JP2017215759A - Accident forecast system and accident forecast method - Google Patents

Abstract

PROBLEM TO BE SOLVED: To more accurately forecast an occurrence rate of accidents on a road.SOLUTION: In an accident forecast system, an accident forecast table creation processing part creates an accident forecast table indicating an accident occurrence rate for each traffic condition by learning an accident occurrence pattern for a specific section of a road with at least past traffic data and past accident data on the basis of a specific learning algorithm. A traffic data acquisition processing part acquires current traffic data from a sensor which measures a traffic condition for the section. A probe information acquisition processing part acquires current probe information on a vehicle traveling through the section from an outside probe information system. An accident forecast processing part forecasts an accident occurrence rate by using the current traffic data, the current probe information and the accident forecast table for the section.SELECTED DRAWING: Figure 1

Description

  Embodiments described herein relate generally to an accident prediction system and an accident prediction method.

  Regarding traffic accidents that have a particularly large impact on the cause of traffic congestion on the road, traffic controllers set up on the road based on various sensors provided on the roadside and video information from CCTV cameras, etc. The user is notified by displaying on the displayed display board or the like. Recently, the traffic accident information notification has been advanced one step, and learning is performed using traffic data measured in the past (including traffic data measured at the time of the traffic accident) at each location on the road. Study on technology for forecasting accidents is underway.

JP 2010-39992 A JP 2009-223460 A

  However, the accident prediction of the prior art cannot be said to sufficiently reflect the latest traffic situation, and there is room for improvement in accuracy.

  The accident prediction system in the embodiment includes an accident prediction table creation processing unit, a traffic data acquisition processing unit, a probe information acquisition processing unit, and an accident prediction processing unit. The accident forecast table creation processing unit learns an accident occurrence pattern based on a predetermined learning algorithm using at least past traffic data and past accident data for a predetermined section of a road, Create an accident forecast table that represents the degree of accident occurrence. The traffic data acquisition processing unit acquires current traffic data from a sensor that measures traffic conditions for the section. The probe information acquisition processing unit acquires current probe information of a vehicle traveling in the section from an external probe information system. The accident prediction processing unit predicts the degree of occurrence of the accident using the current traffic data, the current probe information, and the accident prediction table for the section.

FIG. 1 is a block diagram showing an example of the configuration of the accident prediction system in the first embodiment. FIG. 2 is an explanatory diagram schematically illustrating an example of a relationship between a road section and a road sensor unit in the first embodiment. FIG. 3 is a flowchart showing an example of probe information acquisition processing in the first embodiment. FIG. 4 is a diagram showing an example of a tabulation result of probe information in the first embodiment. FIG. 5 is a flowchart illustrating an example of the flow of the accident forecast table creation process in the first embodiment. FIG. 6 is a diagram showing an example of a general configuration of the self-organizing map used in the first embodiment. FIG. 7 is a diagram showing an example of a more specific configuration of the self-organizing map used in the first embodiment. FIG. 8 is a diagram showing an example of the accident prediction table in the first embodiment. FIG. 9 is a flowchart showing an example of the flow of the accident prediction process in the first embodiment. FIG. 10 is an explanatory diagram when the accident prediction process is performed using the self-organizing map of FIG. FIG. 11 is a block diagram showing an example of the configuration of the accident prediction system in the second embodiment. FIG. 12 is a schematic diagram for explaining the outline of the accident prediction process in the second embodiment. FIG. 13 is a diagram illustrating an example of an accident occurrence degree adjustment table according to the second embodiment. FIG. 14 is a flowchart showing an example of the flow of accident prediction processing in the second embodiment. FIG. 15 is a block diagram showing an example of the configuration of the accident prediction system in the third embodiment. FIG. 16 is a schematic diagram for explaining the outline of the accident prediction process in the third embodiment. FIG. 17 is a diagram illustrating an example of an input adjustment table in the third embodiment. FIG. 18 is a flowchart showing an example of the flow of accident prediction processing in the third embodiment.

  Hereinafter, embodiments of the present invention will be described with reference to the drawings. In the following, “forecast” refers to traffic accidents (hereinafter also simply referred to as “accidents”) based on past traffic data (including traffic data at the time of the accident) at each point on the road. It includes the meaning of calculating / predicting the risk of occurrence and reporting it as an accident forecast, but without simply reporting the prediction result, only for “predicting” the likelihood of an accident occurring at each point. It also includes meaning. Further, the “route” includes the meaning of the route in the road law, but is not limited thereto, and includes the meaning of a road in a management unit.

(First embodiment)
First, the configuration of the accident prediction system 1 in the first embodiment will be described with reference to FIGS. 1 and 2. FIG. 1 is a block diagram illustrating an example of a configuration of an accident prediction system 1 according to the first embodiment. FIG. 2 is an explanatory diagram schematically illustrating an example of a relationship between a road section and a road sensor unit in the first embodiment.

The accident forecast system 1 shown in FIG. 1 includes sections A-1, A-2,..., A- (n-1), An, and section B-1 of the route B shown in FIG. B-2, ..., B- (m-1), road sensor units RS _A-1 , RS _A-2 , ..., RS _{A- (n-1)} , corresponding to B-m, RS _A-n , RS _B-1 , RS _B-2 ,..., RS _{B- (m−1)} , RS _B-m (hereinafter referred to as “RS” unless otherwise distinguished). It is a system that predicts the degree of accident occurrence that indicates the likelihood of traffic accidents in each section using traffic data.

  The road sensor unit RS includes a sensor (sensing device) that measures a traffic situation (such as a traveling vehicle) for a corresponding section. This sensor is composed of, for example, a loop coil installed under the road surface, a camera that monitors the road surface from above, an ultrasonic sensor, or some combination thereof.

