Driving diagnosis device, driving diagnosis method, and driving diagnosis program
The driving diagnostic device addresses the cost and security issues of managing diverse vehicles by using sensors not connected to onboard equipment to adjust diagnostic models, thereby reducing system management costs and enhancing diagnostic accuracy.
Patent Information
- Application Number
- JP2021148770
- Authority / Receiving Office
- JP · JP
- Patent Type
- Patents
- Current Assignee / Owner
- Filing Date
- 2021-09-13
- Publication Date
- 2024-11-13
- Estimated Expiration
- 2041-09-13
AI Technical Summary
Managing driving diagnostic systems across vehicles of different manufacturers is costly due to the need for compatibility with various onboard equipment, and there are security concerns in obtaining operation information from vehicles not designed for the system.
A driving diagnostic device that acquires driving data from sensors not connected to the onboard device, adjusts a diagnostic model using second data from the onboard device, and performs diagnosis with first data from sensors, reducing the number of data items used for diagnosis.
This approach reduces the management cost of driving diagnostic systems by minimizing the need for compatibility with onboard equipment and enhances diagnostic accuracy using a combination of first and second data.
Smart Images

Figure 0007582136000001 
Figure 0007582136000002 
Figure 0007582136000003
Abstract
Description
[Technical field]
[0001] The present invention relates to a driving diagnosis device, a driving diagnosis method, and a driving diagnosis program for diagnosing driving. [Background technology]
[0002] Patent Document 1 discloses a driving diagnosis management system that acquires vehicle operation information from an on-board device and performs a diagnosis on driving skills using the operation information. [Prior art documents] [Patent documents]
[0003] [Patent Document 1] JP 2019-14473 A Summary of the Invention [Problem to be solved by the invention]
[0004] If the vehicle to be diagnosed is a vehicle of another company that is not involved in the design of the driving diagnosis system, it is not easy to obtain operation information from the on-board device. In addition, it is not desirable from the viewpoint of security. Therefore, when managing many types of vehicles, it is necessary to prepare a driving diagnosis system that is compatible with the on-board device installed in the vehicle, which increases management costs.
[0005] The present invention aims to provide a driving diagnosis device, a driving diagnosis method, and a driving diagnosis program that can reduce the management costs of a driving diagnosis system corresponding to an on-board device installed in a vehicle when managing many types of vehicles. [Means for solving the problem]
[0006] The driving diagnosis device according to claim 1 comprises: No on-board device that collects driving information To the vehicle Established An acquisition unit that acquires first data related to driving of the vehicle acquired from a sensor; different from the vehicle from which the first data was acquired Mounted on the vehicle The above Obtained from sensors connected to the vehicle Driving information an adjustment unit that adjusts a diagnostic model for diagnosing driving by inputting second data so that diagnosis using the first data is possible; and of the vehicle from which the first data was acquired A diagnosis unit that performs diagnosis regarding driving; The first data and the second data exist for each operation item, and the adjustment unit adjusts the diagnostic model by reducing the number of data items used for diagnosis.
[0007] The driving diagnosis device described in claim 1 diagnoses driving using first data acquired from a sensor not connected to an on-board device. When diagnosing driving, the driving diagnosis device adjusts a diagnostic model that uses second data mounted on the on-board device to perform diagnosis using the first data, and diagnoses driving. In other words, according to the driving diagnosis device, the second data connected to the on-board device is utilized to diagnose driving based on first data from a sensor or the like installed on the vehicle afterwards, thereby reducing the management cost of a driving diagnosis system corresponding to an on-board device mounted on a vehicle. According to the driving diagnosis device of claim 1, the number of items used for diagnosis can be reduced, thereby reducing management costs.
[0010] Claim 2 The driving diagnosis device described in Claim 1 In the driving diagnosis device according to the ,before The adjustment unit adjusts the diagnostic model by changing a threshold value used for the diagnosis.
