Information processing device, information processing method, and information processing program

Abstract

To reduce data volume for vehicle information and reduce omission of vehicle information indicating collisions in the case of executing processing for determining the present / absence of a collision on detected vehicle information.SOLUTION: An information processing apparatus comprises: an acquisition unit that acquires vehicle information including an acceleration of a vehicle and a time of detection at which the acceleration was detected; a derivation unit that derives an amount of change in the acceleration per unit time using the vehicle information; a setting unit that sets, using the time of detection, a threshold value for the amount of change in accordance with an interval at which the acceleration was detected; and an extraction unit that extracts vehicle information corresponding to the amount of change as objective data if the amount of change is equal to the threshold value or larger.SELECTED DRAWING: Figure 5

Description

[Technical field]

[0001] The present invention relates to an information processing device, an information processing method, and an information processing program that reduce the amount of data input to a neural network that determines a collision and suppresses the loss of data indicating a collision. [Background technology]

[0002] Patent document 1 discloses an accident determination system in which, when an in-vehicle device that transmits vehicle information to a management server predicts an accident, it transmits a signal to the management server, and, if the management server receives the signal but does not receive accident determination information from the in-vehicle device within a specified period of time, it uses the vehicle information to determine whether or not an accident has occurred. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2017-010279 A Summary of the Invention [Problem to be solved by the invention]

[0004] However, vehicle information may contain a huge amount of data, including data detected from a plurality of on-board devices mounted on the vehicle. Therefore, when a process for determining whether or not a collision has occurred is executed based on the detected vehicle information, the amount of calculation may become huge, resulting in high calculation costs. In addition, when vehicle information is selected to reduce calculation costs, there is a risk that vehicle information indicating a collision may be missed.

[0005] The present invention aims to provide an information processing device, an information processing method, and an information processing program that can reduce the amount of vehicle information data and suppress the loss of vehicle information indicating a collision when performing a process to determine whether or not a collision occurs based on detected vehicle information. [Means for solving the problem]

[0006] The information processing device according to claim 1 further includes an acquisition unit that acquires vehicle information including an acceleration of a vehicle and a detection time when the acceleration is detected, and a vehicle information acquisition unit that acquires a vehicle information including an acceleration of a vehicle and a detection time when the acceleration is detected, The interval at which the acceleration was detected The system includes a derivation unit that derives the amount of change in the acceleration at a hit, a setting unit that uses the detection time to set a threshold value for the amount of change according to the interval at which the acceleration is detected, and an extraction unit that extracts the vehicle information corresponding to the amount of change as target data if the amount of change is equal to or greater than the threshold value.

[0007] The information processing device according to claim 1 acquires vehicle information including the acceleration of the vehicle and the detection time when the acceleration is detected, derives the amount of change in acceleration per unit time using the vehicle information, sets a threshold value for the amount of change according to the interval at which the acceleration is detected using the detection time, and extracts vehicle information corresponding to the amount of change as target data if the amount of change is equal to or greater than the threshold. That is, according to the information processing device, a threshold value according to the interval at which the acceleration is detected is set, and if the amount of change in acceleration per unit time is equal to or greater than the threshold, extracts vehicle information corresponding to the amount of change as target data. This reduces the amount of vehicle information data and suppresses the omission of vehicle information indicating a collision when performing a process for determining whether or not a collision has occurred for the detected vehicle information.

[0008] An information processing device according to a second aspect of the present invention is the information processing device according to the first aspect, wherein the setting unit sets the threshold value to a larger value as the interval becomes shorter.

[0009] According to the information processing device of claim 2, vehicle information can be extracted without underestimating the derived amount of change in acceleration.

[0010] The information processing device according to a third aspect of the present invention is the information processing device according to the second aspect, wherein the setting unit sets the threshold value derived by dividing the interval by a predetermined value.

[0011] According to the information processing device of claim 3, it is possible to more easily set a threshold value according to the interval at which the acceleration is detected.

[0012] An information processing device according to a fourth aspect of the present invention is the information processing device according to the second or third aspect, wherein the setting unit sets a lower limit value of the interval, and sets the threshold value when the interval is equal to or greater than the lower limit value.

