Center, generation program, generation method, and generation system

Abstract

A center (3) is configured to perform data communication with a plurality of on-vehicle devices (2) mounted on each of a plurality of vehicles and is provided with an acquisition unit (61) and generation units (62, 65). The acquisition unit is configured to acquire primary processed data for each of the plurality of vehicles, the primary processed data being vehicle data processed into a format independent of the type of the vehicle and the manufacturer of the vehicle. The generation unit is configured to generate, as secondary processed data, data obtained by extracting a feature amount using one or more pieces of the primary processed data acquired by the acquisition unit.

Description

Center, generation program, generation method, and generation system CROSS-REFERENCE TO RELATED APPLICATIONS

[0001] This international application claims the benefit of Japanese Patent Application No. 2024-105137, filed with the Japan Patent Office on June 28, 2024, the entire disclosure of which is incorporated herein by reference.

[0002] The present disclosure relates to a center, a generation program, a generation method, and a generation system that utilize data acquired from a vehicle.

[0003] Patent Document 1 describes a service providing server that provides services by accessing a digital twin that reproduces the state of a vehicle in the real world in a virtual space by collecting vehicle data from multiple vehicles.

[0004] International Publication No. 2023 / 276957

[0005] When providing a service to a vehicle, it may be necessary to acquire vehicle data related to the vehicle from the target vehicle to which the service is to be provided.

[0006] After detailed consideration by the inventors, it was found that in order to provide a service to a vehicle, it may be necessary to generate new information necessary for the service using vehicle data obtained from the vehicle, which may reduce the convenience of providing the service.

[0007] The present disclosure facilitates the use of vehicle data.

[0008] One aspect of the present disclosure is a center configured to perform data communication with a plurality of on-board devices mounted on a plurality of vehicles, and including an acquisition unit and a generation unit.

[0009] The acquisition unit is configured to acquire, for each of the plurality of vehicles, primary processed data, which is vehicle data that has been processed into a format that is independent of the vehicle model and vehicle manufacturer.

[0010] The generating unit is configured to generate, as the secondary processed data, data in which feature amounts are extracted using one or more pieces of primary processed data acquired by the acquiring unit.

[0011] In the center of the present disclosure configured as above, the service providing server and the service application do not need to generate new secondary processed data using the vehicle data acquired from the vehicle, which makes it easier to use the vehicle data.

[0012] Another aspect of the present disclosure is a generation program for causing a computer at a center configured to perform data communication with multiple on-board devices installed in each of multiple vehicles to function as an acquisition unit and a generation unit.

[0013] A computer controlled by the generation program of the present disclosure can constitute a part of the center of the present disclosure, and can obtain the same effects as the center of the present disclosure.

[0014] Yet another aspect of the present disclosure is a generation method executed at a center configured to perform data communication with a plurality of on-board devices mounted on a plurality of vehicles, respectively.

[0015] In the generation method of the present disclosure, the center acquires primary processed data for each of a plurality of vehicles, which is vehicle data that has been processed into a format that is independent of the vehicle model and vehicle manufacturer, and then generates secondary processed data by extracting feature quantities using one or more of the acquired primary processed data.

[0016] The generation method of the present disclosure is a method executed at the center of the present disclosure, and by executing this method, it is possible to obtain the same effects as those of the center of the present disclosure.

[0017] According to another aspect of the present disclosure, there is provided a generation system including a plurality of on-board devices mounted on a plurality of vehicles, and a center configured to perform data communication between the plurality of on-board devices. In the generation system of the present disclosure, the center includes an acquisition unit and a generation unit.

[0018] The generation system of the present disclosure is a system that includes the center of the present disclosure, and can obtain the same effects as the center of the present disclosure.

[0019] 1 is a block diagram showing the configuration of a mobility IoT system. FIG. 2 is a block diagram showing the configuration of an on-board device and a center of a first embodiment. FIG. 3 is a functional block diagram showing the functional configuration of an on-board device and a center of a first embodiment. FIG. 4 is a diagram showing the configuration of primary processed data. FIG. 5 is a diagram showing the configuration of a CAN frame. FIG. 6 is a diagram showing the configuration of a vehicle data conversion table. FIG. 7 is a diagram showing the configuration of secondary processed data. FIG. 8 is a flowchart showing the procedure for generating and synchronizing secondary processed data. FIG. 9 is a block diagram showing the configuration of an on-board device and a center of a second embodiment. FIG. 10 is a functional block diagram showing the functional configuration of an on-board device and a center of a second embodiment. FIG. 11 is a flowchart showing the procedure for generating and synchronizing a model.

