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

Abstract

To make suitable for a driver an output method of information that is to be output into a vehicle during driving of the vehicle.SOLUTION: An information processing device includes: an identification unit that identifies a reaction of the driver to evaluation information which is obtained by evaluation of driving of the driver of the vehicle, the evaluation information being output from an output unit during driving of the vehicle; an estimation unit that estimates an output method of the evaluation information which is suitable for the driver, based on the driver's reaction identified by the identification unit; and a change unit that changes an output method of the evaluation information which is output from the output unit, to the output method of the evaluation information which is estimated by the estimation unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present disclosure relates to an information processing device, an information processing method, and an information processing program. [Background technology]

[0002] Patent Document 1 discloses a technique that can reduce the annoyance caused by the user being notified of more information than necessary about the external charging time schedule. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Laid-Open No. 2017-079538 Summary of the Invention [Problem to be solved by the invention]

[0004] The technology of Patent Document 1 realizes a notification method suitable for a user by adjusting the frequency of sending information related to a time schedule to the user's smartphone. However, the technology of Patent Document 1 does not take into consideration how to make the output method of information output in the vehicle suitable for the driver while driving the vehicle, and there is room for improvement.

[0005] Therefore, an object of the present disclosure is to provide an information processing device, an information processing method, and an information processing program that can make the method of outputting information inside the vehicle while driving suitable for the driver. [Means for solving the problem]

[0006] The information processing device according to claim 1 includes an identification unit that identifies a driver's reaction to evaluation information that evaluates the driving of a driver of a vehicle and is output from an output unit while the vehicle is being driven, an estimation unit that estimates an output method of the evaluation information that is suitable for the driver based on the driver's reaction identified by the identification unit, and a change unit that changes the output method of the evaluation information output from the output unit to the output method of the evaluation information estimated by the estimation unit. an acquisition unit that acquires driving operation information related to the driving operation of the driver and driver information indicating the behavior of the driver from the vehicle; Equipped with The identification unit identifies whether the driver's reaction to the evaluation information output from the output unit is good or bad, depending on an expression detected from an image of the driver's face captured by a camera within a predetermined time after the evaluation information is output, which is included in the driver information acquired by the acquisition unit, as the driver's behavior when the evaluation information is output from the output unit, and stores the good or bad of the driver's reaction to the evaluation information output from the output unit by one output method in a storage unit. . The information processing device of claim 2 is in claim 1, and when the identification unit detects, as the driver's behavior when the evaluation information is output from the output unit, operation of a cancel switch, which is a switch that stops the output of the evaluation information and is included in the driver information acquired by the acquisition unit, within a predetermined time after the output of the evaluation information, the identification unit identifies that the driver's reaction to the evaluation information output from the output unit is poor.

[0007] In the information processing device according to claim 1, the identification unit identifies the driver's reaction to the evaluation information output from the output unit while the vehicle is being driven. The estimation unit estimates an output method of the evaluation information suitable for the driver based on the driver's reaction identified by the identification unit. The change unit changes the output method of the evaluation information output from the output unit to the output method of the evaluation information estimated by the estimation unit. In this way, the information processing device can make the output method of the evaluation information output in the vehicle while driving suitable for the driver by changing the output method of the evaluation information based on the driver's reaction to the evaluation information output from the output unit while the vehicle is being driven.

[0008] Other aspects of The information processing device before The system includes an update unit that updates a trained model that has undergone machine learning to adjust the output method of the evaluation information suitable for other drivers who have similar personal characteristics to the driver, to a model that estimates the output method of the evaluation information suitable for the driver, using personal characteristic information that indicates the personal characteristics of the driver and reaction information that accumulates the reactions of the driver identified by the identification unit.

[0009] Other aspects ofIn the information processing device, an update unit updates a trained model suitable for other drivers having similar personal characteristics to the driver to a model that estimates an output method of evaluation information suitable for the driver, using the personal characteristic information and reaction information of the driver. As a result, by using a trained model suitable for other drivers having similar personal characteristics as a base, the information processing device can generate a model that estimates an output method of evaluation information suitable for the driver in a shorter time than when not using the trained model as a base.

[0010] Other aspects of The information processing device before The estimation unit estimates an output method of the evaluation information suitable for the driver by inputting the personal characteristic information and the reaction information of the driver into the model updated by the update unit.

[0011] Other aspects of In the information processing device, the estimation unit estimates an output method of evaluation information suitable for the driver by inputting the personal characteristic information and reaction information of the driver into the model updated by the update unit. As a result, the information processing device can cause the output unit to output evaluation information using an output method optimized based on the personal characteristics of the driver and the reaction of the driver to the evaluation information output from the output unit while driving the vehicle.

[0012] Other aspects of The information processing device before The determination unit determines a reaction of the driver to the evaluation information output from the output unit based on the behavior of the driver when the evaluation information is output from the output unit.

[0013] Other aspects of In the information processing device, the identification unit identifies the driver's reaction to the evaluation information output from the output unit based on the driver's behavior when the evaluation information is output from the output unit. As a result, the information processing device can make the output method of the evaluation information output into the vehicle while driving suitable for the driver without asking the driver for their opinion on the output method of the evaluation information output from the output unit.

[0014] Other aspects of The information processing device before The determination unit determines the driver's reaction to the evaluation information output from the output unit based on the driver's response to a question regarding the evaluation information.

[0015] Other aspects of In the information processing device, the identification unit identifies the driver's reaction to the evaluation information output from the output unit based on the driver's response to the question regarding the evaluation information. This allows the information processing device to accurately identify the driver's reaction to the evaluation information output from the output unit compared to when the driver's reaction to the evaluation information output from the output unit is identified only indirectly.

[0016] Claim 3 The information processing method according to the present invention includes identifying a reaction of a driver to evaluation information that evaluates the driving of a driver of a vehicle, the evaluation information being output from an output unit while the driver is driving the vehicle, estimating an output method of the evaluation information that is suitable for the driver based on the identified reaction of the driver, and changing the output method of the evaluation information output from the output unit to the estimated output method of the evaluation information. The method acquires driving operation information relating to the driving operation of the driver and driver information indicating the behavior of the driver from the vehicle, and determines whether the driver's reaction to the evaluation information output from the output unit is good or bad according to an expression detected from an image of the driver's face captured by a camera within a predetermined time after the evaluation information is output, which is included in the acquired driver information, as the behavior of the driver when the evaluation information is output from the output unit, and stores the good or bad of the driver's reaction to the evaluation information output from the output unit by one output method in a storage unit as the driver's reaction information. The processing is performed by a computer.