[0013] According to the information processing device recited in claim 4, the amount of vehicle information can be further reduced.

[0014] The information processing device according to claim 5 is an information processing device according to any one of claims 1 to 4, wherein the setting unit sets the threshold value using a trained model that has undergone machine learning to determine the threshold value for the amount of change using previously acquired vehicle information as learning data.

[0015] According to the information processing device of claim 5, it is possible to extract vehicle information that reflects data acquired in the past.

[0016] The information processing device according to claim 6 is the information processing device according to any one of claims 1 to 5, wherein the setting unit sets the threshold value of the amount of change according to statistical information that collects previously acquired vehicle information.

[0017] According to the information processing device of claim 6, it is possible to extract vehicle information that reflects data acquired in the past.

[0018] The information processing method according to claim 7 includes acquiring vehicle information including an acceleration of the vehicle and a detection time when the acceleration is detected, and using the vehicle information. The interval at which the acceleration was detected The amount of change in the acceleration at the hit is derived, and a threshold value for the amount of change corresponding to the interval at which the acceleration is detected is set using the detection time, and if the amount of change is equal to or greater than the threshold value, the vehicle information corresponding to the amount of change is extracted as target data.

[0019] The information processing method described in claim 7 acquires vehicle information including the acceleration of the vehicle and the detection time when the acceleration is detected, derives the amount of change in acceleration per unit time using the vehicle information, sets a threshold value for the amount of change according to the interval at which the acceleration is detected using the detection time, and extracts vehicle information corresponding to the amount of change as target data if the amount of change is equal to or greater than the threshold. That is, according to the information processing method, a threshold value according to the interval of the detection time of the acceleration is set, and if the amount of change in acceleration per unit time is equal to or greater than the threshold, extracts vehicle information corresponding to the amount of change as target data. This reduces the amount of vehicle information data and suppresses the omission of vehicle information indicating an accident when performing a process to determine whether or not a collision has occurred for the detected vehicle information.

[0020] The information processing program according to claim 8 further comprises acquiring vehicle information including an acceleration of the vehicle and a detection time when the acceleration is detected, and using the vehicle information to The interval at which the acceleration was detected The computer executes a process to derive the amount of change in the acceleration at the hit, set a threshold value for the amount of change according to the interval at which the acceleration is detected using the detection time, and if the amount of change is equal to or greater than the threshold value, extract the vehicle information corresponding to the amount of change as target data.

[0021] The computer that executes the information processing program according to claim 8 acquires vehicle information including the acceleration of the vehicle and the detection time when the acceleration is detected, derives the amount of change in acceleration per unit time using the vehicle information, sets a threshold value for the amount of change according to the interval at which the acceleration is detected using the detection time, and extracts vehicle information corresponding to the amount of change as target data if the amount of change is equal to or greater than the threshold. That is, according to the computer, a threshold value according to the interval at which the acceleration is detected is set, and if the amount of change in acceleration per unit time is equal to or greater than the threshold, extracts vehicle information corresponding to the amount of change as target data. This reduces the amount of vehicle information data and suppresses the omission of vehicle information indicating an accident when performing a process to determine whether or not a collision has occurred for the detected vehicle information. Effect of the Invention

[0022] According to the present invention, when a process for determining the presence or absence of a collision is executed based on detected vehicle information, the amount of vehicle information data can be reduced and loss of vehicle information indicating a collision can be suppressed. [Brief description of the drawings]

