Snow removal decision support system and program, road management method

Abstract

The present invention aims to prevent a decline in road traffic functions caused by variations and delays in dispatch decisions that rely on conventional visual patrols and empirical rules when determining whether snow should be removed from roads in snowy environments. [Solution] To solve this problem, the present invention provides a system, program, and road management method that acquires road surface information, traffic information, weather information, vehicle driving information, road service information, snow removal information, etc., and based on this, classifies roads into management units and analyzes and evaluates the priority of snow removal according to the percentage of bad road sections and the reliability of the information. Furthermore, the system is configured to predict the need for snow removal based on past learning data and dynamically adjust priorities. This enables optimal allocation of work resources and rapid response.

Description

[Technical Field]

[0001] The present invention relates to a system that supports decisions on snow removal and disposal on roads in snowy environments, and in particular to a priority analysis type snow removal and disposal decision support system that has the function of analyzing priorities based on the proportion of bad road sections in road management units, traffic, weather, driving information, etc. [Background technology]

[0002] In cold, snowy regions, in order to maintain urban functions and ensure smooth road traffic during the winter, it is necessary to remove snow from roads when it accumulates, and visual patrols are carried out to determine when snow removal work should be carried out. However, in the past, decisions regarding snow removal were often based on the subjective judgment and experience of patrol officers, and assessments of poor road conditions remained qualitative and abstract, making it difficult to objectively compare and determine the necessity and priority of snow removal. [Prior art documents] [Non-patent literature]

[0003] [Non-Patent Document 1] Takikawa City Civil Engineering Division, "Snow Removal in Takikawa City," About Snow Removal, [online], March 31, 2025, Takikawa City, [Retrieved May 26, 2025], Internet<URL:https: / / www.city.takikawa.lg.jp / site / jyohaisetu / > [Non-patent document 2] Hiroo Town Construction and Waterworks Division, "Regarding Snow Removal on Town Roads," Snowplow Dispatch Standards, [online], Publication Date Unknown, Hiroo Town, [Retrieved May 26, 2025], Internet<URL:https: / / www.town.hiroo.lg.jp / kurashi / seikatsu / josetsu / choudounojosetsu / > Summary of the Invention [Problem to be solved by the invention]

[0004] Until now, visual patrols have been the main method of determining when to carry out snow removal work, and decisions have been made based on the experience and subjectivity of patrol officers. This has resulted in inconsistencies in judgment and delayed responses, resulting in issues such as a decline in road traffic functions during the winter and an increased risk of road obstructions, congestion, and accidents. In particular, in wide-area road networks, there is a demand for support methods for making efficient and objective decisions regarding snow removal. Furthermore, the multiple indicators used to grasp the condition of a rough road are not standardized, and the analytical processing is abstract, which is also a factor limiting the conventional technology. [Means for solving the problem]

[0005] The above problems can be solved by the invention having the following configuration. The above problem can be solved by a configuration that can acquire road surface information, traffic information, weather information, vehicle driving information, snow removal information, etc. in snowy environments, evaluate roads for each management unit based on this information, quantitatively calculate and analyze the priority of snow removal based on the proportion of bad road sections and the reliability of the information, and adjust the priority based on future predictions as necessary. An example of the configuration of the present invention will be described below in accordance with the claims. [1] A snow removal decision support system characterized by comprising: an information acquisition unit that acquires information on road surface conditions in a snowy environment, including at least one of the following: unevenness of the snow-covered road surface, thickness of packed snow on the road surface, snow quality on the road surface, accumulated snow on the road surface, melting snow on the snow-covered road surface, frozen road surface, mortar-shaped deformation of the snow-covered road surface, or ruts on the snow-covered road surface; and an analysis unit that, based on the information acquired by the information acquisition unit, divides the road into multiple management units consisting of route units or construction section units, calculates the proportion of bad road sections in each management unit that have an evaluation value above a predetermined standard, and, if the proportion exceeds a predetermined threshold, quantitatively evaluates the priority of snow removal for that management unit based on the predetermined standard. [2] [1] A snow removal decision support system as described in [1], characterized in that the analysis unit includes a process for quantitatively scoring the priority of snow removal for each management unit based on a plurality of predetermined tiered evaluation criteria in accordance with the proportion of bad road sections in each management unit. [3] A snow removal decision support system as described in [1] or [2], characterized in that the analysis unit evaluates the reliability of the information regarding the bad road sections in each management unit based on the proportion of patrol driving for that management unit, and if the proportion is less than a predetermined proportion, includes processing to exclude or correct the information used to evaluate that management unit. [4] A snow removal decision support system as described in any one of [1] to [3], wherein the information acquisition unit or the analysis unit acquires or references route information corresponding to main roads and residential roads from a geographic information system owned by the road administrator, and the analysis unit includes a configuration for, for main roads, integrating multiple sections managed with branch numbers on the geographic information system based on a common system number or route name and processing them as a route unit, and also enabling processing on a branch number unit basis as necessary, and for residential roads, processing includes processing multiple routes as a construction section unit that groups together in an area, and evaluating the road condition ratio on a route unit or a construction section unit as a management unit, and further includes a configuration for, for residential roads, enabling priority evaluation on a route unit or a branch number unit as necessary in addition to processing on a construction section unit. [5] A snow removal decision support system as described in any one of [1] to [4], wherein the information acquisition unit acquires, in addition to information about the bad road, at least one of traffic information including congestion conditions, weather information, vehicle driving information including bus delays, or road service information including the occurrence of stranded vehicles, and the analysis unit includes a process for rule-based correction or weighted evaluation of the snow removal priority of each management unit based on the information about the bad road and the information acquired by the information acquisition unit. [6] A snow removal decision support system as described in any one of [1] to [5], wherein the analysis unit uses a model machine-learned based on learning data including information about the bad roads and snow removal information, and further adds at least one of the traffic information, the weather information, the vehicle driving information, or the road service information, to analyze and evaluate the priority of snow removal for each management unit using the learning model. [7] [6] A snow removal decision support system as described in [6], characterized in that the analysis unit uses the machine-learned model based on past learning data including information about the bad roads and the snow removal information to predict the possibility that snow removal will be necessary in the near future, and includes a process of adjusting the snow removal priority of each management unit based on the prediction results. [8] A program for causing a computer to function as the snow removal decision support system described in any one of [1] to [7]. [9] A road management method using a computer, wherein the computer acquires, via a network, information on road surface conditions in a snowy environment, at least one of the following information: unevenness of the snow-covered road surface, thickness of packed snow on the road surface, snow quality on the road surface, accumulated snow on the road surface, melting snow on the snow-covered road surface, frozen road surface, mortar-shaped deformation of the snow-covered road surface, or rutting on the snow-covered road surface; based on the acquired information, divides the road into multiple management units consisting of route units or construction sections; calculates the proportion of bad road sections in each management unit that have an evaluation value above a predetermined standard; and, if the proportion exceeds a predetermined threshold, performs a process to quantitatively evaluate the priority of snow removal for that management unit based on the predetermined standard.

