Operation evaluation model compatible device, terminal device, control method, program and storage medium

Abstract

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

Description

Technical Field

[0001] The present invention relates to a technique for utilizing a model obtained by learning.

Background Art

[0002] Conventionally, a system has been known in which data is aggregated from a plurality of vehicles to a server device, and the server device distributes information regarding a learning result obtained by machine learning. For example, Patent Document 1 discloses a system that collects, as environmental data, situations such as the weather and time zone during the driving of each vehicle, and learns for each situation indicated by the environmental data.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] Regarding situation recognition and situation judgment during driving, there are individual differences based on the driver's experience and the like, and the recognition and judgment may vary depending on the driver. On the other hand, Patent Document 1 does not consider such individual differences at all.

[0005] The present invention has been made to solve the above problems, and a main object thereof is to provide a driving evaluation model adaptation device capable of distributing a driving evaluation model that is a learning result adapted to the usage situation, and a terminal device that receives the driving evaluation model.

Means for Solving the Problems

[0006] The invention according to claim 1 is a driving evaluation model adaptation device, comprising an information acquisition unit that acquires driver information regarding a driver who drives a moving body, a captured image around the moving body, and evaluation information regarding driving evaluated by a determiner based on the captured imageFor each group of the aforementioned judges From the trained driving evaluation model 、 The system includes an extraction unit that extracts a driving evaluation model in a matching group that matches the aforementioned driver information.

[0007] The invention described in claim 10 is based on a captured image of the area around a moving object and evaluation information relating to the driving that the judge has evaluated based on the captured image. For each group of the aforementioned judges A control method performed by a driving evaluation model adaptation device equipped with a storage unit for storing learned driving evaluation models, comprising: an information acquisition step for acquiring driver information relating to a driver operating a moving object; and an extraction step for extracting a driving evaluation model in an adaptation group that is compatible with the driver information.

[0008] The invention described in claim 11 is based on a captured image of the area around a moving object and evaluation information relating to the driving evaluated by the judge based on the captured image, For each group of the aforementioned judges A program executed by a computer that references a memory unit that stores learned driving evaluation models, wherein the computer functions as an information acquisition unit that acquires driver information relating to a driver operating a moving object, and an extraction unit that extracts driving evaluation models in a suitability group that matches the driver information. [Brief explanation of the drawing]

[0009] [Figure 1] This is a schematic configuration of the driving evaluation system. [Figure 2] This shows the block configuration of the server and terminal devices. [Figure 3] This is a correspondence table between the identification number of the driving evaluation model and each item representing the profile of the evaluator corresponding to that driving evaluation model. [Figure 4] This is an example flowchart illustrating the procedure for distributing a driving evaluation model. [Figure 5] This is an example of a flowchart showing the processing procedure for receiving and utilizing driving evaluation models. [Figure 6] An example of a display output by the terminal device is shown. [Modes for carrying out the invention]

[0010] According to a preferred embodiment of the present invention, the driving evaluation model matching device includes an information acquisition unit that acquires driver information relating to a driver operating a moving object, and an extraction unit that extracts a driving evaluation model in a matching group that matches the driver information from driving evaluation models learned for each group of judges classified according to the commonality of the profiles, based on a captured image of the area around the moving object and evaluation information relating to driving evaluated by a judge with a profile based on the captured image.

[0011] The above-described driving evaluation model matching device comprises an information acquisition unit, a storage unit, and an extraction unit. The storage unit stores a driving evaluation model learned based on captured images of the surroundings of a moving object and evaluation information about driving evaluated by an evaluator based on the captured images. Here, the driving evaluation models stored in the storage unit are generated for each group of evaluators classified according to the commonality of their profiles. The information acquisition unit acquires driver information about the driver operating the moving object. The extraction unit extracts a driving evaluation model in a matching group that matches the acquired driver information. Here, "matching group" refers to a group of evaluators classified according to the commonality of their profiles that matches the acquired driver information. According to this embodiment, 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.