  The road sensor unit RS includes a traffic data processing unit. Specifically, the traffic data processing unit, based on traffic data measured by the sensor, traffic volume [vehicles / h], average speed [km / h], vehicle density [vehicles / km] of vehicles traveling on the road. ], Occupancy (occupancy) [%], etc. are calculated, and the calculation result is transmitted to the road traffic control device 2. This calculation and transmission are executed in units of time such as 1 minute or 5 minutes. Alternatively, the road sensor unit RS may transmit only the measurement result of the sensor to the traffic data acquisition processing unit 211 of the road traffic control device 2, and the traffic data acquisition processing unit 211 may calculate the traffic volume and the like.

  Here, in the first embodiment, the accident prediction system 1 includes a road traffic control device 2 and an accident prediction table creation device 3. The road traffic control device 2 and the accident forecast table creation device 3 acquire probe information from the external probe information system 4. Here, the probe information refers to information such as the position, speed, acceleration, steering wheel operation, brake operation, various lamp states, and wiper operations transmitted by the probe car. The probe car refers to a vehicle having such a function of transmitting information. The road traffic control device 2 is, for example, a computer system generally called a road traffic control system. The road traffic control device 2 is shown as a single computer device in FIG. 1 for the sake of brevity, but may be realized by a plurality of computer devices.

  The road traffic control device 2 includes a processing unit 21, a storage unit 22, a display unit 23, and an input unit 24. In addition, although the road traffic control apparatus 2 also has a communication part for communication with an external apparatus, in order to simplify description, illustration and description are abbreviate | omitted.

  The processing unit 21 controls the overall operation of the road traffic control device 2 and realizes various functions of the road traffic control device 2. The processing unit 21 includes, for example, a central processing unit (CPU), a read only memory (ROM), and a random access memory (RAM). The CPU comprehensively controls the operation of the road traffic control device 2. The ROM is a storage medium that stores various programs and data. The RAM is a storage medium for temporarily storing various programs and rewriting various data. The CPU executes a program stored in the ROM, the storage unit 22 or the like using the RAM as a work area (working area). The processing unit 21 includes a traffic data acquisition processing unit 211, a probe information acquisition processing unit 212, a reception processing unit 213, an accident forecast processing unit 214, a display control unit 215, and a notification unit 216.

  The traffic data acquisition processing unit 211 periodically acquires measured traffic data from each road sensor unit RS installed for each road section. Then, the traffic data acquisition processing unit 211 transmits the acquired traffic data so as to be accumulated as the current traffic data in the current database 221 of the storage unit 22, and the past is sent to the storage unit 32 of the accident forecast table creation device 3. Send it to accumulate as traffic data. In addition, when there are a plurality of road lanes and the road sensor unit RS is set corresponding to each lane, the traffic data acquisition processing unit 211 may integrate the traffic data of each lane, for example. Further, in the present embodiment, for example, traffic data of the latest several minutes is referred to as current traffic data, and past long-term traffic data including current traffic data is referred to as past traffic data. The past traffic data also includes traffic data measured when an accident occurs.

  The probe information acquisition processing unit 212 acquires vehicle probe information from the probe information system 4 via a communication network. In the present embodiment, for example, probe information of the latest few minutes may be referred to as current probe information, and long-term probe information including the current probe information may be referred to as past probe information. However, the current probe information used for accident prediction is not limited to the latest few minutes, but may be history information of probe information of several tens of minutes to several hours.

  The probe information includes, for example, vehicle position, speed, acceleration, steering wheel operation, brake operation, various lamp states, and wiper operation information. In addition, the probe information acquisition processing unit 212 aggregates data necessary for accident prediction based on the probe information. For example, the probe information acquisition processing unit 212 determines the staying section of the vehicle from the position information, and performs the following calculations (101) to (105) for each section.

(101) Calculation of the number and ratio of vehicles that performed wiper operation (102) Calculation of the number and ratio of vehicles that performed rapid acceleration (103) Calculation of the number and ratio of vehicles that performed braking (104) Hazard lamp Calculation of number and ratio of vehicles that have been lit (105) Calculation of number and ratio of vehicles that have lit headlamps

  Hereinafter, the probe information acquisition process will be described more specifically. FIG. 3 is a flowchart showing an example of probe information acquisition processing in the first embodiment. First, the probe information acquisition processing unit 212 acquires probe information from the probe information system 4 (step S1).

  Next, the probe information acquisition processing unit 212 extracts one probe information from the acquired probe information (step S2).

  Next, the probe information acquisition processing unit 212 analyzes the position information of the extracted probe information and determines the stay section (step S3).

  Next, the probe information acquisition processing unit 212 determines the state of the vehicle (for example, wiper operation, rapid acceleration, brake operation, hazard lamp lighting, headlamp lighting, etc.) (step S4).

  Next, the probe information acquisition processing unit 212 determines whether or not the processing of all vehicles has been completed for the acquired probe information (step S5). If Yes, the process proceeds to step S6. If No, the process proceeds to step S2. Return.

  In step S6, the probe information acquisition processing unit 212 performs an aggregation process for each section. Next, the probe information acquisition processing unit 212 outputs (accumulates) the aggregation results to the probe information database 223 (step S7). FIG. 4 is a diagram showing an example of a tabulation result of probe information in the first embodiment.

  FIG. 4A shows the ratio of vehicles that have performed wiper operation, rapid acceleration, brake operation, hazard lamp lighting, and headlamp lighting for each section of route A. FIG. For example, in the section A-1, the ratio of the vehicle performing the wiper operation is 0.53 (53%). Similarly, FIG. 4B shows the ratio of vehicles that have performed wiper operation, sudden acceleration, brake operation, hazard lamp lighting, and headlamp lighting for each section of route B. FIG.

  Returning to FIG. 1, the reception processing unit 213 stores the accident prediction table (details will be described later) received from the transmission processing unit 313 of the accident prediction table creation device 3 in the accident prediction table database 222 of the storage unit 22. . When there are a plurality of accident prediction tables, the reception processing unit 213 stores each accident prediction table in the accident prediction table database 222 together with the identification information.