[0020] First Embodiment A first embodiment of the present disclosure will be described below with reference to the drawings.

[0021] 1, a mobility IoT system 1 of this embodiment includes a plurality of in-vehicle devices 2, a center 3, and a service providing server 4. IoT is an abbreviation for Internet of Things.

[0022] The in-vehicle device 2 is mounted on a vehicle and has a function of performing data communication with the center 3 via a wide area wireless communication network NW.

[0023] The center 3 is a device that manages the mobility IoT system 1. The center 3 has a function of performing data communication between the multiple in-vehicle devices 2 and the service providing server 4 via the wide area wireless communication network NW.

[0024] The service providing server 4 is, for example, a server installed to provide a service for selecting a vehicle to which a shadow mode application is to be distributed. Note that the mobility IoT system 1 may include multiple service providing servers each providing a different service content.

[0025] As shown in FIG. 2, the in-vehicle device 2 includes a microcomputer 11, a vehicle interface (hereinafter referred to as vehicle I / F) 12, a communication unit 13, and a storage unit 14.

[0026] The microcomputer 11 includes a CPU 21 , a ROM 22 , a RAM 23 , an input / output unit 24 , and a bus 25 .

[0027] The various functions of the microcomputer 11 are realized by the CPU 21 executing a program stored in a non-transitory physical recording medium. In this example, the ROM 22 corresponds to the non-transitory physical recording medium storing the program. Execution of this program also executes a method corresponding to the program. Note that some or all of the functions executed by the CPU 21 may be configured as hardware using one or more ICs, etc.

[0028] The input / output unit 24 is a circuit for inputting and outputting data between the CPU 21 and the outside of the microcomputer 11 .

[0029] The bus 25 connects the CPU 21, the ROM 22, the RAM 23, and the input / output unit 24 so that data can be input and output to and from each other.

[0030] The vehicle I / F 12 is an input / output circuit for transmitting and receiving signals to and from electronic control devices, sensors, and the like mounted on the vehicle.

[0031] The vehicle I / F 12 includes a power supply voltage input port, a general-purpose input / output port, a CAN communication port, an Ethernet communication port, and the like.

[0032] The power supply voltage input port includes a +B voltage port to which a +B voltage is input and an IG voltage port to which an IG voltage is input. The CAN communication port is a port for transmitting and receiving data according to the CAN communication protocol. The Ethernet communication port is a port for transmitting and receiving data based on the Ethernet communication protocol. CAN is an abbreviation for Controller Area Network. Ethernet is a registered trademark.

[0033] Other electronic control units mounted on the vehicle are connected to the CAN communication port and the Ethernet communication port, thereby enabling the in-vehicle device 2 to transmit and receive communication frames to and from the other electronic control units.

[0034] The communication unit 13 performs data communication with the center 3 via the wide area wireless communication network NW.

[0035] The storage unit 14 is a storage device for storing various data, and includes a vehicle data conversion table 26 (described later), a vehicle data storage unit 27 (described later), and a download data storage unit 28 (described later).

[0036] The center 3 includes a control unit 31 , a communication unit 32 , and a storage unit 33 .

[0037] The control unit 31 is an electronic control device mainly composed of a microcomputer including a CPU 41, a ROM 42, a RAM 43, etc. The various functions of the microcomputer are realized by the CPU 41 executing a program stored in a non-transitory tangible recording medium. In this example, the ROM 42 corresponds to the non-transitory tangible recording medium storing the program. Furthermore, the execution of this program results in the execution of a method corresponding to the program. Note that some or all of the functions executed by the CPU 41 may be configured as hardware using one or more ICs, etc. Furthermore, the number of microcomputers constituting the control unit 31 may be one or more.

[0038] The communication unit 32 performs data communication between the plurality of in-vehicle devices 2 and the service providing server 4 via the wide area wireless communication network NW.

[0039] The storage unit 33 is a storage device for storing various data, and includes a primary processed data storage unit 44 (to be described later) and a secondary processed data storage unit 45 (to be described later).

[0040] As shown in FIG. 3, the in-vehicle device 2 includes a data acquisition unit 51, a primary processing unit 52, and a data linking unit 53 as functional blocks realized by the CPU 21 executing a program stored in the ROM 22.

[0041] The data acquisition unit 51 acquires data input to the vehicle I / F 12 (i.e., data input to the general-purpose input / output port, the CAN communication port, and the Ethernet communication port). Examples of data input to the general-purpose input / output port include image data captured by a camera mounted on the vehicle. Data input to the CAN communication port is a CAN frame. Data input to the Ethernet communication port is an Ethernet frame.

