JP2022179490A - Driving evaluation model adaptation device, terminal equipment, control method, program, and storage medium - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a driving evaluation model adaptation device capable of distributing a driving evaluation model as a learning result adapted to a use situation.

SOLUTION: A server device 1 stores a driving evaluation model learnt on the basis of a photographic image of the vicinity of a mobile body and an evaluation value related to driving determined on the basis of the photographic image by a determining person. In this case, the driving evaluation model is generated for each group of determining persons classified in accordance with commonality of profiles. The server device 1 acquires profile information Ip related to a driver who drives a mobile body, and extracts the driving evaluation model in the adapted group adapted to the acquired profile information Ip from a driving evaluation model DB 10.

SELECTED DRAWING: Figure 4

COPYRIGHT: (C)2023,JPO&INPIT

Description

TECHNICAL FIELD The present invention relates to technology that utilizes a model obtained by learning.

2. Description of the Related Art Conventionally, there has been known a system in which data from a plurality of vehicles are collected in a server device, and information on learning results obtained by machine learning by the server device is distributed. For example, Patent Literature 1 discloses a system that collects conditions such as weather and time of day when each vehicle is traveling as environmental data, and learns for each condition indicated by the environmental data.

JP 2015-135552 A

Regarding situation recognition and situation judgment during driving, there are individual differences based on driver's experience, etc., and recognition and judgment may differ depending on the driver. On the other hand, Patent Document 1 does not consider such individual differences at all.

The present invention has been made to solve the above-described problems, and includes a driving evaluation model matching device capable of distributing a driving evaluation model, which is a learning result adapted to usage conditions, and a driving evaluation model receiving device. The main purpose is to provide a terminal device that

The invention according to claim 1 is a driving evaluation model matching device, which includes an information acquisition unit for acquiring driver information about a driver who drives a mobile object, a captured image around the mobile object, and a judge having a profile. Driving in a matching group that matches the driver information from a driving evaluation model learned for each group of the judges classified by the commonality of the profiles based on the evaluation information on driving evaluated based on the photographed image an extraction unit for extracting the evaluation model.

According to the eighth aspect of the present invention, the judges are classified according to the commonality of the profile based on the photographed image around the moving body and the evaluation information about the driving evaluated by the judge having the profile based on the photographed image. A control method executed by a driving evaluation model matching device having a storage unit for storing driving evaluation models learned for each group, the information obtaining step of obtaining driver information about a driver who drives a moving object; an extracting step of extracting a driving evaluation model in a matching group that matches the driver information.

According to a ninth aspect of the invention, the judges are classified according to the commonality of the profiles based on the photographed images around the moving body and the evaluation information regarding driving evaluated by the judges having the profiles based on the photographed images. A program executed by a computer that refers to a storage unit that stores a driving evaluation model learned for each group of the information acquisition unit that acquires driver information about a driver who drives a moving object, and the driver information The computer functions as an extraction unit that extracts the driving evaluation model in the matching group that matches the .

It is a schematic structure of a driving evaluation system. 2 shows a block configuration of a server device and a terminal device; It is a correspondence table between the identification number of the driving evaluation model and each item representing the profile of the judge corresponding to the driving evaluation model. FIG. 10 is an example of a flowchart showing a procedure of delivery processing of a driving evaluation model; FIG. It is an example of a flowchart showing a processing procedure for receiving and utilizing a driving evaluation model. 3 shows an example of display output by a terminal device.

According to a preferred embodiment of the present invention, the driving evaluation model matching device includes: an information acquisition unit that acquires driver information about a driver who drives a mobile object; Driving in a matching group that matches the driver information from a driving evaluation model learned for each group of the judges classified by the commonality of the profiles based on the evaluation information on driving evaluated based on the photographed image an extraction unit for extracting the evaluation model.

The driving evaluation model matching device includes an information acquisition unit, a storage unit, and an extraction unit. The storage unit stores a driving evaluation model learned based on a photographed image of the surroundings of the moving body and evaluation information regarding driving evaluated by a judge based on the photographed image. Here, the driving evaluation model stored in the storage unit is generated for each group of judges classified according to commonality of profiles. The information acquisition unit acquires driver information about a driver who drives the mobile object. The extraction unit extracts a driving evaluation model in the matching group that matches the acquired driver information. Here, the “matching group” refers to a group matching the acquired driver information among the groups of judges classified by the commonality of profiles. According to this aspect, the driving evaluation model matching device can suitably extract a driving evaluation model that matches the characteristics of the driver indicated by the acquired driver information.