[0017] Claim 4 The information processing program according to the present invention causes a computer to identify a reaction of a driver of a vehicle to evaluation information that evaluates the driving of the driver of the vehicle, the evaluation information being output from an output unit while the driver is driving the vehicle, estimate an output method of the evaluation information that is suitable for the driver based on the identified reaction of the driver, and change the output method of the evaluation information output from the output unit to the estimated output method of the evaluation information. The method acquires driving operation information relating to the driving operation of the driver and driver information indicating the behavior of the driver from the vehicle, and determines whether the driver's reaction to the evaluation information output from the output unit is good or bad according to an expression detected from an image of the driver's face captured by a camera within a predetermined time after the evaluation information is output, which is included in the acquired driver information, as the behavior of the driver when the evaluation information is output from the output unit, and stores the good or bad of the driver's reaction to the evaluation information output from the output unit by one output method in a storage unit as the driver's reaction information. , and execute the processing. [Effects of the Invention]

[0019] As described above, the information processing device, information processing method, and information processing program according to the present disclosure can make the method of outputting information inside the vehicle while driving suitable for the driver. [Brief explanation of the drawings]

[0020] [Figure 1] 1 is a diagram showing a schematic configuration of an information processing system according to an embodiment of the present invention; [Figure 2] 1 is a block diagram showing a hardware configuration of a vehicle according to an embodiment of the present invention; [Figure 3] FIG. 2 is a block diagram showing an example of a functional configuration of the vehicle-mounted device according to the present embodiment. [Figure 4] FIG. 2 is a block diagram showing the hardware configuration of a management server and a driver terminal according to the present embodiment. [Figure 5] FIG. 2 is a block diagram showing the configuration of a storage unit of the management server according to the present embodiment. [Figure 6] FIG. 2 is a block diagram illustrating an example of a functional configuration of a management server according to the present embodiment. [Figure 7] 10 is a flowchart showing the flow of a learning process by the management server according to the present embodiment. [Figure 8] 10 is a flowchart showing the flow of update processing by the management server according to the present embodiment. [Figure 9] 10 is a flowchart showing the flow of a change process by the management server according to the present embodiment. [Figure 10] 10 is an explanatory diagram showing an example of output of evaluation information output to an MID while driving a vehicle according to the present embodiment. FIG. [Figure 11] 10A and 10B are explanatory diagrams showing an example of evaluation information output from a speaker while driving the vehicle according to the present embodiment. [Figure 12] 10 is a display example displayed on the display unit of the driver's terminal according to the present embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0021] The information processing system 10 according to this embodiment will be described below. The information processing system 10 according to this embodiment is a system that adapts the method of outputting information inside the vehicle while the vehicle is being driven to suit the driver.

[0022] (First embodiment) First, a first embodiment of the information processing system 10 according to the present embodiment will be described. FIG. 1 is a diagram showing a schematic configuration of an information processing system 10. As shown in FIG.

[0023] 1, the information processing system 10 includes a vehicle 60, a management server 20, and a driver terminal 40. The vehicle-mounted device 15, the management server 20, and the driver terminal 40 mounted on the vehicle 60 are connected via a network N and are capable of communicating with each other.

[0024] The vehicle 60 may be any of an engine vehicle, a hybrid vehicle, and an electric vehicle, but in the first embodiment, as an example, the vehicle 60 is an engine vehicle.

[0025] The management server 20 is a server computer owned by a predetermined business operator. The management server 20 is an example of an "information processing device."

[0026] The driver terminal 40 is a mobile terminal held by the driver of the vehicle 60. As an example, the driver terminal 40 may be a portable personal computer (notebook PC), a smartphone, a tablet terminal, or the like. In the first embodiment, as an example, the driver terminal 40 is a smartphone.

[0027] 1 illustrates only one vehicle 60 as a vehicle and one driver terminal 40 as a driver terminal, but there are actually a plurality of vehicles and driver terminals. That is, in the information processing system 10, there are a plurality of vehicles and driver terminals, and there are a plurality of drivers corresponding to each vehicle.

[0028] Next, a description will be given of the hardware configuration of the vehicle 60. FIG.

[0029] As shown in FIG. 2, the vehicle 60 includes an on-board device 15, a plurality of ECUs (Electronic Control Units) 70, a steering angle sensor 71, an acceleration sensor 72, a vehicle speed sensor 73, a turn signal switch 74, a microphone 75, a camera 76, an input switch 77, a monitor 78, a speaker 79, and a GPS device 80.

[0030] The vehicle-mounted device 15 includes a CPU (Central Processing Unit) 61, a ROM (Read Only Memory) 62, a RAM (Random Access Memory) 63, a storage unit 64, an in-vehicle communication I / F (Interface) 65, an input / output I / F 66, and a wireless communication I / F 67. The CPU 61, the ROM 62, the RAM 63, the storage unit 64, the in-vehicle communication I / F 65, the input / output I / F 66, and the wireless communication I / F 67 are connected to each other via an internal bus 68 so as to be able to communicate with each other.

[0031] The CPU 61 is a central processing unit that executes various programs and controls each part. That is, the CPU 61 reads programs from the ROM 62 or the storage unit 64 and executes the programs using the RAM 63 as a work area. The CPU 61 controls each of the above components and performs various arithmetic processing in accordance with the programs recorded in the ROM 62 or the storage unit 64.

[0032] The ROM 62 stores various programs and various data. The RAM 63 serves as a working area for temporarily storing programs or data.

[0033] The storage unit 64 is configured by a storage device such as an eMMC (embedded multi media card) or a UFS (universal flash storage), and stores various programs and various data.

[0034] The in-vehicle communication I / F 65 is an interface for connecting to the ECU 70. The interface uses a communication standard based on the CAN protocol. The in-vehicle communication I / F 65 is connected to an external bus 89.