[0023] [Figure 1] FIG. 1 is a diagram showing a schematic configuration of an information processing system according to each embodiment. [Diagram 2] FIG. 2 is a block diagram showing a hardware configuration of a vehicle according to each embodiment. [Diagram 3] FIG. 2 is a block diagram showing a functional configuration of the vehicle-mounted device according to each embodiment. [Figure 4] FIG. 2 is a block diagram showing a hardware configuration of a center server in each embodiment. [Diagram 5] FIG. 2 is a block diagram showing the functional configuration of a center server according to the first embodiment. [Figure 6] 10 is a block diagram illustrating the relationship between detection time and acceleration, which is provided for explaining the setting of a threshold value in each embodiment. FIG. [Figure 7] 5 is a flowchart showing a flow of a process for extracting vehicle information executed in the center server of the first embodiment. [Figure 8] FIG. 11 is a block diagram showing the functional configuration of a center server according to a second embodiment. [Figure 9] 10 is a flowchart showing a flow of a process for extracting vehicle information executed in a center server of a second embodiment. [Figure 10] 13 is a flowchart showing the flow of a process for generating a trained model executed in the center server of the second embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0024] [First embodiment] An information processing system including an information processing device of the present invention will be described. The information processing system is a system that extracts data for detecting a collision of a vehicle using information related to the driving of the vehicle (hereinafter referred to as "vehicle information") acquired from an on-board device mounted on the vehicle.

[0025] (Overall composition) 1, an information processing system 10 according to an embodiment of the present invention includes a vehicle 12 and a center server 30 as an information processing device. The vehicle 12 is equipped with an on-board device 20, and the on-board devices 20 are mutually connected to the center server 30 via a network N.

[0026] Although FIG. 1 illustrates one vehicle 12 including an in-vehicle device 20 for one center server 30, the numbers of vehicles 12, in-vehicle devices 20, and center servers 30 are not limited to this.

[0027] The vehicle-mounted device 20 is a device that acquires vehicle information related to the driving of the vehicle 12 and transmits it to the center server 30. Here, the vehicle information according to this embodiment is data related to driving detected from each device mounted on the vehicle 12. For example, the vehicle information according to this embodiment is time-series data including the vehicle acceleration and the time at which the acceleration is detected (hereinafter referred to as "detection time"). Also, a form in which the detection time according to this embodiment is time will be described. However, this is not limited to this. The detection time may be, for example, the elapsed time from a reference point such as the start of the engine.

[0028] The center server 30 is installed, for example, at a manufacturer that manufactures the vehicle 12 or at a car dealership affiliated with the manufacturer. The center server 30 acquires vehicle information from the in-vehicle device 20 and extracts target data for detecting a vehicle collision from the acquired vehicle information. The extracted target data may be transmitted to an external device that detects a vehicle collision, or may be stored as target data.

[0029] (vehicle) As shown in FIG. 2, the vehicle 12 according to this embodiment includes an in-vehicle device 20, a plurality of ECUs (Electronic Control Units) 22, and a plurality of in-vehicle devices 24.

[0030] The vehicle-mounted device 20 includes a central processing unit (CPU) 20A, a read only memory (ROM) 20B, a random access memory (RAM) 20C, an in-vehicle communication interface (I / F) 20D, and a wireless communication interface 20E. The CPU 20A, the ROM 20B, the RAM 20C, the in-vehicle communication interface 20D, and the wireless communication interface 20E are connected to each other so as to be able to communicate with each other via an internal bus 20G.

[0031] The CPU 20A is a central processing unit that executes various programs and controls each part. That is, the CPU 20A reads out the programs from the ROM 20B and executes the programs using the RAM 20C as a working area.

[0032] The ROM 20B stores various programs and various data. In the present embodiment, the ROM 20B stores a collection program 100 that collects vehicle information related to the operation of the vehicle 12 from the ECU 22. When the collection program 100 is executed, the vehicle-mounted device 20 executes a process of transmitting the vehicle information to the center server 30. The ROM 20B also stores history information 110, which is backup data of the vehicle information. The RAM 20C temporarily stores programs or data as a working area.

[0033] The in-vehicle communication I / F 20D is an interface for connecting to each ECU 22. The interface uses a communication standard based on the CAN protocol. The in-vehicle communication I / F 20D is connected to the external bus 20F.

[0034] The wireless communication I / F 20E is a wireless communication module for communicating with the center server 30. The wireless communication module uses communication standards such as 5G, LTE, and Wi-Fi (registered trademark). The wireless communication I / F 20E is connected to a network N.

[0035] The ECU 22 includes at least an ADAS (Advanced Driver Assistance System)-ECU 22A.