In one aspect of the driving evaluation model matching device, the driving evaluation model matching device further includes a transmission unit that transmits information about the driving evaluation model in the matching group to a communication terminal provided in the moving body. According to this aspect, the driving evaluation model matching device can suitably supply a driving evaluation model that matches the characteristics of the driver based on the driver information of the driver of the mobile object.

In another aspect of the driving evaluation model matching device, the driver information and the profile include at least residential area information regarding the residential area of the driver and the determiner, and the driving evaluation extracted by the extracting unit. The model is a driving evaluation model for a group that matches the residence area information included in the driver information, among the groups of the judges classified according to the commonality of the residence area information. According to this aspect, the driving evaluation model matching device can suitably extract the driving evaluation model specialized for the residential area of the driver of the mobile object.

In another aspect of the driving evaluation model matching device, the driver information and the profile further include driving history information of the driver and the determiner, and the driving evaluation model extracted by the extraction unit includes: A driving evaluation model for a group that matches the residential area information and the driving history information included in the driver information, among the groups of the judges classified according to the commonality of the residential area information and the driving history information. According to this aspect, the driving evaluation model matching device can suitably extract a driving evaluation model that matches the residential area and driving experience of the driver of the mobile object.

According to another preferred embodiment of the present invention, a terminal device includes: a transmitter for transmitting driver information about a driver who drives a mobile object to the above-described driving evaluation model matching device; a receiving unit that receives information about a driving evaluation model in a matching group that matches the driver information; an imaging unit that generates a captured image; and applying the driving evaluation model to the captured image. and an evaluation information generation unit that generates evaluation information about. According to this aspect, the terminal device can suitably receive the driving evaluation model generated by using as a teacher a matching group of judges who match the driver information, and can generate evaluation information that matches the senses of the driver.

In one aspect of the terminal device, the terminal device further includes an output unit that performs display or audio output based on the evaluation information generated by the evaluation information generating means. According to this aspect, the driving evaluation model matching device can suitably notify the driver or the like of the evaluation information generated by the acquired driving evaluation model. Preferably, the evaluation information is information indicating driving difficulty or information indicating visibility.

According to another preferred embodiment of the present invention, based on the photographed image of the surroundings of the moving body and the evaluation information regarding driving evaluated based on the photographed image by the judge having the profile, the driving is classified according to the commonality of the profiles. A control method executed by a driving evaluation model matching device having a storage unit that stores a driving evaluation model learned for each group of judges, wherein information for acquiring driver information about a driver who drives a moving object an obtaining step; and an extracting step of extracting a driving evaluation model in a matching group that matches the driver information. By executing this control method, the driving evaluation model matching device can suitably extract a driving evaluation model that matches the characteristics of the driver indicated by the acquired driver information.

According to another preferred embodiment of the present invention, based on the photographed image of the surroundings of the moving body and the evaluation information regarding driving evaluated based on the photographed image by the judge having the profile, the driving is classified according to the commonality of the profile. a program executed by a computer that refers to a storage unit that stores a driving evaluation model learned for each group of judges, the information acquiring unit acquiring driver information about a driver who drives a moving object; The computer is caused to function as an extraction unit that extracts a driving evaluation model in the matching group that matches the driver information. By executing this program, the computer can suitably extract a driving evaluation model that matches the characteristics of the driver indicated by the acquired driver information. Preferably, the program is stored in a storage medium.

Preferred embodiments of the present invention will be described below with reference to the drawings.

[Outline of driving evaluation system]
FIG. 1 is a schematic configuration of a driving evaluation system according to this embodiment. The driving evaluation system is a system for evaluating driving on a road on which a vehicle travels, and includes a server device 1 and a terminal device 2 .

The server device 1 stores a driving evaluation model DB 10, which is a database of models (also referred to as "driving evaluation models") for determining an evaluation of driving on the road displayed in the photographed image taken on the road. I remember. The driving evaluation model is a pattern classifier obtained by supervised machine learning, and is learning data learned by applying a neural network (deep learning), for example. In this embodiment, a combination of a photographed image taken on the road and an evaluation value of driving difficulty determined by a person who refers to the photographed image (also referred to as a "determiner") is learned as teacher data. By doing so, a driving evaluation model is generated. The evaluation value of the driving difficulty may be, for example, a two-step evaluation value of “0” indicating that it is easy to drive or “1” indicating that it is difficult to drive, or an evaluation value of three or more steps. good. The evaluation value of the driving difficulty is an example of "evaluation information" in the present invention.