[0035] A plurality of ECUs 70 are provided for each function of the vehicle 60, and in the first embodiment, ECUs 70A, 70B, 70C, and 70D are provided. The ECU 70A is exemplified as an ECU for electric power steering, and a steering angle sensor 71 is connected to the ECU 70A. The ECU 70B is exemplified as an ECU for VSC (Vehicle Stability Control), and an acceleration sensor 72 and a vehicle speed sensor 73 are connected to the ECU 70B. In addition to the acceleration sensor 72 and the vehicle speed sensor 73, a yaw rate sensor may be connected to the ECU 70B.

[0036] The ECU 70C is exemplified by an engine ECU, which detects the engine speed and engine torque of the vehicle 60 to control the engine. The ECU 70C also detects fuel efficiency based on fuel flow rates obtained from sensors (not shown). The ECU 70C also detects accelerator operation of the vehicle 60. The engine speed, engine torque, fuel efficiency, and accelerator operation detected by the ECU 70C are stored in the memory unit 64 and transmitted to the management server 20 as driving operation information related to the driver's driving operation. The ECU 70D is exemplified by a steering ECU, which is connected to a turn signal switch 74. The turn signal switch 74 is provided on a steering column for activating a turn signal. The ECU 70D detects the driver's operation of the turn signal switch 74 as a turn signal operation. The turn signal operation detected by the ECU 70D is stored in the memory unit 64 and transmitted to the management server 20 as driving operation information.

[0037] The steering angle sensor 71 is a sensor for detecting the steering angle of the steering wheel. The steering angle detected by the steering angle sensor 71 is stored in the storage unit 64 and is also transmitted to the management server 20 as driving operation information.

[0038] The acceleration sensor 72 is a sensor for detecting acceleration acting on the vehicle 60. As an example, the acceleration sensor 72 is a three-axis acceleration sensor that detects acceleration acting in the vehicle longitudinal direction as the X-axis direction, the vehicle width direction as the Y-axis direction, and the vehicle height direction as the Z-axis direction. The acceleration detected by the acceleration sensor 72 is stored in the memory unit 64 and is also transmitted to the management server 20 as driving operation information.

[0039] The vehicle speed sensor 73 is a sensor for detecting the speed of the vehicle 60. The vehicle speed sensor 73 is, for example, a sensor provided on a wheel. The vehicle speed detected by the vehicle speed sensor 73 is stored in the storage unit 64 and transmitted to the management server 20 as driving operation information.

[0040] The input / output I / F 66 is an interface for communicating with a microphone 75 , a camera 76 , an input switch 77 , a monitor 78 , a speaker 79 , and a GPS device 80 that are mounted on the vehicle 60 .

[0041] The microphone 75 is a device that is provided on a front pillar, a dashboard, or the like of the vehicle 60, and collects sounds emitted by the driver of the vehicle 60. The microphone 75 may also be provided in a camera 76, which will be described later.

[0042] The camera 76 is an imaging device that captures images using an imaging element such as a CCD (Charge Coupled Device) image sensor or a CMOS (Complementary Metal Oxide Semiconductor) image sensor. The camera 76 includes, for example, a first camera provided at the front of the vehicle 60 to capture an image ahead of the vehicle, and a second camera provided above the windshield or on the dashboard of the vehicle 60 and facing the driver. The image captured by the first camera of the camera 76 is used, for example, to recognize the distance between the vehicle and a preceding vehicle traveling ahead of the vehicle, lane markings, traffic lights, and the like. The image captured by the second camera of the camera 76 is used, for example, to detect the driver's facial expression. The images captured by the camera 76 are stored in the storage unit 64. The image captured by the first camera of the camera 76 is transmitted to the management server 20 as driving operation information. The image captured by the second camera of the camera 76 is transmitted to the management server 20 as driver information indicating the driver's behavior. The camera 76 may be configured as an imaging device for other purposes, such as a drive recorder or an ADAS (Advanced Driver Assistance System). The camera 76 may be connected to the in-vehicle device 15 via the ECU 70 (for example, a camera ECU).

[0043] The input switch 77 is provided on an instrument panel, a center console, a steering wheel, etc., and is a switch for inputting an operation by the driver's finger. For example, a push-button numeric keypad, a touchpad, etc. can be used as the input switch 77. In the first embodiment, a cancel switch is provided on the steering wheel as the input switch 77. When operated by the driver, the cancel switch stops (cancels) the output of evaluation information that evaluates the driver's driving and is output from the monitor 78 and the speaker 79. The operation of the cancel switch is stored in the memory unit 64 and is also transmitted to the management server 20 as driver information.

[0044] The monitor 78 is a liquid crystal monitor provided on an instrument panel, a meter panel, or the like, for displaying operation suggestions related to functions of the vehicle 60 and images explaining the functions. The monitor 78 may be provided as a touch panel that also serves as the input switch 77.

[0045] The speaker 79 is a device provided on the instrument panel, center console, front pillar, dashboard, or the like, for outputting audio and the like that suggests operations related to functions of the vehicle 60 and explains the functions. The speaker 79 may also be provided on the monitor 78.

[0046] In the first embodiment, evaluation information is output from the monitor 78 and the speaker 79 while the vehicle 60 is being driven. The evaluation information is information that evaluates the driver's driving, and indicates, for example, whether the driver's driving was good or bad. The monitor 78 and the speaker 79 are examples of an "output unit."

[0047] The GPS device 80 is a device that measures the current position of the vehicle 60. The GPS device 80 includes an antenna (not shown) that receives signals from GPS satellites. The GPS device 80 may be connected to the vehicle-mounted device 15 via a car navigation system that is connected to the ECU 70 (for example, a multimedia ECU).

[0048] The wireless communication I / F 67 is a wireless communication module for communicating with the management server 20. The wireless communication module uses communication standards such as 5G, LTE, and Wi-Fi (registered trademark). The wireless communication I / F 67 is connected to the network N.

[0049] Next, the functional configuration of the vehicle-mounted device 15 will be described. FIG. 3 is a block diagram showing an example of the functional configuration of the vehicle-mounted device 15. As shown in FIG.

[0050] 3, the CPU 61 of the vehicle-mounted device 15 has, as functional components, an acquisition unit 61A, a determination unit 61B, a control unit 61C, a management unit 61D, and a transmission unit 61E. Each functional component is realized by the CPU 61 reading and executing a program stored in the ROM 62 or the storage unit 64.