[0042] The primary processing unit 52 processes the vehicle data acquired by the data acquisition unit 51 into common data (hereinafter referred to as primary processed data) in which the same physical quantities have the same values ​​regardless of the vehicle model and vehicle manufacturing company (hereinafter referred to as manufacturer) by referring to the vehicle data conversion table 26 stored in the memory unit 14.

[0043] The vehicle data conversion table 26 contains conversion information for converting vehicle data of the vehicle (hereinafter referred to as the "own vehicle") in which the on-board device 2 is mounted into common data. The conversion information may be set based on the Vehicle Signal Specifications (VSS). VSS stands for Vehicle Signal Specifications.

[0044] The primary processed data includes, for example, a time stamp, a vehicle speed, a steering angle, an accelerator pedal position, a brake pedal position, and a vehicle position, as shown in FIG.

[0045] Here, a specific example of processing vehicle data into primary processed data will be described.

[0046] As shown in Fig. 5, a CAN frame is composed of a start of frame, arbitration field, control field, data field, CRC field, ACK field, and end of frame. The arbitration field is composed of an 11-bit or 29-bit identifier (i.e., ID) and a 1-bit RTR bit.

[0047] The 11-bit identifier used in CAN communication is called a CAN ID. The CAN ID is set in advance based on the content of the data included in the CAN frame, the source of the CAN frame, the destination of the CAN frame, etc.

[0048] The data field is a payload consisting of first, second, third, fourth, fifth, sixth, seventh, and eighth data, each of which is 8 bits (i.e., 1 byte). Hereinafter, each of the first to eighth data in the data field will also be referred to as CAN data.

[0049] The primary processing unit 52 first divides the first to eighth data into 1-byte pieces and extracts eight CAN data. The CPU 41 then refers to the vehicle data conversion table 26 and converts each extracted data piece into a control label and vehicle data. The control label is identification information that indicates the type of the vehicle data.

[0050] The vehicle data conversion table 26 includes normalization information and semantic information.

[0051] The normalization information is information for normalizing the extracted data so that the same physical quantity has the same value regardless of the vehicle model and manufacturer.

[0052] Semantic information is information (e.g., an arithmetic expression or a conversion table) for converting normalized vehicle data into meaningful vehicle data. Vehicle data before normalization may also be used. Semantic information includes newly generating information that was not included in the payload of a communication frame using an arithmetic expression or the like.

[0053] As shown in FIG. 6, the normalization information of vehicle data conversion table 26 includes setting items such as "CANID," "ECU," "position," "DLC," "unique label," "resolution," "offset," and "unit."

[0054] "ECU" is identification information that indicates the ECU that is the sender of the CAN frame. For example, "ENG" indicates an engine ECU.

[0055] "Position" is information indicating the position (e.g., bit position) of the CAN data within the data field. "DLC" is information indicating the data length. DLC stands for Data Length Code. In other words, "DLC" bits of data are extracted from the "position" of the data field.

[0056] "Unique label" is information indicating the control label. For example, "ETHA" indicates the intake air temperature, and "NE1" indicates the engine speed. "Resolution" is information indicating the numerical value per bit. "Offset" indicates the offset amount of the numerical value of the data. "Unit" indicates the unit of the data.

[0057] Therefore, data corresponding to the "unique label" is extracted from the CAN frame using the "CAN ID," "ECU," "position," "DLC," and "unique label." The extracted data is then converted into vehicle data expressed by the "resolution," "offset," and "unit."

[0058] Further, the semantic information of the vehicle data conversion table 26 is, for example, a conversion formula for converting a "steering movement angle" whose control label is "SSA" into a "steering angle" by subtracting a "steering zero point" whose control label is "SSAZ" as shown in Fig. 6. In this way, the vehicle data representing the "steering movement angle" and the vehicle data representing the "steering zero point" are converted into vehicle data representing a "steering angle" which has the meaning of "amount of steering from a reference position". A "unique label", "unit", etc. are assigned to the vehicle data newly generated by the semanticization.

[0059] The system also has a vehicle data conversion table 26 for data on "shift position," which is a predetermined control label. The vehicle data conversion table 26 converts the data into data indicating "P range," "N range," "D range," and "R range," respectively.