[0012] In one embodiment of the above-described driving evaluation model matching device, the driving evaluation model matching device further comprises a transmitting unit that transmits information regarding the driving evaluation model in the matching group to a communication terminal provided on the mobile body. In this embodiment, 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 body.

[0013] In another embodiment of the above-described driving evaluation model matching device, the driver information and profile include at least residential area information relating to the residential areas of the driver and the judge, and the driving evaluation model extracted by the extraction unit is a driving evaluation model in the group of judges that matches the residential area information included in the driver information, from among the groups of judges classified by the commonality of the residential area information. In this embodiment, the driving evaluation model matching device can suitably extract a driving evaluation model specific to the residential area of ​​the driver of the mobile vehicle.

[0014] In another embodiment of the driving evaluation model matching device described above, the driver information and profile further include driving history information of the driver and the judge, and the driving evaluation model extracted by the extraction unit is a driving evaluation model in the group of judges that is compatible with the driving history information included in the driver information, from among the groups of judges classified by the commonality of the residential area information and the driving history information. In this embodiment, the driving evaluation model matching device can suitably extract a driving evaluation model that is compatible with the residential area and driving experience of the driver of the mobile vehicle.

[0015] According to another preferred embodiment of the present invention, the terminal device comprises a transmitting unit that transmits driver information relating to a driver operating a mobile object to the driving evaluation model fitting device described above; a receiving unit that receives information from the driving evaluation model fitting device regarding a fitting group that matches the driver information regarding the driving evaluation model; a shooting unit that generates an image; and an evaluation information generation unit that generates evaluation information relating to driving by applying the driving evaluation model to the image. In this embodiment, the terminal device can suitably receive a driving evaluation model generated using a fitting group of judges that matches the driver information as training material, and generate evaluation information that is in line with the driver's perception.

[0016] In one aspect of the terminal device, the terminal device further includes an output unit that performs display or voice output based on the evaluation information generated by the evaluation information generation means. According to this aspect, the driving evaluation model adaptation 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 good visibility.

[0017] According to another preferred embodiment of the present invention, a control method executed by a driving evaluation model adaptation device including a storage unit that stores a driving evaluation model learned for each group of the judges classified according to the commonality of the profiles, based on a captured image around the moving body and evaluation information regarding driving evaluated by a judge having a profile based on the captured image, includes an information acquisition step of acquiring driver information regarding a driver who drives the moving body, and an extraction 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 adaptation device can suitably extract a driving evaluation model that matches the characteristics of the driver indicated by the acquired driver information.

[0018] According to another preferred embodiment of the present invention, a program executed by a computer that refers to a storage unit that stores a driving evaluation model learned for each group of the judges classified according to the commonality of the profiles, based on a captured image around the moving body and evaluation information regarding driving evaluated by a judge having a profile based on the captured image, causes the computer to function as an information acquisition unit that acquires driver information regarding a driver who drives the moving body, and an extraction unit that extracts a driving evaluation model in a 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 above program is stored in a storage medium.

Example

[0019] Hereinafter, preferred embodiments of the present invention will be described with reference to the drawings.

[0020] [Overview of the Operation Evaluation System] Figure 1 shows a schematic configuration of the driving evaluation system according to this embodiment. The driving evaluation system is a system for evaluating driving on roads on which a vehicle travels, and comprises a server device 1 and a terminal device 2.

[0021] Server device 1 stores a driving evaluation model DB10, which is a database of models (also called "driving evaluation models") for determining the evaluation of driving on a road displayed in a captured image taken on the road. The driving evaluation model is a pattern classifier obtained by supervised machine learning, and is, for example, training data learned by applying a neural network (deep learning). In this embodiment, the driving evaluation model is generated by training a combination of captured images taken on the road and evaluation values ​​of driving difficulty determined by a person who has referred to the captured image (also called a "judge") as training data. The evaluation value of driving difficulty may be, for example, a two-stage evaluation value of "0" indicating easy driving or "1" indicating difficult driving, or it may be an evaluation value of three or more stages. The evaluation value of driving difficulty is an example of "evaluation information" in the present invention.