[10] [9] A road management method as described in [9], characterized in that the computer executes a process of quantitatively scoring the priority of snow removal for each management unit based on a plurality of predetermined graded evaluation criteria, depending on the proportion of bad road sections in the management unit.

[11] [9] or

[10] , a road management method, characterized in that the computer evaluates the reliability of the information regarding the bad road sections in each management unit based on the proportion of patrol driving for that management unit, and if the proportion is less than a predetermined proportion, performs a process of excluding or correcting the information used to evaluate that management unit.

[12] A road management method described in any one of [9] to

[11] , wherein the computer obtains or references route information corresponding to trunk roads and local roads from a geographic information system owned by the road administrator, and for trunk roads, integrates multiple sections managed with branch numbers on the geographic information system based on a common system number or route name and processes them as route units, and can also process them on a branch number basis as necessary, and for local roads, processes them as construction section units that group multiple routes together in an area, and performs a process to evaluate the road condition ratio on a route unit or construction section unit basis as a management unit, and further performs a process for local roads that, in addition to processing on a construction section unit, enables priority evaluation on a route unit or branch number unit as necessary.

[13] A road management method described in any one of [9] to

[12] , characterized in that the computer acquires, in addition to information about the bad road, at least one of traffic information including congestion conditions, weather information, vehicle driving information including bus delays, or road service information including the occurrence of stranded vehicles, and performs a process of correcting or weighting and evaluating the priority of snow removal for each management unit on a rule-based basis based on the information about the bad road and the acquired information.

[14] A road management method according to any one of [9] to

[13] , characterized in that the computer uses a machine-learned model based on learning data including information about the bad roads and snow removal information, and further adds at least one of the traffic information, the weather information, the vehicle driving information, or the road service information, to perform a process of analyzing and evaluating the priority of snow removal for each management unit using the learning model.

[15]

[14] A road management method as described in

[14] , characterized in that the computer uses the machine-learned model based on past learning data including information about the bad roads and the snow removal information to predict the possibility of snow removal being required in the near future, and performs a process to adjust the snow removal priority of each management unit based on the prediction results. [Effects of the Invention]

[0006] The present invention can appropriately evaluate the necessity and priority of snow removal work based on bad road information on snow-covered road surfaces, thereby reducing delays and excessive deployment of snow removal work and preventing a decline in road traffic functions. In particular, by comprehensively analyzing acquired road surface, traffic, weather, driving, and snow removal information, calculating the proportion of bad roads for each management unit, and scoring it using a tiered evaluation standard, it becomes possible to make efficient snow removal decisions according to priority. Furthermore, by predicting future occurrences of bad roads and road obstructions based on past learning data and adjusting priorities based on the results, it becomes possible to respond proactively, contributing to the optimal allocation of work resources and the improvement of services for residents. [Brief explanation of the drawings]