[0036] The ADAS-ECU 22A controls the advanced driving assistance system. The vehicle speed sensor 24A, the yaw rate sensor 24B, the acceleration sensor 24C, and the external sensor 24D, which constitute the in-vehicle device 24, are connected to the ADAS-ECU 22A. The vehicle speed sensor 24A is a sensor that detects the speed of the vehicle, the yaw rate sensor 24B is a sensor that detects the angular velocity of the vehicle when it turns, and the acceleration sensor 24C is a sensor that detects the acceleration in the traveling direction of the vehicle. The external sensor 24D is a group of sensors used to detect the surrounding environment of the vehicle 12. The external sensor 24D includes, for example, a camera that captures an image of the surroundings of the vehicle 12, a millimeter wave radar that transmits a search wave and receives a reflected wave, and a lidar (Laser Imaging Detection and Ranging) that scans the front of the vehicle 12.

[0037] As shown in FIG. 3, in the vehicle-mounted device 20 of this embodiment, a CPU 20A executes a collection program 100 to function as a collection unit 200 and an output unit 210.

[0038] The collection unit 200 has a function of acquiring information detected by the in-vehicle devices 24 from each ECU 22 of the vehicle 12 and collecting vehicle information.

[0039] The output unit 210 has a function of outputting the vehicle information collected by the collection unit 200 to the center server 30.

[0040] (Center server) 4, the center server 30 includes a CPU 30A, a ROM 30B, a RAM 30C, a storage 30D, and a communication I / F 30E. The CPU 30A, the ROM 30B, the RAM 30C, the storage 30D, and the communication I / F 30E are connected to each other via an internal bus 30F so as to be able to communicate with each other. The functions of the CPU 30A, the ROM 30B, the RAM 30C, and the communication I / F 30E are the same as those of the CPU 20A, the ROM 20B, the RAM 20C, and the wireless communication I / F 20E of the vehicle-mounted device 20 described above. The communication I / F 30E may perform wired communication.

[0041] The storage 30D as a memory is configured by a hard disk drive (HDD) or a solid state drive (SSD) and stores various programs and various data. In the present embodiment, the storage 30D stores an information processing program 120 and a vehicle information database (hereinafter referred to as "vehicle information DB") 130. The ROM 30B may store the information processing program 120 and the vehicle information DB 130.

[0042] The information processing program 120 as a program is a program for controlling the center server 30. With the execution of the information processing program 120, the center server 30 executes various processes including a process of acquiring vehicle information and a process of extracting target data from the vehicle information.

[0043] The vehicle information DB 130 stores the vehicle information received from the vehicle-mounted device 20 and the extracted target data.

[0044] As shown in FIG. 5, in the center server 30 of this embodiment, a CPU 30A executes an information processing program 120 to function as an acquisition unit 300, a derivation unit 310, a setting unit 320A, an extraction unit 330, and a storage unit 340A.

[0045] The acquisition unit 300 has a function of acquiring vehicle information transmitted from the vehicle-mounted device 20 of the vehicle 12. Here, the acquisition unit 300 according to the present embodiment acquires, as the vehicle information, time-series data including the acceleration of the vehicle and the detection time.

[0046] The derivation unit 310 uses the vehicle information to derive the amount of change in acceleration per unit time (jerk) of the vehicle 12. Specifically, the derivation unit 310 uses the detection time included in the vehicle information to derive the interval at which the acceleration is detected (hereinafter referred to as the "detection interval"). The derivation unit 310 divides the corresponding acceleration by the derived detection interval to derive the jerk of the vehicle 12.

[0047] The setting unit 320A sets a jerk threshold value according to the derived detection interval. Here, the jerk according to this embodiment varies according to the detection interval.

[0048] For example, as shown in Figure 6, if the difference in acceleration detected between detection points A and C is am / s 2 The difference in acceleration detected between detection points B and C is am / s 2 In addition, as shown in FIG 6, it is assumed that the detection interval between A and C is 2×dt, and the detection interval between B and C is dt.