Here, each driving evaluation model registered in the driving evaluation model DB 10 is generated for each group of judges having common profiles such as gender and driving history, as will be described later. When the server device 1 receives information indicating the profile of the user of the terminal device 2 (also referred to as "profile information Ip") from the terminal device 2, the server device 1 generates a driving evaluation model that matches the profile indicated by the profile information Ip. It extracts from driving evaluation model DB10. Then, the server device 1 transmits information indicating the extracted driving evaluation model (also referred to as “extracted model information Im”) to the terminal device 2 . The server device 1 is an example of a "driving evaluation model matching device" in the present invention.

The terminal device 2 is, for example, a stationary navigation device or a mobile terminal such as a smartphone, and performs route guidance to a destination, display of a map around the current position, and the like. In addition, the terminal device 2 receives from the server device 1 the extracted model information Im regarding the driving evaluation model that matches the profile of the user by transmitting the profile information Ip indicating the profile of the user of the terminal device 2 to the server device 1 . . Then, the terminal device 2 inputs the image captured by the camera to the driving evaluation model indicated by the extracted model information Im, thereby acquiring the evaluation value of the driving difficulty of the road displayed in the image, and obtaining the driving difficulty level of the road displayed in the image. Output based on degree evaluation value. The terminal device 2 is an example of a "communication terminal" and a "terminal device" in the present invention.

[Device configuration]
FIG. 2A shows a schematic configuration of the server device 1. As shown in FIG. As shown in FIG. 2A, the server device 1 has a communication unit 11, a storage unit 12, and a control unit 15. The communication unit 11, storage unit 12, and control unit 15 are interconnected via a bus line.

Under the control of the control unit 15, the communication unit 11 receives the profile information Ip transmitted from the terminal device 2, transmits the extracted model information Im to the terminal device 2, and the like. The communication unit 11 is an example of the "transmitting unit" in the present invention. The storage unit 12 stores a program for controlling the operation of the server device 1 and holds information required for the operation of the server device 1 . The storage unit 12 also stores a driving evaluation model DB 10 . The data structure of the driving evaluation model DB 10 will be described later.

The control unit 15 includes a CPU, a ROM, a RAM, and the like (not shown), and performs various controls on each component in the server device 1 . When the communication unit 11 receives the profile information Ip, the control unit 15 extracts a driving evaluation model from the driving evaluation model DB 10 based on the profile indicated by the profile information Ip, and communicates extracted model information Im regarding the extracted driving evaluation model. It is transmitted to the terminal device 2 by the unit 11 . The control unit 15 is an example of an “information acquisition unit”, an “extraction unit”, and a computer that executes a program in the present invention.

FIG. 2B shows a schematic configuration of the terminal device 2. As shown in FIG. As shown in FIG. 2B, the terminal device 2 mainly includes a communication section 21, a storage section 22, a sensor section 23, an input section 24, a control section 25, and an output section . The communication section 21, storage section 22, sensor section 23, input section 24, control section 25 and output section 26 are connected to each other via a bus line.

Under the control of the control unit 25, the communication unit 21 transmits profile information Ip to the server device 1, receives extracted model information Im transmitted from the server device 1, and the like. The communication section 21 is an example of the "transmitting section" and the "receiving section" in the present invention.

The storage unit 22 stores programs executed by the control unit 25 and information necessary for the control unit 25 to execute predetermined processing. In this embodiment, the storage unit 22 stores a map DB 20 including road data, facility information, and the like. The storage unit 22 also stores profile information Ip generated by the control unit 25 based on the input to the input unit 24 and the like. Profile information Ip is an example of "driver information" in the present invention. Furthermore, the storage unit 22 stores the extraction model information Im that the communication unit 21 receives from the server device 1 .

The sensor unit 23 includes a camera 31 that captures scenery in the direction in which the vehicle is traveling, a GPS receiver 32 that generates absolute position information of the vehicle, and an autonomous positioning device 33 such as a gyro sensor and a speed sensor. The sensor section 23 supplies the generated output signal to the control section 25 . The camera 31 is an example of the "shooting unit" in the present invention.