[0060] As shown in FIG. 3 , the data linking unit 53 manages access from the service application 16 installed in the vehicle to the secondary processed data stored in the download data storage unit 28 (described later). The service application 16 is installed in the in-vehicle device 2 or another electronic control unit connected to the in-vehicle device 2 and provides a predetermined service to the vehicle user. The predetermined service is, for example, a service that provides driving advice to make driving easier for the driver or driving advice tailored to the driver. For example, driving advice may be advice to reduce the number of sudden braking attempts for a driver who tends to brake suddenly (e.g., advice such as "press the brake pedal quickly"). For example, driving advice may be advice to reduce the number of sudden acceleration attempts for a driver who tends to accelerate suddenly (e.g., advice such as "press the accelerator pedal slowly").

[0061] The data linking unit 53 uploads the image data acquired by the data acquisition unit 51 and the primary processed data generated by the primary processing unit 52 to the center 3 together with information identifying the driver of the vehicle and information identifying the vehicle.

[0062] The center 3 has functional blocks realized by the CPU 41 executing a program stored in the ROM 42, including a primary processing data acquisition unit 61, a secondary processing unit 62, a data management unit 63, and a data distribution unit 64.

[0063] The primary processed data acquisition unit 61 acquires image data and primary processed data uploaded to the center 3 from multiple vehicle-mounted devices 2, and stores the acquired image data and primary processed data in the primary processed data storage unit 44 of the center 3.

[0064] The secondary processing unit 62 uses the plurality of primary processed data and image data stored in the primary processed data storage unit 44 to generate common data that can be used in common by the service application 16 and the service providing server 4. The secondary processing unit 62 starts generating common data when the primary processed data for the required period has been accumulated.

[0065] The secondary processing unit 62 stores the generated plurality of common data in the secondary processed data storage unit 45. Hereinafter, the common data stored in the secondary processed data storage unit 45 will be referred to as secondary processed data.

[0066] The secondary processing unit 62 generates secondary processed data indicating the driver's facial direction, or secondary processed data indicating whether the driver is feeling drowsy, for example, by analyzing the image data.

[0067] The data stored in the primary processed data storage unit 44 and the secondary processed data storage unit 45 can be accessed by the administrator of the center 3 via an interface provided in the center 3 .

[0068] The secondary processing unit 62 generates secondary processed data indicating whether or not a traffic jam has occurred by determining whether or not a preset traffic jam determination condition is met, for example. The traffic jam determination condition is, for example, that the vehicle speed is less than 10 km / h and the distance between the vehicle ahead and the vehicle is 20 m or less for 10 minutes or more.

[0069] The secondary processed data includes, for example, an environment model data set 71, a vehicle model data set 72, and a human model data set 73, as shown in FIG.

[0070] The environment model data set 71 includes "personal ID," "VIN," "traffic jam," "expressway," "general road," "parking lot," "geofence," "day / night," and "timestamp."

[0071] "Personal ID" is information that identifies the person driving the vehicle. "VIN" is a registration number unique to the vehicle. "Traffic jam" indicates whether the vehicle is in a traffic jam. "Expressway" indicates whether the vehicle is traveling on an expressway. "General road" indicates whether the vehicle is traveling on a general road. "Parking lot" indicates whether the vehicle is parked in a parking lot. "Geofence" is information that identifies the geofence to which the vehicle belongs. "Day / night" indicates whether the vehicle is traveling during the day or at night. "Timestamp" indicates the time, for example in seconds, when the in-vehicle device 2 acquired the data.

[0072] The vehicle model data set 72 includes "personal ID", "VIN", "driving", "stopped", "power off", "ACC use status", "navigation use status", "vehicle speed", "position information", and "timestamp".

[0073] "Driving" indicates whether the vehicle is driving or not. "Stopped" indicates whether the vehicle is stopped or not. "Power Off" indicates whether the IG power supply of the vehicle is off or not. "ACC Use Status" indicates whether the vehicle is using auto cruise control or not. "Navigation Use Status" indicates whether the vehicle is using the route guidance function of the navigation device or not. "Vehicle Speed" indicates the driving speed of the vehicle. "Location Information" indicates the location of the vehicle by latitude and longitude.

[0074] The human model data set 73 includes "personal ID", "VIN", "driver type", "number of occupants", "driving tendency", "face direction", "drowsiness", and "timestamp".

[0075] "Driver type" indicates the age, gender, driving history, etc. of the driver of the vehicle. "Number of occupants" indicates the number of people in the vehicle. "Driving tendency" indicates the driving tendency of the driver of the vehicle. "Driving tendency" indicates, for example, whether the driver brakes or turns suddenly more or less than average. "Facial direction" indicates the facial direction of the driver of the vehicle. "Drowsiness" indicates whether the driver of the vehicle is drowsy.