[0049] When the difference in the detected acceleration is divided by each detection interval to derive and compare the jerk between AC and the jerk between BC, the ratio of the jerk between BC to the jerk between AC is 2. That is, when the difference in the acceleration is the same, the derived jerk becomes smaller as the detection interval becomes larger. Therefore, in this embodiment, the jerk threshold is set smaller as the detection interval becomes larger. Specifically, the setting unit 320A derives a threshold by dividing a predetermined reference value by the derived detection interval, and sets the derived threshold as the jerk threshold. As a result, even if the jerk value becomes smaller according to the detection interval, the target jerk is detected without missing anything.

[0050] In addition, in this embodiment, as the detection interval becomes smaller, the derived jerk value becomes larger, so the jerk threshold is set to be larger according to the detection interval. However, if the detection interval is too small, the derived jerk will frequently be equal to or greater than the threshold. Therefore, if the detection interval related to the vehicle information is equal to or greater than a predetermined interval (e.g., 40 ms), the jerk threshold is set and the vehicle information is extracted. In other words, if the detection interval related to the vehicle information is less than the predetermined interval, the jerk threshold is not set and the vehicle information is not extracted.

[0051] The predetermined reference value according to the present embodiment may be set by a user or may be set by tallying up the acceleration when a collision occurs. For example, the lower limit value of the acceleration related to the vehicle information in which a collision occurs may be set as the predetermined reference value. The acceleration occurring when a collision occurs may be tallied, and a value corresponding to the top 95 percent of the acceleration (5th percentile) may be set as the predetermined reference value using the tallied acceleration. The predetermined reference value may be set using statistics such as the average value, median value, variance, and standard deviation of the tallied acceleration. The predetermined reference value may be set according to the type of vehicle.

[0052] The extraction unit 330 extracts vehicle information using the derived jerk and the set jerk threshold. Specifically, when the derived jerk is equal to or greater than the threshold, the extraction unit 330 extracts the vehicle information corresponding to the jerk as target data.

[0053] The storage unit 340A stores the extracted vehicle information as target data, and also stores the acquired vehicle information.

[0054] (Flow of Control) The flow of each process executed in the information processing system 10 of this embodiment will be described with reference to the flowchart in Fig. 7. Each process in the center server 30 is executed by the CPU 30A of the center server 30 functioning as an acquisition unit 300, a derivation unit 310, a setting unit 320A, an extraction unit 330, a storage unit 340A, and a generation unit 350. The process of extracting vehicle information shown in Fig. 7 is executed, for example, when an instruction to extract vehicle information is input.

[0055] In step S100, CPU 30A acquires vehicle information including the acceleration of vehicle 12 and the detection time when the acceleration is detected.

[0056] In step S101, the CPU 30A derives the jerk of the vehicle 12 by using the vehicle information.

[0057] In step S102, CPU 30A derives a jerk threshold value by dividing the detection interval by a predetermined reference value, and sets the jerk threshold value.

[0058] In step S103, the CPU 30A determines whether the jerk is equal to or greater than the threshold. If the jerk is equal to or greater than the threshold (step S103: YES), the CPU 30A proceeds to step S104. On the other hand, if the jerk is not equal to or greater than the threshold (the jerk is less than the threshold) (step S103: NO), the CPU 30A proceeds to step S106.

[0059] In step S104, CPU 30A extracts vehicle information corresponding to the jerk as target data.

[0060] In step S105, CPU 30A stores the extracted target data.

[0061] In step S106, CPU 30A stores the acquired vehicle information as target data.

[0062] In step S107, CPU 30A determines whether or not to end the process of extracting vehicle information. If the process of extracting vehicle information is to be ended (step S107: YES), CPU 30A ends the process of extracting vehicle information. On the other hand, if the process of extracting vehicle information is not to be ended (step S107: NO), CPU 30A proceeds to step S100 and acquires vehicle information.

[0063] (Summary of the first embodiment) The center server 30 as an information processing device in this embodiment acquires vehicle information including the vehicle acceleration and the detection time at which the acceleration was detected, uses the vehicle information to derive the amount of change in acceleration per unit time, and uses the detection time to set a threshold value for the amount of change according to the interval at which the acceleration was detected, and if the amount of change is greater than or equal to the threshold value, extracts vehicle information corresponding to the amount of change as target data.