[0051] The acquisition unit 61A acquires driving operation information. As an example, the acquisition unit 61A acquires the steering angle, acceleration, vehicle speed, and turn signal operation of the vehicle 60 detected by the steering angle sensor 71, acceleration sensor 72, vehicle speed sensor 73, and turn signal switch 74 as the driving operation information. The acquisition unit 61A also acquires the engine speed, engine torque, fuel economy, and accelerator operation of the vehicle 60 detected by the ECU 70C as the driving operation information. The acquisition unit 61A also acquires an image captured by the first camera of the camera 76 as the driving operation information. Note that the above information is only a portion of the driving operation information that the acquisition unit 61A can acquire, and the acquisition unit 61A also acquires information related to the driver's driving operation other than the above information as the driving operation information.

[0052] The acquiring unit 61A also acquires, from the management server 20, an output method of the evaluation information suitable for the driver of the vehicle 60. As an example, the output method of the evaluation information is determined by combining the output frequency of the evaluation information, the content to be displayed on the monitor 78, and the content to be output from the speaker 79. The output frequency of the evaluation information is an index of how many times the evaluation information is displayed on the monitor 78 and how many times it is output from the speaker 79 per unit time. The display content on the monitor 78 includes, for example, the text content, the text color, the text size, etc. The output content from the speaker 79 includes, for example, the voice type, such as male or female voice, or low or high voice, and the tone type, such as gentle or harsh tone.

[0053] The determination unit 61B determines the items of evaluation information to be output from the monitor 78 and the speaker 79 based on the driving operation information acquired by the acquisition unit 61A. In the first embodiment, a plurality of items such as "Good Pause," "Bad Pause," "Good Braking," and "Bad Braking" are provided as the items of evaluation information. Each item of evaluation information is linked to a specific piece of driving operation information. The determination unit 61B then determines the item linked to the driving operation information acquired by the acquisition unit 61A as the item of evaluation information to be output from the monitor 78 and the speaker 79. For example, the determination unit 61B determines the item of evaluation information to be output from the monitor 78 and the speaker 79 to be "Good Braking" or "Bad Braking" based on the acceleration and vehicle speed of the vehicle 60 acquired as driving operation information by the acquisition unit 61A.

[0054] Furthermore, the determining unit 61B determines the output method of the evaluation information suitable for the driver of the vehicle 60 acquired by the acquiring unit 61A as the output method of the evaluation information to be output from the monitor 78 and the speaker 79 of the vehicle 60.

[0055] The control unit 61C performs control to output the items of evaluation information determined by the determination unit 61B from the monitor 78 and the speaker 79 while the vehicle 60 is being driven, using the output method determined by the determination unit 61B.

[0056] The management unit 61D manages the driver's behavior when the evaluation information is output from the monitor 78 and the speaker 79. The management unit 61D manages, as the driver's behavior, whether or not the cancel switch is operated within a predetermined time after the evaluation information is output, and the driver's facial expression. Specifically, if the cancel switch is operated within a predetermined time after the evaluation information is output, the management unit 61D stores the operation of the cancel switch as driver information in the storage unit 64. The management unit 61D also controls the second camera of the camera 76 to capture an image of the driver's face within a predetermined time after the evaluation information is output, and stores the captured image as driver information in the storage unit 64.

[0057] The transmission unit 61E transmits the driving operation information and the driver information to the management server 20. The transmission unit 61E transmits the driving operation information and the driver information stored in the memory unit 64 to the management server 20 periodically, for example, once a day.

[0058] Next, a description will be given of the hardware configuration of the management server 20 and the driver terminal 40. Fig. 4 is a block diagram showing the hardware configuration of the management server 20 and the driver terminal 40. Since the management server 20 and the driver terminal 40 basically have a general computer configuration, the management server 20 will be described as a representative.

[0059] 4, the management server 20 includes a CPU 21, a ROM 22, a RAM 23, a storage unit 24, an input unit 25, a display unit 26, and a communication unit 27. Each component is connected to each other via a bus 28 so as to be able to communicate with each other.

[0060] The CPU 21 is a central processing unit that executes various programs and controls each part. That is, the CPU 21 reads programs from the ROM 22 or the storage unit 24 and executes the programs using the RAM 23 as a work area. The CPU 21 controls each of the above components and performs various arithmetic processing in accordance with the programs recorded in the ROM 22 or the storage unit 24.

[0061] The ROM 22 stores various programs and various data. The RAM 23 serves as a working area for temporarily storing programs or data.

[0062] The storage unit 24 is configured by a storage device such as a hard disk drive (HDD), a solid state drive (SSD), or a flash memory, and stores various programs and various data.

[0063] The input unit 25 includes a pointing device such as a mouse, a keyboard, a microphone, a camera, and the like, and is used to perform various inputs.

[0064] The display unit 26 is, for example, a liquid crystal display, and displays various information. The display unit 26 may function as the input unit 25 by adopting a touch panel system.

[0065] The communication unit 27 is an interface for communicating with other devices. For this communication, a wired communication standard such as Ethernet (registered trademark) or FDDI, or a wireless communication standard such as 4G, 5G, Bluetooth (registered trademark), or Wi-Fi (registered trademark) is used.

[0066] FIG. 5 is a block diagram showing the configuration of the storage unit 24 of the management server 20. As shown in FIG. As shown in FIG. 5, the storage unit 24 includes a program storage unit 30, an individual characteristic storage unit 32, an individual response storage unit , and a trained model storage unit .

[0067] The program storage unit 30 stores a learning program 30A and an information processing program 30B. The learning program 30A is a program that causes the CPU 21 to execute a machine learning learning process (see FIG. 7) described later and generate a trained model as a result of the learning process. The information processing program 30B is a program that causes the CPU 21 to execute an update process (see FIG. 8) and a change process (see FIG. 9) described later.

[0068] The personal characteristic storage unit 32 stores personal characteristic information indicating the personal characteristics of each driver of each vehicle 60. The personal characteristic information includes, for example, the age, gender, and personality of the driver. A method for generating the personal characteristic information of the driver of the vehicle 60 will be described later.

[0069] The individual response storage unit 34 stores response information that accumulates the driver's responses to the evaluation information output from the monitor 78 and the speaker 79 while driving the vehicle 60. The response information includes, for example, whether the response of each driver to the evaluation information output by each output method is good or bad. For example, the individual response storage unit 34 stores response information such as "Driver A's response to the evaluation information output by output method A is good, but the response to the evaluation information output by output method B is bad" or "Driver B's response to the evaluation information output by output method A is bad, but the response to the evaluation information output by output method B is good."