[0007] [Figure 1] 1 is a system configuration diagram of a snow removal decision support system according to the present invention. [Figure 2] FIG. 10 is a flowchart illustrating an example of a patrol flow. [Figure 3] FIG. 10 is a flowchart illustrating an example of a flow of a fixed camera. [Figure 4] FIG. 2 is a diagram illustrating an example of a road surface condition. [Figure 5] FIG. 1 is a cross-sectional view showing an example of road surface conditions (unevenness of snow-covered road surface). [Figure 6] FIG. 2 is a cross-sectional view showing an example of road surface conditions (thickness of packed snow on the road surface). [Figure 7] FIG. 1 is a diagram illustrating an example of a traffic situation. [Figure 8] FIG. 1 is a diagram illustrating an example of a road space situation. [Figure 9] FIG. 10 is a diagram illustrating an example of weather conditions. [Figure 10] FIG. 2 is a diagram illustrating an example of a vehicle driving situation. [Figure 11] 1 is a flowchart illustrating an example of the flow of a snow removal decision support system according to the present invention. [Figure 12] FIG. 10 is a diagram showing an example of a determination criterion in a determination unit of the present invention. [Figure 13] FIG. 1 is a diagram illustrating an example of the hardware configuration of a snow removal decision-making support system according to the present invention. FIG. 1 is a block diagram that schematically illustrates the basic configuration of the snow removal decision-making support system according to the present invention. While this diagram focuses on major functional modules, such as an information acquisition unit, an analysis unit, and a determination unit, the present invention may also include functions for acquiring and processing information related to road service status and snow removal status. While these components are not illustrated in FIG. 1, they function as components in embodiments of the present invention. FIG. 11 also illustrates an overview of a typical processing flow for information acquisition, analysis, and decision-making in a snow removal decision-making support system, and is an auxiliary diagram for understanding embodiments of the present invention. In the present invention, information related to road service status and snow removal status are also considered to be extremely important factors in determining the need for snow removal and determining priorities. However, since this information is not explicitly illustrated in FIG. 12, FIG. 12 should be understood as merely an example. DETAILED DESCRIPTION OF THE INVENTION

[0008] Hereinafter, an embodiment of a snow removal decision support system of the present invention will be described with reference to the drawings. This embodiment exemplifies the technical idea of the present invention and does not unduly limit the technical scope of the invention described in the claims. Furthermore, not all of the configurations described below are essential elements, and some of the configurations may be appropriately changed, added, deleted, or replaced with other configurations. As long as similar operational effects are achieved, these are included in the technical scope of the present invention. The components and means described in this specification may be independent inventions, and a combination of multiple components may also form a new form of invention. One embodiment of the present invention is a system for supporting decisions on snow removal and disposal on roads in snowy environments, and is equipped with a configuration for analyzing and evaluating the priority of snow removal and disposal for each road management unit based on various information.

[0009] 1 is a system configuration diagram of a snow removal decision support system 600 of the present invention. Snow removal decision support system 600 includes an information acquisition unit 610 that acquires information on road surface conditions, traffic conditions, road space conditions, weather conditions, and vehicle driving conditions, an analysis unit 620 that analyzes the road surface conditions, traffic conditions, road space conditions, weather conditions, and vehicle driving conditions obtained from the information acquired by the information acquisition unit 610, and a decision unit 630 that determines the need for snow removal based on the results of the analysis by analysis unit 620. In the embodiment, the snow removal decision support system 600 is communicatively connected to a road surface condition providing server 100, a traffic condition providing server 200, a road space condition providing server 300, a weather condition providing server 400, and a vehicle driving condition providing server 500 via a network NW. Although FIG. 1 shows only one vehicle Vh and one terminal device TM for grasping road surface conditions, a plurality of vehicles Vh and terminal devices TM may be connected to the network NW. Although only one fixed camera CAM is shown in FIG. 1 to grasp the road space situation, multiple fixed cameras CAM may be connected to the network NW. Furthermore, in the present invention, the snow removal decision support system is configured to include information on the road service situation and information on the snow removal situation as components.

[0010] The terminal device TM, fixed camera CAM, road surface condition providing server 100, traffic condition providing server 200, road space condition providing server 300, weather condition providing server 400, vehicle traveling condition providing server 500, and snow removal decision support system 600 communicate via a network NW. The network NW includes, for example, some or all of a WAN (Wide Area Network), LAN (Local Area Network), the Internet, a provider device, a wireless base station, a dedicated line, etc. The communication method is not limited to the network NW, but data can also be sent and received via a memory card. Data can also be downloaded and uploaded via the network NW. In addition, in the present invention, the function of providing information on the road service status and information on the snow removal status is configured to be included in the snow removal decision support system 600 and functions as a component. This information is acquired via the network NW through a dedicated server, terminal device, etc.

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

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

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

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

[0015] The road surface condition providing server 100 provides road surface conditions via the network NW to the snow removal decision support system 600. The road surface conditions provided are information for each road, and include some or all of the following: unevenness of the snow-covered road surface, thickness of packed snow on the road surface, snow quality on the road surface, accumulated snow on the road surface, snow melting on the snow-covered road surface, frozen road surface, bowl-shaped deformation of the snow-covered road surface, ruts on the snow-covered road surface, accumulated snow on the road surface, and whether or not the road width has been reduced due to accumulated snow. FIG. 4 is a diagram showing an example of road surface conditions, where a portion 110 where the snow-covered road surface is extremely uneven is displayed in black on the map.

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

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

[0018] The traffic condition providing server 200 provides traffic conditions via the network NW to the snow removal decision support system 600. The traffic conditions provided are information for each road, and include some or all of the following: traffic volume, passing speed, average speed, and whether or not there is congestion or congestion. FIG. 7 is a diagram showing an example of traffic conditions, with locations 210 with heavy traffic congestion displayed in black on the map.

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

[0020] The weather condition providing server 400 provides weather conditions via the network NW to the snow removal decision support system 600. The weather conditions provided are information for each region, and include some or all of the following: time, weather (sunny, rainy, snowy, etc.), temperature, amount of snowfall, snow depth, snow density and weight, wind speed, forecast (amount of snowfall, snow depth, etc.), and whether or not there are any warnings (blizzards, heavy snow, etc.) or advisories (heavy snow, wind and snow, avalanches, etc.). FIG. 9 shows an example of weather conditions, where snowfall amount 410 and warning 420 are displayed in numbers and letters.

