risk, and input to the analysis unit 620 and the determination unit 630.

[0025] The satellite survey status server uses satellite remote sensing technology with artificial satellites equipped with SAR (Synthetic Aperture Radar), optical sensors, microwave sensors, etc., to detect snow cover, compacted snow, snowdrifts, road surface freezing, unevenness of snow-covered road surfaces, areas where snow removal has been completed and not, impassable areas, cavities under the road surface, road damage, road collapses, and flooding. This uses satellite-acquired data such as optical images, SAR images, temperature data, scattering intensity values, polarization information, and phase information to detect time-series changes in snow cover conditions and abnormalities in road surface conditions with high accuracy. Furthermore, by applying interferometric analysis techniques such as InSAR (Interferometric SAR) and DInSAR (Differential Interferometric SAR), it is possible to comprehensively understand subtle height changes due to compacted snow and freezing, changes after snow removal, and areas where snow has accumulated. This allows for the detection of snow depth, remaining compacted snow, and areas where snow removal has been insufficient. The satellite survey status provision server transmits snow accumulation data, estimated snow removal requirements, snow removal completion evaluations, and traffic impact indicators to the snow removal decision support system 600 via the network (NW). This information is compiled and organized by route, work section, or local road, and used in conjunction with other information sources to make decisions regarding snow removal. The determination of whether snow removal has been completed or not, and the traffic impact index, are integrated and evaluated in the analysis unit 620, and may be used for priority decisions in the decision unit 630 and for disaster risk assessment in the prediction unit.

[0026] The resident reporting status server collects and manages information regarding complaints, requests, and reports from residents. It supports multiple communication methods, including AI (artificial intelligence) voice reporting, reporting via SNS (e.g., LINE), web form reporting, email reporting, smartphone app reporting, voice assistant reporting, and traditional telephone reporting with input of interview results by staff. The resident reporting status server provides information regarding resident reporting status to the snow removal decision support system 600 via the network. "AI-based voice notification reception" refers to a system that automatically analyzes voice notification content transmitted via telephone or other voice input means using AI (artificial intelligence) technologies such as speech recognition and natural language processing. This enables quantitative understanding of notification content and automatic storage and learning of notification information without the need for human intervention by operators. The AI-powered voice notification system analyzes the content of the notification (e.g., uncleared snow, snowdrifts, ice, road obstruction, etc.) obtained through dialogue with the caller, as well as the location of the notification (address, facility name, landmark, etc.), using speech recognition and natural language processing, and automatically registers it in the notification database. In addition to SNS notifications and web notifications, citizen-participation notification platforms (e.g., FixMyStreet Japan) also handle posted data, including notification content and location information, in the same way. This data includes text entered by the caller, photos, GPS coordinates, and multiple-choice items, and is handled together with notification information entered by local government officials. The collected reports are classified by location, content, and method of reporting, and organized into report density maps and complaint histories for each route or work section. These are used as basic information by the road snow removal department when assigning priorities for snow removal, and by linking them with the local population or number of households, it becomes possible to make decisions that balance the number of reports with the scope of impact. Resident notification information is automatically sorted by AI (artificial intelligence), and only notifications related to snow removal are extracted. After extraction, the urgency (road impassable, road clearing route, in front of hospital facilities, etc.), geographical characteristics of the target area (main roads / local roads, width, traffic volume, etc.), notification density, and population or household distribution are evaluated to derive priorities. This information is then subjected to integrated analysis by the analysis unit 620 and used as decision-making material by the decision unit 630. In particular, it functions as a source of information that supports highly accurate decisions that influence the necessity, timing, and method of snow removal (daytime / nighttime, etc.). Furthermore, the resident reporting status information may be configured to evaluate its reliability by cross-referencing it with external sensing information such as satellite survey data and fiber optic survey data, and then weighting and prioritizing it accordingly. This makes it possible to improve the reliability and reproducibility of decisions by mutually complementing multiple information sources, without relying on subjective judgment.

[0027] The snow removal status provision server provides snow removal status to the snow removal decision support system 600 via the network NW. The information regarding snow removal status is road-specific and is mainly managed by road administrators. It includes some or all of the following: information on snow removal routes (main roads, etc.) and work sections (local roads, etc.), road conditions, traffic conditions, information on snow removal operators, types and number of snow removal vehicles (shovels, graders, rotary snowplows, dozers, dump trucks, spreaders), prior snow removal plans and work guidelines, snow removal implementation standards, snow removal completion standards, snow removal work plans, dispatch orders to snow removal operators, snow removal implementation status, snow removal work status (including the current location of snow removal vehicles and video / images from snow removal vehicles), snow removal operation records and snow removal performance information (operating hours, location information, history, etc.), snow removal work daily reports, patrol results, budget management, settlement management, complaints and requests, and information on snow disposal sites and snow storage areas. Furthermore, road administrators formulate snow removal plans and guidelines in advance, and the following are planned: snow removal implementation system (organization, implementation system, patrols, snow-related consultation desk, snow removal contractors, snow removal vehicles, snow removal work evaluation, snow removal dispatch orders, public awareness activities, etc.), snow removal classification (main roads, auxiliary main roads, suburban main roads, fully contracted work areas, designated contracted work areas, local roads, road clearing routes, etc.), snow removal implementation methods (snow removal standards, snow removal dispatch standards, snow removal methods, snow removal duration, snow removal time, snow removal time, routes, snow disposal sites, anti-slip measures by applying de-icing agents, etc.), and types of snow removal work (normal snow removal work, fresh snow removal work, road surface leveling work, widening snow removal work, transport snow removal work, intersection snow removal work, bottleneck work, narrow road snow removal work, snow peeling work, de-icing agent application work, etc.). In snow removal operations, after patrols by road administrators and snow removal companies, snow removal implementation plans and work plans are formulated, snow removal work is carried out, and patrols are also conducted after the snow removal work is completed. This information may be used as data for prioritizing and deciding on the implementation of snow removal and clearing operations. Furthermore, information corresponding to the details of snow removal work and responses (work status, operational records, daily work reports, patrol results, etc.) may be stored within the system as snow removal information. This information regarding snow removal and clearing conditions may be used in the analysis unit 620 for correlation analysis between work performance and changes in road surface, evaluation of the relationship between working time and finish quality, and confirmation of spatiotemporal consistency with the location where complaints occurred. Furthermore, the improvement department may readjust and optimize its decision-making logic and allocation policies through actions such as detecting deviations from work guidelines and implementation standards, evaluating whether snow removal responses are sufficient or insufficient, and comparing the performance of each snow removal contractor. In addition, the road snow removal department may implement measures such as revising the snow removal implementation plan, redesigning the work sequence, dynamically adjusting resource allocation, and optimizing the use of snow disposal sites, based on these analysis results and performance evaluations. Furthermore, patrol results and finish evaluation information from in-vehicle video and images can also be used as feedback learning data, and the system may be configured to contribute to improving the accuracy of judgment models and AI (artificial intelligence) processing. In addition, images, videos, and acceleration sensor data collected by patrol vehicles regarding the road surface conditions after snow removal may also be included as information used for performance evaluation and feedback learning. Furthermore, this information, along with information regarding the status of snow removal and clearing, reflects changes in road surface conditions and the finished state. In this specification, the snow removal and clearing information may be configured to partially include elements of road surface information. This information can be used by the road snow removal department to formulate snow removal plans, assign priorities, and decide whether to perform snow removal during the day or at night. It may also be structured to be integrated and analyzed with other information as needed.

