System and method of operating the system

Abstract

To improve the accuracy of vehicle operation diagnostics. [Solution] The system comprises an in-vehicle device that acquires information on operation characteristics of multiple drivers with different driving characteristics, and a server device that communicates with the in-vehicle device. The server device uses the information on operation characteristics to derive criteria for classifying the operation characteristics into multiple categories corresponding to the driving characteristics. Provided that the criteria correspond to a predetermined degree of convergence, the server device sends information to the in-vehicle device to construct a model for classifying the operation characteristics into the categories using the criteria. The in-vehicle device then uses the model to classify the operation characteristics of the drivers into the categories.

Description

Technical Field

[0001] The present disclosure relates to a system and a method for operating the system.

Background Art

[0002] Techniques for diagnosing the state of a moving body based on the behavior of the moving body including a vehicle are known. For example, Patent Documents 1 to 3 disclose systems that detect information obtained by detecting the behavior of a vehicle or the like and perform diagnosis of the vehicle or the like by processing the information on a server on the cloud.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Patent Document 2

Patent Document 3

Summary of the Invention

Problems to be Solved by the Invention

[0004] There is room for improving the accuracy of various diagnoses using machine learning or the like for vehicle driving.

[0005] Hereinafter, a system or the like that enables improvement in the accuracy of diagnosis for vehicle driving will be disclosed.

Means for Solving the Problems

[0006] The system in this disclosure is a system comprising an in-vehicle device that acquires information on operation feature quantities for each of several drivers with different driving characteristics, and a server device that communicates with the in-vehicle device, wherein the server device uses the information on operation feature quantities to derive a criterion for classifying the operation feature quantities into several categories corresponding to the driving characteristics, and, on the condition that the criterion corresponds to a predetermined degree of convergence, sends information to the in-vehicle device for constructing a model that classifies the operation feature quantities into the categories according to the criterion, and the in-vehicle device classifies the operation feature quantities of the drivers into the categories using the model.

[0007] A method for operating a system in another aspect of the present disclosure is a method for operating a system having an in-vehicle device that acquires information on operation feature quantities for each of a plurality of drivers with different driving characteristics, and a server device that communicates with the in-vehicle device, the method comprising: the server device using the information on operation feature quantities to derive criteria for classifying the operation feature quantities into a plurality of categories corresponding to the driving characteristics; the server device sending information to the in-vehicle device for constructing a model for classifying the operation feature quantities into the categories according to the criteria, provided that the criteria correspond to a predetermined degree of convergence; and the in-vehicle device classifying the operation feature quantities of the drivers into the categories using the model. [Effects of the Invention]

[0008] The system described in this disclosure will enable improved accuracy in diagnosing vehicle operation. [Brief explanation of the drawing]

[0009] [Figure 1] This is a diagram showing an example of the configuration of an information processing system. [Figure 2] This is a sequence diagram illustrating an example of the operation of an information processing system. [Figure 3] This is a flowchart illustrating an example of server device operation. [Modes for carrying out the invention]

[0010] The embodiments will be described below.

[0011] Figure 1 shows an example of the configuration of an information processing system in one embodiment. The information processing system 1 has one or more server devices 10, multiple in-vehicle devices 13, and one or more user terminals 14 that are connected to each other via a network 11 so as to be able to communicate information with each other. The server device 10 is, for example, a server computer that belongs to a cloud computing system or other computing system and functions as a server that implements various functions. The in-vehicle devices 13 are, for example, navigation systems, etc., that have communication functions and information processing functions, and are installed in multiple vehicles 12. The vehicles 12 are passenger cars, commercial vehicles, etc., and are vehicles in which some or all of the driving is done manually by the driver. The vehicles 12 are, for example, gasoline cars, electric vehicles (BEV, Battery Electric Vehicle), hybrid vehicles (HEV, Hybrid Electric Vehicle), plug-in hybrid vehicles (PHEV, Plug-in Hybrid Electric Vehicle), fuel cell vehicles (FCEV, Fuel Cell Electric Vehicle), etc. The user terminal 14 is an information processing terminal used by the operator of the information processing system 1, and is, for example, a PC (Personal Computer), a tablet terminal, a smartphone, etc. The network 11 is, for example, the internet, but may be an ad hoc network, LAN, MAN (Metropolitan Area Network), or other network, or any combination thereof.