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

[0022] As a method for understanding the narrowing of road width due to snow accumulation, it is acceptable to use camera and image recognition functions of smartphones, communication-type drive recorders, fixed-point cameras, etc. installed in vehicles to determine the snow accumulation situation, or to use the same functions to determine the narrowing of road width from the number of lanes and the number of vehicles side by side.It is also acceptable to determine the lane driving position of a route bus or other vehicle from the latitude and longitude (which lane out of three lanes on each side the bus is driving in, or which lane out of two lanes on each side the bus is driving in, etc.) and determine the narrowing of road width due to snow accumulation.

[0023] The information acquisition unit 610 operating in the snow removal decision support system 600 acquires road surface conditions from the road surface condition providing server 100, traffic conditions from the traffic condition providing server 200, road space conditions from the road space condition providing server 300, weather conditions from the weather condition providing server 400, and vehicle driving conditions from the vehicle driving condition providing server 500 via the network NW. The road surface conditions provided by the road surface condition providing server 100 are stored as road surface information 640. The traffic conditions provided by the traffic condition providing server 200 are stored as traffic information 650. The road space conditions provided by the road space condition providing server 300 are stored as road space information 660. The weather conditions provided by the weather condition providing server 400 are stored as weather information 670. The vehicle driving conditions provided by the vehicle driving condition providing server 500 are stored as vehicle driving information 680. Furthermore, the information acquisition unit 610 may store information related to road service status. The information related to road service status is information for each road and is mainly managed by road service providers (such as the Japan Automobile Federation), and includes some or all of the following: rescue requests (date, time, location, rescue 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 battery, locked keys in the car, running out of gas, flat tires, wheels coming off or falling off, flooding or submersion, recovery from snowy or muddy roads, accidents, slips and falls, disaster or damage status, towing or transportation of vehicles, removal, towing or transportation of abandoned vehicles, removal, towing or transportation of damaged vehicles, removal, towing or transportation of accident vehicles, location information of stranded vehicles, status of stranded vehicles, road conditions, traffic conditions, EV charging support, vehicle inspection results, etc. The road service status is stored as road service information. Additionally, the information acquisition unit 610 may store information regarding the status of snow removal. The information regarding the status of snow removal is information for each road, is mainly managed by road administrators, and may include some or all of the following: information regarding snow removal routes (such as main roads) and work areas (such as residential roads), road conditions, traffic conditions, information regarding snow removal companies, the type and number of snow removal vehicles (shovels, graders, rotary scooters, dozers, dump trucks, spreaders), advance snow removal plans and work guidelines, snow removal implementation standards, snow removal completion standards, snow removal implementation plans, snow removal work plans, dispatch orders to snow removal companies, snow removal implementation status, snow removal work status (including the current locations of snow removal vehicles and video and images from snow removal vehicles), snow removal operation results (operating hours, location information, history, etc.), daily snow removal work reports, patrol results, budget management, settlement management, complaints and requests, and information regarding snow dumping sites and snow storage areas. The snow removal situation is stored as snow removal information. In addition, road administrators formulate snow removal plans and guidelines in advance, which include the snow removal implementation structure (organization, implementation structure, patrols, snow consultation desk, snow removal contractors, snow removal vehicles, snow removal work evaluation, snow removal dispatch orders, public relations and awareness activities, etc.), snow removal classification (main roads, secondary main roads, suburban main roads, fully outsourced construction sections, designated outsourced construction sections, residential roads, road clearance routes, etc.), snow removal implementation methods (snow removal standards, snow removal dispatch standards, snow removal methods, snow removal extensions, snow removal times, snow removal times, routes, snow dump sites, anti-freeze spraying to prevent slipping, etc.), and types of snow removal work (regular snow removal, new snow removal, road surface leveling, widening snow removal, snow transportation and removal, intersection snow removal, bottleneck area response, alley snow removal, snow removal, anti-freeze spraying, etc.). In snow removal work, after patrols by road managers and snow removal companies, implementation plans and work plans for snow removal are drawn up, snow removal work is carried out, and patrols are also carried out after the snow removal work has been completed. This information may be used as information and data for evaluating snow removal priorities and making decisions about implementation. The information acquired by the information acquisition unit 610 may be only a part of the road surface conditions, traffic conditions, road space conditions, weather conditions, vehicle driving conditions, road service conditions, and snow removal conditions.

[0024] The analysis unit 620 operating in the snow removal decision support system 600 analyzes each type of information obtained from the information acquired by the information acquisition unit 610, including road surface information 640, traffic information 650, road space information 660, weather information 670, and vehicle driving information 680, and stores the analysis results as 690. The stored analysis results 690 may be visualized in the form of a map display, a table, a time series graph, etc. The analysis unit 620 may also analyze road service information and snow removal information. The information analyzed by the analysis unit 620 may be only a part of the road surface information 640, traffic information 650, road space information 660, weather information 670, vehicle driving information 680, road service information, and snow removal information. Furthermore, the information to be analyzed may be all or part of the information, and may be selectively processed as needed.

