Information processing system and method for processing an information processing system

Abstract

To control the increase in processing load by avoiding the determination of the reproducibility of unnecessary unstable behavior.SOLUTION: An information processing system stores target vehicle data including information on positions and travel of a plurality of target vehicles, and determines whether or not unstable behavior is reproducible based on the target vehicle data when the system detects unstable behavior, which is a sudden change in behavior of the target vehicles. When a total number of target vehicles in all adjacent areas adjacent to an area of interest to be determined is less than a total threshold value, or when a predicted number of target vehicles entering the area of interest is less than a predicted inflow threshold value, based on the target vehicle data in a plurality of predetermined areas, the reproducibility determination in the area of interest is not performed.SELECTED DRAWING: Figure 5

Description

Technical Field

[0001] The present invention relates to an information processing system and a method for processing an information processing system.

Background Art

[0002] Conventionally, as a technical document related to an information processing system, Japanese Patent Application Laid-Open No. 2020-052607 is known. This publication shows an information processing system that determines whether an unstable behavior is caused by a driver when a target vehicle for information collection exhibits an unstable behavior.

Prior Art Document

Patent Document

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] By the way, in order to statistically utilize the unstable behavior of a vehicle, attention is paid to the reproducibility of the unstable behavior, and it has been considered to transmit information on the unstable behavior to other vehicles when the behavior is reproducible. However, there has been a problem that performing the reproducibility determination even when there are few other vehicles to which the information on the unstable behavior should be transmitted or when there are no other vehicles causes an unnecessary increase in the processing load.

Means for Solving the Problems

[0005] One aspect of the present disclosure is an information processing system that stores target vehicle data including information on the positions and travels of a plurality of target vehicles, and determines whether there is reproducibility in unstable behavior, which is a sudden behavior change of a target vehicle, based on the target vehicle data when the unstable behavior is detected. When the total value of the number of target vehicles in all adjacent areas adjacent to the target area to be determined among the plurality of areas is less than the total threshold value based on the target vehicle data in a plurality of preset areas, or when the predicted number of inflowing target vehicles into the target area is less than the predicted inflow threshold value, the determination of reproducibility in the target area is not performed.

[0006] In the information processing system according to one aspect of the present disclosure, an inflow ratio that is the ratio of the number of target vehicles that have flowed from an adjacent area into the target area within a certain period of time to the number of target vehicles in the adjacent area may be calculated for each adjacent area, and the predicted number of inflowing target vehicles into the target area may be calculated using the inflow ratios of all adjacent areas adjacent to the target area.

[0007] Another aspect of the present disclosure is a processing method of an information processing system that stores target vehicle data including information on the positions and travels of a plurality of target vehicles, and determines whether there is reproducibility in unstable behavior, which is a sudden behavior change of a target vehicle, based on the target vehicle data when the unstable behavior is detected. When the total value of the number of target vehicles in all adjacent areas adjacent to the target area to be determined among the plurality of areas is less than the total threshold value based on the target vehicle data in a plurality of preset areas, or when the predicted number of inflowing target vehicles into the target area is less than the predicted inflow threshold value, the determination of reproducibility in the target area is not performed.

Effect of the Invention

[0008] According to one aspect and another aspect of the present disclosure, an increase in processing load can be suppressed by avoiding the determination of reproducibility of unnecessary unstable behavior.

Brief Description of the Drawings

[0009]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Mode for Carrying Out the Invention

[0010] Hereinafter, embodiments of the present disclosure will be described with reference to the drawings.

[0011] FIG. 1 is a diagram showing an information processing system 100 according to an embodiment. As shown in FIG. 1, in the information processing system 100, target vehicles 2 (target vehicles 2A to 2Z) are communicably connected to the information processing server 10 via a network N. The network N is a wireless communication network. The network N can adopt a well-known one as long as it is wireless communication. The target vehicle 2 is a vehicle that is an information collection target of the information processing system 100.

[0012] FIG. 2 is a diagram for explaining the detection of unstable behavior. As shown in FIG. 2, when the target vehicle 2A slips due to road surface freezing or the like, the target vehicle 2A transmits target vehicle data including information on the position where the slip occurred (unstable behavior position D) to the information processing server 10. The information processing server 10 provides information on unstable behavior to, for example, the target vehicle 2B traveling behind the target vehicle 2A. Thereby, in the target vehicle 2B, it becomes possible to suppress the occurrence of slip at the unstable behavior position D. Note that the information processing system 100 according to the present embodiment only needs to be able to realize the determination of the reproducibility of unstable behavior, and does not necessarily have to have a function of providing information to other target vehicles 2.