[0028] The information acquisition unit 610, which operates in the snow removal decision support system 600, acquires road surface conditions from the road surface condition provision server 100, traffic conditions from the traffic condition provision server 200, road space conditions from the road space condition provision server 300, weather conditions from the weather condition provision server 400, vehicle driving conditions from the vehicle driving conditions provision server 500, road service conditions from the road service conditions provision server, fiber optic survey conditions from the fiber optic survey conditions provision server, satellite survey conditions from the satellite survey conditions provision server, resident notification conditions from the resident notification conditions provision server, and snow removal conditions from the snow removal conditions provision server via the network NW. Road surface conditions provided by the road surface condition provision server 100 are stored as road surface information 640. Traffic conditions provided by the traffic condition provision server 200 are stored as traffic information 650. Road space conditions provided by the road space condition provision server 300 are stored as road space information 660. Weather conditions provided by the weather condition provision server 400 are stored as weather information 670. Vehicle driving conditions provided by the vehicle driving conditions provision server 500 are stored as vehicle driving information 680. Road service conditions provided by the road service condition provision server are stored as road service information. Fiber optic survey conditions provided by the fiber optic survey condition provision server are stored as fiber optic survey information. Satellite survey conditions provided by the satellite survey condition provision server are stored as satellite survey information. Resident notification conditions provided by the resident notification condition provision server are stored as resident notification information. Snow removal conditions provided by the snow removal condition provision server are stored as snow removal information. The information acquired by the information acquisition unit 610 may include at least two of the following types of information, including at least information on resident reports: road surface conditions, traffic conditions, road space conditions, weather conditions, vehicle driving conditions, road service conditions, fiber optic survey conditions, satellite survey conditions, resident report conditions, and snow removal conditions. It is not necessary to acquire all of the information. Furthermore, this information is passed on to the analysis unit 620, decision unit 630, road snow removal unit, improvement unit, etc., and used for judgment, analysis, learning, etc. in each unit. The information acquisition unit 610 may also be configured to manage information by adding metadata such as the type of information, source, acquisition frequency, acquisition time, and related route information, enabling dynamic and real-time information utilization. Furthermore, the information acquisition unit 610 may be configured to acquire information from external organizations such as administrative agencies (police, fire department, Self-Defense Forces, etc.), infrastructure operators (telecommunications, electricity, gas, water, sewage, etc.), transportation operators (railways, buses, etc.), snow removal companies, construction and civil engineering companies, and tourist facility operators. This information may include requests regarding disasters, recovery, and snow removal, traffic disruptions, facility conditions, and evacuation support needs. Furthermore, the information acquisition unit 610 may be configured to dynamically select and limit the types of information to be acquired according to the system's purpose, status, load, etc. For example, if 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, which operates within the snow removal decision support system 600, analyzes various types of information acquired by the information acquisition unit 610, including road surface information 640, traffic information 650, road space information 660, weather information 670, vehicle travel information 680, road service information, fiber optic survey information, satellite survey information, resident notification information, and snow removal information, for each type of information, and stores the analysis results 690. The analysis unit 620 is one of the core components of the snow removal decision support system 600 and performs individual and integrated analysis based on the acquired information. The analysis results 690 may be visualized in the form of a map display, tabular format, time-series display, graph, etc., and may be configured to contribute to subsequent decision-making processes and decisions. The analysis unit 620 may also have an integrated analysis function that allows for the cross-referencing and comparison of multiple pieces of information, in addition to individual analysis. For example, by mapping optical fiber vibration data, satellite image data, and vehicle driving anomaly data to the same area and comparing and aggregating the anomaly scores of each piece of information, it becomes possible to evaluate the overlap and accuracy of anomaly occurrences at that location and derive the necessity of snow removal with high accuracy. This complements the limitations of individual information and enables decision-making based on the consistency of multiple pieces of information.

[0030] Furthermore, the analysis unit 620 may incorporate an AI (artificial intelligence) model, for example, using a neural network or a decision tree-based machine learning model, to take multiple pieces of information as input and generate a snow removal necessity score (numerical or class classification) for each location as output. The output score is used as a decision criterion in the decision unit 630 and for prioritizing in the road snow removal unit. Furthermore, the analysis unit 620 may be configured to provide the analyzed information to the improvement unit as training data or update data, contributing to improving the accuracy of the decision model and retraining the model. Specifically, by using effect indicators obtained after snow removal (such as a decrease in resident reports, improvement in traffic speed, and changes in the number of complaints) as training signals and performing online learning to sequentially adjust the model weights, adaptive decisions can be made according to regional characteristics and seasonal trends. The training targets include date and time, location, content of reports, report density, complaint classification, congestion occurrence, traffic volume, snow accumulation conditions, snow removal history, etc., making it possible to construct statistical trends and reproducible decision logic for snow removal decisions. In addition, the analysis unit 620 may be configured to detect signs of disaster occurrence, and may be configured to perform a disaster screening analysis different from snow removal judgment using multiple types of abnormal information (such as a sudden increase in reports, traffic disruptions, weather warnings, abnormal vibrations of optical fibers, and surface anomalies in satellite images). Disaster analysis is performed in parallel with normal processing based on indicators and models specialized for disaster judgment. In addition, resident reports are subjected to AI (artificial intelligence)-based content sorting, urgency assessment, report density aggregation, geographical characteristic assessment of the target area, and integration with regional population or household numbers. The analysis unit 620 comprehensively evaluates these multi-stage evaluation results and has the function to assess the necessity and priority of snow removal in each region with high accuracy. Furthermore, the analysis unit 620 may be configured to focus on the time or period of information acquisition and perform weighting processing according to the reliability, immediacy, and impact on traffic of the information. Alternatively, the analysis unit 620 may be configured to weight the reliability or priority of various types of information (e.g., road surface information, traffic information, road space information, weather information, vehicle driving information, road service information, fiber optic survey information, satellite survey information, resident report information, snow removal information, etc.) obtained by the information acquisition unit 610 according to the time of acquisition, and perform analysis processing based on this weighting. Such weighting processing according to time of day may also be utilized in deciding whether to carry out snow removal during the day or at night. For example, if resident reports tend to be concentrated in the morning, a configuration that places more emphasis on the density of reports during that time period, or a configuration that distinguishes satellite data provided at night from daytime information and adjusts its weight accordingly, can enable highly reliable decisions based on the time axis. Furthermore, the analysis unit 620 may be configured to analyze the causal relationship between factors influencing changes in road conditions, trends in the occurrence of bad roads, and weather conditions or snow removal / clearing responses using statistical or machine learning methods. This makes it possible to accurately grasp the mechanisms of bad road occurrence and the effectiveness of snow removal / clearing responses, contributing to improved preventative dispatch decisions and priority evaluations.

[0031] These analysis results 690 are transmitted to the decision unit 630 and used as information to help determine the necessity of snow removal. They are also distributed to various components such as the road snow removal unit, road clearing unit, infrastructure maintenance unit, improvement unit, and prediction unit as needed, contributing to improved judgment and management accuracy across 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 comparison with snow removal implementation history, comparative analysis with snow removal method selection history, and evaluation of implementation effectiveness. The system could also be structured to grasp trends in snow accumulation and road conditions by cross-referencing and analyzing past weather and traffic information. Furthermore, the system may be structured to analyze the causal relationship between factors influencing changes in road conditions, trends in the occurrence of bad roads, and weather conditions or snow removal measures, using statistical or machine learning methods. This would allow for a more accurate understanding of the mechanisms of bad road occurrence and the effectiveness of countermeasures, contributing to priority assessment and preventive decision-making. These analysis results can be used as information on changes in road conditions regarding the necessity and urgency of snow removal, and may be structured to contribute to priority assessment and work decisions. The output scores can be displayed on a GIS (Geographic Information System) for each road section or area on the map, and may be color-coded (e.g., in a heatmap format) according to the score level. This allows operators and decision-makers to intuitively identify high-priority areas and support quick response decisions. The information to be analyzed is not limited to all information; analysis may be performed using any combination of information depending on the target area, operational structure, processing purpose, etc. Furthermore, by performing processes such as matching image data with non-image data (e.g., comparing image analysis results with optical fiber data), spatiotemporal interpolation processing for areas with frequent anomalies (for nighttime and severe weather conditions), and processing to improve the responsiveness of disaster response decisions (multifaceted risk assessment using AI and XAI), the system can be configured to provide advanced decision-making support that does not rely on a single sensor. Furthermore, the system may be configured to obtain distribution information regarding the population or number of households in a region from statistical information databases or administrative information, and to integrate this information with the density and urgency of resident reports, thereby enabling snow removal decisions that are appropriate to the population size and density of the region. In addition, the system may be configured to dynamically adjust the weighting coefficients of each analysis indicator based on the regional attributes. For example, in areas with a large elderly population, the urgency of reports may be given a higher weight, and in areas near main roads, the weighting of traffic impact may be increased, thereby realizing priority evaluations that are tailored to the specific circumstances of each region. Furthermore, the analysis unit 620 may be configured to perform priority weighting processing using distribution information on vulnerable road users (elderly people, people requiring care, schoolchildren, people with disabilities) in the target area, as well as location information of medical facilities, welfare facilities, and educational facilities, and to correct the priority of snow removal and clearing operations for each road from the perspective of prioritizing welfare and the protection of human lives. Traditionally, decision-making has been primarily based on empirical rules and rules, making it difficult to integrate and evaluate large amounts of unstructured information (resident reports, images, social media, vibration data, etc.). In contrast, this invention uses AI (artificial intelligence) to learn and estimate the nonlinear relationships and time-series trends between this information, enabling highly sophisticated and reproducible decision-making processes. Furthermore, the snow removal necessity score generation process performed by the analysis unit 620 is comprised of multivariate analysis or machine learning methods that take multiple pieces of information as input. For example, variables such as resident report density, traffic speed reduction rate, number of days without snow removal, snow depth, temperature, snowfall forecast, and past snow removal history are used as features, and these are normalized or categorized to construct the 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 training data will be based on past snow removal results (whether or not a team was dispatched, priority, regional population composition, number of complaints, etc.), and weight optimization will be performed using supervised learning. The output is defined as a score from 0 to 100 for each target area, with a higher score indicating a greater urgency for snow removal. This score, stored as analysis result 690, is used by the decision unit 630 to determine whether or not action is necessary through threshold determination, etc. This configuration enables the analysis unit 620 to integrate and analyze both standardized information (such as sensor data) and non-standardized information (such as resident reports and video analysis results), achieving flexible decision-making support that goes beyond conventional rule-based processing.