[0025] The analysis unit 620 may be equipped with a process for dividing the road into multiple management units (main roads, community roads, etc.) consisting of route units or construction sections based on the acquired road surface information 640, and calculating the proportion of bad road sections in each management unit that have an evaluation value above a predetermined standard. To determine whether a road section is bad, one or more of a number of indicators can be used, such as the amplitude of unevenness on a snow-covered road surface, an estimated value of packed snow thickness, changes in snow quality, snow depth, and whether the road surface is frozen. In determining unevenness, amplitude and variation may be calculated based on the vertical fluctuation value acquired by the vehicle's acceleration sensor, and evaluated as an unevenness index. Alternatively, threshold values (for example, an amplitude of 5 mm or more is considered a caution level, and an amplitude of 15 mm or more is considered a level requiring snow removal) may be set to perform a step-by-step evaluation. The thickness of packed snow may be evaluated using a directly measured value or the amount of step estimated from acceleration fluctuations recorded while the vehicle is traveling as a guide for thickness. Furthermore, the determination of a rough road may include processing to analyze image data, for example, by recognizing snow accumulation, ruts, ice, melting snow, and mottled patterns of snow on the road surface from images taken by a fixed camera, an in-vehicle camera, a drone, a smartphone, etc. using methods such as object detection and image segmentation, and converting them into corresponding rough road indicators. This makes it possible to acquire visual features that are difficult to detect using sensor data in a complementary manner. Furthermore, the system may be equipped with a process for quantitatively scoring the priority of snow removal for each management unit based on predetermined graded evaluation criteria (e.g., 0-20% as low, 21-50% as medium, and over 51% as high) according to the calculated proportion of bad road sections. In addition, the reliability of the bad road information may be evaluated based on the distance or frequency of patrol driving for each management unit, and if the reliability is below a predetermined rate, the relevant information may be excluded or corrected before processing. The analysis unit 620 may also be configured to perform a process of correcting or weighting the priority of snow removal and evaluation in accordance with pre-set rules based on multiple pieces of information such as bad road information, traffic information, weather information, vehicle driving information, and road service information. The term "construction area" as used here refers to a geographical area predefined for the purpose of managing residential roads on a surface-by-surface basis, and refers to a work unit determined by the road administrator. "Rough roads" here refer to roads on which it is difficult for vehicles to travel due to road surface conditions such as unevenness of the snow-covered road surface, thickness of packed snow on the road surface, quality of snow on the road surface, accumulated snow on the road surface, melting snow on the snow-covered road surface, frozen road surface, bowl-shaped deformation of the snow-covered road surface, and ruts on the snow-covered road surface.

[0026] The analysis unit 620 may be configured to integrate various road information related to main roads and community roads using common route numbers and route names based on route information obtained from a GIS (geographic information system), and process the information on a route-by-route or construction section-by-section basis. Main roads (main roads, secondary roads, suburban roads, etc.) can be processed on a branch number basis as necessary depending on the road structure and traffic conditions, and for residential roads, a configuration may be provided that allows selection of evaluation on a route or branch number basis in addition to a construction section basis. The "branch number" referred to here refers to the identification number assigned to each section when a major road is divided into multiple sections and managed in a GIS (geographic information system).For example, even if it is the same route, it is subdivided into "main number - branch number (e.g. R001-1, R001-2)" between intersections or at the change in road structure. This configuration allows the analysis unit 620 to not only evaluate the entire route, but also grasp and evaluate the poor road conditions and traffic obstructions for each individual branch number section in more detail. Evaluation by branch number is also effective in identifying localized danger areas due to uneven distribution of frozen roads or packed snow. In addition, route information corresponding to the management unit may be obtained in advance from a GIS (geographic information system) owned by the road administrator, and may be referenced and processed as master registered information in a computer.

[0027] The analysis unit 620 may apply a machine learning model constructed using learning data based on various information to perform processing to predict and analyze the necessity and priority of snow removal. This machine learning model can include features such as past snow removal records, the occurrence of bad roads, and traffic, weather, and traffic information. In addition, the analysis uses image data and measurement data contained in each piece of information (date and time, address, latitude and longitude, weather data, sensing data, passing speed, average speed, delay time, acceleration, vibration, vehicle data, probe data, etc.), and can complement or weight and correct the acquired information based on the prediction results. The machine learning method may be any of supervised learning, reinforcement learning, deep learning, and the like. Furthermore, the process may include dynamically adjusting the snow removal priority of each management unit based on predictions of bad road conditions or road obstructions in the near future (for example, from a few hours to the next day). At this time, the priority score for the management unit may be corrected or reevaluated and updated according to the prediction result. The analysis unit 620 may also be configured to use a machine learning model to execute a process of analyzing and evaluating the priority of snow removal for each management unit based on the acquired information.

[0028] The decision unit 630 operating in the snow removal decision support system 600 makes an integrated and comprehensive decision on the necessity of snow removal based on some or all of the analysis results 690 of the various information (road surface information 640, traffic information 650, road space information 660, weather information 670, vehicle driving information 680, road service information, and snow removal information) analyzed by the analysis unit 620, and stores the decision result 695. The stored determination results 695 may be visualized on a map, displayed as a list, or displayed on a real-time monitoring screen such as a dashboard. Furthermore, the decision unit 630 may be equipped with an analysis function, a judgment function, and a decision function using AI (artificial intelligence). Furthermore, snow removal decision support system 600 may include an information providing unit that provides to the outside some or all of the analysis results 690, the judgment results 695, and the information acquired by information acquisition unit 610 (road surface information, traffic information, road space information, weather information, vehicle driving information, road service information, snow removal information), etc. The inclusion of an information providing unit has the effect of making information related to snow removal widely known.