[0022] Here, each driving evaluation model registered in the driving evaluation model DB10 is generated for each group of evaluators who share common profile characteristics such as gender and driving history, as will be described later. When the server device 1 receives information indicating the user profile of terminal device 2 from terminal device 2 (also called "profile information Ip"), it extracts a driving evaluation model from the driving evaluation model DB10 that matches the profile indicated by profile information Ip. The server device 1 then transmits information indicating the extracted driving evaluation model (also called "extracted model information Im") to terminal device 2. The server device 1 is an example of the "driving evaluation model matching device" in the present invention.

[0023] Terminal device 2 is, for example, a stationary navigation device or a mobile terminal such as a smartphone, which provides route guidance to a destination and displays a map of the area around the current location. Terminal device 2 also transmits profile information Ip, which indicates the user profile of terminal device 2, to server device 1, and receives extracted model information Im, which relates to a driving evaluation model that matches the user's profile, from server device 1. Then, terminal device 2 inputs the image captured by the camera into the driving evaluation model indicated by the extracted model information Im, obtains an evaluation value for the driving difficulty of the road displayed in the image, and outputs based on the evaluation value of the driving difficulty. Terminal device 2 is an example of a "communication terminal" and a "terminal device" in the present invention.

[0024] [Device configuration] Figure 2(A) shows the schematic configuration of server device 1. As shown in Figure 2(A), server device 1 has a communication unit 11, a storage unit 12, and a control unit 15. The communication unit 11, the storage unit 12, and the control unit 15 are interconnected via a bus line.

[0025] The communication unit 11, based on the control of the control unit 15, receives profile information Ip transmitted from the terminal device 2 and transmits extracted model information Im to the terminal device 2. The communication unit 11 is an example of a "transmission unit" in this invention. The storage unit 12 stores programs for controlling the operation of the server device 1 and holds information necessary for the operation of the server device 1. The storage unit 12 also stores the operation evaluation model DB 10. The data structure of the operation evaluation model DB 10 will be described later.

[0026] The control unit 15 includes a CPU, ROM, RAM, etc. (not shown) and performs various controls on each component within the server device 1. When the communication unit 11 receives profile information Ip, the control unit 15 extracts an operation evaluation model from the operation evaluation model DB 10 based on the profile indicated by the profile information Ip, and transmits extracted model information Im related to the extracted operation evaluation model to the terminal device 2 via the communication unit 11. The control unit 15 is an example of a computer that executes the "information acquisition unit," "extraction unit," and program in the present invention.

[0027] Figure 2(B) shows the schematic configuration of terminal device 2. As shown in Figure 2(B), terminal device 2 mainly consists of a communication unit 21, a storage unit 22, a sensor unit 23, an input unit 24, a control unit 25, and an output unit 26. The communication unit 21, storage unit 22, sensor unit 23, input unit 24, control unit 25, and output unit 26 are interconnected via a bus line.

[0028] The communication unit 21, based on the control of the control unit 25, transmits profile information Ip to the server device 1 and receives extracted model information Im transmitted from the server device 1. The communication unit 21 is an example of a "transmitting unit" and a "receiving unit" in the present invention.

[0029] The storage unit 22 stores programs executed by the control unit 25 and information necessary for the control unit 25 to perform predetermined processes. In this embodiment, the storage unit 22 stores a map DB 20 containing road data and facility information. The storage unit 22 also stores profile information Ip generated by the control unit 25 based on inputs to the input unit 24, etc. Profile information Ip is an example of "driver information" in this invention. Furthermore, the storage unit 22 stores extracted model information Im received by the communication unit 21 from the server device 1.

[0030] The sensor unit 23 includes a camera 31 that captures the scenery in the direction of the vehicle's movement, 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 unit 23 supplies the generated output signals to the control unit 25. The camera 31 is an example of the "imaging unit" in this invention.