The input unit 24 is a button, a touch panel, a remote controller, a voice input device, or the like for the user to operate. A signal is supplied to the control unit 25 . The output unit 26 is, for example, a display, a speaker, or the like that outputs based on the control of the control unit 25 .

The control unit 25 includes a CPU that executes programs, and controls the entire terminal device 2 . For example, the control unit 25 generates the profile information Ip based on the user's input through the input unit 24 and stores it in the storage unit 22 . Further, the control unit 25 transmits the profile information Ip to the server device 1 through the communication unit 21 , thereby receiving the extraction model information Im through the communication unit 21 and storing it in the storage unit 22 . In addition, the control unit 25 inputs an image generated by the camera 31 (also referred to simply as a “camera image”) to the driving evaluation model indicated by the received extracted model information Im, thereby obtaining an image of the front captured by the camera 31. Acquire an evaluation value indicating the driving difficulty of the road. The control unit 25 is an example of the "evaluation information generation unit" in the present invention.

[Driving evaluation model DB]
Each driving evaluation model registered in the driving evaluation model DB 10 is generated for each group of judges having common profiles such as gender and driving history, and is associated with common profile classification information. This will be described with reference to FIG.

FIG. 3 is a correspondence table between the identification number (also referred to as “model ID”) of each driving evaluation model included in the driving evaluation model DB 10 and the classification information of the judge's profile corresponding to the driving evaluation model. The correspondence table in FIG. 3 has items of “sex”, “driving history”, “place of residence”, “age”, and “model ID”.

Here, the driving evaluation model with the model ID “M001” is a photographed image referred to by a judge who is male, has less than 5 years of driving history, resides in Tokyo, and is between 25 and 39 years old. A driving evaluation model obtained by learning a combination of driving difficulty evaluation values determined by an determiner with reference to a photographed image as teacher data is shown. Similarly, the driving evaluation model with the model ID “M002” includes a photographed image referred to by a judge who is male, has less than five years of driving experience, resides in Tokyo, and is aged between 40 and 59. A driving evaluation model obtained by learning a combination of driving difficulty evaluation values determined by an determiner with reference to a photographed image as teacher data is shown. In addition, the driving evaluation model with the model ID “M251” is a photographed image referenced by a judge who is female, has less than 5 years of driving history, resides in Saitama Prefecture, and is 60 to 69 years old. A driving evaluation model obtained by learning a combination of driving difficulty evaluation values determined by a person with reference to photographed images as teacher data is shown. In addition, the driving evaluation model with the model ID “M342” is a photographed image referenced by a judge who is female, has a driving history of 5 years or more, resides in Kanagawa prefecture, and is 24 years old or younger, and The driving evaluation model obtained by learning the combination with the evaluation value of the driving difficulty determined by referring to the photographed image as teacher data is shown. In addition, the driving evaluation model with the model ID “M445” is a photographed image referenced by a judge who is female, has a driving history of 5 years or more, resides in Hokkaido, and is 70 years or older, and a photographed image taken by the judge. A driving evaluation model obtained by learning a combination of driving difficulty evaluation values determined by referring to images as teacher data is shown.

In this way, the driving evaluation model is generated for each group when the judges are grouped based on sex, driving history, place of residence, and age. In general, the degree of driving difficulty perceived by a driver varies depending on the driver's gender, driving history, place of residence (that is, the area where the vehicle is frequently driven), age, and the like. In consideration of the above, in the present embodiment, judges are divided into groups based on profile items that affect the degree of difficulty of driving felt by the driver, and the server device 1 generates a pre-generated driving evaluation for each divided group. The model is stored as the driving evaluation model DB10.

In the example of FIG. 3, the driving history is classified into two categories, less than 5 years and 5 years or more, the place of residence is classified by prefecture, and the age is classified into 5 stages. The method is not limited to this. For example, driving history may be divided into three or more tiers, and residence may be categorized by broader areas (eg, seven regions) or more detailed areas. Similarly, age may be classified by stages other than five stages. In place of or in addition to the driving history, the correspondence table of FIG. 3 includes items related to the driving history other than the driving history (for example, the number or frequency of accidents, the number or frequency of sudden braking, etc.). good too.

[Distribution of driving evaluation model]
FIG. 4 is an example of a flowchart showing the procedure of the driving evaluation model delivery process executed by the server device 1 . The server device 1 repeatedly executes the processing of the flowchart of FIG.