[0029] 11 is a flowchart showing an example of the flow of the snow removal decision support system 600. The information acquisition unit 610 periodically acquires information on road surface conditions (e.g., every few minutes) from the road surface condition providing server 100 (S10). The information acquisition unit 610 periodically acquires information on traffic conditions (e.g., every few minutes) from the traffic condition providing server 200 (S11). The information acquisition unit 610 periodically acquires information on road space conditions (e.g., every few minutes) from the road space condition providing server 300 (S12). The information acquisition unit 610 periodically acquires information on weather conditions (e.g., every few minutes) from the weather condition providing server 400 (S13). The information acquisition unit 610 periodically acquires information on vehicle driving conditions (e.g., every few minutes) from the vehicle driving condition providing server 500 (S14). The analysis unit 620 then extracts, from the road surface information 640, locations where road width has been significantly reduced due to snow accumulation (S15). The analysis unit 620 extracts, from the traffic information 650, sections where congestion is occurring continuously (S16). The analysis unit 620 extracts, from the road space information 660, dangerous locations where snow banks are high (for example, approximately 1 meter or more) and visibility is reduced, etc. (S17). The analysis unit 620 extracts, from the weather information 670, areas where the amount of snowfall since the start of snowfall has been 10 cm or more (S18). The analysis unit 620 extracts, from the vehicle travel information 680, sections where bus delays are continuing for 30 minutes or more (S19). Next, based on the results of the above analysis, the decision unit 630 comprehensively determines the necessity of snow removal measures, and makes a decision to execute the measures as necessary (S20). 11 shows an example of a typical processing flow, and is not limited to this. In this embodiment, various information such as road service information and snow removal information (not shown) are also acquired by the information acquisition unit 610 and can be subject to analysis processing by the analysis unit 620. The results of these analyses are configured to be used by the determination unit 630 to determine snow removal and set priorities. Furthermore, it may also be equipped with information from road users and residents (disaster information, damage information, relief information, restoration information, requests, inquiries, complaints regarding snow removal, etc.) using an app-based consultation reception system or SNS (Social Networking Service), information from government (police, fire department, Self-Defense Forces, etc.), infrastructure operators (telecommunications, electricity, gas, water, sewerage, etc.), transportation operators (railways, buses, etc.), snow removal and removal companies, construction and civil engineering companies (including construction industry associations), garbage collection companies, delivery companies, tourism operators (inns, hotels, tourist facilities, roadside stations, etc.), designated public institutions (Disaster Countermeasures Basic Act) (disaster information, damage information, relief information, restoration information, requests, inquiries, complaints regarding snow removal, etc.), and information from the government's Emergency Disaster Response Headquarters and Emergency Disaster Response Headquarters.

[0030] 12 is a diagram showing an example of the determination criteria used by the determination unit 630. The determination unit 630 can determine the necessity of snow removal measures based on the following triggers: heavy snowfall of 10 cm / h or more (element 1) 631; snow accumulation causing a decrease in road width and bus delays of 30 minutes or more (element 2) 632; fine weather causing snow to melt and making the snow-covered road surface more uneven, resulting in worsening traffic congestion (element 3) 633; a heavy snow warning being issued, causing cars to skid and get stuck in the snow, resulting in congestion (element 4) 634; frequent tire lock on a frozen road surface at -10°C, causing self-inflicted accidents and resulting in congestion (element 5) 635; etc. In addition, some or all of the judgment result 695 determined by the decision unit 630, the analysis result 690 derived by the analysis unit 620, and the various information (road surface information, traffic information, road space information, weather information, vehicle driving information, road service information, snow removal information) acquired by the information acquisition unit 610 can be sent via an information provision unit, etc., to snow removal companies via email, data provided to a GIS (Geographic Information System) for road managers, linked to an autonomous driving system or MaaS (Mobility as a Service), information provided to government agencies (police, fire department, Self-Defense Forces, etc.) and the media, and information disclosure functions for road users and residents (websites, smartphone apps, etc.). Note that this information provision does not necessarily have to go through the information provision unit, allowing for flexibility in configuration. Examples of information disclosure functions for road users and residents include providing the following information: unevenness of snow-covered road surfaces, thickness of packed snow on the road surface, traffic congestion, camera images, height of snow banks around routes and intersections, future snowfall forecasts and snow depths, bus route delay information, stuck vehicle locations, snow removal orders and implementation status, snow removal orders and implementation status, and patrol results. This snow removal decision support system is also characterized by being configured to be able to transmit this information, analysis results, decision results, snow removal implementation plans, etc. to mobile terminal devices (such as mobile phones, smartphones, tablets, laptops, and game consoles) or fixed terminal devices (such as desktop computers, smart TVs, set-top boxes, digital signage, kiosks, car navigation systems, and car display audio systems). 12 shows an example of a typical determination criterion, and the determination unit 630 is not limited to this example. In this embodiment, various information such as road service information and snow removal information (not shown) is also used as information for the determination by the determination unit 630.

[0031] The snow removal decision support system 600 can be effective with one or more of the following factors: road surface conditions, traffic conditions, road space conditions, weather conditions, vehicle driving conditions, road service conditions, and snow removal conditions. Furthermore, by using two or more factors, a synergistic effect can be obtained. The snow removal decision support system 600 may be configured to continuously acquire and analyze various information, and dynamically reevaluate and reconfigure it as needed based on the analysis results and the latest information. This allows for flexible responses that can quickly adapt to changes in the field.