[0013] The target vehicle 2 is a vehicle that provides data to be processed by the information processing system 100. An ID [identification] (vehicle identification number) for identifying the vehicle is assigned to the target vehicle 2. There may be one target vehicle. The target vehicles 2 do not necessarily have the same configuration and may have different vehicle types or the like. The target vehicle may be an autonomous vehicle or a vehicle without an autonomous driving function. The target vehicle 2 may be a vehicle without map information.

[0014] The unstable behavior is a sudden change in behavior that makes the driving of the target vehicle 2 unstable. The unstable behavior includes slipping. The unstable behavior may include sudden deceleration or sudden steering angle change. The unstable behavior may include lane departure of the target vehicle 2 or excessive approach to an object (such as a collision warning) by the target vehicle 2. The object may include structures such as utility poles, guardrails, road signs, and walls, or may include moving objects such as other vehicles, pedestrians, and bicycles.

[0015] The target vehicle data collected by the information processing system 100 includes the position information of the target vehicle 2. The position information is generated in association with time. The target vehicle data may include an ID. The target vehicle data may include the vehicle speed information of the target vehicle 2, the acceleration information, the steering angle information, or the yaw rate information. The target vehicle data may include the detection information of surrounding objects by the sensors of the target vehicle 2 or the information on the driving position relative to the lane. The target vehicle data may include the driving operation information of the driver. The above-mentioned various types of information are associated with the position information and time of the target vehicle 2.

[0016] [Configuration of Information Processing System] Hereinafter, the configuration of the information processing system 100 according to this embodiment will be described. The information processing system 100 shown in FIG. 1 includes an information processing server 10. The information processing system 100 may include at least a part of the in-vehicle computing devices of target vehicles 2A to 2Z.

[0017] The information processing server 10 is provided in a facility such as an information management center and is configured to be communicable with the target vehicles 2A to 2Z. FIG. 3 is a block diagram showing an example of the configuration of the information processing server 10. The information processing server 10 shown in FIG. 3 is configured as a general computer including a processor 11, a storage unit 12, a communication unit 13, and a user interface 14.

[0018] The processor 11 operates, for example, an operating system to control the information processing server 10. The processor 11 is an arithmetic unit such as a CPU [Central Processing Unit] including a control device, an arithmetic device, a register, and the like. The processor 11 oversees the storage unit 12, the communication unit 13, and the user interface 14. The storage unit 12 is configured to include at least one of a memory and a storage. The memory is a recording medium such as a ROM [Read Only Memory] or a RAM [Random Access Memory]. The storage is a recording medium such as an HDD [Hard Disk Drive].

[0019] The communication unit 13 is a communication device for performing communication via the network N. For the communication unit 13, a network device, a network controller, a network card, or the like can be used. The user interface 14 is a device including output devices such as a display and a speaker, and input devices such as a touch panel. Note that the information processing server 10 does not necessarily have to be provided in a facility and may be mounted on a moving body such as a vehicle or a ship. The information processing server 10 may be composed of a plurality of servers.

[0020] The information processing server 10 is connected to a target vehicle database 15 that stores past target vehicle data of the target vehicle 2. The target vehicle database 15 has a storage device such as an HDD and can have a configuration similar to a well-known database.

[0021] The target vehicle database 15 may store the target vehicle data in association with a plurality of preset areas. The areas are set, for example, by dividing a certain range on a map. The areas may be set, for example, in 10 km meshes (10 km square), 5 km meshes, 3 km meshes, or 1 km meshes. They may also be set in meshes of 10 km or more. The areas do not have to be of the same shape and may be set as areas where the environment is likely to be uniform according to the terrain.

[0022] The areas may be set as mesh codes. The mesh codes are defined from latitude and longitude information, and unique codes are assigned to each mesh. When mesh codes are used for the areas, the target vehicle 2 and the information processing server 10 do not have to have map information. The position information of the target vehicle 2 can be obtained as latitude and longitude information from a GPS [Global Positioning System] or GNSS [Global Navigation Satellite System] mounted on the target vehicle 2. Eliminating the need for maps also contributes to cost reduction. Note that the target vehicle database 15 may be integrated with the information processing server 10 or may be provided in a facility separate from the information processing server 10.