[0011] Claim 2 According to the driving diagnosis device described in the above, driving can be diagnosed in consideration of the accuracy of the first data and the second data.
[0012] Claim 3 In the driving diagnosis device described in claim 1 or 2, the diagnostic model is a trained model that has been subjected to machine learning for the diagnosis using the second data, and the adjustment unit adjusts the diagnostic model by adding the first data to the second data and performing machine learning.
[0013] Claim 3According to the driving diagnosis device described in the above, in addition to the second data, the first data acquired in the past can be utilized to diagnose driving in the first data.
[0014] Claim 4 The driving diagnosis method described in No on-board device that collects driving information To the vehicle Established acquiring first data relating to operation of the vehicle from a sensor; different from the vehicle from which the first data was acquired Mounted on the vehicle The above Obtained from sensors connected to the vehicle Driving information A diagnostic model for diagnosing driving by inputting second data is adjusted so that diagnosis using the first data is possible, and the first data is input to the adjusted diagnostic model to perform the above. of the vehicle from which the first data was acquired Driving diagnostics the first data and the second data exist for each operation item, and a process of reducing the number of data items used for diagnosis and adjusting the diagnostic model is executed by a computer.
[0015] Claim 4 The computer executing the driving diagnosis method described in performs driving diagnosis using first data acquired from a sensor not connected to an on-board device. When performing driving diagnosis, the driving diagnosis method adjusts a diagnostic model that performs diagnosis using second data mounted on the on-board device so that diagnosis can be performed using the first data, and performs driving diagnosis. In other words, according to the driving diagnosis method, the second data connected to the on-board device is utilized to perform driving diagnosis based on the first data of a sensor or the like installed on the vehicle at a later date, thereby reducing the management cost of a driving diagnosis system corresponding to the on-board device mounted on the vehicle. According to the driving diagnosis method recited in claim 4, the number of items used in the diagnosis can be reduced, thereby reducing management costs.
[0016] Claim 5 The driving diagnosis program described in No on-board device that collects driving information To the vehicle Established acquiring first data relating to operation of the vehicle from a sensor; different from the vehicle from which the first data was acquired Mounted on the vehicle The above Obtained from sensors connected to the vehicle Driving informationA diagnostic model for diagnosing driving by inputting second data is adjusted so that diagnosis using the first data is possible, and the first data is input to the adjusted diagnostic model to perform the above. of the vehicle from which the first data was acquired Driving diagnostics the first data and the second data exist for each operation item, and the number of data items used for diagnosis is reduced to adjust the diagnostic model. The processing is executed by a computer.
[0017] Claim 5 A computer that executes the driving diagnosis program described in performs a driving diagnosis using first data acquired from a sensor not connected to an on-board device. When performing a driving diagnosis, the computer adjusts a diagnostic model that performs a diagnosis using second data mounted on the on-board device so that a diagnosis can be performed using the first data, and performs a driving diagnosis. In other words, the computer utilizes the second data connected to the on-board device to perform a driving diagnosis based on the first data of a sensor or the like that is installed in the vehicle after the fact, thereby reducing the management cost of a driving diagnosis system that corresponds to an on-board device mounted on a vehicle. According to the driving diagnosis program recited in claim 5, the number of items used in the diagnosis can be reduced, thereby reducing management costs. Effect of the Invention
[0018] According to the present invention, when managing many types of vehicles, it is possible to reduce the management costs of driving diagnosis systems corresponding to the on-board devices installed in the vehicles. [Brief description of the drawings]
[0019] [Figure 1] 1 is a diagram showing a schematic configuration of a driving diagnosis system according to an embodiment; [Diagram 2] 1 is a block diagram showing a hardware configuration of a vehicle according to an embodiment; [Diagram 3] FIG. 2 is a block diagram showing a functional configuration of the vehicle-mounted device according to the embodiment. [Figure 4] 1 is a block diagram showing a hardware configuration of a measuring device according to an embodiment; [Diagram 5] FIG. 2 is a block diagram showing the functional configuration of the measuring device according to the embodiment. [Figure 6]FIG. 2 is a block diagram showing a hardware configuration of a center server according to an embodiment. [Figure 7] FIG. 2 is a block diagram showing a functional configuration of a center server according to an embodiment. [Figure 8] 4 is a flowchart showing a flow of a driving diagnosis process executed in the center server of the embodiment. [Figure 9] 13 is a flowchart showing the flow of machine learning processing executed in a center server of a modified example. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS
[0020] A driving diagnosis system including the driving diagnosis device of the present invention will be described. The driving diagnosis system utilizes data related to driving skills obtained from a sensor connected to an on-board device of a vehicle, and diagnoses driving skills using data related to driving skills obtained from a sensor not connected to the on-board device.