[0032] <Hardware configuration> FIG. 13 illustrates an example of the hardware configuration of a terminal device TM, a fixed camera CAM, a road surface condition providing server 100, a traffic condition providing server 200, a road space condition providing server 300, a weather condition providing server 400, a vehicle driving condition providing server 500, and a snow removal decision support system 600. This diagram illustrates an example in which the terminal device TM is a mobile phone such as a smartphone. The terminal device TM includes, for example, a CPU 701, a RAM 702, a ROM 703, a secondary storage device 704 such as a flash memory, a touch panel 705, and a wireless communication module 706, all interconnected via an internal bus or a dedicated communication line. Application programs such as a road patrol app are downloaded via a network NW and stored in the secondary storage device 704. The fixed camera CAM includes, for example, a CPU 901, a RAM 902, a ROM 903, a secondary storage device 904 such as a flash memory, a lens / image sensor 905, and a communication device 906, all interconnected via an internal bus or a dedicated communication line. Application programs such as a camera application are downloaded via the network NW and stored in the secondary storage device 904 . Each server includes, for example, a NIC 801, a CPU 802, a RAM 803, a ROM 804, a secondary storage device 805 such as a flash memory or a HDD, and a drive device 806, all interconnected via an internal bus or a dedicated communication line. A portable storage medium such as an optical disk is attached to the drive device 806. A program stored in the secondary storage device 805 or the portable storage medium attached to the drive device 806 is loaded into the RAM 803 by a DMA controller (not shown) or the like, and executed by the CPU 802, thereby realizing the functional units of each server. Road surface information 640, traffic information 650, road space information 660, weather information 670, vehicle driving information 680, analysis results 690, and judgment results 695 are stored in the secondary storage device 805. Note that each server may be implemented using cloud computing. Furthermore, the snow removal decision support system 600 may be configured to be able to communicate with each corresponding server in order to acquire and process road service information, snow removal information, and the like. Furthermore, the snow removal decision support system 600 is configured in a computing environment (cloud or on-premise) equipped with the memory, processor and storage area necessary for the processing of each component, such as the information acquisition unit 610, analysis unit 620 and decision unit 630. The system may also be configured with computing resources including a GPU (Graphics Processing Unit), a TPU (Tensor Processing Unit) or an AI accelerator to execute the AI (Artificial Intelligence) models used in each component. Furthermore, this configuration is an example of the hardware configuration shown in FIG. 13, and other configurations (edge device configuration, IoT node configuration, etc.) may be used depending on the embodiment.

[0033] The above describes the form for carrying out the present invention using an embodiment, but the present invention is not limited to such an embodiment, and various modifications and substitutions can be made within the scope that does not deviate from the gist of the present invention. Although the embodiments of the present invention have been described above with reference to the drawings, the present invention is not limited to these embodiments or the illustrated configurations. For example, aspects including configurations described in this specification, such as information on road service status or information on snow removal status, which are not illustrated, are also included within the technical scope of the present invention. Therefore, various modifications, alterations, and substitutions can be made to the present invention without departing from the spirit and scope of the present invention. [Explanation of symbols]

[0034] 100: Road surface condition server 200: Traffic information server 300: Road space situation providing server 400: Weather information server 500: Vehicle driving status server 600: Snow removal decision support system 610: Information acquisition department 620: Analysis Department 630: Decision Section 640: Road surface information 650: Traffic information 660: Road spatial information 670: Weather information 680: Vehicle driving information 690:Analysis results 695: Judgment result

Claims

1. Information regarding road conditions in a snowy environment, Unevenness of snow-covered road surface, thickness of packed snow on the road surface, quality of snow on the road surface, accumulated snow on the road surface, melting snow on snow-covered road surface, frozen road surface, bowl-shaped deformation of snow-covered road surface, or ruts on snow-covered road surface, an information acquisition unit that acquires at least one piece of information; Dividing the road into a plurality of management units each consisting of a route unit or a construction section unit based on the information acquired by the information acquisition unit; Calculating the percentage of bad road sections in each management unit that have an evaluation value equal to or higher than a predetermined standard; an analysis unit that executes a process of quantitatively scoring the priority of snow removal for each management unit based on a plurality of predetermined graded evaluation criteria in accordance with the proportion of the bad road sections in the management unit; A snow removal decision support system comprising:

2. The snow removal decision support system according to claim 1, The snow removal decision support system is characterized in that the analysis unit evaluates the reliability of the information regarding the bad road sections in each management unit based on the proportion of patrol driving for that management unit, and if the proportion is less than a predetermined proportion, includes processing to exclude or correct the information used to evaluate the management unit.

3. The snow removal decision support system according to claim 1, The information acquisition unit or the analysis unit acquires or refers to route information corresponding to trunk roads and community roads from a geographic information system owned by a road administrator, The analysis unit includes a configuration for integrating multiple sections of a trunk road that are managed with branch numbers on the geographic information system based on a common route number or route name and processing them as a route unit, and also for processing them as a branch number unit as necessary; For community roads, a process is included in which a plurality of routes are grouped together as a construction section unit, and the proportion of the bad road sections is evaluated using the route unit or the construction section unit as a management unit; Furthermore, the snow removal decision support system is characterized by including a configuration that allows priority evaluation for residential roads on a route or branch number basis as needed, in addition to processing on a construction section basis.

4. The snow removal decision support system according to claim 1, The information acquisition unit acquires at least one of traffic information including traffic congestion information, weather information, vehicle travel information including bus delay information, and road service information including the occurrence of stranded vehicles, in addition to information regarding bad roads, A snow removal decision-making support system characterized in that the analysis unit includes a process for rule-based correction or weighted evaluation of the snow removal priority of each management unit based on information regarding the rough road and information acquired by the information acquisition unit.