[0070] The trained model storage unit 36 ​​stores the trained model generated as a result of the learning process and an updated model obtained by updating the trained model, in association with the driver. The updated model is an example of a "model."

[0071] Next, the functional configuration of the management server 20 will be described. FIG. 6 is a block diagram showing an example of the functional configuration of the management server 20. As shown in FIG.

[0072] 6, the CPU 21 of the management server 20 has, as functional components, an acquisition unit 21A, a generation unit 21B, an identification unit 21C, an update unit 21D, an estimation unit 21E, and a change unit 21F. Each functional component is realized by the CPU 21 reading and executing an information processing program 30B stored in the storage unit 24. The acquisition unit 21A acquires driving operation information and driver information from the vehicle 60.

[0073] The generation unit 21B generates personal characteristic information for each driver of each vehicle 60 based on the driving operation information acquired by the acquisition unit 21A and the results of a test to estimate the personal characteristics of each driver of each vehicle 60. For example, the generation unit 21B generates personal characteristic information for driver A as "Age: 35 years old, Gender: Male, Personality: Gentle" based on the driving operation information of driver A and the results of the test. The personal characteristic information generated by the generation unit 21B is associated with the driver and stored in the personal characteristic storage unit 32.

[0074] Furthermore, every time the acquisition unit 21A acquires driving operation information, the generation unit 21B updates the personal characteristic information of the driver linked to the acquired driving operation information. For example, the generation unit 21B updates the personal characteristic information of the driver A stored in the personal characteristic storage unit 32 to, for example, "age: 35, gender: male, personality: short-tempered" based on the driving operation information acquired by the acquisition unit 21A after a certain period of time has elapsed since the generation of the personal characteristic information of the driver A and the results of the above-mentioned test.

[0075] The identification unit 21C identifies whether the driver's reaction to the evaluation information output from the monitor 78 and the speaker 79 while driving the vehicle 60. In the first embodiment, as an example, the identification unit 21C identifies whether the reaction is good or bad based on the driver's behavior when the evaluation information is output from the monitor 78 and the speaker 79.

[0076] For example, if the determination unit 21C detects the driver's operation of the cancel switch as the behavior based on the driver information acquired by the acquisition unit 21A, the determination unit 21C determines that the driver's reaction to the evaluation information is "bad." Furthermore, if the determination unit 21C detects the driver's unpleasant facial expression as the behavior based on the driver information acquired by the acquisition unit 21A, the determination unit 21C determines that the driver's reaction to the evaluation information is "bad." Furthermore, if the determination unit 21C detects the driver's happy facial expression as the behavior based on the driver information acquired by the acquisition unit 21A, the determination unit 21C determines that the driver's reaction to the evaluation information is "good." The determination unit 21C detects the driver's facial expression by performing known image processing on an image of the driver's face captured by the second camera of the camera 76, which the acquisition unit 21A acquired as the driver information.

[0077] Then, the good or bad reaction of the driver to the evaluation information output by the one output method (for example, output method A) identified by the identification unit 21C is stored in the individual reaction storage unit 34 as reaction information of the driver.

[0078] The update unit 21D updates a learned model that has undergone machine learning to adjust the method of outputting evaluation information suitable for other drivers who have personal characteristics similar to the driver, to an updated model that uses the driver's personal characteristic information and reaction information to estimate the method of outputting evaluation information suitable for the driver.

[0079] First, the update unit 21D identifies other drivers who have personal characteristics similar to that of the driver, by referring to the personal characteristic information of the driver stored in the personal characteristic storage unit 32. In the first embodiment, a driver is defined as "having personal characteristics similar to that of the driver" when the degree of match with the driver's personal characteristic information is equal to or greater than a predetermined standard.

[0080] Next, the update unit 21D acquires the learned model of the other driver identified above from the learned model storage unit 36. Note that, if there are multiple other drivers whose degree of match with the driver's personal characteristic information is equal to or exceeds a predetermined standard, the update unit 21D acquires the learned model of the other driver with the greatest degree of match. Then, the update unit 21D inputs the driver's personal characteristic information stored in the personal characteristic storage unit 32 and the driver's reaction information stored in the personal reaction storage unit 34 into the acquired learned model of the other driver as learning data for performing machine learning on the model to adjust the output method of evaluation information suitable for the driver. As a result of the machine learning, the learned model of the other driver is updated to an updated model that estimates the output method of evaluation information suitable for the driver.

[0081] Then, the updated model of the driver updated by the update unit 21D is stored in the learned model storage unit 36 ​​in association with the driver.

[0082] The estimation unit 21E estimates an output method of evaluation information suitable for the driver based on the good or bad of the driver's reaction identified by the identification unit 21C. Specifically, the estimation unit 21E estimates an output method of evaluation information suitable for the driver by inputting the personal characteristic information of the driver stored in the personal characteristic storage unit 32 and the reaction information of the driver stored in the personal reaction storage unit 34 into an updated model of the driver stored in the learned model storage unit 36.

[0083] In the first embodiment, the estimation unit 21E periodically, for example daily, uses the driver's personal characteristic information stored in the personal characteristic memory unit 32 and the driver's reaction information stored in the personal reaction memory unit 34 as learning data, and updates the updated model through machine learning to estimate an output method of the latest evaluation information suitable for the driver.

[0084] The change unit 21F changes the output method of the evaluation information output from the monitor 78 and the speaker 79 to the output method of the evaluation information estimated by the estimation unit 21E. In the first embodiment, the change unit 21F changes the output method of the evaluation information output from the monitor 78 and the speaker 79 to the vehicle 60 by transmitting the output method of the evaluation information estimated by the estimation unit 21E to the vehicle 60.

[0085] Next, the flow of the learning process in which the management server 20 generates a learned model will be described. 7 is a flowchart showing the flow of the learning process by the management server 20. The CPU 21 reads out the learning program 30A from the storage unit 24, loads it into the RAM 23, and executes it, thereby carrying out the learning process.

[0086] 7, the CPU 21 acquires learning data to be trained by the model from the personal characteristic storage unit 32 and the personal response storage unit 34. Specifically, the CPU 21 acquires personal characteristic information corresponding to the driver of the vehicle 60 for which a trained model is to be generated from the personal characteristic storage unit 32, and acquires response information corresponding to the driver from the personal response storage unit 34. In the first embodiment, the model to be trained using the above learning data is a neural network. Then, the process proceeds to step S11.