[0021] (Overall composition) 1, a driving diagnosis system 10 according to an embodiment of the present invention includes a plurality of vehicles 12 and a center server 40 serving as a driving diagnosis device. The vehicles 12 include a vehicle 12A equipped with an on-board device 20 and a vehicle 12B equipped with a measuring device 30. The on-board device 20 and the measuring device 30 are mutually connected to the center server 40 via a network N.
[0022] Although FIG. 1 illustrates two vehicles 12 each including an on-board device 20 or a measuring device 30 for one center server 40, the number of vehicles 12, on-board devices 20, and measuring devices 30 is not limited to this.
[0023] The measuring device 30 is a device that measures positioning information, acceleration, and the like of the vehicle 12 and transmits the information to a center server 40. The center server 40 is installed, for example, at a manufacturer that manufactures the vehicle 12 or at a car dealership affiliated with the manufacturer.
[0024] (vehicle) As shown in FIG. 2, a vehicle 12A 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.
[0025] 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.
[0026] 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.
[0027] The ROM 20B stores various programs and various data. In the present embodiment, the ROM 20B stores a collection program 100 that collects driving information related to the state and control of the vehicle 12A from the ECU 22. When the collection program 100 is executed, the vehicle-mounted device 20 executes a process of transmitting the driving information to the center server 40. The ROM 20B also stores history information 110, which is backup data of the driving information. The RAM 20C temporarily stores programs or data as a working area.
[0028] 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.
[0029] The wireless communication I / F 20E is a wireless communication module for communicating with the center server 40. 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.
[0030] The ECU 22 includes at least an ADAS (Advanced Driver Assistance System)-ECU 22A, a steering ECU 22B, a brake ECU 22C, and an engine ECU 22D.
[0031] The ADAS-ECU 22A controls the advanced driving assistance system. A vehicle speed sensor 24A, a yaw rate sensor 24B, and an external sensor 24C, which constitute the in-vehicle device 24, are connected to the ADAS-ECU 22A. The external sensor 24C is a group of sensors used to detect the surrounding environment of the vehicle 12A. The external sensor 24C includes, for example, a camera that captures an image of the surroundings of the vehicle 12A, 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 area ahead of the vehicle 12A.
[0032] The steering ECU 22B controls the power steering. A steering angle sensor 24D constituting the in-vehicle device 24 is connected to the steering ECU 22B. The steering angle sensor 24D is a sensor that detects the steering angle of the steering wheel.
[0033] The brake ECU 22C controls a brake system of the vehicle 12A. A brake actuator 24E constituting the in-vehicle device 24 is connected to the brake ECU 22C.
[0034] The engine ECU 22D controls the engine of the vehicle 12A. A throttle actuator 24F and sensors 24G constituting the in-vehicle device 24 are connected to the engine ECU 22D. The sensors 24G include an oil temperature sensor for measuring the temperature of the engine oil, an oil pressure sensor for measuring the oil pressure of the engine oil, and a rotation sensor for detecting the engine speed.