[0031] The input unit 24 includes buttons, a touch panel, a remote controller, a voice input device, etc., for user operation. It accepts inputs such as specifying a destination for route searching and inputting the driver's profile, and supplies the generated input signals to the control unit 25. The output unit 26 includes, for example, a display or speaker that outputs based on the control of the control unit 25.

[0032] The control unit 25 includes a CPU that executes programs and controls the entire terminal device 2. For example, the control unit 25 generates profile information Ip based on user input from the input unit 24 and stores it in the storage unit 22. The control unit 25 also transmits the profile information Ip to the server device 1 via the communication unit 21, and the communication unit 21 receives the extracted model information Im and stores it in the storage unit 22. The control unit 25 also inputs an image generated by the camera 31 (also simply called a "camera image") to the driving evaluation model indicated by the received extracted model information Im, and obtains an evaluation value indicating the difficulty of driving on the road ahead as captured by the camera 31. The control unit 25 is an example of an "evaluation information generation unit" in the present invention.

[0033] [Driving Evaluation Model Database] Each driving evaluation model registered in the driving evaluation model DB10 is generated for each group of evaluators who share common profile characteristics such as gender and driving history, and is associated with classification information of those common profiles. This will be explained with reference to Figure 3.

[0034] Figure 3 is a correspondence table between the identification number (also called "Model ID") of each driving evaluation model included in the driving evaluation model DB10 and the classification information of the evaluator's profile corresponding to that driving evaluation model. The correspondence table in Figure 3 has the following items: "Gender," "Driving History," "Place of Residence," "Age," and "Model ID."

[0035] Here, the driving evaluation model with model ID "M001" is a driving evaluation model obtained by training the model with training data consisting of combinations of photographs referenced by an evaluator who is male, has less than 5 years of driving experience, resides in Tokyo, and is between 25 and 39 years old, and the driving difficulty rating determined by the evaluator based on the photographs. Similarly, the driving evaluation model with model ID "M002" is a driving evaluation model obtained by training the model with training data consisting of combinations of photographs referenced by an evaluator who is male, has less than 5 years of driving experience, resides in Tokyo, and is between 40 and 59 years old, and the driving difficulty rating determined by the evaluator based on the photographs. Furthermore, the driving evaluation model with model ID "M251" is a driving evaluation model obtained by training the model with training data consisting of combinations of photographs referenced by an evaluator who is female, has less than 5 years of driving experience, resides in Saitama Prefecture, and is between 60 and 69 years old, and the driving difficulty rating determined by the evaluator based on the photographs. Furthermore, the driving evaluation model with model ID "M342" is a model obtained by training the model with training data consisting of combinations of photographs referenced by an evaluator who is female, has more than 5 years of driving experience, resides in Kanagawa Prefecture, and is 24 years of age or younger, and the driving difficulty rating determined by that evaluator based on the photographs. Furthermore, the driving evaluation model with model ID "M445" is a model obtained by training the model with training data consisting of combinations of photographs referenced by an evaluator who is female, has more than 5 years of driving experience, resides in Hokkaido, and is 70 years of age or older, and the driving difficulty rating determined by that evaluator based on the photographs.

[0036] Thus, the driving evaluation model is generated for each group when the evaluators are grouped based on gender, driving history, place of residence, and age. Generally, the perceived difficulty of driving varies depending on the driver's gender, driving history, place of residence (i.e., the area they frequently drive in), age, etc. Taking the above into consideration, in this embodiment, evaluators are grouped based on profile items that influence the perceived difficulty of driving, and the server device 1 stores the pre-generated driving evaluation model for each group as the driving evaluation model DB10.

[0037] In the example in Figure 3, driving experience was classified into two categories: less than 5 years and 5 years or more. Residence was classified by prefecture, and age was classified into five categories. However, the classification method for each item is not limited to these. For example, driving experience may be divided into three or more categories, and residence may be classified by a broader area (e.g., 7 regions) or a more detailed area. Similarly, age may be classified into categories other than five. In addition to or instead of driving experience, the correspondence table in Figure 3 may include items related to driving history other than driving experience (e.g., number or frequency of accidents, number or frequency of sudden braking, etc.).