[0064] As described above, according to this embodiment, when a process is executed to determine whether or not a collision has occurred based on detected vehicle information, the amount of vehicle information data can be reduced and loss of vehicle information indicating a collision can be suppressed.

[0065] [Second embodiment] In the first embodiment, a configuration in which a threshold is derived and set by dividing a predetermined reference value by a detection interval is described. In the second embodiment, a configuration in which a threshold is set using a trained model that has been subjected to machine learning for setting a threshold is described.

[0066] Note that the configuration of the information processing system according to this embodiment (see FIG. 1), an example of the hardware configuration of the vehicle 12 (see FIG. 2), an example of the functional configuration of the vehicle-mounted device 20 (see FIG. 3), an example of the hardware configuration of the center server 30 (see FIG. 4), and a graph showing the relationship between detection time and acceleration (see FIG. 6) are the same as those in the first embodiment, and therefore descriptions thereof will be omitted. Below, differences from the first embodiment will be described. Also, the same components are given the same symbols, and descriptions thereof will be omitted.

[0067] As shown in FIG. 8, in the center server 30 of this embodiment, the CPU 30A executes the information processing program 120 to function as an acquisition unit 300, a derivation unit 310, a setting unit 320B, an extraction unit 330, a memory unit 340B, and a generation unit 350.

[0068] The setting unit 320B sets the jerk threshold value using a trained model that has undergone machine learning to set the jerk threshold value. For example, the trained model learns previously acquired vehicle information (acceleration) in which a collision has occurred as training data. The trained model calculates, as a predetermined reference value, a value corresponding to the top 95 percent (5th percentile) of the magnitude of acceleration among all the acquired accelerations. The trained model derives and sets the threshold value using the predetermined reference value. Note that the trained model according to this embodiment is, for example, a regression model.

[0069] The storage unit 340B stores the extracted vehicle information. The storage unit 340B also stores the acquired vehicle information. The storage unit 340B also stores a trained model generated by the generation unit 350, which will be described later.

[0070] The generation unit 350 executes machine learning using previously acquired vehicle information on collision-occurring vehicles, and generates a trained model.

[0071] (Flow of Control) The flow of each process executed in the information processing system 10 of this embodiment will be described with reference to the flowchart in Fig. 9. Each process in the center server 30 is executed by the CPU 30A of the center server 30 functioning as an acquisition unit 300, a derivation unit 310, a setting unit 320B, an extraction unit 330, and a storage unit 340B. The process of extracting vehicle information shown in Fig. 9 is executed, for example, when an instruction to extract vehicle information is input. Note that in Fig. 9, the same steps as those in the extraction process shown in Fig. 7 are denoted by the same reference numerals as those in Fig. 7, and their description will be omitted.

[0072] In step S108, CPU 30A inputs the acquired vehicle information to the learned model, and sets the jerk threshold value output from the learned model.

[0073] Next, a process for generating a trained model executed in the information processing system 10 of the present embodiment will be described with reference to the flowchart of Fig. 10. The generation process shown in Fig. 10 is executed, for example, when an instruction to execute a process for generating a trained model is input.

[0074] In step S200, CPU 30A acquires, as learning data, previously acquired vehicle information regarding a vehicle collision that has occurred.

[0075] In step S201, CPU 30A executes machine learning using the acquired learning data to generate a learned model.

[0076] In step S202, CPU 30A inputs vehicle information to the generated trained model, and evaluates the trained model using the jerk threshold value output from the trained model.

[0077] In step S203, CPU 30A determines whether or not to end the process of generating a trained model. If the process of generating a trained model is to be ended (step S203: YES), the process proceeds to step S204. On the other hand, if the process of generating a trained model is not to be ended (step S203: NO), CPU 30A proceeds to step S200 and acquires training data.

[0078] In step S204, CPU 30A stores the generated trained model.

[0079] (summary) The center server 30 serving as an information processing device in this embodiment uses the trained model to set a jerk threshold and extract vehicle information.

[0080] As described above, according to this embodiment, vehicle information can be extracted by reflecting previously acquired vehicle information.