  For each road section, the accident forecast processing unit 214 presents current traffic data (for example, traffic volume, occupation rate, average speed), current probe information (for example, wiper operation, rapid acceleration, brake operation, hazard lamp lighting, headlight And the accident occurrence degree is predicted using the accident prediction table (details will be described later).

  The display control unit 215 performs control so that the accident occurrence degree calculated by the accident forecast processing unit 214 is displayed on the display unit 23 as an accident forecast. For example, it is preferable to notify the controller of the section where the accident occurrence degree is high, such that an accident is likely to occur by lighting up an alarm lamp of the display unit 23. In the road traffic control device 2, when the alarm lamp is turned on as described above, for example, an alarm sound may be generated by an audio output means (not shown).

  The notification unit 216 notifies the vehicle 5 having the probe information transmission function of the accident occurrence degree calculated by the accident prediction processing unit 214. This notification may or may not pass through the probe information system 4.

  The storage unit 22 is a storage device such as an HDD (Hard Disk Drive) or an SSD (Solid State Drive). The storage unit 22 stores a current database 221, an accident prediction table database 222, and a probe information database 223.

  The current database 221 stores traffic data (current traffic data) for the last several minutes, for example, acquired by the traffic data acquisition processing unit 211. Further, in the current database 221, the traffic data acquired by the traffic data acquisition processing unit 211 is accumulated and road characteristic data representing the characteristics of the target road (for example, road length, sensor installation position, peripheral information of each measurement point, Stores information managed in road traffic control such as toll gate location), measure information, accident information, construction information, speed limit information, etc. The road characteristic data representing the characteristic of the target road may be input at the time of system construction in advance, but may be additionally written and corrected by a controller or the like. In addition, information managed in road traffic control such as measure information, accident information, construction information, and speed limit information may be manually input by a user of the road traffic control device 2 (such as a controller). The current traffic data in the current database 221 is used when the accident prediction processing unit 214 performs an accident prediction. At this time, when the accident prediction is performed, the road characteristic data stored in the current database 221 is referred to and the current traffic data corresponding to the corresponding part of the accident prediction is stored in a data set (for example, traffic volume [unit / h]). Occupancy rate [%] (or vehicle density [vehicle / km]) and average speed [km / h] set).

  The accident forecast table database 222 stores one or more accident forecast tables (details will be described later).

  The probe information database 223 sequentially stores the probe information collected by the probe information acquisition processing unit 212.

  The display unit 23 displays, for example, an accident forecast result by the accident forecast processing unit 214. The display unit 23 is realized by, for example, a liquid crystal display device (LCD (Liquid Crystal Display)), an organic EL (Electro-Luminescence) display device, or the like.

  The input unit 24 receives a user operation on the road traffic control device 2. The input unit 24 is an input device such as a keyboard and a mouse.

  The accident forecast table creation device 3 is a computer device for creating an accident forecast table. The accident forecast table creation device 3 includes a processing unit 31, a storage unit 32, a display unit 33, and an input unit 34. The accident forecast table creation device 3 also has a communication unit for communication with an external device, but illustration and description are omitted for the sake of brevity.

  The processing unit 31 controls the overall operation of the accident forecast table creation device 3 and realizes various functions of the accident forecast table creation device 3. The processing unit 31 includes, for example, a CPU, a ROM, and a RAM. The CPU comprehensively controls the operation of the accident forecast table creation device 3. The ROM is a storage medium that stores various programs and data. The RAM is a storage medium for temporarily storing various programs and rewriting various data. The CPU executes a program stored in the ROM, the storage unit 32, or the like using the RAM as a work area (working area). The processing unit 31 includes a probe information acquisition processing unit 311, an accident forecast table creation processing unit 312, and a transmission processing unit 313.

  Since the function of the probe information acquisition processing unit 311 is the same as the function of the probe information acquisition processing unit 212, description thereof is omitted. The probe information acquisition processing unit 311 accumulates the collected probe information in the probe information database 322 of the storage unit 32.

  The accident forecast table creation processing unit 312 uses the past traffic data in the past database 321, past accident data, and past probe information in the probe information database 322 to perform predetermined learning for roads divided into a plurality of sections. Accident occurrence patterns are learned based on algorithms (for example, learning algorithms using self-organizing maps), and traffic conditions (traffic volume, occupancy rate, average speed, wiper operation, rapid acceleration, brake operation, hazard lamp lighting, previous Create an accident forecast table that shows the degree of accident occurrence for each lighting. Here, a self-organizing map is a type of neural network that is applied to important fields in the real world, such as process analysis, control, search systems, and information analysis for management. Is a clustering algorithm without prior knowledge such as a teacher signal (an output considered to be ideal for input data). Specific contents of this self-organizing map will be described later.

  In addition, the accident forecast table creation processing unit 312 obtains past traffic data, past accident data, and past probe information acquired at a predetermined timing or when a user inputs an instruction. Use to update the accident forecast table. The predetermined timing is, for example, the timing at which past traffic data, past accident data, and past probe information for the most recent year are accumulated every year. At this time, an accident prediction table is created using the data for one year accumulated in the accident forecast table creation device 3, and the accident prediction table is transmitted to the road traffic control device 2 for accident prediction. The accident forecast table in the table database 222 is updated. In addition, when there is an instruction input by the user, for example, when a flow of vehicles on the target road changes due to a large road around the target road, for example, about several months thereafter, etc. When a sufficient amount of past traffic data, past accident data, and past probe information are accumulated, the user uses the input unit 34 of the accident forecast table creation device 3 to input instructions for updating the accident forecast table. This is the case.

  The transmission processing unit 313 sends the accident forecast table (detailed later) created by the accident forecast table creation processing unit 312 (detailed later) to the reception processing unit 213 of the processing unit 21 of the road traffic control device 2. Send.