[0012] In this embodiment, the information processing system 1 includes an in-vehicle device 13 that acquires information on operation feature quantities for each of several drivers with different driving characteristics, and a server device that communicates with the in-vehicle device 13. The server device 10 uses the operation feature quantities of each of the several drivers to perform an optimization process that derives criteria (hereinafter referred to as classification criteria) for classifying the operation feature quantities into categories corresponding to several driving characteristics (hereinafter referred to as characteristic categories). Provided that the classification criteria correspond to a predetermined degree of convergence, the server device 10 sends information to the in-vehicle device 13 for constructing a model (hereinafter referred to as a diagnostic model) 108 that classifies the operation feature quantities into characteristic categories according to the classification criteria. Here, the characteristic categories are categories corresponding to the driving characteristics of the drivers, for example, categories according to the presence or absence of dangerous driving tendencies or the number of accidents. The operation feature quantities are, for example, control quantities such as accelerators and brakes, and motion states such as the speed and acceleration of the vehicle 12. Furthermore, the classification criteria are the types of operation feature quantities that can be classified into the characteristic categories of the corresponding drivers (hereinafter referred to as focus operation feature quantities) and the classification threshold for the focus operation feature quantities. The in-vehicle device 13 classifies the focus operation features for each driver into characteristic categories using the diagnostic model 108. The in-vehicle device 13 then sends information on the focus operation features to be newly diagnosed using the diagnostic model 108 to the server device 10. In this way, the server device 10 performs optimization processing on the diagnostic model 108, and once the correspondence between operation features and characteristic categories converges to a predetermined degree, that is, once the reliability of the classification criteria has increased to a certain level or higher, the diagnostic model 108 is transferred to the in-vehicle device 13. Therefore, the in-vehicle device 13 can perform more accurate diagnoses using the diagnostic model 108. Furthermore, by sending information on the focus operation features set as classification criteria from the in-vehicle device 13 to the server device 10, the server device 10 can perform further optimization processing using information that is more in line with the classification criteria based on the information sent from the in-vehicle device 13. Therefore, the reliability of the diagnostic model 108 is further improved. In this way, the accuracy of the diagnosis regarding the driving of the vehicle 12 can be improved.

[0013] Next, an example configuration of the server device 10 will be described.

[0014] The server device 10 includes a communication unit 101, a storage unit 102, and a control unit 103. The server device 10 may be a single computer, or it may consist of two or more computers that are connected and operate in coordination with each other. When the server device 10 consists of two or more computers, the configuration shown in Figure 1 is appropriately arranged across the two or more computers.

[0015] The communication unit 101 includes one or more communication interfaces. The communication interface is, for example, a LAN interface. The communication unit 101 receives information used in the operation of the control unit 103 and transmits information obtained through the operation of the control unit 103. The server device 10 is connected to the network 11 by the communication unit 101 and communicates information with the in-vehicle device 13 and the user terminal 14 via the network 11.

[0016] The storage unit 102 includes, for example, one or more semiconductor memories, one or more magnetic memories, one or more optical memories, or a combination of at least two of these, which function as main memory, auxiliary memory, or cache memory. The semiconductor memory is, for example, RAM (Random Access Memory) or ROM (Read Only Memory). The RAM is, for example, SRAM (Static RAM) or DRAM (Dynamic RAM). The ROM is, for example, EEPROM (Electrically Erasable Programmable ROM). The storage unit 102 stores information used in the operation of the control unit 103 and information obtained by the operation of the control unit 103.

[0017] The control unit 103 includes one or more processors, one or more dedicated circuits, or a combination thereof. The processor is, for example, a general-purpose processor such as a CPU (Central Processing Unit), or a dedicated processor such as a GPU (Graphics Processing Unit) specialized for specific processing. The dedicated circuit is, for example, an FPGA (Field-Programmable Gate Array), an ASIC (Application Specific Integrated Circuit), etc. While controlling each part of the server device 10, the control unit 103 executes information processing related to the operation of the server device 10.

[0018] The functions of the server device 10 are realized by executing a control program on the processor included in the control unit 103. The control program is a program for causing a computer to execute the processing of the steps included in the operation of the server device 10, thereby causing the computer to realize the functions corresponding to the processing of those steps. That is, the control program is a program for causing a computer to function as the server device 10. Also, some or all of the functions of the server device 10 may be realized by a dedicated circuit included in the control unit 103. Further, the control program may be stored in a non-transitory recording and storage medium readable by the server device 10, and the server device 10 may read it from the medium.

[0019] In this embodiment, the storage unit 102 stores the diagnosis model 108. The diagnosis model 108 is an AI (Artificial Intelligence) model optimized to derive a classification criterion for classifying operation feature amounts into characteristic classifications according to a plurality of driving characteristics, that is, a target operation feature amount and its threshold value, using the operation feature amounts of each of a plurality of drivers acquired from the in-vehicle device 13.