[0032] Based on multiple pieces of information obtained from the information acquisition unit 610, the analysis unit 620 evaluates indicators such as the necessity, urgency, traffic impact, and difficulty of snow removal for each road or management unit, and derives integrated evaluation information including these indicators. The evaluation information is expressed in numerical score or hierarchical rank format and is used in formulating snow removal implementation plans. Furthermore, the analysis unit 620 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 forward the implementation date or reallocating resources. Furthermore, the analysis unit 620 acquires time-series data on future snowfall, temperature fluctuations, rainfall, and other forecast information (temperature, humidity, snow quality, moisture content, snow load) based on short-term weather forecasts. Based on this forecast information, it determines the start time for snow removal preparation work and identifies work sections that require prior attention. This improves the ability to respond to sudden snowfall and freezing, and increases the accuracy of planning. Furthermore, predictive information regarding snow load may be used to evaluate the risk that the load will pose to traffic or road structures. If the predicted snow load exceeds a threshold, the priority of work in the affected section will be increased, and a snow removal and clearing plan that takes this risk into consideration will be formulated. Regarding the evaluation of workload, the workload for each section is numerically scored by setting load conversion coefficients linked to the average working speed (km / h) for each heavy machine and fuel and labor costs, based on past snow removal daily reports and operational records (snow depth, operating hours, fuel consumption, road length, number of vehicles, etc.). Specifically, the required workload (t / km or cubic meters / km) is calculated according to the length, width, and snow depth of the target section, and the time or cost required to process that workload is estimated. This enables relative workload comparisons with other sections and the leveling of operational plans. Furthermore, regarding the utilization of short-term weather forecast information, time-series data such as the probability of snowfall, temperature, wind speed, humidity, and presence or absence of rainfall for each region will be obtained from a Web API or publicly available data from the Japan Meteorological Agency, and snow removal decisions will be made based on statistical weather pattern analysis. For example, if snow removal was frequently required in the past under the conditions of "temperature below -2°C" and "probability of snowfall of 70% or higher," the system will be configured to increase the likelihood of pre-dispatch decisions when these conditions are met. Regression analysis, Bayesian inference, random forests, or time-series forecasting models (e.g., LSTM) may be used for the model. The evaluation score is calculated as a weighted average of various factors such as the necessity, urgency, traffic impact, and difficulty of snow removal. If the score exceeds a predetermined threshold, the decision unit 630 is notified that the location is a candidate for priority response or pre-deployment. The score calculation logic and threshold may also be configured to be editable externally 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 past performance information such as trends in changes in priority in the target area, operating hours, and snow removal unit costs. Alternatively, the system may be configured to calculate estimated implementation costs based on the required working hours, number of vehicles, and number of personnel for each potential snow removal solution, and then determine whether or not to implement the solution based on a comparison with the budget. Furthermore, the evaluation information may be structured to derive an integrated score by applying predetermined weights to multiple indicators. For example, a weighted average score such as "traffic impact 70 points, workload 30 points" may be used for the overall evaluation. The evaluation may also include a process to classify the results into categories such as "priority response," "normal response," and "delayed response" based on the score. This clarifies the basis for decisions made when formulating snow removal plans in road snow removal departments, thereby increasing 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 and clearing measures. Specifically, it includes various indicators based on the necessity, 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, elderly, those requiring care, schoolchildren, people with disabilities), and the locational relationship of medical, welfare, and educational facilities. These indicators may be configured to dynamically adjust their weighting according to regional attributes and facility distribution. Furthermore, these evaluation indicators can be integrated with AI (artificial intelligence) weather and traffic forecasting models and urgency assessments of resident reports, and can be structured as evaluation information that includes predictions of short-term response needs. In addition, the evaluation information can be expressed in numerical score or hierarchical rank format and used in the planning process by the road snow removal department. In addition, performance evaluation information from patrol results and in-vehicle images may also be incorporated as feedback learning data and used in constructing the evaluation information.

[0034] In this specification, "judgment information" refers to information related to judgments regarding the necessity, urgency, priority, timing of response, and feasibility of snow removal, derived by the analysis unit 620 or the improvement unit. The judgment 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 the necessity of external support, and dynamic resource reallocation processing. The judgment information is expressed in score format or judgment categories and is used as the basis for decision-making in subsequent processing.

[0035] The analysis unit 620 may perform analysis based on a specific definition of "bad road" in order to evaluate the necessity and priority of snow removal. Here, a bad road refers to a road condition in which vehicle travel becomes difficult due to unevenness of the snow-covered road surface, compacted snow thickness, snow quality, snow accumulation, freezing, snowmelt, bowl-shaped deformation, rutting, etc. The analysis unit 620 may be configured to perform a bad road evaluation for each target section using one or more of these indicators and to calculate a bad road score that will be useful in determining the priority of snow removal. For example, in evaluating unevenness, the amplitude and variability are calculated based on the vertical fluctuation values ​​obtained from the vehicle's acceleration sensor, and these are quantitatively expressed as an unevenness index. Furthermore, by setting thresholds and evaluating in stages (e.g., an amplitude of 5 mm or more is a cautionary level, and 15 mm or more is a level requiring snow removal), it contributes to the standardization of on-site judgment. Furthermore, compacted snow thickness can be evaluated using directly measured values ​​or estimated step amounts from acceleration, etc., as a guideline for thickness. In addition, regarding road surface conditions, image data obtained from fixed-point cameras, in-vehicle cameras, drones, smartphones, etc., may be used to perform image analysis such as object detection and image segmentation to recognize snow accumulation, snow piles, freezing, snowmelt, etc., and convert them into a road condition index. The analysis unit 620 may include a process that uses these road condition indicators to calculate the percentage of road conditions exceeding a predetermined standard for each management unit, which is a division of the road into route units or work sections. The system may then perform scoring based on a tiered evaluation according to the percentage (e.g., 0-20% = low, 21-50% = medium, over 51% = high) and reflect this in the priority order for snow removal. Furthermore, the analysis unit 620 may be configured to manage road information in units of branch numbers using a GIS (Geographic Information System) and to perform detailed evaluations of individual sections on main roads and local roads. This configuration makes it possible to identify localized hazardous points, such as between intersections and at points of gradient change, in addition to the entire route, contributing to the prioritization and efficiency of snow removal and clearing operations. Furthermore, the system may be configured to evaluate the reliability of information for the relevant section based on factors such as the mileage and frequency of patrol vehicles, and to perform correction and exclusion processing if the reliability falls below a predetermined threshold. In addition, the analysis unit 620 may use multiple pieces of information (such as road conditions, traffic, weather, vehicle movement, and road services) to correct or weight average the snow removal priority score using a pre-configured rule-based logic. This configuration enables consistent decision-making based on both rules and actual measurement data. Furthermore, the analysis unit 620 in this embodiment may be configured to comprehensively analyze distribution information of vulnerable road users (elderly people, people requiring care, schoolchildren, people with disabilities, etc.) in the target area, weather forecast values ​​related to snow load, and snow removal response history and regional characteristics for each management unit, and generate a unique risk score that numerically represents the urgency of snow removal response for each road or work section. This score is used for priority evaluation and correction processing of response order. Furthermore, when formulating a snow removal and snow clearing plan for the road snow removal department, it is possible to group target areas by priority based on evaluation information and create a schedule for each time slot and work method. For example, by prioritizing early morning work on routes and areas requiring emergency response, and utilizing times with low traffic volume, it is possible to create a system that balances efficiency and reliability by arranging work in a time-slot format.