  The storage unit 32 is a storage device such as an HDD or an SSD. The storage unit 32 stores a past database 321 and a probe information database 322. The past database 321 stores past traffic data and past accident data. The past traffic data is sequentially accumulated by the traffic data received from the traffic data acquisition processing unit 211 of the road traffic control device 2.

  The past accident data is data of past accidents that occurred on the target road. The past accident data may be stored in the past database 321 of the storage unit 32 by inputting the past accident data, for example, using the input unit 34 of the accident forecast table creation device 3 while looking at the accident report or the like. . Specifically, the past accident data includes, for example, an accident occurrence point, an accident occurrence date and time, an accident type, and the like as information on the accident. The past accident data is preferably accident information over the past several years. The past accident data is input by the user through the input unit 34 of the accident prediction table creation device 3 or by the user through the input unit 24 of the road traffic control device 2 and is input from the road traffic control device 2 to the accident prediction table. You may make it store in the past database 321 of the memory | storage part 32 by transmitting to the production apparatus 3. FIG. Alternatively, past accident data in another computer device is stored in the past database 321 of the storage unit 32 of the accident forecast table creation device 3 via an information storage medium such as a DVD (Digital Versatile Disk) or a USB (Universal Serial Bus) memory. You may make it store in.

  The probe information database 322 sequentially stores the probe information collected by the probe information acquisition processing unit 311.

  The display unit 33 displays various screens. The display unit 33 is realized by, for example, a liquid crystal display device (LCD), an organic EL display device, or the like.

  The input unit 34 receives a user operation on the accident forecast table creation device 3. The input unit 34 is an input device such as a keyboard and a mouse.

  Next, the operation of the accident prediction system 1 in the first embodiment will be described. First, the accident forecast table creation processing in the first embodiment will be described with reference to FIG. 5 (refer to other figures as appropriate). FIG. 5 is a flowchart illustrating an example of the flow of the accident forecast table creation process in the first embodiment.

  As shown in FIG. 5, the accident forecast table creation processing unit 312 first reads past traffic data and past accident data from the past database 321 in step S11.

  Next, the accident forecast table creation processing unit 312 reads past probe information from the probe information database 322 in step S12.

  Next, in step S13, the accident forecast table creation processing unit 312 determines past traffic data, past probe information, and the likelihood of an accident (accident) based on past traffic data, past accident data, and past probe information. Learning the correlation with the incidence). As a learning method, for example, the following method using a self-organizing map is used.

FIG. 6 is a diagram showing an example of a general configuration of the self-organizing map used in the first embodiment. As shown in FIG. 6, the self-organizing map is a two-layered neural network having an input layer and a competitive layer (output layer). Input layer, data x ₁ to be analyzed, ..., x _i, ..., represented as a plane having the same number of units and x _n. Here, the data x ₁ to be analyzed, ..., x _i, ..., a combination of x _n, referred to as an input vector. Further, the competitive layer is represented as a plane having a plurality of units 1,..., J,. Each unit of the input layer and each unit of the competitive layer are related by a weight vector w _j = (w _j1 ,..., W _ji ,..., W _jn ) having the same dimension as the input vector.

  FIG. 7 is a diagram showing an example of a more specific configuration of the self-organizing map used in the first embodiment. As shown in FIG. 7, the past traffic data read from the past database 321 and the past probe information read from the probe information database 322 are used as input vectors to be learned.

  In the self-organizing map of FIG. 7, first, (1) a process of determining a winner unit and updating the weight vector of the winner unit is executed. And (2) the process which updates the weight vector of the vicinity unit located in the vicinity of a winner unit is performed. The winner unit is one unit on the competitive layer that is associated with the input vector by a weight vector that is most similar to the input vector. In addition, the weight vector is updated using a mathematical formula that takes into account the number of learnings and a predetermined learning coefficient. Note that the method of determining the weight vector most similar to the input vector and the details of the mathematical formula used for updating the weight vector are disclosed in, for example, Japanese Patent Application Laid-Open No. 2014-35639. Omitted.

  Moreover, the accident occurrence degree set corresponding to the past traffic data and past probe information used as the input vector is input. The accident occurrence degree is a value indicating the likelihood of occurrence of an accident set corresponding to the input vector. When each element of the input vector is data at the time of occurrence of an accident, the accident occurrence degree is set to “1” (or “100”), for example. Further, when each element of the input vector is data when there is no accident, the accident occurrence degree is set to “0”, for example. When each element of the input vector is data immediately before the occurrence of the accident, the accident occurrence degree is set to a value smaller than the accident occurrence degree (“1” (or “100”)) at the time of the accident occurrence.

  In the first embodiment, after the above processes (1) and (2) are executed, (3) the accident occurrence distribution corresponding to the winning units and neighboring units on the competitive layer with the inputted accident occurrence degrees. The process of updating the value of the unit on the layer is executed. Specifically, the value of the unit corresponding to the winner unit is updated by the input accident occurrence degree, and the value of the unit corresponding to the neighboring unit is updated by a value smaller than the input accident occurrence degree. Details of this update processing are also disclosed in the above-mentioned Japanese Patent Application Laid-Open No. 2014-35639, and therefore further explanation is omitted here.

  In the first embodiment, the correlation between the past traffic data, the past probe information, and the accident occurrence degree is learned by repeatedly executing the processes (1) to (3).

  Returning to FIG. 5, in step S <b> 14, the accident forecast table creation processing unit 312 creates an accident forecast table based on the learning result in step S <b> 13. That is, the accident forecast table creation processing unit 312 tabulates the correlation obtained by the self-organizing map shown in FIG. 7, and defines the correlation between past traffic data, past probe information, and the degree of accident occurrence. Create a forecast table. An example of the accident prediction table will be described with reference to FIG.