[0035] The vehicle speed sensor 24A, yaw rate sensor 24B, external sensor 24C, steering angle sensor 24D, brake actuator 24E, throttle actuator 24F, and sensors 24G in this embodiment are examples of "sensors connected to the vehicle-mounted device."
[0036] 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.
[0037] The collection unit 200 has a function of acquiring the state of the in-vehicle device 24 from each ECU 22 of the vehicle 12A, and driving information related to the driving of the vehicle 12A obtained from the in-vehicle device 24. The driving information includes information such as vehicle speed, acceleration, yaw rate, steering angle, accelerator opening, and brake pedal depression force or stroke. The driving information may also include a captured image of the outside of the vehicle 12A captured by a camera serving as the external sensor 24C.
[0038] The output unit 210 has a function of outputting the driving information collected by the collection unit 200 to the center server 40.
[0039] (Measuring Equipment) 4, the measurement device 30 includes a CPU 30A, a ROM 30B, a RAM 30C, a storage 30D, a communication I / F 30E, a sensor 30F, and a GPS (Global Positioning System) device 30G. The CPU 30A, the ROM 30B, the RAM 30C, the storage 30D, the communication I / F 30E, the sensor 30F, and the GPS device 30G are connected to each other so as to be able to communicate with each other via an internal bus 30H. 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.
[0040] The storage 30D as a memory is configured with a HDD (Hard Disk Drive) or SSD (Solid State Drive) and stores various programs and information related to the measurement results acquired from the sensor 30F and the GPS device 30G (hereinafter referred to as "measurement information"). The storage 30D of this embodiment stores a collection program 120. The ROM 30B may also store the collection program 120. Here, the measurement information is an example of the "first data" and the driving information is an example of the "second data".
[0041] The sensor 30F is an acceleration sensor that detects the acceleration applied to the measuring device 30 mounted on the vehicle, and an angular velocity sensor that detects the angular velocity in the yaw direction.
[0042] The GPS device 30G is a device that receives positioning information from a plurality of GPS satellites that measures the position of the measuring device 30 mounted on the vehicle 12B, and detects the position. The GPS device 30G includes an antenna (not shown) that receives the positioning information from the GPS satellites.
[0043] The collection program 120 as a program performs processing to acquire positioning information, acceleration, and angular velocity as measurement information and transmit them to the center server 40.
[0044] The sensor 30F and the GPS device 30G according to the present embodiment are examples of "sensors not connected to an in-vehicle device".
[0045] As shown in FIG. 5, in the measuring device 30 of this embodiment, a CPU 30A executes a collection program 120 to function as a collection unit 300 and an output unit 310.
[0046] The collection unit 300 collects, as the measurement information, positioning information of the measurement device 30 mounted on the vehicle 12B from the GPS device 30G, and the acceleration and angular velocity of the vehicle 12B from the sensor 30F.
[0047] The output unit 310 has a function of outputting the driving information collected by the collection unit 300 to the center server 40.
[0048] (Center server) 6, the center server 40 includes a CPU 40A, a ROM 40B, a RAM 40C, a storage 40D, and a communication I / F 40E. The CPU 40A, the ROM 40B, the RAM 40C, the storage 40D, and the communication I / F 40E are connected to each other via an internal bus 40F so as to be able to communicate with each other. The functions of the CPU 40A, the ROM 40B, the RAM 40C, and the communication I / F 40E 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 40E may perform wired communication.
[0049] The storage 40D 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 40D stores a driving diagnosis program 130, a driving information database (DB) 140, and a diagnosis model 150. The ROM 40B may store the driving diagnosis program 130, the driving information DB 140, and the diagnosis model 150.
[0050] The driving diagnosis program 130 as a program is a program for controlling the center server 40. In accordance with the execution of the driving diagnosis program 130, the center server 40 executes various processes including a driving diagnosis process for diagnosing the driving skill of the driver of the vehicle 12.