[0087] In step S11, the CPU 21 generates a trained model that estimates an output method of evaluation information suitable for the driver by inputting the training data acquired in step S10 into the model, and then proceeds to step S12.

[0088] In step S12, the CPU 21 associates the trained model generated in step S11 with the driver and stores it in the trained model storage unit 36. Then, the learning process ends.

[0089] Next, we will explain the flow of the update process in which the management server 20 updates the learned model of another driver who has similar personal characteristics to the driver of the vehicle 60 to an updated model that estimates an output method of evaluation information suitable for the driver.

[0090] 8 is a flowchart showing the flow of the update process by management server 20. The update process is performed by CPU 21 reading information processing program 30B from storage unit 24, expanding it into RAM 23, and executing it. In the following explanation of FIG. 8, the driver of vehicle 60 will be referred to as "driver A," and another driver who has similar personal characteristics to the driver of vehicle 60 will be referred to as "driver B."

[0091] 8, the CPU 21 refers to the personal characteristic information of the driver A stored in the personal characteristic storage unit 32 and identifies the driver B who has personal characteristics similar to those of the driver A. Then, the process proceeds to step S21.

[0092] In step S21, the CPU 21 acquires the learned model of the driver B identified in step S20 from the learned model storage unit 36. Then, the process proceeds to step S22.

[0093] In step S22, CPU 21 updates the trained model of driver B acquired in step S21 to an updated model that estimates an evaluation information output method suitable for driver A. Specifically, CPU 21 inputs the personal characteristic information of driver A stored in personal characteristic storage unit 32 and the reaction information of driver A stored in personal reaction storage unit 34 as training data into the trained model of driver B. As a result of machine learning, the trained model of driver B is thereby updated to an updated model that estimates an evaluation information output method suitable for driver A. Then, the process proceeds to step S23.

[0094] In step S23, the CPU 21 associates the updated model updated in step S22 with the driver A and stores the updated model in the learned model storage unit 36. Then, the update process ends.

[0095] Next, a flow of a change process in which the management server 20 changes the output method of the evaluation information output from the monitor 78 and the speaker 79 of the vehicle 60 to an output method of the evaluation information suitable for the driver of the vehicle 60 will be described.

[0096] 9 is a flowchart showing the flow of the change processing by the management server 20. The change processing is performed by the CPU 21 reading out the information processing program 30B from the storage unit 24, loading it into the RAM 23, and executing it.

[0097] 9, the CPU 21 acquires driver information from the vehicle 60. Then, the process proceeds to step S31. In the first embodiment, the driver information is transmitted from the vehicle 60 to the management server 20 periodically, for example, once a day.

[0098] In step S31, the CPU 21 determines whether the driver's reaction to the evaluation information output from the monitor 78 and the speaker 79 while driving the vehicle 60 is good or bad. In the first embodiment, as an example, the CPU 21 determines whether the driver's reaction to the evaluation information when the evaluation information is output from the monitor 78 and the speaker 79 while driving the vehicle 60, from the driver's behavior based on the driver information acquired in step S30. Then, the process proceeds to step S32.

[0099] In step S32, the CPU 21 estimates an output method of evaluation information suitable for the driver based on the quality of the driver's reaction identified in step S31. Specifically, the CPU 21 estimates an output method of evaluation information suitable for the driver by inputting the driver's personal characteristic information stored in the personal characteristic storage unit 32 and the driver's reaction information stored in the personal reaction storage unit 34 into the updated model of the driver stored in the learned model storage unit 36. Then, the process proceeds to step S33.

[0100] In step S33, the CPU 21 changes the output method of the evaluation information output from the monitor 78 and the speaker 79 to the output method of the evaluation information estimated in step S32. In the first embodiment, the CPU 21 changes the output method of the evaluation information output from the monitor 78 and the speaker 79 to the vehicle 60 by transmitting the output method of the evaluation information estimated in step S32 to the vehicle 60. Then, the change process ends.

[0101] Next, the evaluation information output from the monitor 78 and the speaker 79 while the vehicle 60 is being driven before and after the change process shown in FIG. 9 is described.

[0102] 10 is an explanatory diagram showing an example of evaluation information output to the monitor 78, specifically, the multi-information display (hereinafter referred to as "MID") 78A while driving the vehicle 60. Specifically, FIG. 10(A) is an example of evaluation information output to the MID 78A before execution of the change process, and FIG. 10(B) is an example of evaluation information output to the MID 78A after execution of the change process.

[0103] As shown in FIGS. 10(A) and 10(B), evaluation information 50 is output to the MID 78A. As an example, in FIGS. 10(A) and 10(B), "Brakes Good" is output as the evaluation information 50 while the vehicle 60 is being driven. In this case, the character content of the evaluation information 50 in FIGS. 10(A) and 10(B) is the same, but the character size of the evaluation information 50 is different. Specifically, the character size of the evaluation information 50 in the output example shown in FIG. 10(B) is larger than the character size of the evaluation information 50 in the output example shown in FIG. 10(A). In this way, the output example shown in FIG. 10(B) is an example in which the CPU 21 has changed the output method of the evaluation information by estimating that increasing the character size of the evaluation information 50 would be more suitable for the driver based on the driver's reaction when the evaluation information 50 shown in FIG. 10(A) is output to the MID 78A while the vehicle 60 is being driven.

[0104] Fig. 11 is an explanatory diagram showing an example of evaluation information output from the speaker 79 while driving the vehicle 60. Specifically, Fig. 11(A) is an example of evaluation information output from the speaker 79 before execution of the change process, and Fig. 11(B) is an example of evaluation information output from the speaker 79 after execution of the change process.

[0105] As shown in FIGS. 11(A) and 11(B), evaluation information 50 is output from speaker 79. As an example, in FIG. 11(A), while driving vehicle 60, a voice saying "good brakes" is output from speaker 79 as evaluation information 50. At this time, the voice output from speaker 79 in FIG. 11(A) is a male voice with a strict tone. Also, in FIG. 11(B), while driving vehicle 60, a voice saying "good brakes" is output from speaker 79 as evaluation information 50. At this time, the voice output from speaker 79 in FIG. 11(B) is a female voice with a gentle tone. In this way, the output example shown in Figure 11(B) is an example in which the CPU 21 has changed the output method of the evaluation information based on the driver's reaction when the evaluation information 50 shown in Figure 11(A) is output from the speaker 79 while driving the vehicle 60, and has estimated that changing the voice of the evaluation information 50 to a gentle, female tone would be more suitable for the driver.