[0020] Next, a configuration example of the in-vehicle device 13 will be described.

[0021] The in-vehicle device 13 includes a communication unit 131, a memory unit 132, a control unit 133, a positioning unit 134, an input unit 135, an output unit 136, and a detection unit 137. These may be configured as one control device, or may be configured by two or more control devices, or by a control device and other devices such as a communication device. The control device includes, for example, an ECU (Electronic Control Unit), etc. The communication device includes, for example, a DCM (Data Communication Module), etc. Each unit is connected to each other or to the equipment of the vehicle 12 so as to be able to communicate information via an in-vehicle network conforming to a standard such as CAN (Controller Area Network). Also, the in-vehicle device 13 may be configured to include a part of a device equivalent to the user terminal 14.

[0022] The communication unit 131 includes a communication module corresponding to a wired or wireless LAN standard, a module corresponding to a mobile communication standard such as LTE (Long Term Evolution), 4G (4th Generation), or 5G (5th Generation), etc. The in-vehicle device 13 is connected to the network 11 via the communication unit 131 through a nearby router device or a mobile communication base station, and performs information communication with other devices via the network 11.

[0023] The memory unit 132 includes one or more semiconductor memories, one or more magnetic memories, one or more optical memories, or a combination of at least two of these. The semiconductor memory is, for example, a RAM or a ROM. The RAM is, for example, a SRAM or a DRAM. The ROM is, for example, an EEPROM. The memory unit 132 functions as, for example, a main memory device, an auxiliary memory device, or a cache memory. The memory unit 132 stores information used for the operation of the control unit 133 and information obtained by the operation of the control unit 133.

[0024] The control unit 133 includes one or more processors, one or more dedicated circuits, or a combination thereof. The processors are general-purpose processors such as CPUs, or dedicated processors such as GPUs specialized for specific processing. The dedicated circuits are, for example, FPGAs or ASICs. The control unit 133 controls each part of the in-vehicle device 13 and performs information processing related to the operation of the in-vehicle device 13.

[0025] The functions of the control unit 133 are realized by executing a control / processing program on the processor included in the control unit 133. The control / processing program is a program that causes the computer to execute the processing steps included in the operation of the control unit 133, thereby realizing the functions corresponding to the processing of those steps. In other words, the control / processing program is a program that causes the computer to function as the control unit 133. Furthermore, some or all of the functions of the control unit 133 may be realized by dedicated circuits included in the control unit 133.

[0026] The positioning unit 134 includes one or more GNSS (Global Navigation Satellite System) receivers. GNSS includes, for example, GPS (Global Positioning System), QZSS (Quasi-Zenith Satellite System), BeiDou, GLONASS (Global Navigation Satellite System), and Galileo. The positioning unit 134 sends the positioning result to the control unit 133, which then obtains the location information of the in-vehicle device 13, i.e., the vehicle 12.

[0027] The input unit 135 includes one or more input interfaces. These input interfaces include, for example, a microphone for receiving voice input, physical keys, capacitive keys, a pointing device, or a touchscreen integrated with a display. The input interface also includes an interface with a camera provided in the vehicle 12 that captures images of the interior or exterior of the vehicle 12. The camera may be built into the in-vehicle device 13 or it may be a separate unit. The input unit 135 receives information used for the operation of the control unit 133, such as user input (operations, voice, etc.) or images of the driver, etc., captured by the camera, and sends the received information to the control unit 133.

[0028] The output unit 136 includes one or more output interfaces. These output interfaces include, for example, a speaker for outputting sound, a display for outputting images, etc. The display is, for example, an LCD (Liquid Crystal Display) or an organic EL (Electro-Luminescence) display. The output unit 136 outputs information obtained through the operation of the control unit 133.

[0029] The detection unit 137 has sensors that detect various events occurring in the vehicle 12, or an interface with sensors. The sensors include, for example, sensors that detect the vehicle 12's speed, longitudinal acceleration, lateral acceleration, deceleration, accelerator operation amount, brake operation amount, steering angle, turn signal illumination time, fuel consumption per unit time, eco mode selection status, odometer value, safety equipment operation information, remaining amount of engine oil, brake pad wear, battery degradation, etc. The sensors also include millimeter wave, infrared, and other radars that detect targets around the vehicle 12. The detection unit 137 sends vehicle information indicating various states of the vehicle 12 detected by the sensors to the control unit 133.