First, the server device 1 determines whether or not the profile information Ip transmitted from the terminal device 2 has been received (step S101). Here, the profile information Ip includes profile information such as gender, driving history, place of residence, and age of the user of the terminal device 2, for example. Then, when the server apparatus 1 receives the profile information Ip (step S101; Yes), the process proceeds to step S102. On the other hand, if the server device 1 does not receive the profile information Ip (step S101; No), the processing of the flowchart ends.

After receiving the profile information Ip in step S101, the server device 1 refers to the profile indicated by the profile information Ip, and selects a driving evaluation model corresponding to the group of judges (matching group) that matches the profile from the driving evaluation model DB 10. Extract (step S102). Specifically, the server device 1 refers to the correspondence table shown in FIG. A model is extracted from the driving evaluation model DB10. For example, if the gender indicated by the profile information Ip is “male”, the driving history is “3 years”, the place of residence is “Tokyo”, and the age is “45 years old”, the second record in FIG. The driving evaluation model with the model ID "M002" is extracted from the driving evaluation model DB10.

Then, the server device 1 transmits the extracted model information Im regarding the driving evaluation model extracted from the driving evaluation model DB 10 to the terminal device 2 that transmitted the profile information Ip (step S103). As a result, the server device 1 can suitably supply the driving evaluation model adapted to the user's profile to the terminal device 2 that is the transmission source of the profile information Ip.

[Reception and utilization of driving evaluation model]
FIG. 5 is an example of a flow chart showing a processing procedure for receiving and utilizing a driving evaluation model executed by the terminal device 2 . The terminal device 2 repeatedly executes the processing of the flowchart of FIG.

First, the terminal device 2 determines whether the driving evaluation model has not been acquired or whether the profile has been changed since the driving evaluation model was acquired (step S201). In this case, the terminal device 2 determines whether the extracted model information Im received from the server device 1 is stored in the storage unit 22 and whether the profile information Ip has been changed since the storage unit 22 stored the extracted model information Im. determine whether

Then, if the terminal device 2 has not yet acquired the driving evaluation model, or if the profile has been changed since the acquisition of the driving evaluation model (step S201; Yes), the terminal device 2 transmits the profile information Ip to the server device 1. (step S202). After that, the server device 1 that has received the profile information Ip executes the flowchart of FIG. Then, the terminal device 2 receives the extracted model information Im from the server device 1 (step S203).

On the other hand, when the terminal device 2 has acquired the driving evaluation model and determines that the profile has not been changed since the acquisition of the driving evaluation model (step S201; No), the process proceeds to step S204.

Next, the terminal device 2 determines whether or not the vehicle is running (step S204). When the terminal device 2 determines that the vehicle is running (step S204; Yes), the terminal device 2 inputs the camera image generated by the camera 31 to the driving evaluation model indicated by the extraction model information Im, thereby determining the driving difficulty level. A degree evaluation value is calculated (step S205). Then, the terminal device 2 performs an output based on the evaluation value of the driving difficulty determined in step S205 (step S206). In this case, the terminal device 2 uses the output unit 26 to perform display and/or audio output according to the evaluation value of the driving difficulty level calculated in step S205. On the other hand, when the vehicle is stopped (step S204; No), the terminal device 2 ends the processing of the flowchart. This prevents repeated calculation of the evaluation value of the driving difficulty level based on camera images taken at the same point.

FIG. 6 is a display example of the terminal device 2 in step S206. In the example of FIG. 6, the terminal device 2 displays the camera image on the display, and also displays guide images 81 and 82 superimposed on the camera image.

In the example of FIG. 6, the terminal device 2 displays a guidance image 81 indicating that a right turn should be made after 300 m based on the set guidance route information, and at the same time, according to the evaluation value of the driving difficulty determined in step S205. A guide image 82 based on this is displayed. In the example of FIG. 6, since the evaluation value of the driving difficulty level determined in step S205 is a value indicating that driving is difficult, the terminal device 2 displays the guidance image 82 indicating a warning to be careful when driving. it's shown. In addition to the guidance image 82, the terminal device 2 may output a voice warning that the driver should be careful while driving.