  FIG. 8 is a diagram showing an example of the accident prediction table in the first embodiment. In the accident forecast table shown in FIG. 8, the traffic volume, occupancy rate, average speed, wiper operation, rapid acceleration, brake operation, hazard lamp lighting, headlamp lighting for each unit in the competitive layer (and accident distribution) Each weight and the accident occurrence degree are associated with each other.

  Next, the accident prediction process in the first embodiment will be described with reference to FIG. FIG. 9 is a flowchart showing an example of the flow of the accident prediction process in the first embodiment.

  As shown in FIG. 9, the accident forecast processing unit 214 first determines whether or not the forecast timing has arrived in Step S21. If Yes, the process proceeds to Step S22. If No, the process returns to Step S21. For example, the forecast timing may be set every five minutes, but is not limited thereto.

  Next, the accident prediction processing unit 214 performs processing for each route in steps S22 to S28. That is, when the accident prediction processing unit 214 performs accident prediction for each section for a plurality of routes, the accident prediction processing unit 214 first performs the processing of steps S23 to S27 for the first route, and then performs steps S23 to S27 for the second route. The process of... Is sequentially performed for all routes.

  As described above, the accident prediction processing unit 214 performs processing for each section in steps S23 to S27. That is, the accident forecast processing unit 214 first performs steps S24 to S26 for the first section, and then performs steps S24 to S26 for the second section with respect to the route of interest,. The process of, is performed for all sections.

  In step S24, the accident forecast processing unit 214 reads the current traffic data (for example, traffic volume, occupation rate, average speed) from the current database 221 of the storage unit 22 for the section of interest.

  Next, in step S25, the accident prediction processing unit 214 reads the current probe information (for example, wiper operation, rapid acceleration, brake operation, hazard lamp lighting, headlamp lighting) from the probe information database 223 for the section of interest. .

  Next, in step S26, the accident prediction processing unit 214 reads out the accident prediction table corresponding to the section from the accident prediction table database 222 of the storage unit 22, and uses it together with the current traffic data and the current probe information to predict the accident. I do.

  Here, step S26 will be described with reference to FIG. FIG. 10 is an explanatory diagram when the accident prediction process is performed using the self-organizing map of FIG. As shown in FIG. 10, in this self-organizing map, the following processes (11) to (13) are executed.

(11) Determine the winner unit. The method for determining the winner unit is the same as in the case of (1) (FIG. 7).
(12) Select a unit on the accident distribution layer corresponding to the winner unit.
(13) Output the degree of accident occurrence of the selected unit.

  In this way, the accident forecast processing unit 214 can acquire the accident occurrence degree of each section for each route for a plurality of routes in steps S22 to S28.

  In step S29, the display control unit 215 performs control so that the accident prediction result (accident occurrence degree, etc.) by the accident prediction processing unit 214 is displayed as an accident prediction on the display unit 23 together with an alarm lamp or the like. Thereby, a controller using the road traffic control device 2 can recognize the likelihood of an accident corresponding to the current traffic situation for each section of the target road. After step S29, the process returns to step S21.

  As described above, according to the accident prediction system 1 of the first embodiment, the accident occurrence degree can be predicted with higher accuracy using the probe information. In other words, in addition to information (traffic data) obtained from the road sensor section RS, real-time vehicle state information based on probe information can be used to enable accident prediction more quickly and with high accuracy. Can be improved. Further, the notification unit 216 can notify the vehicle 5 of the degree of accident occurrence and the like, and the road traffic safety can be further improved.

  Note that general weather information is for a wide area and does not necessarily match the weather conditions of individual sections. Further, the weather information is not updated as frequently as the accident forecast of the present embodiment. Therefore, in the present embodiment, for example, weather information of each section can be accurately recognized in real time based on the wiper operation information in the probe information, which can greatly contribute to improving the accuracy of forecasting the degree of accident occurrence.

(Second Embodiment)
Next, an accident prediction system 1 according to the second embodiment will be described with reference to FIGS. In the second embodiment, as compared with the first embodiment, the probe information is not used for creating the accident prediction table or calculating the accident occurrence degree, but is calculated using the accident prediction table. It differs in that it is used to adjust the incidence. Hereinafter, descriptions of the same matters as in the first embodiment will be omitted as appropriate.

  FIG. 11 is a block diagram showing an example of the configuration of the accident prediction system 1 in the second embodiment. The probe information acquisition processing unit 311 and the probe information database 322 in the accident forecast table creation device 3 in FIG. 1 are not in the accident forecast table creation device 3 in FIG.

  Then, the accident forecast table creation processing unit 312 does not use the past probe information for the road divided into a plurality of sections, and uses the past traffic data and the past accident data in the past database 321 to perform a predetermined process. Accident forecasting table that shows the degree of accident occurrence for each traffic situation (traffic volume, occupation rate, average speed, etc.) by learning accident occurrence patterns based on learning algorithms (for example, learning algorithms using self-organizing maps) create.

  Further, in the road traffic control device 2 of FIG. 11, a forecast adjustment unit 217 (accident prediction processing unit) and an accident occurrence degree adjustment table 224 are newly provided (details will be described later). The accident forecast processing unit 214 does not use the current probe information for each road section, and uses the current traffic data (for example, traffic volume, occupation rate, average speed) and the accident forecast table to Predict the incidence.

  Also, the forecast adjustment unit 217 adjusts the accident occurrence degree calculated (forecasted) by the accident forecast processing unit 214 using the current probe information. Specifically, the forecast adjustment unit 217 includes, for example, wiper operation, rapid acceleration, brake operation, hazard lamp lighting, headlamp lighting, sudden deceleration (not shown in FIG. 4) among the information indicated by the current probe information. For at least one of the above, when the proportion of executed vehicles is a predetermined value (for example, 50%) or more, the accident occurrence degree is increased by a predetermined value. For example, if the percentage of vehicles that performed wiper operation is greater than or equal to a predetermined value, it is considered that it is raining at that location, so the accident occurrence rate is increased considering the effects of rain based on statistics etc. To do. Similarly, for sudden acceleration, braking, hazard lamp lighting, headlamp lighting, and sudden deceleration, the accident occurrence rate is increased based on statistics and the like.