[0038] [Distribution of driving evaluation model] Figure 4 is an example flowchart showing the procedure for distributing the operational evaluation model executed by Server Device 1. Server Device 1 repeatedly executes the process shown in the flowchart in Figure 4.

[0039] First, server device 1 determines whether or not it has received profile information Ip transmitted from terminal device 2 (step S101). Here, profile information Ip includes, for example, profile information of the user of terminal device 2, such as gender, driving history, place of residence, and age. If server device 1 has received profile information Ip (step S101; Yes), it proceeds to step S102. On the other hand, if server device 1 has not received profile information Ip (step S101; No), it terminates the process in the flowchart.

[0040] After receiving profile information Ip in step S101, server device 1 refers to the profile indicated by profile information Ip and extracts a driving evaluation model from the driving evaluation model DB10 that corresponds to the group of judges who fit that profile (matching group) (step S102). Specifically, server device 1 refers to the correspondence table shown in Figure 3 and extracts a driving evaluation model from the driving evaluation model DB10 that corresponds to the model ID recorded in the record corresponding to the gender, driving history, place of residence, and age included in profile information Ip. For example, if the gender indicated by profile information Ip is "male", the driving history is "3 years", the place of residence is "Tokyo", and the age is "45 years old", then the driving evaluation model with model ID "M002" recorded in the second record in Figure 3 is extracted from the driving evaluation model DB10.

[0041] Then, the server device 1 transmits the extracted model information Im related to the operation evaluation model extracted from the operation evaluation model DB 10 to the terminal device 2, which is the source of the profile information Ip (step S103). This allows the server device 1 to suitably supply the terminal device 2, which is the source of the profile information Ip, with an operation evaluation model that matches the user's profile.

[0042] [Receiving and utilizing the driving evaluation model] Figure 5 is an example of a flowchart showing the processing procedure for receiving and utilizing the driving evaluation model performed by terminal device 2. Terminal device 2 repeatedly executes the process shown in the flowchart in Figure 5.

[0043] First, terminal device 2 determines whether the operation evaluation model has not been acquired, or whether there have been any changes to the profile since the operation evaluation model was acquired (step S201). In this case, terminal device 2 determines whether the extracted model information Im received from server device 1 is stored in storage unit 22, and whether there have been any changes to the profile information Ip since the extracted model information Im was stored in storage unit 22.

[0044] Then, if terminal device 2 has not yet acquired the driving evaluation model, or if there have been changes to the profile since the driving evaluation model was acquired (step S201; Yes), it sends profile information Ip to server device 1 (step S202). After receiving profile information Ip, server device 1 executes the flowchart in Figure 4 and sends extracted model information Im, which indicates a driving evaluation model that matches the profile indicated by profile information Ip, to terminal device 2. Then, terminal device 2 receives extracted model information Im from server device 1 (step S203).

[0045] On the other hand, if terminal device 2 has already acquired the operation evaluation model and determines that there have been no changes to the profile since the acquisition of the operation evaluation model (step S201; No), it proceeds to step S204.

[0046] Next, terminal device 2 determines whether the vehicle is in motion (step S204). If terminal device 2 determines that the vehicle is in motion (step S204; Yes), it inputs the camera image generated by camera 31 into the driving evaluation model indicated by the extracted model information Im to calculate a driving difficulty evaluation value (step S205). Then, terminal device 2 outputs based on the driving difficulty evaluation value determined in step S205 (step S206). In this case, terminal device 2 uses the output unit 26 to display and / or output audio according to the driving difficulty evaluation value calculated in step S205. On the other hand, if the vehicle is stopped (step S204; No), terminal device 2 terminates the flowchart processing. This prevents the repeated calculation of the driving difficulty evaluation value based on camera images taken at the same location.

[0047] Figure 6 shows an example of the display of terminal device 2 in step S206. In the example in Figure 6, terminal device 2 displays the camera image on the display and also displays guidance images 81 and 82 superimposed on the camera image.

