JP2021167823A - Route search device, control method, program, and storage medium - Google Patents

Abstract

To provide a route search device capable of executing route search under suitable consideration of individual differences in drivers.SOLUTION: A server device 1 receives profile information on a driver who drives a mobile body and information on a departure place and destination of a vehicle from terminal equipment 2. The server device 1 calculates an evaluation value of driving difficulty based on a driving evaluation model corresponding to the profile information with respect to each of roads composing a plurality of routes from the departure place to destination. Then, the server device 1 determines a recommended route on the basis of the calculated evaluation value of driving difficulty.SELECTED DRAWING: Figure 4

Description

The present invention relates to a route search technique.

Conventionally, there has been known a system that aggregates data from a plurality of vehicles into a server device and distributes information on learning results obtained by the server device by machine learning. For example, Patent Document 1 discloses a system that collects conditions such as the weather and time zone when each vehicle is traveling as environmental data and learns each situation indicated by the environmental data.

Japanese Unexamined Patent Publication No. 2015-135552

Regarding situational awareness and situational judgment during driving, there are individual differences based on the driver's experience, etc., and the recognition and judgment may differ depending on the driver. Therefore, even in the route search, the route suitable for traveling may differ depending on the driver. Patent Document 1 does not mention any point in which such individual differences of drivers should be taken into consideration.

The present invention has been made to solve the above problems, and an object of the present invention is to provide a route search device capable of performing a route search in consideration of individual differences of drivers.

The invention according to claim 1 is a route search device, which comprises a first acquisition unit for acquiring driver information about a driver who drives a moving body and information on a starting point and a destination of the moving body. Evaluation information output from the driving evaluation model by inputting captured images corresponding to each of the roads constituting the plurality of routes from the starting point to the destination into the driving evaluation model corresponding to the driver information. A second acquisition unit for acquiring the above, and a route determination unit for determining a recommended route from the plurality of routes based on the evaluation information are provided.
The invention according to claim 5 is a route search device, which comprises a first acquisition unit for acquiring driver information about a driver who drives a moving body and information on a starting point and a destination of the moving body. Based on the second acquisition unit that acquires evaluation information based on the driving evaluation model corresponding to the driver information, and the evaluation information based on the evaluation information, for each of the roads constituting the plurality of routes from the departure point to the destination. The driving evaluation model includes a route determining unit that determines a recommended route from the plurality of routes, and the driving evaluation model includes a photographed image of the surroundings of the moving body and evaluation information regarding driving evaluated by a judge having a profile based on the photographed image. Based on the above, it is a driving evaluation model in a conforming group that matches the driver information from the driving evaluation model learned for each group of the judges classified according to the commonality of the profiles.
The invention according to claim 10 is a route search device, which comprises a first acquisition unit for acquiring driver information about a driver who drives a moving body and information on a starting point and a destination of the moving body. The driver information is provided for each of the second acquisition unit that acquires captured images taken on each of the roads constituting the plurality of routes and the roads constituting the plurality of routes from the starting point to the destination. The third acquisition unit includes a third acquisition unit that acquires evaluation information based on the operation evaluation model corresponding to the above, and a route determination unit that determines a recommended route from the plurality of routes based on the evaluation information. By inputting the captured image acquired by the second acquisition unit into the driving evaluation model, evaluation information for each of the roads is acquired.

The invention according to claim 14 is a control method executed by a route search device, and obtains driver information about a driver who drives a moving body and information on a departure point and a destination of the moving body. 1 From the driving evaluation model by inputting the captured images corresponding to each of the acquisition process and the roads constituting the plurality of routes from the starting point to the destination into the driving evaluation model corresponding to the driver information. It has a second acquisition step of acquiring the output evaluation information, and a route determination step of determining a recommended route from the plurality of routes based on the evaluation information.
The invention according to claim 16 is a control method executed by a route search device, and obtains driver information about a driver who drives a moving body and information on a departure point and a destination of the moving body. 1 acquisition step, a second acquisition step of acquiring evaluation information based on a driving evaluation model corresponding to the driver information for each of the roads constituting the plurality of routes from the departure point to the destination, and the above-mentioned. The driver evaluation model includes a route determination step of determining a recommended route from the plurality of routes based on the evaluation information, and the driver evaluation model is evaluated based on the photographed image around the moving body and a judge having a profile. It is a driving evaluation model in a conforming group that matches the driver information from the driving evaluation model learned for each group of the judges classified according to the commonality of the profile based on the evaluation information related to the driver.