[0106] As described above, in the management server 20, the CPU 21 identifies whether the driver's response to the evaluation information output from the monitor 78 and the speaker 79 while the vehicle 60 is being driven is good or bad. The CPU 21 also estimates an output method of the evaluation information that is suitable for the driver based on the identified quality of the driver's response. The CPU 21 then changes the output method of the evaluation information output from the monitor 78 and the speaker 79 to the estimated output method of the evaluation information. In this way, the management server 20 can change the output method of the evaluation information based on the quality of the driver's response to the evaluation information output from the monitor 78 and the speaker 79 while the vehicle 60 is being driven, thereby making it possible to make the output method of the evaluation information output inside the vehicle while driving suitable for the driver.

[0107] Furthermore, in the management server 20, the CPU 21 updates a trained model that has undergone machine learning to adjust the output method of evaluation information suitable for other drivers who have similar personal characteristics to the driver, to an updated model that estimates the output method of evaluation information suitable for the driver, using the driver's personal characteristic information and reaction information. As a result, by using the trained model suitable for other drivers who have similar personal characteristics as a base, the management server 20 can generate a model that estimates the output method of evaluation information suitable for the driver in a shorter time than when not using the trained model as a base.

[0108] Furthermore, in the management server 20, the CPU 21 estimates an output method of the evaluation information suitable for the driver based on the response of the identified driver. This allows the management server 20 to output the evaluation information from the monitor 78 and the speaker 79 using an output method optimized based on the individual characteristics of the driver and the response of the driver to the evaluation information output from the monitor 78 and the speaker 79 while driving the vehicle 60.

[0109] Furthermore, in the management server 20, the CPU 21 identifies whether the driver's reaction to the evaluation information output from the monitor 78 and the speaker 79 is good or bad, based on the driver's behavior when the evaluation information is output from the monitor 78 and the speaker 79. As a result, the management server 20 can make the output method of the evaluation information output in the vehicle while driving suitable for the driver, without asking the driver for his / her opinion on the output method of the evaluation information output from the monitor 78 and the speaker 79.

[0110] (Second embodiment) Next, a second embodiment of the information processing system 10 according to the present invention will be described while omitting or simplifying parts that overlap with other embodiments.

[0111] In the second embodiment, the identification unit 21C identifies whether the driver's reaction to the evaluation information output from the monitor 78 and the speaker 79 is good or bad, based on the driver's response to questions about the evaluation information.

[0112] First, based on the fact that the acquisition unit 21A has acquired, as driving operation information, that an ignition switch (not shown) of the vehicle 60 has been switched from the ON position to the OFF position, the identification unit 21C transmits content information including a question regarding the evaluation information to the driver terminal 40. Then, based on the fact that the acquisition unit 21A has acquired, as driving operation information, answer information indicating the driver's answer to the question, the identification unit 21C identifies, from the content of the answer information, whether the driver's reaction to the evaluation information output from the monitor 78 and the speaker 79 is good or bad.

[0113] FIG. 12 is an example of a display displayed on the display unit 46 of the driver's terminal 40. In the example display shown in FIG. 12, message information 52, a good button 54, a normal button 56, and a bad button 58 are displayed.

[0114] The message information 52 shows various messages to the driver. As an example, in Fig. 12, the message information 52 displays "What did you think of the method for outputting the evaluation information today?" In this way, the message information 52 shown in Fig. 12 presents the driver with a question about the evaluation information, asking whether the method for outputting the evaluation information from the monitor 78 and the speaker 79 was good or bad.

[0115] The good button 54 is a button that the driver operates when he or she feels that the method of outputting the evaluation information is good.

[0116] The normal button 56 is a button that the driver operates when he or she feels that the method of outputting the evaluation information is neither good nor bad.

[0117] The bad button 58 is a button that the driver operates when he or she feels that the evaluation information was output in a bad way.

[0118] When any one of the good button 54, the normal button 56, or the bad button 58 is operated, the driver terminal 40 transmits answer information indicating which button was operated to the management server 20. The management server 20, which has acquired the answer information, uses the function of the identification unit 21C to identify whether the driver's response to the evaluation information output from the monitor 78 and the speaker 79 is good or bad, based on the content of the answer information. Specifically, when the content of the answer information indicates the operation of the good button 54, the identification unit 21C identifies the driver's response to the evaluation information output from the monitor 78 and the speaker 79 while driving the vehicle 60 as "good." When the content of the answer information indicates the operation of the normal button 56, the identification unit 21C identifies the driver's response to the evaluation information as "normal." When the content of the answer information indicates the operation of the bad button 58, the identification unit 21C identifies the driver's response to the evaluation information as "bad."

[0119] As described above, in the management server 20, the CPU 21 determines whether the driver's reaction to the evaluation information output from the monitor 78 and the speaker 79 is good or bad, based on the answers of the driver of the vehicle 60 to questions about the evaluation information. This allows the management server 20 to determine the driver's reaction more accurately than when the driver's reaction to the evaluation information output from the monitor 78 and the speaker 79 is determined only indirectly.

[0120] (others) In the above embodiment, the management server 20 is an example of an information processing device, but the present invention is not limited to this. The on-board device 15 mounted on the vehicle 60 may be an example of an information processing device, or the combination of the management server 20 and the on-board device 15 may be an example of an information processing device. When the combination of the management server 20 and the on-board device 15 is an example of an information processing device, the update process shown in Fig. 8 and the change process shown in Fig. 9 are executed by one processor, the CPU 21 of the management server 20 or the CPU 61 of the on-board device 15, or by a combination of multiple processors, the CPU 21 of the management server 20 and the CPU 61 of the on-board device 15.

[0121] In the above embodiment, both the monitor 78 and the speaker 79 of the vehicle 60 are examples of the output unit, but this is not limiting, and either the monitor 78 or the speaker 79 may be an example of the output unit. Furthermore, instead of the monitor 78 and the speaker 79 of the vehicle 60, at least one of the display unit 46 of the driver terminal 40 and a speaker (not shown) may be an example of the output unit.