[0036] The decision unit 630, which operates 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 various information (road surface information 640, traffic information 650, road space information 660, weather information 670, vehicle travel information 680, road service information, fiber optic survey information, satellite survey information, resident notification information, and snow removal information) analyzed by the analysis unit 620, and stores the decision result 695. The judgment result 695 may include the priority of snow removal at each location, the work necessity score, the recommended time of day for snow removal (daytime or nighttime), or whether disaster response is necessary. The judgment result 695 may be displayed in a way that visualizes it on a map, displays it in a list, displays it chronologically, or displays it on a real-time monitoring screen such as a dashboard. Furthermore, the decision unit 630 may be configured to support or automate decision-making using machine learning or rule-based AI (artificial intelligence) models, learning statistical trends, thresholds, correlations, etc., of the analysis results 690 to improve and expedite snow removal decisions. Furthermore, the decision unit 630 may be configured to perform a process to determine whether disaster response is necessary (access to disaster prevention bases, road clearing, securing emergency transport routes, etc.) if a disaster occurs or its signs are detected, in addition to snow removal decision-making. In the event of a disaster, the system switches from the normal snow removal decision-making logic to disaster response decision criteria, and appropriate prioritization and response policies are formulated. Furthermore, the decision unit 630 may be configured to cooperate with the road snow removal unit and, based on the judgment result 695, determine whether snow removal is necessary for the target road, its priority, and the time of implementation (daytime / nighttime), and to support the process of formulating and updating a snow removal implementation plan based on this information. This ensures consistency between judgment and plan, and improves the efficiency of on-site response. Furthermore, the decision unit 630 may be configured to forecast the likelihood of needing snow removal in the near future (for example, a few hours to the next day) based on information such as weather forecasts, snow removal performance, and trends in resident reports. In addition to weather forecast information, various types of information obtained by the information acquisition unit 610 (e.g., road surface information, traffic information, road space information, vehicle driving information, road service information, fiber optic survey information, satellite survey information, etc.) may be used in an integrated manner in the future forecasting process of the decision unit 630. Functionally, this forecasting function differs from the prediction unit, which deals with 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 handed over to the road snow removal unit and used for prior snow removal preparation, provisional setting of priorities, and consideration of response time slots. Furthermore, the judgment result 695 is shared with components such as the Road Clearing Department, Infrastructure Maintenance Department, and Improvement Department, and is used as input information for each department's processing and implementation plan formulation. Furthermore, the decision result 695 may be configured to be notified and provided to external parties (local government officials, snow removal businesses, residents, etc.) via the information provision unit, and the information provision unit may be configured to have the function of notifying in real time the decision result from the decision unit 630 (snow removal necessity, priority, forecast results, etc.) and the medium- to long-term risk forecast result from the forecast unit via a web dashboard, notification email, smartphone push notification, administrative system linkage API, etc. In addition, the judgment result 695 may be used to optimize and retrain the judgment logic in the improvement unit, thus supporting the system's self-improvement. This enables feedback learning with actual snow removal results and complaint information, contributing to improved accuracy in snow removal and clearing. Thus, the decision unit 630 integrates and evaluates the diverse information acquired and analyzed by the analysis unit 620, and functions as a component for making decisions on snow removal, disaster response, and short-term snow removal forecasts. This enables comprehensive and flexible decision-making support, not only for snow removal but also for infrastructure maintenance and disaster response. Furthermore, the snow removal decision support system 600 may be configured to include a function that dynamically re-evaluates and reconstructs analysis results and response plans when information regarding disasters, damage, and recovery changes. This enables flexible decision support that can respond immediately to sudden changes in on-site conditions.

[0037] Figure 11 is a flowchart showing an example of the flow of the snow removal decision support system 600. The information acquisition unit 610 periodically acquires information on road surface conditions from the road surface condition provision server 100 (for example, every few minutes) (S10). The information acquisition unit 610 periodically acquires information on traffic conditions from the traffic condition provision server 200 (for example, every few minutes) (S11). The information acquisition unit 610 periodically acquires information on road space conditions from the road space condition provision server 300 (for example, every few minutes) (S12). The information acquisition unit 610 periodically acquires information on weather conditions from the weather condition provision server 400 (for example, every few minutes) (S13). The information acquisition unit 610 periodically acquires information on vehicle driving conditions from the vehicle driving condition provision server 500 (for example, every few minutes) (S14). The analysis unit 620 then extracts areas where the road width has been significantly reduced due to snow accumulation from the road surface information 640 (S15). The analysis unit 620 extracts sections where traffic congestion is continuously occurring from the traffic information 650 (S16). The analysis unit 620 extracts dangerous areas where snowdrifts are high (for example, about 1m or more) and visibility is poor from the road space information 660 (S17). The analysis unit 620 extracts areas where the amount of snowfall since the start of the snowfall has reached 10cm or more from the weather information 670 (S18). The analysis unit 620 extracts sections where bus delays have continued for 30 minutes or more from the vehicle driving information 680 (S19). Next, based on the results of the above analysis, the decision unit 630 makes a comprehensive determination of the necessity of snow removal and, if necessary, makes a decision to execute the appropriate action (S20). Figure 11 shows an example of a typical processing flow and is not limited thereto. In this embodiment, various types of information not shown, such as snow removal information, resident notification information, fiber optic survey information, satellite survey information, and road service information, can also be acquired by the information acquisition unit 610 and may be subject to analysis processing by the analysis unit 620. These analysis results are used in the decision unit 630 for snow removal decisions and prioritization, and this information may also be used by the road snow removal unit to formulate snow removal implementation plans and by the improvement unit to optimize decision logic.

[0038] Figure 12 shows an example of the criteria used by the decision unit 630. The decision unit 630 can determine the necessity of snow removal measures based on triggers such as: heavy snowfall of 10 cm / h or more (1st element) 631; road width reduced by snow accumulation resulting in bus delays of 30 minutes or more (2nd element) 632; snow melting due to sunny weather, causing severe unevenness on snow-covered roads and worsening traffic congestion (3rd element) 633; ​​heavy snow warning issued, causing vehicles to slip and skid, as well as congestion due to vehicles getting stuck in the snow (4th element) 634; and frequent tire lock-ups on icy roads at -10°C, resulting in self-inflicted accidents and congestion (5th element) 635. Furthermore, some or all of the judgment results 695 determined by the decision unit 630, the analysis results 690 derived by the analysis unit 620, and the various information (road surface information, traffic information, road space information, weather information, vehicle driving information, road service information, fiber optic survey information, satellite survey information, resident notification information, snow removal information) acquired by the information acquisition unit 610 can be used to send email notifications to snow removal companies, provide data to road administrators' GIS (Geographic Information System), link to autonomous driving systems and MaaS (Mobility as a Service), provide information to government agencies (police, fire department, Self-Defense Forces, etc.) and the mass media, and make information publicly available to road users and residents (homepage, smartphone app, etc.) through the information provision unit, etc. It should be noted that these information provision processes do not necessarily need to go through the information provision unit, allowing for structural flexibility. As an example of the function of disclosing information to road users and residents, the following information may be provided: unevenness of the snow-covered road surface, thickness of compacted snow on the road surface, traffic congestion status, camera images, height of snow levees around routes and intersections, future snowfall forecasts and snow depth, bus route delay information, locations where vehicles are stuck, snow removal orders and implementation status, snow removal orders and implementation status, patrol results, etc. Furthermore, this snow removal decision support system is characterized by being configured to transmit this information or the analyzed results, judgment results, snow removal and snow removal implementation plans, etc., to mobile terminal devices (mobile phones, smartphones, tablet devices, laptops, game consoles, etc.) or fixed terminal devices (desktop computers, smart TVs, set-top boxes, digital signage, kiosk terminals, car navigation systems, car display audio systems, etc.). Figure 12 shows an example of typical decision criteria and is not limited to this. In this embodiment, various types of information not shown, such as snow removal information, resident notification information, fiber optic survey information, satellite survey information, and road service information, are also used as decision-making factors by the decision unit 630. Furthermore, these decision results may be used for formulating snow removal implementation plans by the road snow removal unit, optimizing the decision logic by the improvement unit, and processing notifications by the information provision unit.