[0023] Next, the functional configuration of the processor 11 will be described. As shown in FIG. 3, the processor 11 has a target vehicle data recognition unit 11a, an unstable behavior position recognition unit 11b, a storage processing unit 11c, a probability determination unit 11d, and a reproducibility determination unit 11e.

[0024] The target vehicle data recognition unit 11a recognizes the target vehicle data transmitted from the target vehicle 2. The target vehicle data is as described above. The target vehicle data recognition unit 11a acquires the target vehicle data including the position information and time through communication with the target vehicle 2.

[0025] The unstable behavior position recognition unit 11b detects the unstable behavior of the target vehicle 2 based on the target vehicle data acquired by the target vehicle data recognition unit 11a. Hereinafter, among the plurality of target vehicles 2, the vehicle in which the unstable behavior is detected this time will be used as the target vehicle 2A for explanation.

[0026] As the detection of slip, the unstable behavior position recognition unit 11b may use the operation start condition of a well-known antilock brake system [ABS: Antilock Brake System]. For example, in an antilock brake system, as an example, the wheel speed of each wheel is compared with the estimated vehicle body speed, and the system operates when a wheel that is considered to be locked is identified. The estimated vehicle body speed may be obtained from the wheel speeds of each wheel until slip occurs, or may be obtained from the change in acceleration until slip occurs.

[0027] In addition, as the detection of slip, the unstable behavior position recognition unit 11b may use the operation start condition of a well-known vehicle stability control system [VSC: Vehicle Stability Control], or may use the operation start condition of a well-known traction control [TRC: Traction Control System]. The traction control can also be operated by comparing the wheel speed of each wheel with the estimated vehicle body speed and identifying a wheel that is spinning. The unstable behavior position recognition unit 11b may detect the slip of the target vehicle 2 by other well-known methods.

[0028] The unstable behavior position recognition unit 11b may detect a sudden deceleration as an unstable behavior based on the deceleration detected by the acceleration sensor. In this case, the unstable behavior position recognition unit 11b detects a sudden deceleration of the target vehicle 2 when, for example, the absolute value of the deceleration becomes equal to or greater than a sudden deceleration threshold value. The sudden deceleration threshold value is a threshold value of a preset value. Hereinafter, the threshold value used in the description means a threshold value of a preset value.

[0029] The unstable behavior position recognition unit 11b may detect a sudden steering angle change as an unstable behavior based on the yaw rate detected by the yaw rate sensor. In this case, the unstable behavior position recognition unit 11b detects a sudden steering angle change of the target vehicle 2 when, for example, the yaw rate becomes equal to or greater than a steering angle change threshold value. Note that the tire slip angle or the steering angle may be used instead of the yaw rate.

[0030] When the unstable behavior position recognition unit 11b detects an unstable behavior of the target vehicle 2, the unstable behavior position recognition unit 11b recognizes the position information of the target vehicle 2 when the unstable behavior occurred as the unstable behavior position. The unstable behavior position recognition unit 11b recognizes the unstable behavior position in association with time.

[0031] The storage processing unit 11c stores the unstable behavior data including the unstable behavior position in the target vehicle database 15. The storage processing unit 11c stores the unstable behavior data as a part of the target vehicle data. The storage processing unit 11c may store the unstable behavior data in association with a preset area in the target vehicle database 15.

[0032] The probability determination unit 11d determines whether the passing probability of the following vehicle in the target area among the plurality of areas is low based on the target vehicle data in the plurality of preset areas. The target area is an area for determining the reproducibility of the unstable behavior. The target area may be an area where the unstable behavior has been detected over a certain period. The passing probability of the following vehicle is the probability that the target vehicle (following vehicle) in the target area passes through the unstable behavior position.

[0033] The probability determination unit 11d uses, as a feature amount for determining the passing probability of the following vehicle, the total value of the number of target vehicles 2 in all adjacent areas adjacent to the target area (area of interest) to be determined among a plurality of areas, and / or the predicted number of inflows of the target vehicle 2 flowing into the area of interest.

[0034] Specifically, when the total value of the number of target vehicles 2 in all adjacent areas is less than the total threshold value, or when the predicted number of inflows into the area of interest is less than the predicted inflow threshold value, the probability determination unit 11d determines that the passing probability of the following vehicle in the area of interest is low. The adjacent area is an area adjacent to the area of interest. The adjacent area may be limited to an area adjacent to the area of interest and connected to the area of interest by a road.