[0048] In the example shown in Figure 6, terminal device 2 displays a guidance image 81 indicating that the driver should turn right 300m ahead, based on the information of the set guidance route, and also displays a guidance image 82 based on the driving difficulty evaluation value determined in step S205. In the example shown in Figure 6, terminal device 2 displays a guidance image 82 indicating that the driver should be careful because the driving difficulty evaluation value determined in step S205 was a value indicating that the driver is difficult to drive. In addition to the guidance image 82, terminal device 2 may also output an audio warning to be careful while driving.

[0049] As described above, the server device 1 in this embodiment stores a driving evaluation model learned based on captured images of the surroundings of a moving object and evaluation values ​​related to driving determined by the judge based on the captured images. Here, the driving evaluation model is generated for each group of judges classified by the commonality of their profiles. The server device 1 acquires profile information Ip about the driver operating the vehicle and extracts the driving evaluation model DB10 for the matching group that matches the acquired profile information Ip. This allows the server device 1 to suitably extract a driving evaluation model that matches the characteristics of the driver indicated by the acquired profile information Ip.

[0050] [Differentiation] Next, a suitable modification of the embodiment will be described. The following modifications may be applied to the above-described embodiment in any combination.

[0051] (Variation 1) The driving evaluation model may be further classified and generated based on the vehicle's driving environment.

[0052] In this case, the correspondence table in Figure 3 includes not only profile items such as gender, driving history, place of residence, and age, but also items related to the driving environment, such as weather, road type, and time of day. The driving evaluation model is then pre-generated for each classification based on the driving environment items and stored in the driving evaluation model DB10. In this case, the driving evaluation model corresponding to each driving environment is generated by learning the combination of a captured image and the evaluation value of the driving difficulty determined by the evaluator based on the captured image, for each image taken on the road in each driving environment, as training data.

[0053] For example, in step S203 of Figure 5, terminal device 2 receives from server device 1 a driving evaluation model corresponding to each driving environment that matches the profile indicated by profile information Ip. Subsequently, while the vehicle is in motion, terminal device 2 recognizes the current driving environment of the vehicle by referring to the output of sensor unit 23, such as a raindrop sensor (not shown), and map DB 20, etc. Then, terminal device 2 selects a driving evaluation model corresponding to the recognized driving environment and calculates the driving difficulty evaluation value in step S205. Alternatively, instead of the above example, terminal device 2 may recognize the current driving environment of the vehicle before acquiring a driving evaluation model and send information indicating the driving environment along with profile information Ip to server device 1, thereby receiving a driving evaluation model corresponding to the current driving environment of the vehicle from server device 1.

[0054] (Modification 2) The subject judged by the driving evaluation model is not limited to driving difficulty. For example, the subject judged by the driving evaluation model may be the quality of visibility. In this case, each driving evaluation model is generated by learning a combination of photographic images taken on the road and the evaluation value of the quality of visibility determined by an evaluator who referred to the photographic images as training data. Then, as in the embodiment, each of these driving evaluation models is generated for each group of evaluators who share common profile characteristics such as gender and age, and is stored in the driving evaluation model DB10 in association with classification information of the common profile. Then, as in the embodiment, the terminal device 2 receives extracted model information Im from the server device 1 by sending profile information Ip to the server device 1 based on the flowchart in Figure 5. In this case, the server device 1 extracts a driving evaluation model from the driving evaluation model DB10 that matches the profile indicated by the profile information Ip received from the terminal device 2, based on the flowchart in Figure 4, and sends it to the terminal device 2 as extracted model information Im. Then, after receiving the extracted model information Im, terminal device 2 inputs the camera image into the driving evaluation model indicated by the extracted model information Im to obtain an evaluation value regarding the visibility, and displays and / or outputs audio based on that evaluation value.