As described above, the server device 1 according to the present embodiment stores the driving evaluation model learned based on the captured image around the moving body and the driving evaluation value determined by the determiner based on the captured image. Here, the driving evaluation model is generated for each group of judges classified according to commonality of profile. The server device 1 acquires the profile information Ip about the driver who drives the vehicle, and extracts from the driving evaluation model DB 10 the driving evaluation models in the matching groups that match the acquired profile information Ip. As a result, the server device 1 can suitably extract a driving evaluation model that matches the characteristics of the driver indicated by the acquired profile information Ip.

[Modification]
Next, a modification suitable for the embodiment will be described. The following modifications may be applied to the above embodiments in any combination.

(Modification 1)
The driving evaluation model may be generated by further classifying based on the driving environment of the vehicle.

In this case, in the correspondence table of FIG. 3, in addition to profile items such as sex, driving history, place of residence, and age, there are further items related to driving environment such as weather, road type, and time zone. A driving evaluation model is generated in advance for each classification based on items related to the driving environment, and stored in the driving evaluation model DB 10 . In this case, the driving evaluation model corresponding to each driving environment consists of a photographed image and an evaluation of the driving difficulty determined by the judge by referring to the photographed image for each photographed image taken on the road in each driving environment. It is generated by learning combinations with values as teacher data.

Then, for example, in step S203 of FIG. 5, the terminal device 2 receives, from the server device 1, a driving evaluation model corresponding to each driving environment that matches the profile indicated by the profile information Ip. Thereafter, while the vehicle is running, the terminal device 2 refers to the output of the sensor unit 23 such as a raindrop sensor (not shown), the map DB 20, and the like, and recognizes the current running environment of the vehicle. Then, the terminal device 2 selects a driving evaluation model corresponding to the recognized driving environment, and calculates an evaluation value of the driving difficulty level in step S205. Instead of the above example, the terminal device 2 recognizes the current running environment of the vehicle before acquiring the driving evaluation model, and transmits information indicating the running environment together with the profile information Ip to the server device 1. A driving evaluation model corresponding to the current driving environment of the vehicle may be received from the server device 1 .

(Modification 2)
The object to be judged by the driving evaluation model is not limited to the driving difficulty level. For example, the object to be judged by the driving evaluation model may be the visibility. In this case, each driving evaluation model is generated by learning, as teacher data, a combination of a photographed image taken on the road and an evaluation value of the visibility determined by an evaluator who refers to the photographed image. . Each of these driving evaluation models is generated for each group of judges having common profiles such as gender and age, and is associated with the classification information of the common profiles in the driving evaluation model DB 10 as in the embodiment. stored in Then, the terminal device 2 receives the extracted model information Im from the server device 1 by transmitting the profile information Ip to the server device 1 based on the flowchart of FIG. 5, as in the embodiment. In this case, the server device 1 extracts from the driving evaluation model DB 10 a driving evaluation model that matches the profile indicated by the profile information Ip received from the terminal device 2 based on the flowchart of FIG. Send to After receiving the extracted model information Im, the terminal device 2 inputs the camera image to the driving evaluation model indicated by the extracted model information Im, acquires an evaluation value regarding the visibility, and displays based on the evaluation value. Or/and audio output.

According to this modification, since the terminal device 2 performs display and/or audio output based on the evaluation value regarding the good view while the vehicle is running, it is possible to drive on a road that is preferable from the viewpoint of sightseeing or safety. It is possible to appropriately notify the driver of whether or not there is a vehicle. Here, roads that are preferable from the viewpoint of tourism correspond to, for example, roads with excellent scenery in sightseeing spots, and roads that are preferable from the viewpoint of safety correspond to, for example, safe roads where pedestrians are relatively easy to spot even from a distance. do. In addition, for example, when there is a display and/or voice output indicating that the evaluation value regarding the goodness of the view is low, the driver judges that the driver is driving on an unfavorable road from the viewpoint of sightseeing or safety. , it is possible to take measures such as changing the driving route or increasing concentration on driving.

1 Server Device 2 Terminal Device 10 Driving Evaluation Model DB
11, 21 communication section 12, 22 storage section 15, 25 control section 23 sensor section 24 input section 26 output section

Claims (1)

an information acquisition unit that acquires driver information about a driver who drives a mobile object;
Extracting a driving evaluation model in a suitable group that matches the driver information from the learned driving evaluation model based on the photographed image around the moving body and the evaluation information about driving evaluated by the judge based on the photographed image. Department and
A driving evaluation model matching device comprising:

Images