5. The snow removal decision support system according to claim 1, The analysis unit uses a model that has been machine-learned based on learning data including information about bad roads and information about snow removal, Furthermore, at least one of traffic information, weather information, vehicle driving information, and road service information is added, A snow removal decision support system characterized by including a process of analyzing and evaluating the snow removal priority of each management unit using a learning model.

6. The snow removal decision support system according to claim 5, The analysis unit uses the machine-learned model based on past learning data including the information about the rough road and the snow removal information, A snow removal decision support system characterized by including a process for predicting the possibility of snow removal being required in the near future and adjusting the snow removal priority of each management unit based on the prediction results.

7. A snow removal decision support system according to any one of claims 1, 4, or 5, As a result of the quantitative analysis of the snow removal priority by the analysis unit, at least one of information on bad roads, traffic information, weather information, vehicle driving information, road service information, and snow removal information is A snow removal decision support system characterized by being able to transmit and display information on a mobile terminal device or a fixed terminal device.

8. A program for causing a computer to function as the snow removal decision support system according to claim 1, Furthermore, the program is characterized by being capable of executing at least one or more of the following functions: (1) A function for evaluating the reliability of information regarding bad road sections in each management unit based on the patrol driving ratio for that management unit, and excluding or correcting the information if the ratio is less than a predetermined ratio; (2) A function to acquire or refer to route information for trunk roads and community roads using a geographic information system, and to integrate trunk roads based on a common route number or route name and process them as a route unit, while processing community roads as a construction section unit; (3) A function of acquiring at least one of traffic information, weather information, vehicle driving information, and road service information, and correcting or weighting and evaluating the priority of snow removal for each management unit using the acquired information; (4) A function of analyzing and evaluating the priority of snow removal for each management unit using a machine-learned model based on learning data including information on bad roads and snow removal information; (5) A function of predicting the need for future snow removal using a learning model and adjusting the priority of snow removal for each management unit based on the prediction results; (6) A function of transmitting at least one of the information regarding the bad road, the traffic information, the weather information, the vehicle driving information, the road service information, or the snow removal information to a mobile terminal device or a fixed terminal device as a result of quantitatively analyzing the priority of the snow removal.

9. A road management method using a computer, comprising: The computer communicates with the network via As information on road surface conditions under snowy conditions, at least one of the following information is acquired: unevenness of the snow-covered road surface, thickness of packed snow on the road surface, quality of snow on the road surface, accumulated snow on the road surface, melting snow on the snow-covered road surface, freezing of the road surface, bowl-shaped deformation of the snow-covered road surface, or rutting on the snow-covered road surface; Based on the acquired information, the road is divided into a plurality of management units each consisting of a route unit or a construction section unit; Calculating the percentage of bad road sections having an evaluation value equal to or higher than a predetermined standard in each management unit; A road management method characterized by carrying out a process of quantitatively scoring the priority of snow removal for each management unit based on a plurality of predetermined, tiered evaluation criteria, depending on the proportion of bad road sections in the management unit.

10. 10. The road management method according to claim 9, the computer evaluates the reliability of the information regarding the bad road section in each management unit based on a ratio of patrol driving for the management unit; A road management method characterized in that, if the ratio is less than a predetermined ratio, a process is performed to exclude or correct the information used to evaluate the management unit.

11. 10. The road management method according to claim 9, The computer Route information corresponding to main roads and community roads is obtained from or referenced by the geographic information system owned by the road administrator, For trunk roads, multiple sections managed with branch numbers on the geographic information system are integrated based on a common route number or route name and processed as a route unit, and can also be processed by branch number unit as necessary. For community roads, a plurality of routes are processed as a construction section unit that is a surface grouping, and a process is executed to evaluate the proportion of the bad road sections using the route unit or the construction section unit as a management unit; Furthermore, the road management method is characterized in that, for community roads, in addition to processing on a construction section basis, processing is performed that enables priority evaluation on a route or branch number basis as necessary.

12. 10. The road management method according to claim 9, The computer In addition to the information about the bad road, at least one of traffic information including traffic congestion information, weather information, vehicle driving information including bus delay information, or road service information including the occurrence of stranded vehicles is acquired, A road management method characterized by performing a process of correcting or weighting the snow removal priority of each management unit on a rule-based basis based on the information regarding the bad road and the acquired information.

13. 10. The road management method according to claim 9, The computer uses a machine-learned model based on learning data including information on rough roads and snow removal information, Furthermore, at least one of traffic information, weather information, vehicle driving information, and road service information is added, A road management method characterized by carrying out a process of analyzing and evaluating the snow removal priority of each management unit using a learning model.

14. 14. The road management method according to claim 13, The computer uses the machine-learned model based on past learning data including the information about the rough road and the snow removal information, A road management method comprising: predicting the possibility that snow removal will be required in the near future; and performing a process to adjust the snow removal priority of each management unit based on the prediction results.

15. A road management method according to any one of claims 9, 12 or 13, comprising: The computer communicates with the network via As a result of quantitatively analyzing the priority of the snow removal, at least one of information on bad roads, traffic information, weather information, vehicle driving information, road service information, and snow removal information is selected. A road management method characterized in that the road management data can be transmitted to a mobile terminal device or a fixed terminal device and displayed.

Images