The invention according to claim 15 is a program executed by a computer, and is a first acquisition unit that acquires driver information about a driver who drives a moving body and information on a starting point and a destination of the moving body. And, the photographed image corresponding to each of the roads constituting the plurality of routes from the departure place to the destination is input to the driving evaluation model corresponding to the driver information, and is output from the driving evaluation model. The computer functions as a second acquisition unit that acquires evaluation information and a route determination unit that determines a recommended route from the plurality of routes based on the evaluation information.
The invention according to claim 17 is a program executed by a computer, and is a first acquisition unit that acquires driver information about a driver who drives a moving body and information on a starting point and a destination of the moving body. A second acquisition unit that acquires evaluation information based on a driving evaluation model corresponding to the driver information for each of the roads constituting the plurality of routes from the departure point to the destination, and the evaluation information. Based on this, the computer is made to function as a route determination unit that determines a recommended route from the plurality of routes, and the operation evaluation model is an operation evaluated based on a photographed image around a moving body and a judge having a profile. It is a driving evaluation model in a conforming group that matches the driver information from the driving evaluation model learned for each group of the judges classified according to the commonality of the profile based on the evaluation information.

This is a schematic configuration of the route search system. The block configuration of the server device and the terminal device is shown. 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. This is an example of a flowchart showing the procedure of the route search process. It is a schematic configuration of the route search system according to the modified example. It is a schematic configuration of the route search system according to the modified example.

According to a preferred embodiment of the present invention, the route search device includes a first acquisition unit that acquires driver information about a driver who drives a moving body and information on a starting point and a destination of the moving body. Based on the second acquisition unit that acquires evaluation information based on the driving evaluation model corresponding to the driver information, and the evaluation information based on the evaluation information, for each of the roads constituting the plurality of routes from the departure point to the destination. A route determining unit for determining a recommended route from the plurality of routes is provided.

The route search device includes a first acquisition unit, a second acquisition unit, and a route determination unit. The first acquisition unit acquires driver information about the driver who drives the moving body and information on the starting point and the destination of the moving body. The second acquisition unit acquires evaluation information based on the driving evaluation model corresponding to the driver information for each of the roads constituting the plurality of routes from the starting point to the destination. The route determination unit determines a recommended route from a plurality of routes based on the evaluation information acquired by the second acquisition unit. In this aspect, since the route search device performs the route search based on the evaluation information of the driving evaluation model suitable for the driver of the moving body, the route search can be executed in consideration of the individual difference of the driver.

In one aspect of the route search device, the driving evaluation model is based on a photographed image of the surroundings of a moving body and evaluation information on driving evaluated by a judge having a profile based on the photographed image, and is based on the commonality of the profiles. It is a driving evaluation model in a conforming group that matches the driver information from the driving evaluation model learned for each group of the classified judges. Here, the "conformity group" refers to a group that conforms to the acquired driver information among the groups of judges classified according to the commonality of profiles. According to this aspect, the route search device can suitably acquire the evaluation information of each road necessary for the route search based on the driving evaluation model that matches the characteristics of the driver indicated by the acquired driver information.

In another aspect of the route search device, the route search device further includes a third acquisition unit that acquires captured images taken on each of the roads constituting the plurality of routes, and the second acquisition unit is By inputting the captured image acquired by the third acquisition unit into the driving evaluation model, evaluation information for each of the roads is acquired. According to this aspect, the route search device can acquire captured images taken on each road constituting the candidate route, and can suitably calculate the evaluation information corresponding to each road required for the route search.