[0076] The data management unit 63 manages the secondary processed data stored in the secondary processed data storage unit 45. Specifically, the data management unit 63 provides the secondary processed data corresponding to each vehicle to the data distribution unit 64, and provides the secondary processed data required by the service providing server 4 to the service providing server 4.

[0077] The data distribution unit 64 distributes the secondary processed data corresponding to each vehicle, among the plurality of secondary processed data stored in the secondary processed data storage unit 45 , to each in-vehicle device 2 .

[0078] The data linking unit 53 of the in-vehicle device 2 stores the secondary processed data downloaded from the center 3 in the download data storage unit 28 .

[0079] Next, a procedure in which the center 3 generates secondary processed data and synchronizes it with the in-vehicle device 2 will be described.

[0080] As shown in FIG. 8, in S10, the in-vehicle device 2 acquires vehicle data from the vehicle using the data acquisition unit 51.

[0081] At S20, the in-vehicle device 2 processes the vehicle data acquired by the data acquisition unit 51 into primary processed data using the primary processing unit 52, and then uploads the image data acquired by the data acquisition unit 51 and the primary processed data generated by the primary processing unit 52 to the center 3 using the data linking unit 53, together with information identifying the driver of the vehicle and information identifying the vehicle.

[0082] In S30, the center 3 determines whether or not the primary processed data for the required period has been accumulated. If the primary processed data for the required period has not been accumulated, the in-vehicle device 2 repeats the processes of S10 and S20. On the other hand, if the primary processed data for the required period has been accumulated, the center 3 generates secondary processed data by the secondary processing unit 62 in S40.

[0083] In S50, the center 3 stores the secondary processed data generated in S40 in the secondary processed data storage unit 45, thereby updating the secondary processed data.

[0084] In S60, the center 3 synchronizes the secondary processed data between the center 3 and the vehicle-mounted device 2 by distributing the secondary processed data updated in S50 to each vehicle using the data distribution unit 64.

[0085] The center 3 configured in this manner is configured to perform data communication with multiple on-board devices 2 installed in each of multiple vehicles, and is equipped with a primary processed data acquisition unit 61 and a secondary processing unit 62.

[0086] The primary processed data acquisition unit 61 is configured to acquire primary processed data, which is vehicle data that has been processed into a format that is independent of the vehicle model and manufacturer, for each of a plurality of vehicles.

[0087] The secondary processing unit 62 is configured to generate data, as secondary processed data, by extracting feature amounts using one or more pieces of primary processed data acquired by the primary processed data acquisition unit 61 .

[0088] The secondary processed data includes at least one of the operations performed by the occupant on the vehicle, the state of the vehicle, the behavior of the occupant, the driving scene of the vehicle, and the driving environment of the vehicle.

[0089] In this embodiment, the above-mentioned “operations performed by the occupant on the vehicle” corresponds to the “driving tendency” of the human model data set 73 .

[0090] The above-mentioned "vehicle state" corresponds to "driving", "stopped", "power off", "ACC use state", "navigation use state", "vehicle speed", and "location information" in the vehicle model data set 72.

[0091] The above-mentioned “occupant behavior” corresponds to “face direction” and “drowsiness” in the human model data set 73.

[0092] The above-mentioned "vehicle driving scene" corresponds to "highway," "general road," and "parking lot" in the environment model data set 71.

[0093] The above-mentioned "vehicle driving environment" corresponds to "traffic jam" and "day and night" in the environment model data set 71.

[0094] In such a center 3, the service providing server 4 and the service application 16 can acquire data including at least one of the operations performed by the occupant on the vehicle, the vehicle state, the occupant's actions, the vehicle driving scene, and the vehicle driving environment from the environment model dataset 71, the vehicle model dataset 72, and the human model dataset 73 in order to provide services to the vehicle. Therefore, the service providing server 4 and the service application 16 do not need to use the vehicle data acquired from the vehicle to newly generate data including the operations performed by the occupant on the vehicle, the vehicle state, the occupant's actions, the vehicle driving scene, and the vehicle driving environment. This allows the center 3 to easily use the vehicle data.