[0030] The control unit 133 controls the communication unit 131, storage unit 132, positioning unit 134, input unit 135, output unit 136, and detection unit 137 while exchanging various information with these units, and also controls the operation of the vehicle 12. When the vehicle 12 is running, the control unit 133 provides navigation functions by presenting various information such as route information necessary for driving to the driver via the output unit 136, and also controls the partial autonomous driving of the vehicle 12.

[0031] In this embodiment, the memory unit 132 stores the diagnostic model 108 and the in-vehicle agent 139. The diagnostic model 108 is transferred from the server device 10 and stored in the in-vehicle device 13. The control unit 138 executes the diagnostic model 108, which was machine-learned in the server device 10, to perform a diagnosis based on the operational features of the vehicle 12. The in-vehicle agent 139 is an interactive AI module for generating notifications to convey the diagnostic results from the diagnostic model 108 to the driver, and has natural language processing capabilities, a knowledge base on diagnostic results and driver preferences, etc.

[0032] Next, we will describe an example configuration of user terminal 14.

[0033] The user terminal 14 includes a communication unit 141, a storage unit 142, a control unit 143, a positioning unit 144, an input unit 145, and an output unit 146.

[0034] The communication unit 141 includes a communication module compatible with wired or wireless LAN standards, a module compatible with mobile communication standards such as LTE, 4G, or 5G, etc. The user terminal 14 is connected to the network 11 via the communication unit 141 through a nearby router device or mobile communication base station, and communicates information with other devices via the network 11.

[0035] The storage unit 142 includes one or more semiconductor memories, one or more magnetic memories, one or more optical memories, or a combination of at least two of these. The semiconductor memory is, for example, RAM or ROM. The RAM is, for example, SRAM or DRAM. The ROM is, for example, EEPROM. The storage unit 142 functions, for example, as a main memory, auxiliary memory, or cache memory. The storage unit 142 stores information used in the operation of the control unit 143 and information obtained by the operation of the control unit 143.

[0036] The control unit 143 includes one or more processors, one or more dedicated circuits, or a combination thereof. The processor is a general-purpose processor such as a CPU, or a dedicated processor specialized for a specific process such as a GPU. The dedicated circuit is, for example, an FPGA or ASIC. The control unit 143 controls each part of the user terminal 14 and performs information processing related to the operation of the user terminal 14.

[0037] The positioning unit 144 includes one or more GNSS receivers. GNSS includes, for example, GPS, QZSS, BeiDou, GLONASS, and Galileo. The positioning unit 144 sends the positioning result to the control unit 143, which then obtains the location information of the user terminal 14.

[0038] The input unit 145 includes one or more input interfaces. These input interfaces include, for example, a microphone for receiving voice input, physical keys, capacitive keys, a pointing device, a touchscreen integrated with a display, and a camera for capturing images. The input unit 145 receives an operation to input information used in the operation of the control unit 143 and sends the input information to the control unit 143.

[0039] The output unit 146 includes one or more output interfaces. The output interfaces are, for example, speakers, displays, etc. The displays are, for example, LCDs or organic EL displays. The output unit 146 outputs information obtained by the operation of the control unit 143.

[0040] The functions of the control unit 143 are realized by executing a control / processing program on the processor included in the control unit 143. The control / processing program is a program that causes the computer to execute the processing steps included in the operation of the control unit 143, thereby realizing the functions corresponding to the processing of those steps. In other words, the control / processing program is a program that causes the computer to function as the control unit 143. Furthermore, some or all of the functions of the control unit 143 may be realized by dedicated circuits included in the control unit 143.

[0041] Next, the operation of the information processing system 1 will be explained using Figures 2 and 3.

[0042] Figure 2 is a sequence diagram illustrating the operation procedure of the information processing system 1 in this embodiment. Figure 2 shows the procedure for the coordinated operation of the server device 10, multiple in-vehicle devices 13, and user terminals 14. The steps related to various information processing of the server device 10, each in-vehicle device 13, and user terminals 14 in Figure 2 are executed by their respective control units 103, 133, and 143. Furthermore, the steps related to the sending and receiving of various information of the server device 10, each in-vehicle device 13, and user terminals 14 are executed by the respective control units 103, 133, and 143 sending and receiving information to each other via the communication units 101, 131, and 141, respectively. In the server device 10, each in-vehicle device 13, and user terminals 14, the control units 103, 133, and 143 respectively appropriately store the information to be sent, received, and processed in the storage units 102, 132, and 142. Furthermore, in each in-vehicle device 13 and user terminal 14, the control units 133 and 143 receive various types of information via input units 135 and 145, respectively, and output various types of information via output units 136 and 146, respectively.