[0055] According to this modified version, the terminal device 2 displays and / or provides audio output based on an evaluation value regarding visibility while the vehicle is in motion, thereby suitably informing the driver whether they are driving on a road that is favorable from a tourism or safety perspective. Here, a road favorable from a tourism perspective is, for example, a road with excellent scenery in a tourist area, and a road favorable from a safety perspective is, for example, a safe road where pedestrians can be easily spotted even from a distance. Furthermore, if the driver receives a display and / or audio output indicating a low evaluation value regarding visibility, they can determine that they are driving on a road that is unfavorable from a tourism or safety perspective and take appropriate measures such as changing their driving route or increasing their concentration on driving. [Explanation of symbols]

[0056] 1 Server device 2 Terminal devices 10. Operational Evaluation Model DB 11, 21 Communications Department 12, 22 Storage section 15, 25 Control Unit 23 Sensor section 24 Input section 26 Output section

Claims

1. An information acquisition unit that acquires driver information about the driver operating the mobile vehicle, An extraction unit extracts a driving evaluation model in a suitable group that matches the driver information from a driving evaluation model learned for each group of judges based on captured images of the surroundings of a moving object and evaluation information regarding driving evaluated by the judge based on the captured images. A device that conforms to an operational evaluation model, equipped with the following features.

2. The aforementioned judge is a driving evaluation model adaptation device according to claim 1, which includes a profile.

3. The driving evaluation model adapting device according to claim 2, wherein the learned driving evaluation model is a driving evaluation model learned for each group of judges classified by the commonality of the profiles.

4. The driving evaluation model conforming device according to any one of claims 1 to 3, further comprising a transmitting unit for transmitting information relating to the driving evaluation model in the conforming group to a communication terminal provided on the mobile body.

5. The group of judges is classified according to the commonality of the judges' profiles, The aforementioned driver information and profile include at least residential area information relating to the residential areas of the driver and the judge, The driving evaluation model matching device according to any one of claims 2 to 4, wherein the driving evaluation model extracted by the extraction unit is a driving evaluation model in the group of judges that is compatible with the residential area information included in the driver information, among the groups of judges classified by the commonality of the residential area information.

6. The aforementioned driver information and profile further include the driving history information of the driver and the judge, The driving evaluation model matching device according to claim 5, wherein the driving evaluation model extracted by the extraction unit is a driving evaluation model in a group of judges classified by the commonality of the residential area information and the driving history information that is compatible with the residential area information and driving history information included in the driver information, among the groups of judges classified by the commonality of the residential area information and the driving history information.

7. A transmitting unit that transmits driver information relating to a driver operating a mobile object to the driving evaluation model adaptation device according to any one of claims 1 to 6, A receiving unit that receives information regarding the driving evaluation model in a suitability group that is suitable for the driver information from the driving evaluation model suitability device, The imaging unit generates the captured image, An evaluation information generation unit generates evaluation information related to driving by applying the driving evaluation model to the aforementioned captured image, A terminal device equipped with the following features.

8. The terminal device according to claim 7, further comprising an output unit that performs display or audio output based on the evaluation information generated by the evaluation information generation unit.

9. The terminal device according to claim 7 or 8, wherein the evaluation information is information indicating the difficulty of driving, or information indicating the quality of the view.

10. A control method executed by a driving evaluation model adaptation device, which includes a storage unit that stores driving evaluation models learned for each group of judges based on captured images of the surroundings of a moving object and evaluation information regarding driving evaluated by the judges based on the captured images, An information acquisition process to acquire driver information about the driver operating the mobile vehicle, An extraction step for extracting a driving evaluation model in a suitability group that matches the aforementioned driver information, A control method having

11. A program executed by a computer that references a memory unit that stores a driving evaluation model learned for each group of judges, based on captured images of the surroundings of a moving object and evaluation information regarding driving evaluated by a judge based on the captured images, An information acquisition unit that acquires driver information about the driver operating the mobile vehicle, A program that causes the computer to function as an extraction unit for extracting driving evaluation models in a matching group that matches the aforementioned driver information.

12. A storage medium storing the program described in claim 11.

Images