[0035] The predicted number of inflows is the number of target vehicles 2 predicted to flow from outside the area of interest into the area of interest within a certain period of time. The method for obtaining the predicted number of inflows will be described later. The total threshold value and the predicted inflow threshold value are preset threshold values. The total threshold value and the predicted inflow threshold value may be changed according to other factors. The change of the total threshold value and the predicted inflow threshold value will be described later.

[0036] Here, FIG. 4 is a diagram for explaining an example of the area of interest and adjacent areas. In FIG. 4, the area of interest E0 and adjacent areas E1 to E8 are shown. As shown in FIG. 4, the probability determination unit 11d recognizes the number of target vehicles 2 in the area of interest E0 and adjacent areas E1 to E8 based on the target vehicle data.

[0037] When the total value of the number of target vehicles 2 in all adjacent areas E1 to E8 adjacent to the area of interest E0 is less than the total threshold value, the probability determination unit 11d determines that the passing probability of the following vehicle in the area of interest E0 is low. For example, the total value of the number of vehicles in adjacent areas E1 to E8 in FIG. 4 is the sum of the number of vehicles N1 to N8 (number of vehicles N1 + number of vehicles N2 + number of vehicles N3 + number of vehicles N4 + number of vehicles N5 + number of vehicles N6 + number of vehicles N7 + number of vehicles N8).

[0038] The probability determination unit 11d may calculate the inflow ratio from each of the adjacent areas E1 to E8 to the target area E0, and calculate the predicted number of inflows into the target area E0 using the inflow ratios of all the adjacent areas E1 to E8 adjacent to the target area E0.

[0039] First, the probability determination unit 11d calculates the number of target vehicles 2 (inflow number) that have flowed from the adjacent area E1 to the target area E0 within a certain period of time from the change in the position information of the target vehicle 2 included in the target vehicle data. The certain period of time may be 5 minutes, 10 minutes, or 30 minutes. The certain period of time may be 30 minutes or more and is not particularly limited.

[0040] The probability determination unit 11d calculates the inflow ratio a1 from the adjacent area E1 to the target area E0 as the ratio of the number of inflows from the adjacent area E1 to the target area E0 to the number of target vehicles 2 in the adjacent area E1. For example, if the certain period of time is 30 minutes and 100 target vehicles 2 have existed in the adjacent area E1 in the most recent 30 minutes, and the number of inflows from the adjacent area E1 to the target area E0 is 30, the inflow ratio a1 is 30%. Similarly, the probability determination unit 11d calculates the inflow ratios a2 to a8 of the adjacent areas E2 to E8.

[0041] The probability determination unit 11d calculates the predicted number of inflows into the target area E0 using the inflow ratios a1 to a8 of the adjacent areas E1 to E8 and the number of target vehicles 2 N1 to N8 in the adjacent areas E1 to E8. For example, the predicted number of inflows into the target area E0 in FIG. 4 is the sum of the products of the inflow ratios a1 to a8 and the numbers N1 to N8 (inflow ratio a1 × number N1 + inflow ratio a2 × number N2 + inflow ratio a3 × number N3 + inflow ratio a3 × number N3 + inflow ratio a4 × number N4 + inflow ratio a5 × number N5 + inflow ratio a6 × number N6 + inflow ratio a6 × number N6 + inflow ratio a7 × number N7 + inflow ratio a8 × number N8). The numbers N1 to N8 of the target vehicles 2 can be the numbers of target vehicles 2 existing in each of the adjacent areas E1 to E8 within the same certain period of time as the calculation of the inflow ratio.

[0042] When the predicted number of inflows of the target area E0 calculated is less than the inflow prediction threshold, the probability determination unit 11d determines that the probability of a following vehicle passing through in the target area E0 is low. Note that the probability determination unit 11d may calculate the predicted number of inflows by other methods. The probability determination unit 11d may calculate the number of target vehicles 2 that have flowed from the adjacent areas E1 to E8 into the target area E0 within a certain period of time as the predicted number of inflows of the target area E0.

[0043] The probability determination unit 11d may change the total threshold. The probability determination unit 11d totals the number N0 of vehicles in the target area E0 and the total number of vehicles N1 to N8 in all adjacent areas E1 to E8 over a certain period of time (for example, 5 minutes) from past target vehicle data. The probability determination unit 11d may focus on the aggregated distribution of the total number of adjacent areas E1 to E8 when the number of vehicles in the target area E0 is zero, and adopt the top 5% value as the total threshold. The total threshold may be the top 7% value or the top 3% value, and is not particularly limited.