  FIG. 12 is a schematic diagram for explaining the outline of the accident prediction process in the second embodiment. In the second embodiment, as described above, first, probe information (current probe information and past probe information) is not used, current traffic data (for example, traffic volume, occupation rate, average speed), and The accident occurrence degree is calculated using the accident prediction table (21), and then the accident occurrence degree is adjusted based on the current probe information (22), and the adjusted accident occurrence degree is set as the accident forecast.

  FIG. 13 is a diagram illustrating an example of the accident occurrence degree adjustment table 224 according to the second embodiment. The accident occurrence degree adjustment table 224 defines changes in the numerical value of the accident occurrence degree with and without adjustment for each of wiper operation, rapid acceleration, brake operation, hazard lamp lighting, and headlamp lighting. The accident occurrence degree adjustment table 224 is information created in advance based on statistics and the like. Note that “with adjustment” is applied, for example, when the ratio of execution of the item in all the vehicles in the target section is a predetermined value (for example, 50%) or more. For example, with respect to the wiper operation, if the ratio of the vehicle that executed the wiper operation is 50% or more among all the vehicles in the target section, “with adjustment” is applied.

  The unit of the numerical value in the column with adjustment is “%”. For example, “+0.2” in the column with adjustment for the wiper operation indicates that the original accident degree is increased by 0.2%. This numerical value is preferably adjusted so as to increase accuracy based on the result of actual operation. The same applies to sudden acceleration, braking operation, hazard lamp lighting, and headlamp lighting. If there is no adjustment, the accident rate is not adjusted.

  FIG. 14 is a flowchart showing an example of the flow of accident prediction processing in the second embodiment. 9 is the same as the flowchart of FIG. 9 except that steps S24 to S26 are changed to steps S31 to S35, and only steps S31 to S35 will be described.

  In step S31, the accident prediction processing unit 214 reads current traffic data (for example, traffic volume, occupation rate, average speed) from the current database 221 of the storage unit 22 for the section of interest.

  Next, in step S32, the accident forecast processing unit 214 reads the accident forecast table corresponding to the section from the accident forecast table database 222 of the storage unit 22, and performs the accident forecast using the current traffic data.

  Next, in Step S33, the forecast adjustment unit 217 reads the current probe information (for example, wiper operation, rapid acceleration, brake operation, hazard lamp lighting, headlamp lighting) from the probe information database 223 for the section of interest.

  Next, in step S34, the forecast adjustment unit 217 determines whether or not the accident occurrence degree needs to be adjusted. If Yes, the process proceeds to step S35, and if No, the process proceeds to step S27. In this step S34, as described above, for example, if the ratio of the vehicle that executed the wiper operation is 50% or more in all the vehicles in the target section for the wiper operation, the accident occurrence degree needs to be adjusted (accident) It is determined that the adjustment in the occurrence adjustment table 224 is applied).

  In step S35, the forecast adjustment unit 217 adjusts the accident occurrence degree. Specifically, for example, the forecast adjustment unit 217 refers to the accident occurrence degree adjustment table 224 (FIG. 13) and adds 0.2% to the accident occurrence degree for the wiper operation. increase.

  Thus, according to the accident prediction system 1 of 2nd Embodiment, the accident occurrence degree calculated without using probe information can be adjusted using probe information. Therefore, for example, when a mechanism for calculating the degree of accident occurrence using an accident forecast table created without using probe information has already been established, the probe information can be effectively utilized with little effort to reduce the degree of accident occurrence. Forecast accuracy can be improved.

(Third embodiment)
Next, an accident prediction system 1 according to the third embodiment will be described with reference to FIGS. Compared to the first embodiment, the third embodiment does not use the probe information for creating the accident prediction table, but inputs the accident information into the accident prediction table when calculating the accident occurrence degree. It differs in that it is used to adjust traffic data. Hereinafter, descriptions of the same matters as in the first embodiment will be omitted as appropriate.

  FIG. 15 is a block diagram showing an example of the configuration of the accident prediction system in the third embodiment. The probe information acquisition processing unit 311 and the probe information database 322 in the accident forecast table creation device 3 in FIG. 1 are not in the accident forecast table creation device 3 in FIG.

  Then, the accident forecast table creation processing unit 312 does not use the past probe information for the road divided into a plurality of sections, and uses the past traffic data and the past accident data in the past database 321 to perform a predetermined process. Accident forecasting table that shows the degree of accident occurrence for each traffic situation (traffic volume, occupation rate, average speed, etc.) by learning accident occurrence patterns based on learning algorithms (for example, learning algorithms using self-organizing maps) create.

  In the road traffic control device 2 of FIG. 15, an input adjustment unit 218 (accident prediction processing unit) and an input adjustment table 225 are newly provided.

  The input adjustment unit 218 adjusts the current traffic data using the current probe information. Specifically, the input adjustment unit 218 executes, for example, at least one of wiper operation, rapid acceleration, brake operation, hazard lamp lighting, headlamp lighting, and rapid deceleration among the information indicated by the current probe information. When the vehicle ratio is a predetermined value (for example, 50%) or more, the numerical value of the current traffic data is increased or decreased by a predetermined value. For example, if the percentage of vehicles that have performed wiper operation is greater than or equal to a predetermined value, it is considered that it is raining at that location.Therefore, the current traffic data is calculated based on statistics and other factors. Increase or decrease. Similarly, for sudden acceleration, braking, hazard lamp lighting, headlamp lighting, and sudden deceleration, the numerical value of the current traffic data is increased or decreased based on statistics or the like.