[0095] The secondary processing unit 62 is configured to generate secondary processed data by extracting feature amounts using one or more primary processed data as the environment model data set 71, the vehicle model data set 72, and the human model data set 73. The feature amounts include “traffic jam,” “expressway,” “general road,” “parking lot,” “geofence,” and “day / night” from the environment model data set 71, “driving,” “parked,” “power off,” “ACC usage status,” and “navigation usage status” from the vehicle model data set 72, and “number of occupants” and “driving tendency” from the human model data set 73.

[0096] The secondary processing unit 62 is configured to further generate data, as secondary processed data, from which feature amounts are extracted by performing image analysis using the image data acquired from the multiple in-vehicle devices 2. The feature amounts include "face direction" and "drowsiness" of the human model data set 73.

[0097] In the embodiment described above, the mobility IoT system 1 corresponds to a generating system, the primary processed data acquisition unit 61 corresponds to an acquisition unit, and the secondary processing unit 62 corresponds to a generation unit.

[0098] The environment model data set 71, the vehicle model data set 72, and the human model data set 73 correspond to secondary processed data.

[0099] Second Embodiment A second embodiment of the present disclosure will be described below with reference to the drawings. In the second embodiment, differences from the first embodiment will be described. The same reference numerals will be used to designate common components.

[0100] As shown in FIG. 9, the mobility IoT system 1 of the second embodiment differs from the first embodiment in that the configuration of the center 3 is changed.

[0101] The center 3 of the second embodiment differs from the first embodiment in that the memory unit 33 further includes a learning model storage unit 46 .

[0102] 10, the center 3 of the second embodiment differs from the first embodiment in that it includes a learning unit 65 and a model distribution unit 66. Note that the secondary processing unit 62 and the data distribution unit 64 are not shown in FIG.

[0103] The learning unit 65 uses the plurality of primary processed data and image data stored in the primary processed data storage unit 44 to generate a learning model that can be used in common by the service application 16 and the service providing server 4. The learning unit 65 starts learning the learning model when the required period of primary processed data has been accumulated.

[0104] The learning unit 65 stores the generated learning model in the learning model storage unit 46 .

[0105] The learning unit 65 generates a learning model that learns individual behavioral characteristics (e.g., the destination of the vehicle driver) by inputting, for example, the vehicle's current location information, the current time, the number of passengers, and the navigation destination. Such a learning model can estimate the vehicle's destination based on the vehicle's current location information, the current time, and the number of passengers. The destination information estimated by the learning model can be used for services such as automatically notifying the driver of the required time to reach the destination or suggesting an alternative route if the route to the destination is congested.

[0106] The learning unit 65 generates one common learning model 81 and multiple individual adaptation learning models 82. The common learning model 81 is a learning model that can be used regardless of the vehicle and driver by using vehicle data and image data acquired from multiple vehicles. The individual adaptation learning model 82 is a learning model that is adapted to each of multiple drivers by using vehicle data and image data individually for multiple vehicles and multiple drivers.

[0107] The learning unit 65 also generates a learning model for estimating the driver's emotions by performing machine learning using, for example, driver image data generated by photographing the driver and vehicle operation data (e.g., steering operation data, accelerator operation data, brake operation data, ADAS function data, and air conditioning control data). ADAS stands for Advanced Driving Assistant System. Examples of the driver's emotions include impatience, irritation, tension, and relaxation.

[0108] The data management unit 63 manages the learning models stored in the learning model storage unit 46. Specifically, the data management unit 63 provides the model distribution unit 66 with a learning model corresponding to each vehicle, and provides the service providing server 4 with a learning model required by the service providing server 4.

[0109] The model distribution unit 66 distributes a learning model corresponding to each vehicle from among the multiple learning models stored in the learning model storage unit 46 to each in-vehicle device 2. The model distribution unit 66 may distribute a common learning model 81 stored in the learning model storage unit 46 to each in-vehicle device 2.

[0110] The data linking unit 53 of the in-vehicle device 2 stores the learning model downloaded from the center 3 in the download data storage unit 28 .

[0111] Next, a procedure in which the center 3 generates a learning model and synchronizes it with the in-vehicle device 2 will be described.

[0112] As shown in FIG. 11, in S110, the in-vehicle device 2 acquires vehicle data from the vehicle using the data acquisition unit 51.

[0113] In S120, the in-vehicle device 2 determines whether the acquired vehicle data is data that needs to be processed for model learning. Specifically, for example, if the vehicle data is image data, it is determined that the data does not need to be processed, and if the vehicle data is not image data, it is determined that the data needs to be processed.

[0114] If the data does not require processing for model learning, the in-vehicle device 2 uploads the acquired vehicle data to the center 3 via the data linking unit 53 .