[0051] The driving information DB 140 stores driving information received from the vehicle-mounted device 20 and measurement information received from the measurement device 30.
[0052] The diagnostic model is a model in which judgment conditions such as thresholds are set for diagnosing driving skills related to driving using driving information received from the vehicle-mounted device 20. Here, the judgment conditions set in the diagnostic model are thresholds and the like corresponding to the driving information received from the vehicle-mounted device 20. The thresholds are judgment conditions for judging driving skills for each driving item from each data related to driving information by analyzing driving information collected in the past.
[0053] That is, by inputting driving information including various data into the diagnostic model, a diagnostic result indicating the driving skill corresponding to the driving information is output.
[0054] As shown in FIG. 7, in the center server 40 of this embodiment, a CPU 40A executes a driving diagnosis program 130 to function as an acquisition unit 400, a storage unit 410, an adjustment unit 420, a diagnosis unit 430, and an output unit 440.
[0055] The acquisition unit 400 has a function of acquiring driving information and measurement information from the on-board device 20 of the vehicle 12A and the measurement device 30 of the vehicle 12B. The acquisition unit 400 acquires driving information and measurement information transmitted from the on-board device 20 and the measurement device 30 at any timing.
[0056] The storage unit 410 stores the driving information acquired from the vehicle-mounted device 20 and the measurement information acquired from the measurement device 30 in the driving information DB 140.
[0057] When diagnosing driving based on the measurement information obtained from the measuring device 30, the adjustment unit 420 adjusts the diagnostic model to correspond to the measurement information obtained from the measuring device 30.
[0058] Specifically, the adjustment unit 420 performs adjustment to limit the number of data related to the driving information to be input to the diagnostic model 150. For example, the driving information related to the in-vehicle device 20 includes vehicle speed, acceleration, yaw rate, steering angle, accelerator opening, brake pedal force or stroke, etc., and the measurement information related to the measurement device 30 includes positioning information, acceleration, angular velocity, etc. of the vehicle 12. Therefore, the number and type of data in each piece of driving information are different.
[0059] For example, the diagnostic model diagnoses sudden start using the vehicle speed, acceleration, and accelerator opening for the driving information related to the in-vehicle device 20. Therefore, the adjustment unit 420 adjusts the measurement information related to the measurement device 30 to diagnose sudden start using the positioning information and acceleration. Also, the diagnostic model diagnoses rough driving using the yaw rate, steering angle, accelerator opening, and brake pedal force for the driving information related to the in-vehicle device 20. Therefore, the adjustment unit 420 adjusts the measurement information related to the measurement device 30 to diagnose rough driving using the acceleration and angular velocity.
[0060] That is, the operation information and measurement information include predetermined data for each operation item to be diagnosed, and the adjustment unit 420 switches the number and type of data used for the operation item and adjusts the diagnosis for the operation item using a diagnostic model.
[0061] In the above embodiment, the adjustment unit 420 performs an adjustment to limit the number of pieces of data to be input to the diagnostic model. However, the present invention is not limited to this. The adjustment unit 420 may adjust the judgment conditions related to the diagnostic model.
[0062] For example, when diagnosing sudden acceleration using driving information related to the measuring device 30, the number and type of data is different from that of the driving information related to the vehicle-mounted device 20, so the accuracy of the driving diagnosis may be inferior compared to the driving information related to the vehicle-mounted device 20.
[0063] Therefore, the adjustment unit 420 may adjust the judgment conditions for the diagnostic model by changing, by adding or subtracting, a threshold value corresponding to the driving information related to the in-vehicle device 20 in order to diagnose the measurement information related to the measuring device 30. For example, when a score for sudden acceleration is calculated from the driving information and the degree of sudden acceleration is diagnosed using the diagnostic model, the adjustment unit 420 adjusts the diagnosis by changing the threshold value for determining the degree of sudden acceleration in the diagnostic model.