In another aspect of the route search device, the route search device further includes a storage unit that stores map data in which evaluation information based on a plurality of driving evaluation models is associated with each road, and the second acquisition unit is , For each of the roads, the evaluation information based on the driving evaluation model corresponding to the driver information is acquired from the map data. According to this aspect, the route search device can suitably acquire the evaluation information corresponding to each road required for the route search by referring to the map data.

In another aspect of the route search device, the route search device further includes a transmission unit that transmits information on the recommended route to a terminal device that moves with the moving body, and the first acquisition unit is the operation. The hand information and the information on the departure place and the destination are received from the terminal device. According to this aspect, the route search device can suitably supply information on a recommended route suitable for the driver of the moving body to the terminal device that guides the route of the moving body.

In another aspect of the route search device, the second acquisition unit transmits the driver information to a server device that stores a plurality of operation evaluation models, thereby performing an operation evaluation corresponding to the driver information. A model is acquired, and evaluation information for each of the roads is calculated based on the driving evaluation model. According to this aspect, the route search device can acquire the evaluation information necessary for the route search and determine the recommended route based on the operation evaluation model suitable for the driver received from the server device. In a preferred example, the evaluation information is information indicating a driving difficulty level or information indicating a good view.

According to another preferred embodiment of the present invention, the control method executed by the route search device includes driver information about a driver who drives a moving body, and information on a starting point and a destination of the moving body. The first acquisition process for acquiring the driver and the second acquisition for acquiring the evaluation information based on the driving evaluation model corresponding to the driver information for each of the roads constituting the plurality of routes from the departure point to the destination. It has a step and a route determining step of determining a recommended route from the plurality of routes based on the evaluation information. By executing this control method, the route search device can execute the route search in consideration of the individual difference of the driver.

According to another preferred embodiment of the present invention, a program executed by a computer acquires driver information about a driver who drives a moving body and information on a starting point and a destination of the moving body. A first acquisition unit, a second acquisition unit that acquires evaluation information based on a driving evaluation model corresponding to the driver information, and a second acquisition unit for each of the roads constituting the plurality of routes from the departure point to the destination. Based on the evaluation information, the computer functions as a route determining unit that determines a recommended route from the plurality of routes. By executing this program, the computer can execute a route search that appropriately considers individual differences of the driver. Preferably, the program is stored in a storage medium.

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

[Overview of route search system]
FIG. 1 is a schematic configuration of a route search system according to this embodiment. The route search system is a system that evaluates each road according to a model selected based on the driver's profile and performs a route search, and includes a server device 1 and a terminal device 2.

When the server device 1 receives the information requesting the route search (also referred to as "route search request information S1") from the terminal device 2, the server device 1 is 1 from the departure point to the destination specified in the route search request information S1. Or search for multiple recommended routes. Here, the route search request information S1 includes profile information such as the gender and driving history of the user of the terminal device 2, and the server device 1 determines the recommended route in consideration of the profile. Then, the server device 1 transmits information indicating the determined recommended route (also referred to as “recommended route information S2”) to the terminal device 2.

The terminal device 2 is, for example, 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 this embodiment, the terminal device 2 transmits the route search request information S1 including the current position information indicating the departure place, the destination information specified by the user input, and the user profile information to the server device 1. By doing so, the recommended route information S2 is received. Then, the terminal device 2 determines the guidance route to be guided based on the received recommended route information S2, and starts the route guidance. The terminal device 2 may store map data or the like necessary for route guidance in advance, or may receive it from the server device 1 as needed.

[Device configuration]
FIG. 2A shows a schematic configuration of the server device 1. As shown in FIG. 2A, the server device 1 includes 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 connected to each other via a bus line.

Based on the control of the control unit 15, the communication unit 11 receives the route search request information S1 transmitted from the terminal device 2 and transmits the recommended route information S2 to the terminal device 2. The communication unit 1 is an example of the "transmission unit" in the present invention.