[0115] On the other hand, if the data requires processing for model learning, the in-vehicle device 2 processes the vehicle data acquired by the data acquisition unit 51 into primary processed data using the primary processing unit 52 at S130, and uploads the primary processed data generated by the primary processing unit 52 to the center 3 using the data linkage unit 53.

[0116] In S140, the center 3 determines whether the primary processed data and image data for the required period have been accumulated. If the primary processed data for the required period has not been accumulated, the in-vehicle device 2 repeats the processes of S110 to S130. On the other hand, if the primary processed data for the required period has been accumulated, the center 3 generates a learning model by the learning unit 65 in S150.

[0117] In S160, the center 3 stores the learning model generated in S150 in the learning model storage unit 46, thereby updating the learning model.

[0118] In S170, the center 3 synchronizes the learning model between the center 3 and the in-vehicle device 2 by distributing the learning model updated in S160 to each vehicle using the model distribution unit 66.

[0119] The center 3 configured in this manner is configured to perform data communication with multiple on-board devices 2 installed in multiple vehicles, and is equipped with a primary processing data acquisition unit 61 and a learning unit 65.

[0120] The learning unit 65 is configured to generate a common learning model 81 and an individual adaptation learning model 82 that learn the behavioral characteristics of the vehicle occupants using multiple primary processed data as secondary processed data. The above-mentioned "behavioral characteristics" correspond to the "vehicle's destination" estimated by the common learning model 81 and the individual adaptation learning model 82.

[0121] In such a center 3, the service providing server 4 and the service application 16 can acquire data including occupant behavior from the common learning model 81 and the individual adaptation learning model 82 in order to provide services to the vehicle. This eliminates the need for the service providing server 4 and the service application 16 to generate new data including occupant behavior using vehicle data acquired from the vehicle. This allows the center 3 to easily use vehicle data.

[0122] In the embodiment described above, the learning unit 65 corresponds to the generation unit, and the common learning model 81 and the individual adaptation learning model 82 correspond to the learning model and the behavioral characteristic model.

[0123] Although one embodiment of the present disclosure has been described above, the present disclosure is not limited to the above embodiment and can be implemented in various modifications.

[0124] [Modification 1] In the first embodiment, the in-vehicle device 2 generates the primary processed data from the vehicle data. However, in the first embodiment, the center 3 may collect vehicle data from the in-vehicle device 2 and generate the primary processed data from the collected vehicle data, thereby acquiring the primary processed data.

[0125] The control unit 31 and the method described herein may be implemented by a special-purpose computer configured by configuring a processor and memory programmed to execute one or more functions embodied in a computer program. Alternatively, the control unit 31 and the method described herein may be implemented by a special-purpose computer configured by configuring a processor with one or more dedicated hardware logic circuits. Alternatively, the control unit 31 and the method described herein may be implemented by one or more special-purpose computers configured by combining a processor and memory programmed to execute one or more functions with a processor configured with one or more hardware logic circuits. Furthermore, the computer program may be stored as instructions executed by a computer on a computer-readable non-transitory tangible recording medium. The method for implementing the functions of each unit included in the control unit 31 does not necessarily need to include software; all of the functions may be implemented using one or more hardware components.

[0126] In the above embodiments, multiple functions of one component may be realized by multiple components, or one function of one component may be realized by multiple components. Furthermore, multiple functions of multiple components may be realized by one component, or one function realized by multiple components may be realized by one component. Furthermore, part of the configuration of the above embodiments may be omitted. Furthermore, at least part of the configuration of the above embodiments may be added to or substituted for the configuration of another of the above embodiments.

[0127] In addition to the center 3 described above, the present disclosure can also be realized in various forms, such as a system including the center 3 as a component, a program for causing a computer to function as the center 3, a non-transient physical recording medium such as a semiconductor memory on which this program is recorded, a generation method, etc. [Technical Idea Disclosed by the Specification] [Item 1] A center (3) configured to perform data communication with a plurality of on-board devices (2) mounted on a plurality of vehicles, respectively, comprising: an acquisition unit (61) configured to acquire, for each of the plurality of vehicles, primary processed data, which is vehicle data processed into a format independent of the vehicle model and the vehicle manufacturer; and generation units (62, 65) configured to generate, as secondary processed data, data in which feature amounts are extracted using one or more of the primary processed data acquired by the acquisition unit.

[0128] [Item 2] The center according to Item 1, wherein the generation unit (62) is configured to further generate, as the secondary processed data, data from which feature amounts are extracted by performing image analysis using one or more image data acquired from a plurality of the in-vehicle devices.