[0043] In step S200, the server device 10 requests operational feature information from multiple in-vehicle devices 13. Step S200 is executed, for example, at any interval from a few days to a few weeks, or as needed in response to the operator's instructions. The operator can instruct the server device 10 to request operational feature information by operating the user terminal 14. The server device 10 stores, for example, the identification information of multiple communicable in-vehicle devices 13 in the storage unit 102, and uses the identification information to send requests for operational feature information to each in-vehicle device 13. The identification information for each in-vehicle device 13 includes the identification information of the driver who operates the vehicle 12 using the in-vehicle device 13.

[0044] In S201, the in-vehicle device 13 acquires operational feature information. Various sensors and input interfaces provided on the vehicle 12 allow the control unit 133 to acquire target information including the amount of control performed by the driver, such as brakes, accelerators, steering wheel, and turn signals, the vehicle's speed, acceleration in the direction of travel and lateral direction, and the distance to other vehicles. Each piece of information may be accompanied by a timestamp at the time of acquisition.

[0045] In S202, the in-vehicle device 13 sends operational feature information to the server device 10.

[0046] In step S203, the server device 10 performs optimization processing of the diagnostic model 108 using the operational feature information sent from the in-vehicle device 13. A detailed procedure for step S203 is shown in Figure 3.

[0047] Figure 3 is a flowchart illustrating an example of the optimization process for the diagnostic model 108 in the server device 10. Each step in Figure 3 is an information processing step performed by the control unit 103.

[0048] In S31, the control unit 103 derives operation feature quantities for each driving scene. The control unit 103 determines the amount of change per unit time of the vehicle 12's speed, longitudinal acceleration, lateral acceleration, deceleration, accelerator operation amount, brake operation amount, steering angle, etc., or the turn signal illumination time, which are included in the operation feature quantity information, and derives driving scenes such as sudden acceleration, sudden braking, and sudden steering. Then, the control unit 103 derives operation feature quantities for each scene, such as the accelerator operation amount and vehicle 12's acceleration during sudden acceleration, the brake operation amount and vehicle 12's acceleration during sudden braking, the steering angle during sudden steering, the turn signal illumination time, and the vehicle 12's lateral acceleration.

[0049] In S32, the control unit 103 derives a characteristic classification. The characteristic classification is a classification of drivers using the in-vehicle device 13, such as whether they have a tendency towards dangerous driving or not, and whether they have a high or low number of accidents. The control unit 103 obtains accident history information for each driver from another server that has information on the drivers' accident history, using the driver's identification information. The control unit 103 then determines whether the number of accidents for each driver over an arbitrary period, for example, the past 1 to several years, is high or low based on an arbitrary standard value, such as the average or median of the total number of accidents, and derives a characteristic classification. The control unit 103 then stores information that associates the operational characteristics of each driver with the derived characteristic classification for each vehicle 12.

[0050] In S33, the control unit 103 derives classification criteria. Specifically, the control unit 103 derives a focus operation feature that can be classified into a corresponding driver characteristic category from multiple types of operation features, and a classification threshold for the focus operation feature. For example, the control unit 103 determines the focus operation feature from among the accelerator operation amount and vehicle 12 acceleration during sudden acceleration, brake operation amount and vehicle 12 acceleration during sudden braking, steering angle during sudden steering, turn signal illumination time, and vehicle 12 lateral acceleration, using machine learning methods such as clustering and decision trees, and analytical methods such as filtering and dimensionality reduction. Then, the control unit 103 derives a threshold for classifying the focus operation feature into a corresponding driver characteristic category, for example, a category with a high number of accidents or a category with a low number of accidents. For example, if the focus operation feature is the amount of brake operation per unit time, a threshold can be derived that classifies the brake operation amount of drivers belonging to the high accident rate category into the high accident rate category, and the brake operation amount of drivers belonging to the low accident rate category into the low accident rate category. Similarly, if the focus operation feature is the turn signal activation time, a threshold can be derived that classifies the turn signal activation time of drivers belonging to the high accident rate category into the high accident rate category, and the turn signal activation time of drivers belonging to the low accident rate category into the low accident rate category.

[0051] In S34, the control unit 103 derives the convergence degree. The convergence degree is, for example, the degree of agreement between the result of classifying the operational features into characteristic categories based on the classification criteria derived in the current optimization processing cycle and the driver characteristic categories associated with the operational features. Alternatively, the convergence degree may be, for example, the difference between the degree of agreement in past optimization processing cycles and the degree of agreement in the current optimization processing cycle. Or, the convergence degree may be the number of times the optimization processing cycle has been executed.