[0064] The diagnosis unit 430 uses the diagnosis model to diagnose the operation items according to the data related to the operation information. Here, when diagnosing the operation items using the measurement information related to the measuring device 30, the diagnosis unit 430 uses the diagnosis model adjusted by the adjustment unit 420 to perform the diagnosis.
[0065] The output unit 440 outputs the diagnosis result by the diagnosis unit 430. Here, the output unit 440 may output the diagnosis result by transmitting it to the vehicle-mounted device 20, the measuring device 30, etc., or may output the diagnosis result by displaying it on a monitor (not shown) provided in the center server 40.
[0066] (Flow of Control) The flow of processing executed in the driving diagnosis system 10 of this embodiment will be described with reference to the flowchart in Fig. 8. The processing in the center server 40 is executed by the CPU 40A of the center server 40 functioning as an acquisition unit 400, a storage unit 410, an adjustment unit 420, a diagnosis unit 430, and an output unit 440. The driving diagnosis processing shown in Fig. 8 is executed, for example, when an instruction to execute driving diagnosis is input.
[0067] In step S100, CPU 40A acquires driving information or measurement information stored in driving information DB 140 as data for diagnosing driving.
[0068] In step S101, the CPU 40A obtains the diagnostic model 150 from the storage 40D.
[0069] In step S102, the CPU 40A determines whether the acquired data is measurement information related to the measuring device 30. If the acquired data is measurement information related to the measuring device 30 (step S102: YES), the CPU 40A proceeds to step S103. On the other hand, if the acquired data is not measurement information related to the measuring device 30 (driving information related to the vehicle-mounted device 20) (step S102: NO), the CPU 40A proceeds to step S104.
[0070] In step S103, CPU 40A adjusts diagnostic model 150.
[0071] In step S104, CPU 40A uses diagnostic model 150 to diagnose driving on the acquired data.
[0072] In step S105, CPU 40A outputs the diagnosis result.
[0073] In step S106, the CPU 40A determines whether or not to end the driving diagnosis process. If the driving diagnosis process is to be ended (step S106: YES), the driving diagnosis process is ended. On the other hand, if the driving diagnosis process is not to be ended (step S106: NO), the CPU 40A proceeds to step S100 and acquires information.
[0074] (Modification) The diagnostic model according to the above embodiment is a model in which a judgment condition such as a threshold value is set. However, the diagnostic model is not limited to this. The diagnostic model may be a trained model that is machine-learned based on the driving information received from the vehicle-mounted device 20 in order to judge the driving skill.
[0075] For example, if the diagnostic model 150 is a model that has been subjected to machine learning using driving information related to the vehicle-mounted device 20 as learning data, the adjustment unit 420 can adjust the model by further learning measurement information related to the measuring device 30 that has been previously acquired and stored in the driving information DB 140.
[0076] The diagnostic model 150 learns driving information related to the vehicle-mounted device 20 and measurement information related to the measurement device 30, and is thereby capable of diagnosing driving based on the measurement information related to the measurement device 30 by utilizing the driving information related to the vehicle-mounted device 20.
[0077] Furthermore, the diagnostic model 150 uses fixed-length data in which predetermined data in the driving information is set in a predetermined location as learning data, so that machine learning is possible even if the amount of data differs between the driving information related to the in-vehicle device 20 and the measurement information related to the measurement device 30. For example, even if any data does not exist in the driving information related to the measurement device 30, null data is set instead of the data and used as learning data, so that machine learning can be performed even if the amount of data differs.
[0078] That is, the adjustment unit 420 adjusts the diagnostic model by having the diagnostic model learn the measurement information related to the measuring device 30 in addition to the driving information related to the in-vehicle device 20. Also, the adjustment unit 420 adjusts the diagnostic model by having the fixed-length data in the driving information learn as learning data and reducing the number of data.