[0129] [Item 3] The center according to item 1 or 2, wherein the secondary processed data includes at least one of operations performed by a passenger on the vehicle, a state of the vehicle, a behavior of the passenger, a driving scene of the vehicle, and a driving environment of the vehicle.

[0130] [Item 4] The center according to any one of Items 1 to 3, wherein the generation unit (65) is configured to generate a behavioral characteristic model that learns behavioral characteristics of an occupant of the vehicle using a plurality of the primary processed data as the secondary processed data.

[0131] [Item 5] A generation program for causing a computer of a center (3) configured to perform data communication with a plurality of on-board devices (2) mounted on a plurality of vehicles to function as: an acquisition unit (61) configured to acquire, for each of the plurality of vehicles, primary processed data, which is vehicle data processed into a format independent of the vehicle model and the vehicle manufacturer; and a generation unit (62, 65) configured to generate, as secondary processed data, data from which feature quantities are extracted using one or more of the primary processed data acquired by the acquisition unit.

[0132] [Item 6] A generation method executed by a center (3) configured to perform data communication with a plurality of on-board devices (2) mounted on a plurality of vehicles, the method comprising: acquiring, for each of the plurality of vehicles, primary processed data, which is vehicle data processed into a format independent of the vehicle model and the vehicle manufacturer; and generating, as secondary processed data, data from which feature quantities are extracted using one or more of the acquired primary processed data.

[0133] [Item 7] A generation system (1) comprising: a plurality of on-board devices (2) mounted on a plurality of vehicles, respectively; and a center (3) configured to perform data communication between the plurality of on-board devices, wherein the center comprises: an acquisition unit (61) configured to acquire, for each of the plurality of vehicles, primary processed data, which is vehicle data processed into a format independent of the vehicle model and the vehicle manufacturer; and a generation unit (62, 65) configured to generate, as secondary processed data, data from which feature quantities are extracted using one or more of the primary processed data acquired by the acquisition unit.

Claims

1. A center (3) configured to perform data communication with a plurality of on-board devices (2) mounted on a plurality of vehicles, the center comprising: an acquisition unit (61) configured to acquire, for each of the plurality of vehicles, primary processed data, which is vehicle data processed into a format independent of the vehicle model and the vehicle manufacturer; and a generation unit (62, 65) configured to generate, as secondary processed data, data from which feature quantities are extracted using one or more of the primary processed data acquired by the acquisition unit.

2. A center as described in claim 1, wherein the generation unit (62) is configured to further generate data from which feature values ​​are extracted by performing image analysis using one or more image data acquired from multiple on-board devices as the secondary processed data.

3. A center as described in claim 1 or claim 2, wherein the secondary processed data is data including at least one of the operations performed by the occupant on the vehicle, the state of the vehicle, the behavior of the occupant, the driving scene of the vehicle, and the driving environment of the vehicle.

4. A center as described in claim 1 or claim 2, wherein the generation unit (65) is configured to generate a behavioral characteristic model that learns the behavioral characteristics of the vehicle's occupants using a plurality of the primary processed data as the secondary processed data.

5. A generation program for causing a computer at a center (3) configured to perform data communication with a plurality of on-board devices (2) mounted on a plurality of vehicles to function as: an acquisition unit (61) configured to acquire primary processed data for each of the plurality of vehicles, which is vehicle data processed into a format independent of the vehicle model and vehicle manufacturer; and a generation unit (62, 65) configured to generate, as secondary processed data, data in which feature quantities are extracted using one or more of the primary processed data acquired by the acquisition unit.

6. A generation method executed by a center (3) configured to communicate data with a plurality of on-board devices (2) mounted on a plurality of vehicles, the method comprising: acquiring primary processed data for each of the plurality of vehicles, which is vehicle data processed into a format independent of the vehicle model and vehicle manufacturer; and generating secondary processed data from which feature quantities are extracted using one or more of the acquired primary processed data.

7. A generation system (1) comprising: a plurality of on-board devices (2) mounted on each of a plurality of vehicles; and a center (3) configured to perform data communication between the plurality of on-board devices, wherein the center comprises: an acquisition unit (61) configured to acquire, for each of the plurality of vehicles, primary processed data, which is vehicle data processed into a format independent of the vehicle model and the vehicle manufacturer; and a generation unit (62, 65) configured to generate, as secondary processed data, data in which feature quantities are extracted using one or more of the primary processed data acquired by the acquisition unit.

Images