[0122] In the above embodiment, the driver information includes the operation of the cancel switch and an image of the driver's face within a predetermined time after the evaluation information is output. In this case, instead of or in addition to the above information, the driver information may include the driver's voice collected by the microphone 75 of the vehicle 60 within a predetermined time after the evaluation information is output. In this case, the management server 20, which acquires the driver's voice, can, as a function of the identification unit 21C, detect the driver's emotions based on the driver's behavior when the evaluation information is output from the monitor 78 and the speaker 79. For example, if the identification unit 21C detects a negative emotion as the driver's behavior based on the driver's voice acquired as the driver information, it can identify the driver's reaction to the evaluation information as "bad." Furthermore, if the identification unit 21C detects a positive emotion as the driver's behavior based on the driver's voice acquired as the driver information, it can identify the driver's reaction to the evaluation information as "good." The identification unit 21C detects the driver's emotion by performing a known voice analysis process on the voice uttered by the driver acquired by the acquisition unit 21A as the driver information.

[0123] In the above embodiment, a trained model suitable for another driver having similar personal characteristics to the driver of the vehicle 60 is updated to an updated model that estimates an output method of evaluation information suitable for the driver using the driver's personal characteristic information and reaction information. However, this is not limited to this. A model that estimates an output method of evaluation information suitable for the driver of the vehicle 60 may be generated without using a trained model suitable for another driver. For example, if the CPU 21 determines that there is no other driver having similar personal characteristics to the driver, the CPU 21 may generate a model that estimates an output method of evaluation information suitable for the driver without using a trained model suitable for the other driver. Furthermore, even if the CPU 21 determines that there is another driver having similar personal characteristics to the driver, if the CPU 21 does not wish to use the trained model, the CPU 21 may generate a model that estimates an output method of evaluation information suitable for the driver without using the trained model.

[0124] In the above embodiment, the learning process, update process, and change process executed by the CPU 21 by loading software (programs) may be executed by various processors other than a CPU. Examples of such processors include programmable logic devices (PLDs) (such as field-programmable gate arrays (FPGAs)) whose circuit configuration can be changed after fabrication, and dedicated electrical circuits, such as application-specific integrated circuits (ASICs), which are processors with circuit configurations specifically designed to execute specific processes. The learning process, update process, and change process may be executed by one of these various processors, or by a combination of two or more processors of the same or different types (e.g., multiple FPGAs, or a combination of a CPU and an FPGA). The hardware structure of these various processors is, more specifically, an electrical circuit that combines circuit elements such as semiconductor devices.

[0125] In the above embodiment, the learning program 30A and the information processing program 30B are pre-stored (installed) in the storage unit 24, but this is not limiting. The learning program 30A and the information processing program 30B may be provided in a form recorded on a recording medium such as a CD-ROM (Compact Disk Read Only Memory), a DVD-ROM (Digital Versatile Disk Read Only Memory), or a USB (Universal Serial Bus) memory. The learning program 30A and the information processing program 30B may also be downloaded from an external device via the network N. [Explanation of symbols]

[0126] 20 Management server (information processing device) 21C Specific part 21D Update Department 21E Estimation section 21F Change Section 30B Information Processing Program 60 vehicles 78 Monitor (output section) 79 Speaker (output section)

Claims

1. an identification unit that identifies a reaction of the driver to evaluation information that evaluates the driving of the driver of the vehicle, the evaluation information being output from an output unit while the vehicle is being driven; an estimation unit that estimates an output method of the evaluation information suitable for the driver based on the reaction of the driver identified by the identification unit; a change unit that changes the output method of the evaluation information output from the output unit to the output method of the evaluation information estimated by the estimation unit; an acquisition unit that acquires driving operation information related to the driving operation of the driver and driver information indicating the behavior of the driver from the vehicle; Equipped with The identification unit As the behavior of the driver when the evaluation information is output from the output unit, the quality of the driver's reaction to the evaluation information output from the output unit is determined according to an expression detected from an image of the driver's face captured by a camera within a predetermined time after the evaluation information is output, which is included in the driver information acquired by the acquisition unit; storing, in a storage unit, the good or bad reaction of the driver to the evaluation information output from the output unit by one output method as reaction information of the driver; Information processing device.

2. The identification unit: When detecting, as the behavior of the driver when the evaluation information is output from the output unit, an operation of a cancel switch, which is a switch for canceling the output of the evaluation information, within a predetermined time after the evaluation information included in the driver information acquired by the acquisition unit is output, the driver's reaction to the evaluation information output from the output unit is determined to be poor. The information processing device according to claim 1 .

3. Identifying a reaction of the driver to evaluation information that evaluates the driving of the driver of the vehicle, the evaluation information being output from an output unit while the vehicle is being driven; estimating an output method of the evaluation information suitable for the driver based on the identified reaction of the driver; changing the output method of the evaluation information output from the output unit to the estimated output method of the evaluation information; Acquire driving operation information related to the driving operation of the driver and driver information indicating the behavior of the driver from the vehicle; As the behavior of the driver when the evaluation information is output from the output unit, the quality of the driver's reaction to the evaluation information output from the output unit is determined according to an expression detected from an image of the driver's face captured by a camera within a predetermined time after the evaluation information is output, which is included in the acquired driver information; storing, in a storage unit, the good or bad reaction of the driver to the evaluation information output from the output unit by one output method as reaction information of the driver; An information processing method in which processing is performed by a computer.

4. On the computer, Identifying a reaction of the driver to evaluation information that evaluates the driving of the driver of the vehicle, the evaluation information being output from an output unit while the vehicle is being driven; estimating an output method of the evaluation information suitable for the driver based on the identified reaction of the driver; changing the output method of the evaluation information output from the output unit to the estimated output method of the evaluation information; Acquire driving operation information related to the driving operation of the driver and driver information indicating the behavior of the driver from the vehicle; As the behavior of the driver when the evaluation information is output from the output unit, the quality of the driver's reaction to the evaluation information output from the output unit is determined according to an expression detected from an image of the driver's face captured by a camera within a predetermined time after the evaluation information is output, which is included in the acquired driver information; storing, in a storage unit, the good or bad reaction of the driver to the evaluation information output from the output unit by one output method as reaction information of the driver; An information processing program for executing processing.

Images