[0039] The snow removal decision support system 600 is configured to include an improvement unit that continuously improves some or all of the analysis results 690 (including the analysis method) obtained by the analysis unit 620, the decision results 695 output by the decision unit 630, and the decision criteria. The improvement unit is a core component that realizes "continuous improvement" in the snow removal decision support system 600, and aims to improve decision accuracy, execution validity, and resident satisfaction by forming a learning, verification, and reconstruction loop within a series of processes such as acquisition, analysis, judgment, execution, and evaluation of various information. The Improvement Department includes re-evaluation and retraining functions, including those for AI (artificial intelligence) analysis methods themselves. It uses technologies such as statistical processing, machine learning, and deep learning to improve information acquisition methods, analysis logic, judgment criteria, and prioritization algorithms. For example, this includes optimizing threshold settings, redefining evaluation items, and revising input information selection criteria. Furthermore, the improvement unit may include a function to analyze the causal relationship between factors influencing changes in road conditions, trends in road deterioration, and weather conditions or snow removal measures. This allows for understanding the effectiveness of countermeasures and the mechanisms of occurrence, contributing to improved accuracy in decision-making logic and prioritization. Furthermore, the Improvement Unit uses road surface information, traffic information, road space information, weather information, vehicle driving information, road service information, fiber optic survey information, satellite survey information, resident report 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 this data. In addition, the Improvement Unit may be configured to use various information obtained by the Information Acquisition Unit 610 (e.g., road surface information, traffic information, road space information, weather information, vehicle driving information, road service information, fiber optic survey information, satellite survey information, resident report information, snow removal information, etc.) as learning targets, in addition to the analysis results from the Analysis Unit 620, the judgment results from the Decision Unit 630, and the implementation status of the Road Snow Removal Unit. In particular, by coordinating with the resident report status provision server, the system may be configured to dynamically reconfigure the priority criteria and timing of snow removal based on triggers such as the recurrence of reports or an increase in complaints after snow removal. Furthermore, the improvement unit may be configured to collect and analyze traffic congestion information, recurrence of reports and complaints, and road conditions (remaining snow, ruts, uneven surfaces, reduced width, etc.) obtained by patrol vehicles (including not only road administrators but also snow removal companies), and feed this back into future decisions and implementation plans, thereby enabling highly accurate evaluation and improvement of the consistency between actual results and decisions. The Improvement Department is responsible for optimizing the formulation of future snow removal plans by analyzing the correlation between the snow removal implementation plan and priority assignment results formulated by the Road Snow Removal Department, the implementation history after snow removal, snow removal quality, snow removal completion time, remaining snow conditions, and feedback from residents (complaints and further reports). Furthermore, the improvement unit may be configured to continuously improve prediction models related to road damage and subsurface cavities in cooperation with the infrastructure maintenance unit, and to optimize the algorithms for determining road clearing routes and priority locations in cooperation with the road clearing unit. In addition, it may be configured to improve the prediction accuracy of the models to be improved in accordance with the results of future snowfall, traffic, and disaster predictions in cooperation with the prediction unit. The learning timing in the improvement unit is selected as appropriate according to the operational situation, such as nighttime batch processing, periodic learning at regular intervals, or trigger processing when an exceptional surge in complaints or abnormal weather is detected. 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 time-of-day weighting results in the analysis unit 620 and the actual snow removal results, resident satisfaction, and re-reporting status, and to optimize the weight parameters for subsequent attempts. This makes it possible to optimize the accuracy of decisions by taking into account reporting trends, differences in traffic volume, and the difficulty of snow removal according to the time of day. In this invention, the relationship between changes in road conditions (e.g., occurrence and resolution of bad roads), implementation details, and weather conditions is analyzed as a causal model using regression analysis, correlation analysis, etc., and the effectiveness of snow removal is quantitatively evaluated. The improvement department accumulates past snow removal results, weather conditions, road conditions, and trends in resident reports as learning data, and continuously improves the evaluation results and judgment model output through supervised learning. In particular, error feedback through consistency analysis is emphasized. Furthermore, the improvement unit may also be equipped with a function to statistically analyze the errors and discrepancies between the snow removal necessity score, workload score, predicted snowfall amount, and priority correction information based on population density output by the analysis unit 620 and the actual snow removal implementation results. This allows for the detection of excesses or deficiencies (overestimation or underestimation) in the score design logic, and enables the refinement of the entire analysis logic, such as resetting thresholds or reviewing weighting parameters. Furthermore, a mechanism may be provided to dynamically adjust the confidence coefficient for each information source by evaluating the correlation between the integrated analysis results in the analysis unit 620 (e.g., aggregated values ​​of anomaly scores from multiple sources) and the actual traffic disruptions, number of complaints, sections where snow removal was not completed, etc. Furthermore, in generating scores using AI (artificial intelligence) models, it is also possible to use the analysis results of XAI (explainable AI) in conjunction with the AI ​​model to evaluate the validity and transparency of the reasoning behind the decisions, and to reinforce the training data or revise the feature selection for models that lack explainability. Furthermore, the improvement unit may be configured to analyze the consistency between information on changes in road conditions after snow removal, traffic impact information, and weather information, 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, and enables continuous feedback processing to refine and optimize the snow removal implementation plan or response logic. These processes may 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 (route unit, work section unit, etc.), the managing entity (municipalities, prefectures, road administrators, etc.), past snow removal and clearing performance, road width, route type (main roads, local roads, etc.), budget allocation, location of available construction companies, and the number of operating machines. This information is used by the Analysis Department 620 or the Improvement Department to determine whether snow removal and clearing is feasible, to adjust response policies, or to 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 risk in the medium to long term in preparation for special events such as extreme snowfall and snow damage. The prediction unit estimates future large-scale snowfall, traffic paralysis, and disaster risk based on the analysis results 690 accumulated by the analysis unit 620, the history of decision results 695 output by the decision unit 630, past snow removal implementation history, complaint trends, weather change trends, topography, road structure, etc. The prediction unit may be configured to quantitatively or probabilistically predict, for example, the possibility of traffic disruptions, simultaneous vehicle jams at multiple locations, concentrated reporting areas, or the likelihood of snow damage reaching disaster levels, when snowfall of 100 cm or more is expected within 24 hours. This will enable the formulation of wide-area countermeasures, emergency resource deployment, and road clearing preparations in advance, separate from normal snow removal decisions. Furthermore, the prediction unit can learn time-series fluctuations, geographical distribution, similarities with past disaster patterns, etc., using an AI (artificial intelligence) model, and output high-resolution future predictions. Input factors may include past snowfall history, temperature trends, wind direction and speed, snow density, snow removal delays, resident report volume and complaint density, traffic flow attenuation trends, stuck vehicle occurrence history, road surface images, etc. Furthermore, the prediction unit may be configured to work in conjunction with the analysis unit 620 and the improvement unit to improve the reliability of the prediction results and retrain the model, and it may also be equipped with functions to periodically verify the error of the prediction and the deviation from reality. This makes it possible to continuously improve the prediction accuracy. The prediction results are provided to the Infrastructure Maintenance Department or the Road Clearing Department and are used to identify areas where snow removal is difficult and to plan road clearing routes. Furthermore, 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 performed 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 activated when the decision unit 630 determines the need for snow removal, and includes a road snow removal unit that formulates and manages a snow removal implementation plan for the target road. The road snow removal unit is configured to respond flexibly not only to routine snow removal during normal times, but also to large-scale responses caused by heavy snowfall of disaster magnitude. Local governments (road administrators) formulate snow removal plans and snow removal work guidelines in advance, which include the following: snow removal implementation system (organization, implementation system, patrols, snow-related consultation desk, snow removal contractors, snow removal vehicles, snow removal work evaluation, snow removal dispatch orders, public awareness activities, etc.), snow removal classification (main roads, auxiliary main roads, suburban main roads, fully contracted work areas, designated contracted work areas, local roads, road clearing routes, etc.), snow removal implementation methods (snow removal standards, snow removal dispatch standards, snow removal methods, snow removal length, snow removal time, snow removal time, routes, snow disposal sites, slip prevention measures such as de-icing agent application), and types of snow removal work (normal snow removal work, fresh snow removal work, road surface leveling work, widening snow removal work, transport snow removal work, intersection snow removal work, bottleneck work, narrow road snow removal work, snow peeling work, de-icing agent application work, etc.). This information 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 has the primary function of formulating and updating dynamic snow removal implementation plans. 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, it determines the priority order for each target area and route, the working hours (day and night), and the work categories. The Road Snow Removal Unit may also be configured to determine the appropriate working hours for snow removal based on the analysis results of the acquired information, and to formulate and update the snow removal implementation plan based on that determination. In determining the working hours, for example, while nighttime is often suitable for snow removal under normal circumstances due to low traffic volume, in the event of heavy snowfall of disaster magnitude causing traffic disruptions, the system may be configured to prioritize life-saving efforts and carry out snow removal during the daytime. This makes it possible to improve the safety, efficiency, and resident satisfaction of the implemented work. Furthermore, priority adjustments and re-evaluations are carried out by integrating and processing multiple pieces of information, including resident reporting status information. In this specification, the snow removal implementation plan is distinct from the annual snow removal plan predetermined by the local government. Instead, it refers to a dynamic implementation plan that is formulated and updated daily or in real time based on the latest information obtained by the snow removal decision support system 600. Similarly, the assignment of priorities is also structured to be constantly updated and re-evaluated. The areas targeted for snow removal are linked to predefined "route" or "work section" units, and the road snow removal department sets and updates priorities, work types, and implementation timings for each of these management units. By linking route codes or work section IDs with various information (report density, snow removal history, complaint history, etc.), it becomes possible to formulate highly accurate work plans. Furthermore, the road snow removal unit may incorporate an AI (artificial intelligence) analysis and decision-making model. This model can use various sensor information, camera images, and past snow removal records as training data to construct a model that estimates snow accumulation trends and the risk of traffic disruptions. For example, the snow conditions obtained through image recognition may be input into the training model, the degree of snow removal needed to be corrected may be output, and the implementation plan may be adjusted based on this. Furthermore, conventional integrated evaluation processing that is not based on AI (artificial intelligence) can also be carried out in parallel. This includes configurations that integrate resident reporting density, reporting methods (SNS, telephone, etc.), traffic delay information, snow depth, presence or absence of visibility obstruction, and snowplow location information, and then perform prioritization using non-AI weighting processing. Furthermore, the analysis unit 620 or the decision unit 630 may compare the implementation cost for each candidate response with the current remaining budget, automatically adjust the priority of the responses if the budget is exceeded, and register the response as a candidate for requesting external support (wide-area cooperation). This makes it possible to implement a flexible and sustainable snow removal plan even under financial constraints. The road snow removal and clearing unit may work in cooperation with the improvement unit to continuously evaluate and improve the appropriateness and effectiveness of the snow removal and clearing implementation plan based on images and acceleration data from patrol vehicles obtained after snow removal, as well as the occurrence of complaints and repeat reports. Alternatively, the system may be configured to dynamically adjust the work plan according to the time of day with the most reports, the time of day with the most traffic, etc., by utilizing the results of applying time-based weighting analyzed by the analysis unit 620. Furthermore, by coordinating with the infrastructure maintenance department and the road clearing department, it may be possible to share information about road damage and areas difficult to clear that are discovered during snow removal operations, and to coordinate repair and clearing work. In addition, by coordinating with the forecasting department, it may be possible to identify locations where snow removal is expected to be difficult in the future and areas where snow damage is anticipated, and incorporate preventative measures. In a resource-sharing network formed through collaboration among multiple municipalities or snow removal companies, clustering processing is introduced to optimize the matching of resource demand and supply, using resources such as work vehicles, workers, and snow disposal 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.). This information is used for explaining to residents, evaluating work, and settling accounts with snow removal contractors. In addition, the department can disclose and notify residents, businesses, and related organizations of the plan and implementation status through the Information Provision Department. Thus, the Road Snow Removal Department is a core component that activates based on the decisions made by the Decision-Making Department 630, dynamically and flexibly formulates and updates prioritized snow removal implementation plans, and achieves highly efficient snow removal operations that satisfy citizens through cooperation with other departments. Furthermore, the road snow removal department may also record information regarding the snow removal contractor's performance (date and time of implementation, amount of snow removed, distance covered, time taken, etc.) and use this information for settlement processing based on contracts and for visualizing work performance. Furthermore, the road snow removal unit may be configured to dynamically formulate and update a snow removal schedule using the most efficient combination, by predicting the efficiency of each work section, taking into account the number of operational snow removal vehicles and workers, travel time, standby status, etc. Furthermore, in snow removal, the system may be configured to execute a route selection algorithm that minimizes the cost function, taking into account the remaining capacity and real-time congestion status of each snow disposal 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. Furthermore, the road snow removal unit may be configured to dynamically adjust the work order, resource allocation, and response time for each management unit by comprehensively referring to information such as the snow removal necessity score, workload score, and predicted snowfall amount output by the analysis unit 620. For example, it may be configured to compare scores in multiple management units and immediately raise the priority of sections with scores above a threshold, or to automatically generate a preventative deployment plan when disaster-level snowfall is predicted. In addition, it is possible to define priority areas as zones based on the spatial distribution and temporal changes of scores and perform scheduling processing to carry out concentrated snow removal in those zones. This makes it possible to reflect the sophisticated judgment results of the analysis unit 620 in the snow removal plan in a responsive and flexible manner.