[0079] The flow of processing executed in the driving diagnosis system 10 of the modified example will be described with reference to the flowchart in Fig. 9. The processing in the center server 40 is executed by the CPU 40A of the center server 40 functioning as an acquisition unit 400, a storage unit 410, an adjustment unit 420, a diagnosis unit 430, and an output unit 440. The machine learning processing shown in Fig. 9 is executed, for example, when an instruction to execute learning is input.
[0080] In step S200, the CPU 40A acquires the driving information and the measurement information stored in the driving information DB 140 as learning data for machine learning. Here, the driving information and the measurement information as the learning data are set with diagnostic results as labels. For example, in the learning data, diagnostic results such as sudden acceleration and rough driving are set as labels for each piece of driving information and measurement information.
[0081] In step S201, the CPU 40A executes machine learning on the diagnostic model using the acquired learning data. Here, the CPU 40A executes supervised learning using the driving information and the measurement information as input data and the labels set for the driving information and the measurement information as correct answer data for the input data.
[0082] In step S202, CPU 40A generates a diagnostic model.
[0083] In step S203, the CPU 40A determines whether or not to end the machine learning process. If the machine learning process is to be ended (step S203: YES), the process proceeds to step S204. On the other hand, if the machine learning process is not to be ended (step S203: NO), the CPU 40A proceeds to step S200 and acquires learning data.
[0084] Here, if machine learning is not terminated and machine learning is performed again, the labels set in the driving information and measurement information may be changed and learning may be performed, or the learning data may be changed and learning may be performed again.
[0085] In step S204, CPU 40A stores the diagnostic model.
[0086] Through the above process, a diagnostic model is generated that performs adjustable driving diagnosis according to driving information and measurement information.
[0087] In addition, the diagnostic model according to the above embodiment has been described as a form in which a diagnosis of a driving item is performed according to data related to driving information. However, the present invention is not limited to this. Other data may be estimated from data related to measurement information to perform diagnosis. For example, the vehicle speed of the vehicle 12B may be estimated from positioning information included in the measurement information related to the measurement device 30, and the driving item may be diagnosed using the estimated vehicle speed.
[0088] The measuring device 30 according to the embodiment described above is equipped with the sensor 30F and the GPS device 30G. However, the present invention is not limited to this. The measuring device 30 may be equipped with only the sensor 30F or only the GPS device 30G.
[0089] Further, the measurement device 30 according to the above embodiment has been described as a form in which the position of the vehicle 12B is measured by the GPS device 30G. However, the present invention is not limited to this. For example, the position of the vehicle 12B may be measured by using the communication I / F 30E. For example, when the communication I / F 30E is Wi-Fi (registered commercial), the position and speed of the vehicle 12B can be estimated by storing the connected Wi-Fi (registered commercial) access point and the time of connection to the access point.
[0090] (summary) The center server 40 as the driving diagnosis device of this embodiment diagnoses driving using first data acquired from a sensor not connected to the on-board device. When diagnosing driving, the driving diagnosis device adjusts a diagnostic model that uses second data mounted on the on-board device to perform diagnosis using the first data, and diagnoses driving. In other words, according to the driving diagnosis device, the second data connected to the on-board device is utilized to diagnose driving based on the first data of a sensor or the like installed on the vehicle afterwards, thereby reducing the management cost of a driving diagnosis system corresponding to the on-board device mounted on the vehicle.
[0091] Furthermore, according to the center server 40 of this embodiment, the number of items used in the diagnosis can be reduced, thereby reducing management costs.
[0092] Furthermore, the center server 40 of the present embodiment can diagnose driving while taking into consideration the accuracy of the first data and the second data.
[0093] Furthermore, according to the center server 40 of the present embodiment, in addition to the second data, the first data acquired in the past can be used to diagnose driving in the first data.
[0094] [remarks] In the above embodiment, the center server 40 is the driving diagnosis device, but this is not limited thereto, and the vehicle-mounted device 20 may be the driving diagnosis device. In this case, the vehicle-mounted device 20 acquires measurement information related to the measurement device 30 mounted on the vehicle 12, and executes driving diagnosis processing using a pre-stored diagnosis model.