[0044] The probability determination unit 11d may change the total threshold based on the number of roads connected to the target area E0. The number of roads connected to the target area E0 is the number of roads continuing from all adjacent areas E1 to E8 into the target area E0. Roads that are impassable for vehicles may not be included. The probability determination unit 11d acquires, for example, the number of roads connected to the target area from map information. When the number of roads connected to each area is stored in the target vehicle database 15 as a numerical value for each area, the probability determination unit 11d may acquire the number of roads connected to the target area from the target vehicle database 15.

[0045] The more roads are connected to the target area E0, the probability determination unit 11d may set the total threshold to a smaller value. Even if the number of target vehicles 2 existing in the adjacent areas E1 to E8 is small, the higher the number of roads connected to the target area E0, the higher the probability that the target vehicle 2 will flow into the target area E0, and it can be considered that the probability of a following vehicle passing through is increased compared to the case where the number of roads connected to the target area E0 is small.

[0046] The probability determination unit 11d may acquire traffic volume information of roads connected to the target area E0, and change the total threshold based on the traffic volume information of the roads connected to the target area E0. The traffic volume information can be acquired, for example, from traffic information centers of the country or local governments. The traffic volume information may be acquired by other methods, or the traffic volume information of the road may be generated from past target vehicle data.

[0047] For example, the probability determination unit 11d may set the total threshold to a smaller value as the total traffic volume of the roads connected to the target area E0 is larger. Even if the number of target vehicles 2 existing in the adjacent areas E1 to E8 is small, the probability of the target vehicle 2 flowing into the target area E0 increases as the total traffic volume of the roads connected to the target area E0 is larger, and it can be considered that the passing probability of the following vehicle increases compared to the case where the total traffic volume of the roads connected to the target area E0 is small. The probability determination unit 11d may use only the traffic volume of the main roads among the roads connected to the target area E0. The main road is, for example, a road with a road width of a certain width or more. The main road may be a trunk road designated by the country or local government by laws and regulations.

[0048] The probability determination unit 11d may change the inflow prediction threshold. The probability determination unit 11d totals the number N0 of the target area E0 and the predicted inflow numbers of all adjacent areas E1 to E8 in a certain period (for example, 5 minutes) from past target vehicle data. The probability determination unit 11d may pay attention to the aggregated distribution of the predicted inflow numbers of the adjacent areas E1 to E8 when the number of the target area E0 becomes zero, and adopt the top 5% value as the inflow prediction threshold. The total threshold may be the top 7% value or the top 3% value, and is not particularly limited.

[0049] Similar to the total threshold, the probability determination unit 11d may change the inflow prediction threshold based on the number of roads connected to the target area E0. For example, the probability determination unit 11d may set the total threshold to a smaller value as the number of roads connected to the target area E0 is larger. It can be considered that the probability of the target vehicle 2 flowing into the target area E0 increases as the number of roads connected to the target area E0 is larger, and the passing probability of the following vehicle increases compared to the case where the number of roads connected to the target area E0 is small.

[0050] The probability determination unit 11d may change the inflow prediction threshold based on the traffic volume information of the road connected to the target area E0. For example, the probability determination unit 11d may set the inflow prediction threshold to a smaller value as the total traffic volume of the road connected to the target area E0 is larger. As the total traffic volume of the road connected to the target area E0 is larger, the probability of the target vehicle 2 flowing into the target area E0 increases, and it can be considered that the passing probability of the following vehicle increases compared to the case where the total traffic volume of the road connected to the target area E0 is small.

[0051] When the unstable behavior position recognition unit 11b detects the unstable behavior of the target vehicle 2A (one of the target vehicles 2), the reproducibility determination unit 11e determines whether there is reproducibility in the unstable behavior of the target vehicle 2A. For the determination of reproducibility, as an example, the method described in Japanese Patent Application No. 2022-127863 can be adopted.