[0043] In this embodiment, the information acquisition unit 610 can acquire information regarding the operational 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, municipalities, etc.) or snow removal companies. In this context, "availability information" refers to information including not only currently operational resources but also their potential availability and free schedules for a certain period in the future. Furthermore, deployment location and mobility (response and coverage area), operating hours and shift status (available time slots), reservation status and assignment schedule (avoiding overlap with other tasks), and communication availability (prerequisites for remote collaboration) may also be included as availability information. Furthermore, the information acquisition unit 610 also acquires information regarding the utilization status of the snow disposal site, such as the current congestion status of incoming snow, the remaining acceptance capacity, and the incoming snow schedule, as needed. This information is used to optimize resource reallocation and wide-area coordination in the road snow removal and clearing unit. Based on the information acquired above, the Road Snow Removal Department dynamically reallocates snow removal resources across multiple municipalities and road administrators (wide-area cooperation). This process optimizes the process, including budget adjustments and consistency of implementation plans, minimizing delays and regional disparities in snow removal.

[0044] The snow removal and clearing decision support system 600 may also be configured to include an infrastructure maintenance unit responsible for evaluating the soundness of road infrastructure and making maintenance decisions. The infrastructure maintenance unit is configured to detect and manage the impact on the road surface due to snow removal and clearing, as well as road damage that is likely to worsen due to snow accumulation, freezing, and snow removal work, and to rationally determine the priority of repairs. Furthermore, in the event of a disaster, the damage assessment results for damaged roads can be linked with the road clearing unit and decision unit 630 to enable integrated operation with disaster response processing. The Infrastructure Maintenance Department may use at least two types of information acquired by the Information Acquisition Unit 610, such as satellite survey information, fiber optic survey information, vehicle driving information, road space information, and resident report information, to perform correlation analysis on road surface abnormalities (vibration intensity, changes in vehicle behavior, abnormalities in video, report content, etc.) 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 training data. In this detection process, various types of information obtained by the Information Acquisition Unit 610 (e.g., road surface information, traffic information, road space information, vehicle driving information, fiber optic survey information, satellite survey information, resident report information, etc.) may be used in any combination. Furthermore, for areas deemed high-risk, the presence, depth, and shape of cavities can be obtained through on-site ground surveys (e.g., ground-penetrating radar surveys, camera image acquisition, vibration measurements, etc.), and this data can be re-input as training data for the AI ​​(artificial intelligence) model to continuously improve prediction accuracy. In addition, the system can be configured to visualize the basis for score calculation using XAI (explainable AI) technology, efficiently learn from limited data using active learning, or improve model performance through data augmentation processing using GAN (Generative Adversarial Network), etc. The infrastructure maintenance department's scope of road damage includes uneven road surfaces, cracks, rutting, voids beneath roads, road subsidence, road collapse, structural tilting and deformation, and damage to gutters and shoulders. It has the function of making repair decisions or proposing appropriate responses to these issues. Furthermore, it is responsible for all aspects of maintenance support, including recording, classifying, and prioritizing damaged areas, proposing inspections, and supporting repair contractors. Furthermore, the Infrastructure Maintenance Department may collaborate with the Improvement Department to enhance the accuracy of assessments regarding the necessity of road surface repairs, and may also contribute to real-time detection of damage trends by utilizing road space information and changes in vehicle traffic patterns provided by the Analysis Department 620. If necessary, it can also collaborate with the Prediction Department to make preventative repair proposals based on predictions of future road damage risks. Thus, the Infrastructure Maintenance Department is equipped with functions that contribute to both support for repairs during normal times and rapid decision-making during disasters, and through organic cooperation with other components, it realizes increased efficiency and reduced risk in infrastructure maintenance and management. In this specification, "infrastructure maintenance response" includes recording, classifying, and managing damaged areas, developing inspection plans, assigning priorities, proposing repairs, assisting with contractor arrangements, or similar processes.