[0081] [remarks] In the above embodiment, the center server 30 is equipped with a driving diagnosis device. However, the present invention is not limited to this. The information processing device may be the in-vehicle device 20. For example, the in-vehicle device 20 may use the vehicle information acquired from the in-vehicle device 24 to extract vehicle information as target data, and transmit the extracted target data to the center server 30 or the like.

[0082] In the above embodiment, various processes executed by the CPU 20A and the CPU 30A by reading the software (programs) may be executed by various processors other than the CPU. In this case, examples of the processor include a PLD (Programmable Logic Device) such as an FPGA (Field-Programmable Gate Array) whose circuit configuration can be changed after manufacture, and a dedicated electric circuit such as an ASIC (Application Specific Integrated Circuit) which is a processor having a circuit configuration designed exclusively for executing a specific process. In addition, each of the above-mentioned processes may be executed by one of these various processors, or may be executed by a combination of two or more processors of the same or different types (for example, a plurality of FPGAs, a combination of a CPU and an FPGA, etc.). In addition, the hardware structure of these various processors is, more specifically, an electric circuit that combines circuit elements such as semiconductor elements.

[0083] In the above embodiment, each program has been described as being prestored (installed) in a non-transitory computer-readable recording medium. For example, the collection program 100 in the vehicle-mounted device 20 is prestored in the ROM 20B, and the information processing program 120 in the center server 30 is prestored in the storage 30D. However, the present invention is not limited to this, and each program may be provided in a form recorded in a non-transitory recording medium such as a CD-ROM (Compact Disc Read Only Memory), a DVD-ROM (Digital Versatile Disc Read Only Memory), or a USB (Universal Serial Bus) memory. Also, the program may be downloaded from an external device via a network.

[0084] The process flow described in the above embodiment is merely an example, and unnecessary steps may be deleted, new steps may be added, or the process order may be changed, without departing from the spirit of the invention. [Explanation of symbols]

[0085] 12 Vehicles 30 Center Server 120 Information Processing Program 300 Acquisition Department 310 Derivation part 320A, 320B setting section 330 Extraction part

Claims

1. An acquisition unit that acquires vehicle information including an acceleration of the vehicle and a detection time when the acceleration is detected; a derivation unit that derives an amount of change in the acceleration per interval at which the acceleration is detected, using the vehicle information; a setting unit that sets a threshold value of the amount of change according to an interval at which the acceleration is detected, using the detection time; an extraction unit that extracts, when the amount of change is equal to or greater than the threshold, the vehicle information corresponding to the amount of change as target data; An information processing device comprising:

2. The setting unit is The shorter the interval, the larger the threshold is set. The information processing device according to claim 1 .

3. The setting unit is Setting the threshold value derived by dividing the interval by a predetermined value The information processing device according to claim 2 .

4. The setting unit is A lower limit value of the interval is set, and if the interval is equal to or greater than the lower limit value, the threshold value is set. The information processing device according to claim 2 .

5. The setting unit is The threshold is set using a trained model that has undergone machine learning to determine the threshold for the amount of change using previously acquired vehicle information as training data. The information processing device according to claim 1 .

6. The setting unit is A threshold value for the amount of change is set according to statistical information that collects previously acquired vehicle information. The information processing device according to claim 1 .

7. Acquire vehicle information including an acceleration of the vehicle and a detection time when the acceleration is detected; deriving an amount of change in the acceleration per interval during which the acceleration is detected using the vehicle information; Using the detection time, a threshold value of the amount of change corresponding to an interval at which the acceleration is detected is set; If the amount of change is equal to or greater than the threshold, extracting the vehicle information corresponding to the amount of change as target data. An information processing method in which processing is performed by a computer.

8. Acquire vehicle information including an acceleration of the vehicle and a detection time when the acceleration is detected; deriving an amount of change in the acceleration per interval during which the acceleration is detected using the vehicle information; Using the detection time, a threshold value of the amount of change corresponding to an interval at which the acceleration is detected is set; If the amount of change is equal to or greater than the threshold, extracting the vehicle information corresponding to the amount of change as target data. An information processing program that causes a computer to execute processing.

Images