[0052] In S35, the control unit 103 determines whether the degree of convergence corresponds to the convergence conditions. Convergence conditions include, for example, a condition for the value of the degree of agreement (e.g., 0.8 or more), a condition for the difference in the degree of agreement (e.g., 0.05 or less), and a condition for the number of optimization processing cycles (e.g., 5 or more). If the control unit 103 determines that the degree of convergence corresponds to the convergence conditions (Yes in step S35), it terminates the procedure in Figure 3; otherwise, it returns to step S200 in Figure 2. Note that if past degrees of agreement are used as a criterion for judgment, since there are no past degrees of agreement in the first machine learning cycle of the diagnostic model, the control unit 103 can determine that the degree of convergence does not correspond to the convergence conditions. If the control unit 103 returns to step S200 in Figure 2, it re-executes the request for operational feature information (step S200), the acquisition of operational feature information (step S202), and the optimization processing of the diagnostic model (S203). Therefore, steps S200 to S203 are repeatedly executed until the weekly rate satisfies the convergence condition.

[0053] Returning to Figure 2, in S204, the server device 10 sends optimization processing result information to the user terminal 14. The processing result information includes information for visualizing the type of focus feature, threshold, classification result, degree of convergence, etc.

[0054] In S205, the user terminal 14 outputs the processing results and accepts instructions from the operator. The learning results are presented to the operator, for example, by being displayed on a screen or output by voice. The operator can check the processing results and make an appropriate decision on whether or not to transfer the diagnostic model 109 to the in-vehicle device 13. The operator then inputs processing instructions for the diagnostic model 109 by operating the touch panel, keyboard, etc. The processing instructions are either an instruction to transfer the diagnostic model 109 to the in-vehicle device 13, or an instruction to continue the optimization process of the diagnostic model 109.

[0055] In S206, the user terminal 14 sends a diagnostic model processing instruction to the server device 10.

[0056] In S207, if the diagnostic model processing instruction is an instruction to transfer the diagnostic model 109 to the in-vehicle device 13 (Yes in S207), the server device 10 proceeds to step S208. If the diagnostic model processing instruction is an instruction to continue machine learning of the diagnostic model 109 (No in S207), the server device 10 returns to step S200 and executes steps S200 to S206 again.

[0057] In S208, the server device 10 executes a process to transfer the diagnostic model 108 to the in-vehicle device 13. The server device 10 generates information for configuring the diagnostic model 108, such as source code, configuration files, and reference datasets, in a transferable format.

[0058] In S209, the server device 10 transfers the diagnostic model 108 to the in-vehicle device. The server device 10 sends information to the in-vehicle device 13 for configuring the diagnostic model 108 in the in-vehicle device 13.

[0059] In S210, the in-vehicle device 13 configures the diagnostic model 108. The in-vehicle device 13 obtains and installs an application program for implementing the diagnostic model 108 from the provider's server and sets various information sent from the server device 10. If a focus operation feature is newly set or changed during the optimization process of the diagnostic model 109 in the server device 10, the frequency of acquiring that focus operation feature may be increased in the in-vehicle device 13.

[0060] In S211, the in-vehicle device 13 acquires operational feature information. This operational feature information may be acquired at any interval, such as tens of milliseconds to several seconds. The in-vehicle device 13 may also acquire the operational feature of interest at a higher frequency than other operational features.

[0061] In S212, the in-vehicle device 13 performs a diagnosis using the diagnostic model 108. The control unit 133 executes the diagnostic model 108 and performs a diagnosis using the focus operation feature information, that is, classifying the driving operations corresponding to the focus operation feature into characteristic categories. For example, if the focus operation feature is the amount of brake operation per unit time, the control unit 133 diagnoses a brake operation amount exceeding a threshold, i.e., a brake operation amount indicating sudden braking, as a characteristic category with a high number of accidents, and a brake operation amount below the threshold, i.e., a brake operation amount indicating gentle braking, as a characteristic category with a low number of accidents. Also, for example, if the focus operation feature is the turn signal illumination time, the control unit 103 diagnoses a turn signal illumination time shorter than the threshold, i.e., a turn signal illumination time indicating sudden right or left turns, as a characteristic category with a high number of accidents, and a turn signal illumination time greater than or equal to the threshold, i.e., a turn signal illumination time indicating right or left turns with some leeway, as a characteristic category with a low number of accidents.