[0045] The snow removal decision support system 600 may be configured to include a road clearing unit to support road clearing operations during disasters. The road clearing unit is configured to dynamically formulate and update a road clearing implementation plan based on various information acquired when a disaster occurs and the decision and analysis results provided by each component. Road clearing involves quickly carrying out minimal measures such as debris removal and road surface repair to secure passable routes (road clearing routes) for the purpose of enabling the passage of emergency vehicles, etc., for the purpose of life-saving and rescue operations, emergency supply transport, and recovery support. In abnormal situations such as large-scale disasters or torrential snowfalls, it is an initial response carried out prior to emergency restoration. Local governments (road administrators) formulate road clearing plans in advance, which include road clearing bases (disaster prevention bases, support troop bases, supply depots, etc.), road clearing routes connecting them (wide-area movement routes, access routes, routes within disaster-stricken areas, etc.), and action plans (work timelines) to be taken when a disaster occurs. This information is registered in advance with the road clearing department. After a disaster occurs, the Road Clearing Unit comprehensively evaluates areas that are difficult to pass, locations where vehicles are likely to get stuck, building collapse risks, etc., based on disaster, traffic, and reporting-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 clearing routes. Furthermore, the road clearing unit may be configured to use an AI (artificial intelligence) model to analyze disaster images and traffic disruption scores, and to select the optimal road clearing route from multiple candidate routes. Input information such as fiber optic sensing, satellite images, traffic delay data, patrol cameras, and SNS reports are used, and processing to correct abnormal values ​​and false detections is realized in cooperation with the improvement unit. After determining the road clearing route, the Road Clearing Department automatically generates an implementation plan (Road Clearing Implementation Plan) including the order of road clearing (work timeline), and presents and notifies the road administrator. The work timeline indicates the order and chronological action plan of the road clearing work to be carried out. Alternatively, or in conjunction with it, the Road Clearing Implementation Plan may be formulated based on the priority of each road. The Road Clearing Implementation Plan, as referred to here, includes a work timeline as one of its components, which organizes the start time, processing order, and required time of road clearing work in chronological order based on information on road clearing bases and road clearing routes that have been registered in advance. This implementation plan may also include a process to optimize priorities and implementation order in order to ensure the speed of initial response in the event of a disaster. If necessary, this implementation plan will be distributed to fire departments, police, medical institutions, and related businesses through the Information Provision Department and used for initial response. In this specification, the road clearing implementation plan differs from the static road clearing plans established by local governments during normal times. Instead, it 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. Furthermore, the Road Clearing Department, in cooperation with the Improvement Department, will analyze the results of patrols after road clearing (traffic volume, road surface conditions, complaint occurrences, etc.) to evaluate the effectiveness of the road clearing route and reflect the findings in future improvements. The system may also be structured to collaborate with the Prediction Department to identify risk areas that may become difficult to clear in the future and incorporate countermeasures into the plan. In addition, collaboration with the Infrastructure Maintenance Department will enable route adjustments and repair coordination that take into account the risk of road damage along the road clearing route. In this way, the Road Clearing Unit, using registered road clearing bases, road clearing routes, and work timelines as basic information, works in cooperation with the Decision Unit 630, Analysis Unit 620, Prediction Unit, Improvement Unit, Infrastructure Maintenance Unit, etc., to accurately and quickly formulate and update road clearing implementation plans. As a result, the Snow Removal Decision Support System 600 is configured to flexibly respond not only to normal snow removal decisions but also to road clearing decisions and their implementation during disasters. The Road Clearing Department may be structured to support rapid disaster response through cooperation with other departments (Infrastructure Maintenance Department, Road Snow Removal Department, Improvement Department, etc.), by formulating and managing road clearing implementation plans, including road clearing bases (disaster prevention warehouses, support unit bases, etc.), road clearing routes (wide-area connecting roads, emergency access roads, etc.), and timelines regarding the order of work, based on the decisions of the Decision-Making Department.

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

[0047] The snow removal decision support system in this embodiment is a system for managing snow removal work on roads, and comprises an information acquisition unit 610 that acquires information on weather conditions and information on snow removal status, and an analysis unit 620 that performs analysis processing using the various information acquired by the information acquisition unit 610. The analysis unit 620 grasps information on weather conditions such as the presence or absence of snowfall, the amount of snowfall, the duration of snowfall, and temperature trends, and grasps information on snow removal status such as the time of snow removal work, the frequency of work, the amount of work, and the corresponding routes or work sections. The analysis unit 620 then analyzes information on the occurrence of snowfall, the state of snow accumulation formed or maintained by snowfall, and the status of snow removal work carried out against snowfall or snow accumulation, causally relating them as a temporal progression so that the causal relationships between them can be grasped. For example, this applies to cases where snowfall continues for a certain period of time, and road conditions do not improve despite snow removal work being carried out, or where conditions deteriorate again in a short time after work is carried out. Based on these analysis results, the analysis unit 620 determines whether the road surface condition is difficult to restore through snow removal work and whether this condition persists for a predetermined period of time. Furthermore, based on the determination result, it generates an analysis result indicating that if normal snow removal measures may not be sufficiently effective, it is necessary to implement snow removal measures different from normal measures. In this embodiment, "analyzing causally related events as a temporal progression" means not merely individually understanding the conditions of snowfall, snow accumulation, or snow removal operations, but evaluating, on the same time axis, the relationship between how the occurrence or continuation of snowfall affects the formation or maintenance of snow accumulation, and how much snow removal operations carried out against the snow accumulation contributed to, or did not contribute to, the recovery of road surface conditions. Furthermore, "a state in which road surface conditions are difficult to recover" refers to a state in which, despite snow removal operations being carried out, the safety or passability of the road surface does not recover to the desired level due to snow accumulation, compacted snow, freezing, or a combination thereof. In addition, "a predetermined period" is a period set based on the period in which road surface conditions are expected to recover if normal snow removal operations are continued, and may be dynamically set based on regional characteristics, road type, traffic volume, or past snow removal performance.

[0048] In this embodiment, the snow removal decision support system further includes a road snow removal unit that controls or manages the actual snow removal response based on the analysis results from the analysis unit 620. Based on the analysis results, the road snow removal unit generates a snow removal response command that includes at least one of the following: a dispatch order, an instruction to allocate snow removal vehicles or equipment, or an instruction regarding the priority of the route or work section to be addressed. The snow removal response command generated here may include whether or not dispatch is necessary, the timing of dispatch, the target route or work section, the type of vehicle or equipment to be used, etc., and the content may be dynamically changed according to the analysis results.

[0049] In this embodiment, the road snow removal unit is configured to issue snow removal response commands after confirmation or approval by an operator. This allows the operator to check the analysis results and command content on the screen, and issue the commands after making corrections or additions as necessary, thereby realizing an operation that appropriately combines fully automated processing and human judgment.

[0050] In this embodiment, the snow removal response command is output as a request or notification to a snow removal business operator or an external related organization. This output may be provided by electronic notification via a communication network, display on a dedicated terminal, or by linking with an existing business system, and may be provided in a format appropriate to the entity that will carry out the snow removal response.

[0051] In this embodiment, the road snow removal unit generates snow removal response commands by referring to at least one of the following pre-registered pieces of information: snow removal plans, route information, work section information, or information on snow removal businesses. This makes it possible to generate highly feasible commands that are in line with the analysis results, taking into account predetermined work policies and assigned roles.

[0052] In this embodiment, the analysis unit 620 performs analysis processing using information on resident reports in addition to information on weather conditions and snow removal status. Specifically, it is configured to evaluate or correct the validity of the generated analysis results by considering the number of reports from residents, the content of the reports, the location of the reports, etc. This makes it possible to make judgments that reflect local traffic disruptions and impacts on daily life that are difficult to grasp from sensor information and work records alone. Here, information regarding resident reporting may include the number of complaints from residents, the number of consultations, the frequency of reporting, the location of reporting, the content of reporting, and the temporal changes of these. This information may also include information that indirectly reflects meteorological conditions and the effects of meteorological conditions on the road surface, such as snowfall amount, snow depth, road freezing, and rut formation.

[0053] In this embodiment, when the analysis unit 620 determines that it is difficult to restore the road surface condition through snow removal work, it identifies the factors causing this condition. These factors include at least one of the following: whether or not snow removal work is being carried out, the frequency of work, the amount of work, the efficiency of movement to the snow disposal site, the allocation status of snow removal vehicles or equipment, the availability of personnel, or work competition on the route or construction section. This makes it possible to determine whether the problem is simply due to insufficient snow removal, or whether it is due to resource allocation or operational constraints. In this embodiment, work conflict refers to a situation in which snow removal operations on multiple routes or work sections cannot be carried out simultaneously due to constraints on personnel, vehicles, equipment, or time slots.

[0054] In this embodiment, the analysis unit 620 performs analysis processing using information on resident reports to estimate local weather conditions or road surface conditions in the target route or construction section, and generates analysis results. This makes it possible to make judgments that are in line with the actual situation even in places where there are no observation points or where sufficient sensor information cannot be obtained.

[0055] In this embodiment, the road snow removal unit optimizes snow removal response commands by considering constraints, including the availability of personnel associated with snow removal vehicles or equipment. This ensures that a feasible and effective snow removal response is selected within the limits of available personnel and resources. In this embodiment, optimization means adjusting snow removal commands to reduce delays in snow removal response, workload, deterioration of road surface conditions, or the effects resulting therefrom, within the range that satisfies the aforementioned constraints.