[0052] The reproducibility determination unit 11e determines whether reproducibility is required for each area. When the probability determination unit 11d determines that the passing probability of the following vehicle in the target area is low, the reproducibility determination unit 11e does not determine the reproducibility of the unstable behavior in the target area. When the probability determination unit 11d does not determine that the passing probability of the following vehicle in the target area is low, the reproducibility determination unit 11e determines the reproducibility of the unstable behavior in the target area. The reproducibility determination unit 11e may store in the target vehicle database 15 that the determination of the reproducibility of the unstable behavior has not been performed.

[0053] [Processing method of information processing system] Subsequently, the processing method of the information processing system 100 according to the present embodiment will be described with reference to the drawings. FIG. 5 is a flowchart showing an example of the reproducibility necessity determination process of the information processing system. The reproducibility necessity determination process is performed for each target area.

[0054] As shown in FIG. 5, the information processing server 10 of the information processing system 100 aggregates the target vehicle data of a plurality of areas as S10 by the probability determination unit 11d. The probability determination unit 11d performs the aggregation by acquiring the target vehicle data from the target vehicle database 15. Then, the information processing server 10 proceeds to S11.

[0055] In S11, the information processing server 10 calculates, by the probability determination unit 11d, feature amounts used for determining the passing probability of a following vehicle from the target vehicle data. The probability determination unit 11d calculates, as the feature amounts, the total value of the number of target vehicles 2 in all adjacent areas and the predicted number of inflows into the target area. Then, the information processing server 10 proceeds to S12.

[0056] In S12, the information processing server 10 determines, by the probability determination unit 11d, whether or not the total value of the number of target vehicles 2 in all adjacent areas is less than the total threshold. If it is determined that the total value is less than the total threshold (S12: YES), the information processing server 10 proceeds to S14. If it is not determined that the total value is less than the total threshold (S12: NO), the information processing server 10 proceeds to S13.

[0057] In S13, the information processing server 10 determines, by the probability determination unit 11d, whether or not the predicted number of inflows into the target area is less than the inflow prediction threshold. If it is determined that the predicted number of inflows into the target area is less than the inflow prediction threshold (S13: YES), the information processing server 10 proceeds to S14. If it is not determined that the predicted number of inflows into the target area is less than the inflow prediction threshold (S13: NO), the information processing server 10 proceeds to S16.

[0058] In S14, the information processing server 10 determines, by the probability determination unit 11d, that the passing probability of a following vehicle in the target area is low. Then, in S15, the information processing server 10 determines, by the reproducibility determination unit 11e, not to perform the reproducibility determination in the target area. The information processing server 10 ends the current reproducibility necessity determination process.

[0059] In S16, the information processing server 10 determines that the probability of a following vehicle passing through the target area is low by the probability determination unit 11d. Thereafter, in S15, the information processing server 10 determines not to perform the reproducibility determination in the target area by the reproducibility determination unit 11e. The information processing server 10 ends the current reproducibility necessity determination process.

[0060] FIG. 6(a) is a flowchart showing an example of the first threshold change process. The first threshold change process is executed before the reproducibility necessity determination process.

[0061] As shown in FIG. 6(a), the information processing server 10, as S20, acquires the number of roads connected to the target area by the probability determination unit 11d. The probability determination unit 11d acquires the number of roads connected to the target area from, for example, map information.

[0062] In S21, the information processing server 10 changes the total threshold and the inflow prediction threshold based on the number of roads connected to the target area by the probability determination unit 11d. The probability determination unit 11d changes the total threshold and the inflow prediction threshold to smaller values as the number of roads connected to the target area is larger, for example. Thereafter, the information processing server 10 ends the first threshold change process.

[0063] FIG. 6(b) is a flowchart showing an example of the second threshold change process. The second threshold change process is executed before the reproducibility necessity determination process.

[0064] As shown in FIG. 6(b), the information processing server 10, as S30, acquires the traffic volume information of the roads connected to the target area by the probability determination unit 11d. The traffic volume information can be acquired from, for example, the traffic information centers of countries or local governments.

[0065] In S31, the information processing server 10 changes the total threshold value and the inflow prediction threshold value based on the traffic volume information of the roads connecting to the target area by the probability determination unit 11d. For example, the probability determination unit 11d changes the total threshold value and the inflow prediction threshold value to smaller values as the total value of the traffic volume of the roads connecting to the target area is larger. Thereafter, the information processing server 10 ends the second threshold value change process.