[0062] In S213, the in-vehicle device 13 generates a notification based on the diagnostic results. The control unit 133, if the in-vehicle agent 139 diagnoses, for example, that there are many accidents, generates a notification with phrases such as "Danger of sudden braking!" or "Caution: sudden steering!" to warn of danger. Alternatively, the notification may include, in addition to or instead of phrases, flashing warning lights or outputting warning sounds.

[0063] In S214, the in-vehicle device 13 outputs a notification to the driver. The notification text may be displayed on the display of the output unit 136 or output as audio through the speaker. A warning light may also flash or a warning sound may be emitted. Outputting such notifications can contribute to deterring dangerous driving by the driver. The in-vehicle device 13 may also output the diagnostic results to the driver at the end of the drive, rather than after each diagnosis, to encourage the driver to reflect on the trip. In that case, the in-vehicle device 13 can output a message such as "You tend to brake suddenly a lot, so please be careful" when the number of times the vehicle is diagnosed as having a high number of accidents exceeds an arbitrary threshold.

[0064] Following the above procedure, the diagnostic model 109 optimized by the server device 10 is transferred to the in-vehicle device 13, where a diagnosis based on operational features is performed. If information on newly set or modified operational features of interest is acquired more frequently and sent to the server device 10, the server device 10 can further optimize the model based on information that conforms to the classification criteria. As a result, the reliability of the diagnostic model 108 is further improved. Consequently, the accuracy of the diagnosis regarding the operation of the vehicle 12 can be improved.

[0065] In the above-described operation procedure, the review of the optimization processing results by the operator using the user terminal 14, i.e., steps S204 to S207, may be omitted. In that case, when the convergence condition of the diagnostic model 109 is satisfied in the server device 10, steps S208 onwards are executed, and the diagnostic model 109 is transferred to the in-vehicle device 13.

[0066] In the above-described embodiment, the processing and control program that defines the operation of the vehicle 12 and the user terminal 14 may be stored in the storage unit 102 of the server device 10 or in the storage unit of another server device and downloaded to each device via the network 11, or it may be stored in a non-transient recording and storage medium that can be read by each device and read from the medium by each device.

[0067] As described above, embodiments have been explained based on various drawings and examples, but it should be noted that those skilled in the art will find it easy to make various modifications and alterations based on this disclosure. Therefore, it should be noted that these modifications and alterations are within the scope of this disclosure. For example, the functions, etc., included in each means, each step, etc., can be rearranged in a logically consistent manner, and multiple means, steps, etc., can be combined into one or divided.

[0068] Some embodiments of the present disclosure are described below. However, it should be noted that the embodiments of the present disclosure are not limited to these. [Note 1] A system comprising an in-vehicle device that acquires information on the operational characteristics of multiple drivers with different driving characteristics, and a server device that communicates with the in-vehicle device, The server device uses the information of the operation features to perform a process to derive a criterion for classifying the operation features into a plurality of categories corresponding to the driving characteristics, and, on the condition that the criterion corresponds to a predetermined degree of convergence, sends information to the in-vehicle device for constructing a model for classifying the operation features into the categories according to the criterion. The in-vehicle device classifies the driver's operational characteristics into the categories using the model. system. [Note 2] In Appendix 1, The predetermined degree of convergence is satisfied when the classification of the operational feature quantities, which is determined by the criteria derived in the process, and the operating characteristics corresponding to those operational feature quantities show a predetermined degree of agreement. system. [Note 3] In Appendix 1, The predetermined degree of convergence is satisfied when the process is executed a predetermined number of times. system. [Note 4] In any of the appendices 1 to 3, The aforementioned criteria are a first type of operational feature for classifying into the aforementioned categories and a threshold value for said first type of operational feature. system. [Note 5] In Appendix 4, The server device, when the in-vehicle device uses the model, obtains the first type of operation feature from the in-vehicle device and executes the process using the operation feature including the first type of operation feature. system. [Note 6] In any of the appendices 1 to 5, The server device sends the reference information to the terminal device and, subject to receiving instructions from the terminal device, sends the model to the in-vehicle device. system. [Note 7] A method for operating a system having an in-vehicle device that acquires information on the operational characteristics of multiple drivers with different driving characteristics, and a server device that communicates with the in-vehicle device, The server device uses the information of the operation features to perform a process to derive criteria for classifying the operation features into a plurality of categories corresponding to the driving characteristics, and, on the condition that the criteria correspond to a predetermined degree of convergence, sends information to the in-vehicle device for constructing a model for classifying the operation features into the categories according to the criteria. The in-vehicle device includes classifying the driver's operational characteristics into the categories using the model, How the system works. [Note 8] In Appendix 7, The predetermined degree of convergence is satisfied when the classification of the operational feature quantities, which is determined by the criteria derived in the process, and the operating characteristics corresponding to those operational feature quantities show a predetermined degree of agreement. How the system works. [Note 9] In Appendix 7, The predetermined degree of convergence is satisfied when the process is executed a predetermined number of times. How the system works. [Note 10] In any of the appendices 7 to 9, The aforementioned criteria are a first type of operational feature for classifying into the aforementioned categories and a threshold value for said first type of operational feature. How the system works. [Note 11] In Appendix 10, The server device, when the in-vehicle device uses the model, obtains the first type of operational feature from the in-vehicle device and executes the process using the operational feature including the first type of operational feature. How the system works. [Note 12] In any of the appendices 7 to 11, The server device sends the reference information to the terminal device, and upon receiving instructions from the terminal device, sends the model to the in-vehicle device. How the system works. [Explanation of Symbols]