  Then, the accident forecast processing unit 214 uses the current traffic data (for example, traffic volume, occupation rate, average speed) adjusted using the current probe information and the accident forecast table for each road section. Predict the incidence.

  FIG. 16 is a schematic diagram for explaining the outline of the accident prediction process in the third embodiment. In the third embodiment, as described above, current traffic data (for example, traffic volume, occupation rate, average speed) (31) is adjusted (32) using the current probe information, and the current traffic data after the adjustment is adjusted. In addition, the accident occurrence degree is calculated using the accident prediction table.

  FIG. 17 is a diagram illustrating an example of an input adjustment table in the third embodiment. In the input adjustment table 225, with respect to the current traffic data (traffic volume, occupation rate, average speed), with and without adjustment based on wiper operation, rapid acceleration, brake operation, hazard lamp lighting, and headlamp lighting. It defines the change of the numerical value in case. The input adjustment table 225 is information created in advance based on statistics and the like. Note that “with adjustment” is applied, for example, when the ratio of execution of the item in all vehicles in the target section is equal to or greater than a predetermined value. For example, with respect to the wiper operation, if the ratio of the vehicle that executed the wiper operation is 50% or more among all the vehicles in the target section, “with adjustment” is applied.

  The unit of the numerical value in the column with adjustment is “%”. For example, regarding the traffic volume, “+2” in the column with adjustment based on the wiper operation indicates that the traffic volume is increased by 2% with respect to the original traffic volume. It is preferable to adjust the sign (+, −) and the numerical value of this numerical value so as to increase the accuracy based on the result of actual operation. If there is no adjustment, the current traffic data (traffic volume, occupation rate, average speed) is not adjusted.

  FIG. 18 is a flowchart showing an example of the flow of accident prediction processing in the third embodiment. 9 is the same as the flowchart of FIG. 9 except that steps S24 to S26 are changed to steps S41 to S45, and only steps S41 to S45 will be described.

  In step S41, the input adjustment unit 218 reads current traffic data (for example, traffic volume, occupation rate, average speed) from the current database 221 of the storage unit 22 for the section of interest.

  Next, in step S42, the input adjustment unit 218 reads the current probe information (for example, wiper operation, rapid acceleration, brake operation, hazard lamp lighting, headlamp lighting) from the probe information database 223 for the section of interest.

  Next, in step S43, the input adjustment unit 218 determines whether or not the current traffic data needs to be adjusted. If Yes, the process proceeds to step S44. If No, the process proceeds to step S45. In this step S43, as described above, for example, if the ratio of the vehicles that executed the wiper operation is 50% or more in all the vehicles in the target section for the wiper operation, it is necessary to adjust the current traffic data ( It is determined that the adjustment in the input adjustment table 225 is applied).

  In step S44, the input adjustment unit 218 adjusts the current traffic data. Specifically, the input adjustment unit 218 refers to, for example, the input adjustment table 225 (FIG. 17), and regarding traffic volume, based on “+2” in the column with adjustment based on the wiper operation, Increase by 2% to the amount.

  Next, in step S45, the accident prediction processing unit 214 reads out the accident prediction table corresponding to the section from the accident prediction table database 222 of the storage unit 22, and the current traffic data (in the case of passing through the step S44). Is used together with the adjusted current traffic data) to make an accident forecast.

  Thus, according to the accident forecast system 1 of 3rd Embodiment, the present traffic data input into the table for accident forecasts can be adjusted using probe information. Therefore, for example, when a mechanism for calculating the degree of accident occurrence using an accident forecast table created without using probe information has already been established, the probe information can be effectively utilized with little effort to reduce the degree of accident occurrence. Forecast accuracy can be improved.

(Modification)
In the above embodiment, a method using a self-organizing map is exemplified as a method for performing learning and forecasting. However, as a learning and forecasting method, various methods other than the method using the self-organizing map are conceivable. For example, as a relatively simple method, the past traffic data at the time of the accident is retained (accumulated) and simply compared with the current traffic data, or the past traffic data combinations at the time of the accident are clustered by statistical processing, A method of generating traffic data in a similar case when an accident occurs can be considered. As another method, for example, a method using other multivariate analysis such as a Paysian network is also conceivable.

  Moreover, in said embodiment, the traffic volume, the average speed, the vehicle density, and the occupation rate were illustrated as data used for learning and a forecast. However, even information other than these four types may be used for learning and forecasting as long as it is correlated with the occurrence of an accident. For example, the following (A) to (K) There is a lot of information.

(A) Large vehicle mixing information (mixing rate of large vehicles such as trucks and buses)
(B) Low-speed vehicle mixing information (mixing rate of low-speed vehicles traveling at a speed below a predetermined value, etc.)
(C) Speed limit information (constant speed limit, temporary speed limit, etc.)
(D) Event information (information on the status of events around the road, etc.)
(E) Hazard information (information on road conditions based on hazard maps, etc.)
(F) Motorcycle mixing information (such as motorcycle mixing rate)
(G) Road maintenance information (road construction information, etc.)
(H) Closed information (information indicating the closed state due to accidents or equipment troubles, etc.)
(I) Road surface condition information (information indicating road surface dryness, wetness, freezing, etc.)
(J) Congestion information (congestion length, start position, end position, etc.)
(K) Lane restriction information (1 of 3 lanes is currently unusable)

  Further, the configuration of the road traffic control device 2 and the configuration of the accident prediction table creation device 3 in FIGS. 1, 11, and 15 may be integrated to form a physically single accident prediction system. In this case, since the system is a single system, the configuration and processing are simplified, and the accident forecast table can be easily updated using traffic data and probe information obtained in real time. In this case, for example, the accident forecast table is automatically updated every time when traffic data, accident data, and probe information are accumulated every day or every month, or a predetermined number of accident data is accumulated. A method of automatically updating the accident forecast table every time can be considered.