[0066] According to the information processing system 100 and its processing method according to the present embodiment described above, when it is determined that the subsequent vehicle passing probability of the target area is low from the total value of the number of target vehicles in all adjacent areas adjacent to the target area and the predicted number of inflowing target vehicles into the target area, the determination of the reproducibility of the unstable behavior of the target area is not performed. Therefore, an increase in the processing load can be suppressed by avoiding the determination of the reproducibility of unnecessary unstable behavior.

[0067] Further, according to the information processing system 100, by changing the total threshold value and the inflow prediction threshold value based on the number of roads connecting to the target area or the traffic volume information of the roads connecting to the target area, it is possible to appropriately determine whether or not the reproducibility determination is necessary according to the situation of the target area.

[0068] As described above, the embodiments of the present invention have been described. However, the present invention is not limited to the above-described embodiments. The present invention can be implemented in various forms with various changes and improvements based on the knowledge of those skilled in the art, including the above-described embodiments.

[0069] The probability determination unit 11d does not necessarily need to determine whether or not reproducibility is required using both the total value and the predicted number of inflows, and may be an aspect in which only one of them is used.

[0070] Furthermore, the information processing server 10 does not necessarily need to include the probability determination unit 11d. That is, the determination of the passing probability of the following vehicle is not essential. Based on the target vehicle data in a plurality of preset areas, the reproducibility determination unit 11e does not perform the determination of the reproducibility of the unstable behavior in the target area when the total value of the number of target vehicles 2 in all adjacent areas adjacent to the target area is less than the total threshold value, or when the predicted inflow number of the target area is less than the predicted inflow threshold value. A configuration may be adopted. Also in the reproducibility determination unit 11e, it is not necessarily required to determine the necessity of reproducibility using both the total value and the predicted inflow number, and an aspect of using only one of them may be adopted.

Explanation of Signs

[0071] 2... Target vehicle, 10... Information processing server, 11a... Target vehicle data recognition unit, 11b... Unstable behavior position recognition unit, 11c... Memory processing unit, 11d... Probability determination unit, 11e... Reproducibility determination unit, 15... Target vehicle database, 100... Information processing system, E0... Target area, E1 to E8... Adjacent areas.

Claims

1. An information processing system that stores target vehicle data including information on the positions and driving of a plurality of target vehicles, and determines whether there is reproducibility in an unstable behavior, which is a sudden behavior change of the target vehicle, based on the target vehicle data when the unstable behavior is detected. When the total value of the number of target vehicles in all adjacent areas adjacent to a target area to be determined among the plurality of areas is less than a total threshold value based on the target vehicle data in the plurality of preset areas, or when the predicted number of inflowing target vehicles into the target area is less than an inflow prediction threshold value, the determination of the reproducibility in the target area is not performed. An information processing system that calculates, for each adjacent area, an inflow ratio that is the ratio of the number of target vehicles that have flowed from the adjacent area into the target area within a certain period of time to the number of target vehicles in the adjacent area, and calculates the predicted number of inflowing target vehicles in the target area using the inflow ratios of all the adjacent areas adjacent to the target area.

2. The information processing system according to claim 1, wherein the total threshold value or the inflow prediction threshold value is changed based on the number of roads connected to the target area.

3. The information processing system according to claim 1 or 2, wherein traffic volume information of roads connected to the target area is acquired, and the total threshold value or the inflow prediction threshold value is changed based on the traffic volume information of the roads connected to the target area.

4. A processing method of an information processing system that stores target vehicle data including information on the positions and driving of a plurality of target vehicles, and determines whether there is reproducibility in an unstable behavior, which is a sudden behavior change of the target vehicle, based on the target vehicle data when the unstable behavior is detected. When the total value of the number of target vehicles in all adjacent areas adjacent to a target area to be determined among the plurality of areas is less than a total threshold value based on the target vehicle data in the plurality of preset areas, or when the predicted number of inflowing target vehicles into the target area is less than an inflow prediction threshold value, the determination of the reproducibility in the target area is not performed.

5. A processing method of an information processing system that stores target vehicle data including information on the positions and driving of a plurality of target vehicles, and determines whether there is reproducibility in an unstable behavior, which is a sudden behavior change of the target vehicle, based on the target vehicle data when the unstable behavior is detected. When the total value of the number of target vehicles in all adjacent areas adjacent to a target area to be determined among the plurality of areas is less than a total threshold value based on the target vehicle data in the plurality of preset areas, or when the predicted number of inflowing target vehicles into the target area is less than an inflow prediction threshold value, the determination of the reproducibility in the target area is not performed. ​

Images