[0069] 1. Information Processing System 10 Server devices 11 Network 12 vehicles 13 Terminal devices 101, 131, 141 Communications Department 102, 132, 142 storage section 103, 133, 143 Control Unit 134, 144 Positioning Unit 135, 145 Input section 136, 146 Output section

Claims

1. A system comprising an in-vehicle device and a server device that communicates with the in-vehicle device, The in-vehicle device has a detection unit that acquires information on the operational characteristics of each of several drivers with different driving characteristics, The server device acquires information on the operation features from the in-vehicle device, acquires information on the driving characteristics from another server, derives criteria for classifying the operation features into a plurality of categories corresponding to the driving characteristics using AI (Artificial Intelligence), and, provided that the criteria correspond to a predetermined degree of convergence, sends information to the in-vehicle device for constructing a model that classifies the operation features into the categories using the criteria. The in-vehicle device classifies the driver's operational characteristics into the categories using the model. system.

2. A system comprising an in-vehicle device that acquires information on the operational characteristics of multiple drivers with different driving characteristics, and a server device that communicates with the in-vehicle device, The server device uses the information of the operation features to perform a process to derive a criterion for classifying the operation features into a plurality of categories corresponding to the driving characteristics, and, on the condition that the criterion corresponds to a predetermined degree of convergence, sends information to the in-vehicle device for constructing a model for classifying the operation features into the categories according to the criterion. The in-vehicle device classifies the driver's operational characteristics into the categories using the model. system.

3. In claim 2, The predetermined degree of convergence is satisfied when the classification of the operational feature quantities, which is determined by the criteria derived in the process, and the operating characteristics corresponding to those operational feature quantities show a predetermined degree of agreement. system.

4. In claim 2, The predetermined degree of convergence is satisfied when the process is executed a predetermined number of times. system.

5. In claim 2, The aforementioned criteria are a first type of operational feature for classifying into the aforementioned categories and a threshold value for said first type of operational feature. system.

6. In claim 5, The server device, when the in-vehicle device uses the model, obtains the first type of operation feature from the in-vehicle device and executes the process using the operation feature including the first type of operation feature. system.

7. In claim 2, The server device sends the reference information to the terminal device and, subject to receiving instructions from the terminal device, sends the model to the in-vehicle device. system.

8. A method for operating a system having an in-vehicle device that acquires information on the operational characteristics of multiple drivers with different driving characteristics, and a server device that communicates with the in-vehicle device, The server device uses the information of the operation features to perform a process to derive criteria for classifying the operation features into a plurality of categories corresponding to the driving characteristics, and, on the condition that the criteria correspond to a predetermined degree of convergence, sends information to the in-vehicle device for constructing a model for classifying the operation features into the categories according to the criteria. The in-vehicle device includes classifying the driver's operational characteristics into the categories using the model, How the system works.

9. In claim 8, The predetermined degree of convergence is satisfied when the classification of the operational feature quantities, which is determined by the criteria derived in the process, and the operating characteristics corresponding to those operational feature quantities show a predetermined degree of agreement. How the system works.

10. In claim 8, The predetermined degree of convergence is satisfied when the process is executed a predetermined number of times. How the system works.

11. In claim 8, The aforementioned criteria are a first type of operational feature for classifying into the aforementioned categories and a threshold value for said first type of operational feature. How the system works.

12. In claim 11, The server device, when the in-vehicle device uses the model, obtains the first type of operation feature from the in-vehicle device and executes the process using the operation feature including the first type of operation feature. How the system works.

13. In claim 8, The server device sends the reference information to the terminal device, and upon receiving instructions from the terminal device, sends the model to the in-vehicle device. How the system works.

Images