[0056] In this embodiment, when determining whether it is difficult to restore road surface conditions through snow removal work, the analysis unit 620 may consider, in addition to snowfall and snow accumulation, deterioration of road surface conditions due to snowmelt caused by rising temperatures, refreezing after snowmelt, rutting of the road surface, or a combination thereof. Furthermore, the analysis unit 620 may evaluate the determination result of the difficult-to-restore condition in correspondence with pre-set route classification information such as emergency transport routes, road clearing routes, priority routes, and local roads, and determine the necessity of snow removal measures different from normal snow removal measures depending on the type of route or work section. In addition, the analysis unit 620 may calculate the degree of deterioration and the degree of recovery of road surface conditions using weighting coefficients that reflect snowfall amount, snow accumulation amount, snow removal work amount, traffic volume, past snow removal performance, regional characteristics, etc., and the weighting coefficients may be set differently for each route, each work section, or each region.

[0057] <Hardware Configuration> Figure 13 shows an example of the hardware configuration of a terminal device TM, a fixed-point camera CAM, a road surface condition provision server 100, a traffic condition provision server 200, a road space condition provision server 300, a weather condition provision server 400, a vehicle driving condition provision server 500, and a snow removal decision support system 600. This figure shows an example where the terminal device TM is a mobile phone such as a smartphone. The terminal device TM has a configuration in which, for example, a CPU 701, RAM 702, ROM 703, a secondary storage device 704 such as flash memory, a touch panel 705, and a wireless communication module 706 are interconnected by an internal bus or a dedicated communication line. Application programs such as a road patrol app are downloaded via the network NW and stored in the secondary storage device 704. The fixed-point camera CAM has a configuration in which, for example, a CPU 901, RAM 902, ROM 903, a secondary storage device 904 such as flash memory, a lens / image sensor 905, and a communication device 906 are interconnected by an internal bus or a dedicated communication line. Application programs such as camera apps are downloaded via the network and stored in the secondary storage device 904. Each server has a configuration in which components such as a NIC 801, CPU 802, RAM 803, ROM 804, secondary storage devices 805 such as flash memory or HDDs, and a drive device 806 are interconnected by an internal bus or dedicated communication line. A portable storage medium such as an optical disc is mounted on the drive device 806. Programs stored in the secondary storage device 805 or the portable storage medium mounted on the drive device 806 are loaded into the RAM 803 by a DMA controller (not shown), and executed by the CPU 802, thereby realizing the functional parts 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 also be cloud computing. Furthermore, the snow removal decision support system 600 may be configured to communicate with various servers that handle the acquisition and processing of snow removal information, resident notification information, road service information, fiber optic survey information, satellite survey information, etc. On the other hand, the overall configuration of the snow removal decision support system 600 consists of a computing environment (cloud or on-premise) equipped with the memory, processor, and storage area necessary for processing each component, such as the information acquisition unit 610, analysis unit 620, decision unit 630, improvement unit, prediction unit, road snow removal unit, road clearing unit, infrastructure maintenance unit, and information provision unit. Furthermore, the system may be configured to include computing resources such as a GPU (Graphics Processing Unit), TPU (Tensor Processing Unit), or AI accelerator for executing the AI ​​(artificial intelligence) models used in each component. Furthermore, this configuration is just one example of the hardware configuration shown in Figure 13, and other configurations (edge ​​device configuration, IoT node configuration, etc.) may be used depending on the embodiment.

[0058] Although embodiments of the present invention have been described above with reference to the drawings, the present invention is not limited to these embodiments or illustrated configurations. For example, embodiments including configurations not shown but described herein, such as information on snow removal status, information on resident reporting status, road snow removal unit, improvement unit, prediction unit, road clearing unit, infrastructure maintenance unit, and information provision unit, are also included within the technical scope of the present invention. Therefore, the present invention can be modified, altered, or substituted in various ways without departing from its essence. [Explanation of Symbols]

[0059] 100: Road surface condition server 200: Traffic information server 300: Road space information server 400: Weather information server 500: Vehicle driving status provision 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 operation information 690:Analysis results 695: Judgment result

Claims

1. A snow removal decision support system for managing snow removal operations on roads, An information acquisition unit that acquires information on weather conditions and snow removal status, Based on the information on weather conditions and snow removal status acquired by the information acquisition unit, By causally relating information regarding the occurrence of snowfall, the state of snow accumulation formed or maintained by said snowfall, and the status of snow removal operations for said snowfall or snow accumulation, we can analyze the temporal changes. In order to determine whether the road surface conditions are difficult to restore through snow removal work and whether such conditions continue for a specified period of time, Based on the judgment result, an analysis unit generates an analysis result indicating that it is necessary to carry out snow removal operations that differ from normal snow removal operations, A snow removal and clearing decision support system characterized by comprising the following features.

2. A snow removal and clearing decision support system according to claim 1, The aforementioned snow removal and clearing decision support system includes a road snow removal and clearing unit, Based on the analysis results, the aforementioned road snow removal unit A snow removal decision support system characterized by generating a snow removal response order that includes at least one of the following: a dispatch order, an instruction for the allocation of snow removal vehicles or equipment, or an instruction regarding the priority of the target route or work section.

3. A snow removal and clearing decision support system according to claim 2, The aforementioned road snow removal unit is characterized by issuing the snow removal response command via confirmation or approval by an operator, and is a snow removal decision support system.

4. A snow removal and clearing decision support system according to claim 2, The snow removal decision support system is characterized in that the aforementioned snow removal response command is output as a request or notification to a snow removal business operator or an external related organization.

5. A snow removal and clearing decision support system according to claim 2, The aforementioned road snow removal unit generates the snow removal response command by referring to at least one of the following: a snow removal plan, route information, work section information, or information on a snow removal business operator, as part of a snow removal decision support system.

6. A snow removal and clearing decision support system according to claim 1, The snow removal decision support system is characterized in that the analysis unit further uses information regarding the status of resident reports to evaluate or correct the validity of the analysis results.

7. A snow removal and clearing decision support system according to claim 1, If the analysis unit determines that it is difficult to restore the road surface conditions through snow removal work, it will determine the factors contributing to that condition as follows: A snow removal decision support system characterized by identifying at least one of the following: whether or not snow removal operations are being dispatched, the frequency of operations, the amount of work, the efficiency of movement to snow disposal sites, the allocation status of snow removal vehicles or equipment, the availability of personnel, or work conflicts on routes or construction sections.

8. A snow removal and clearing decision support system according to claim 1, A snow removal decision support system characterized by generating the aforementioned analysis results using information on resident reporting status in order to estimate local weather conditions or road surface conditions in the target route or work section.

9. A snow removal and clearing decision support system according to claim 2, The aforementioned road snow removal unit is characterized by optimizing the snow removal response command, taking into account constraints including the availability of personnel associated with the snow removal vehicles or equipment, and is a snow removal decision support system.

10. A program that includes a sequence of instructions to cause a computer to perform at least one of the following (A) or (B): (A) Functions of the snow removal decision support system according to any one of claims 1 to 2 or 6 to 8, (B) At least one of the following functions (1) through (4): (1) A function to be executed by the snow removal decision support system described in claim 3, which issues snow removal response commands via confirmation or approval by an operator. (2) A function to cause the snow removal decision support system described in claim 4 to execute a snow removal response command, which is output as a request or notification to a snow removal business operator or an external related organization. (3) A function to be executed by the snow removal decision support system described in claim 5, which generates a snow removal response command by referring to at least one of the following: a snow removal plan, route information, work section information, or information on a snow removal business operator that has been registered in advance. (4) A function to be executed by the snow removal decision support system according to claim 9, which optimizes snow removal response commands, taking into account constraints including the availability of personnel associated with snow removal vehicles or equipment, A program that executes the command.

11. A road management method using computers, The aforementioned computer, via the network, We obtain information on weather conditions and snow removal status. Based on the information obtained regarding the weather conditions and the snow removal status, By causally relating information regarding the occurrence of snowfall, the state of snow accumulation formed or maintained by said snowfall, and the status of snow removal operations for said snowfall or snow accumulation, we can analyze the temporal changes. In order to determine whether the road surface conditions are difficult to restore through snow removal work and whether such conditions continue for a specified period of time, A road management method characterized by generating an analysis result indicating the need for snow removal measures different from normal snow removal measures, based on the said determination result.

12. A road management method according to claim 11, The road management method is characterized in that the computer implements the snow removal and clearing measures based on the analysis results through confirmation or approval by an operator.

13. A road management method according to claim 11, Based on the analysis results, the computer, A road management method characterized by optimizing snow removal response by taking into account constraints including the availability of personnel associated with snow removal vehicles or equipment.

Images