[0095] In the above embodiment, various processes executed by the CPU 20A, CPU 30A, and CPU 40A by reading 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 a Field-Programmable Gate Array (FPGA) whose circuit configuration can be changed after manufacture, and a dedicated electric circuit such as an Application Specific Integrated Circuit (ASIC) 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.
[0096] In the above embodiment, each program is 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, the collection program 100 in the measurement device 30 is prestored in the storage 30D, and the driving diagnosis program 130 in the center server 40 is prestored in the storage 40D. However, without being limited to this, 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.
[0097] 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]
[0098] 12 Vehicles 20 Onboard equipment 30 Measuring Equipment 40 Center Server (Driving Diagnosis Device) 40A CPU (processor) 130 Driving diagnostic program 150 Diagnostic Models 400 Acquisition Department 420 Adjustment section 430 Diagnostic Department
Claims
1. An acquisition unit that acquires first data regarding driving of a vehicle acquired from a sensor installed in a vehicle that does not have an on-board device that collects driving information; an adjustment unit that adjusts a diagnostic model for performing a diagnosis regarding driving by inputting second data, which is driving information acquired from a sensor connected to the on-board device mounted on a vehicle different from the vehicle from which the first data was acquired, so that a diagnosis using the first data is possible; a diagnosis unit that inputs the first data to the adjusted diagnostic model and performs a diagnosis regarding driving of the vehicle from which the first data was acquired, The first data and the second data exist for each operation item, The adjustment unit adjusts the diagnostic model by reducing the number of data items used for diagnosis. Driving diagnostic device.
2. A driving diagnosis device as described in claim 1, wherein the adjustment unit adjusts the diagnostic model by changing a threshold value used for the diagnosis.
3. The diagnostic model is a trained model that has been subjected to machine learning for the diagnosis using the second data, The driving diagnosis device according to claim 1 or 2, wherein the adjustment unit adjusts the diagnosis model by performing machine learning by adding the first data to the second data.
4. Acquiring first data regarding the driving of a vehicle obtained from a sensor installed in a vehicle that is not equipped with an on-board device that collects driving information, adjusting a diagnostic model for performing a diagnosis regarding driving by inputting second data, which is driving information acquired from a sensor connected to the in-vehicle device mounted on a vehicle different from the vehicle in which the first data was acquired, so that a diagnosis using the first data is possible; inputting the first data into the adjusted diagnostic model to perform a diagnosis regarding the operation of the vehicle from which the first data was obtained; The first data and the second data exist for each operation item, Adjusting the diagnostic model by reducing the number of items of data used for diagnosis; A driving diagnosis method in which processing is performed by a computer.
5. Acquiring first data regarding the driving of a vehicle obtained from a sensor installed in a vehicle that is not equipped with an on-board device that collects driving information, adjusting a diagnostic model for performing a diagnosis regarding driving by inputting second data, which is driving information acquired from a sensor connected to the in-vehicle device mounted on a vehicle different from the vehicle from which the first data was acquired, so that a diagnosis using the first data is possible; inputting the first data into the adjusted diagnostic model to perform a diagnosis regarding the operation of the vehicle from which the first data was obtained; The first data and the second data exist for each operation item, Adjusting the diagnostic model by reducing the number of items of data used for diagnosis; A driving diagnostic program that causes a computer to execute processing.
Citation Information
Patent Citations
Device and method for predicting future status of driver
JP2003058994A
Thermal protection and drag reduction system for ultra high-speed aircraft
JP2019014473A
Collision preventing device, collision preventing method, collision preventing program, and recording medium
JP2019046319A
Information collection method, information collection system, and information collection program
JP2020021409A
Cited By
Uniform configuration method for integration of industrial wireless network and time-sensitive network
US20260222285A1