  Moreover, you may make the accident forecast table preparation apparatus 3 of FIG.1, FIG.11, FIG.15 into a cloud using a cloud computing technique.

  As mentioned above, although embodiment of this invention was described, the said embodiment is an example to the last, Comprising: It is not intending limiting the range of invention. The above embodiment can be implemented in various forms, and various omissions, replacements, and changes can be made without departing from the spirit of the invention. The above embodiments are included in the scope and gist of the invention, and are included in the invention described in the claims and the equivalents thereof.

DESCRIPTION OF SYMBOLS 1 Accident prediction system 2 Road traffic control apparatus 3 Accident prediction table preparation apparatus 4 Probe information system 21 Processing part 22 Storage part 23 Display part 24 Input part 211 Traffic data acquisition processing part 212 Probe information acquisition processing part 213 Reception processing part 214 Accident Forecast processing unit 215 Display control unit 216 Notification unit 217 Forecast adjustment unit (accident forecast processing unit)
218 Input adjustment unit (accident prediction processing unit)
221 Current database 222 Accident prediction table database 223 Probe information database 224 Accident occurrence degree adjustment table 225 Input adjustment table 31 Processing unit 32 Storage unit 33 Display unit 34 Input unit 311 Probe information acquisition processing unit 312 Accident prediction table creation processing unit 313 Transmission processing unit 321 Past database 322 Probe information database RS Road sensor unit

Claims (14)

Accident forecasting table that shows the degree of accident occurrence for each traffic situation by learning accident occurrence patterns based on a predetermined learning algorithm using at least past traffic data and past accident data for a predetermined section of the road An accident forecast table creation processing unit for creating
For the section, a traffic data acquisition processing unit that acquires current traffic data from a sensor that measures traffic conditions;
From an external probe information system, a probe information acquisition processing unit for acquiring current probe information of a vehicle traveling in the section;
An accident forecast processing unit for forecasting the degree of occurrence of the accident using the current traffic data, the current probe information, and the accident forecast table for the section;
Accident prediction system with   The accident forecast table creation processing unit applies a predetermined learning algorithm to the predetermined section of the road using past probe information obtained from a vehicle in addition to the past traffic data and the past accident data. The accident prediction system according to claim 1, wherein an accident occurrence pattern is learned based on the accident prediction table to create the accident prediction table.   The accident forecast processing unit adjusts the accident occurrence degree using the current probe information after forecasting the accident occurrence degree using the current traffic data and the accident prediction table for the section. The accident prediction system according to claim 1.   The accident prediction processing unit adjusts the degree of occurrence of the accident using the current probe information. Among the information indicated by the current probe information, wiper operation, rapid acceleration, brake operation, hazard lamp lighting, headlamp The accident prediction system according to claim 3, wherein, for at least one of lighting and rapid deceleration, the accident occurrence degree is increased by a predetermined value when the proportion of executed vehicles is equal to or greater than a predetermined value.   The accident forecast processing unit adjusts the current traffic data using the current probe information, and then uses the adjusted current traffic data and the accident forecast table for the section to determine the accident occurrence degree. The accident forecasting system according to claim 1, which forecasts.   The accident prediction processing unit adjusts the current traffic data using the current probe information. Among the information indicated by the current probe information, wiper operation, rapid acceleration, brake operation, hazard lamp lighting, headlamp The accident prediction system according to claim 5, wherein the current traffic data is increased or decreased by a predetermined value when the ratio of vehicles to be executed is at least a predetermined value for at least one of lighting and rapid deceleration.   The accident prediction system according to any one of claims 1 to 6, further comprising a notification unit that notifies the degree of occurrence of the accident to a vehicle having a probe information transmission function. Accident forecasting table that shows the degree of accident occurrence for each traffic situation by learning accident occurrence patterns based on a predetermined learning algorithm using at least past traffic data and past accident data for a predetermined section of the road Accident forecast table creation processing step for creating
For the section, a traffic data acquisition processing step for acquiring current traffic data from a sensor for measuring traffic conditions;
Probe information acquisition processing step for acquiring current probe information of a vehicle traveling in the section from an external probe information system;
Accident forecast processing step for forecasting the degree of occurrence of the accident using the current traffic data, the current probe information, and the accident forecast table for the section;
Accident prediction method including.   In the accident forecast table creation processing step, for a predetermined section of the road, in addition to the past traffic data and the past accident data, past probe information obtained from a vehicle is used for a predetermined learning algorithm. The accident prediction method according to claim 8, wherein an accident occurrence pattern is learned based on the accident prediction table to create the accident prediction table.   The accident prediction processing step adjusts the accident occurrence degree using the current probe information after forecasting the accident occurrence degree using the current traffic data and the accident prediction table for the section. The accident prediction method according to claim 8.   In the accident forecast processing step, when adjusting the accident occurrence degree using the current probe information, among the information indicated by the current probe information, wiper operation, rapid acceleration, brake operation, hazard lamp lighting, headlamp The accident prediction method according to claim 10, wherein the accident occurrence degree is increased by a predetermined value when the ratio of executed vehicles is equal to or greater than a predetermined value for at least one of lighting and rapid deceleration.   In the accident forecast processing step, after adjusting the current traffic data using the current probe information, the accident occurrence degree is predicted using the adjusted current traffic data and the accident forecast table for the section. The accident prediction method according to claim 8.   In the accident forecast processing step, when adjusting the current traffic data using the current probe information, among the information indicated by the current probe information, wiper operation, rapid acceleration, brake operation, hazard lamp lighting, headlamp 13. The accident prediction method according to claim 12, wherein the current traffic data is increased or decreased by a predetermined value when the ratio of vehicles to be executed is at least a predetermined value for at least one of lighting and rapid deceleration.   The accident prediction method according to any one of claims 8 to 13, further comprising a notification step of notifying the accident occurrence degree to a vehicle having a probe information transmission function.

Images