The storage unit 12 stores a program for controlling the operation of the server device 1 and holds information necessary for the operation of the server device 1. Further, the storage unit 12 stores the map data 16, the captured image DB 17, and the driving evaluation model DB 18. The map data 16 includes road data represented by a link corresponding to a road, a node corresponding to a connecting portion (intersection) of the road, and facility information related to the facility. The captured image DB 17 is a database that stores captured images taken on each road in association with the road. For example, there is at least one photographed image registered in the photographed image DB 17 for each link.

The driving evaluation model DB 18 is a database of a model (also referred to as a "driving evaluation model") for determining an evaluation regarding road driving displayed on the photographed image from the photographed image taken on the road. The driving evaluation model is a pattern classifier obtained by supervised machine learning, and is, for example, learning data learned by applying a neural network (deep learning). In this embodiment, a combination of a photographed image taken on the road in advance and an evaluation value of driving difficulty determined by a person who refers to the photographed image (also referred to as a “judgment”) is learned as teacher data. By doing so, a driving evaluation model is generated. Each driving evaluation model registered in the driving evaluation model DB 18 is generated for each group of judges having a common profile such as gender and driving history. The data structure of the operation evaluation model DB18 will be described later. The evaluation value of the driving difficulty level may be, for example, a two-stage evaluation value of "0" indicating that it is easy to drive or "1" indicating that it is difficult to drive, and is an evaluation value of three or more stages. You may. The evaluation value of the driving difficulty level is an example of "evaluation information" in the present invention.

The control unit 15 includes a CPU, ROM, 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 route search request information S1, the control unit 15 minimizes the total cost for each road (link) among the routes from the departure point to the destination indicated by the route search request information S1. Search for the recommended route. At this time, the control unit 15 searches for a route that is easy for the user of the terminal device 2 to drive as a recommended route by determining the cost of each road described above based on the evaluation value of the driving difficulty level. In this case, the control unit 15 extracts a driving evaluation model from the driving evaluation model DB 18 based on the user profile of the terminal device 2 indicated by the route search request information S1, and registers the extracted driving evaluation model and the captured image DB 17. The evaluation value of the driving difficulty of each road is determined using the captured image. The control unit 15 is an example of the “first acquisition unit”, the “second acquisition unit”, the “third acquisition unit”, the “routing determination unit”, and the computer that executes the program in the present invention.

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

Based on the control of the control unit 25, the communication unit 21 transmits the route search request information S1 to the server device 1, receives the recommended route information S2 transmitted from the server device 1, and other information necessary for route guidance. do.

The storage unit 22 stores a program executed by the control unit 25 and information necessary for the control unit 25 to execute a predetermined process. In this embodiment, the storage unit 22 stores information (also referred to as “profile information”) related to the profile generated by the control unit 25 based on the input to the input unit 24 or the like. The profile information is an example of "driver information" in the present invention.

The sensor unit 23 includes a GPS receiver 32 that generates absolute position information of the vehicle and the like, and an autonomous positioning device 33 such as a gyro sensor and a speed sensor. The sensor unit 23 supplies the generated output signal to the control unit 25.

The input unit 24 is a button, a touch panel, a remote controller, a voice input device, etc. for the user to operate, and receives and generates an input for designating a destination for a route search, an input for a driver's profile, and the like. The signal is supplied to the control unit 25. The output unit 26 is, for example, a display, a speaker, or the like that outputs under the control of the control unit 25.

The control unit 25 controls the entire terminal device 2 including a CPU that executes a program and the like. For example, the control unit 25 generates profile information based on user input by the input unit 24 and stores it in the storage unit 22. Further, when the control unit 25 detects the input of the destination by the input unit 24, the input destination information, the current position information output by the GPS receiver 32 or the like, and the storage unit 22 are stored. The route search request information S1 including the profile information is transmitted to the server device 1 by the communication unit 21. Then, when the communication unit 21 receives the recommended route information S2 from the server device 1, the control unit 25 causes the output unit 26 to output the recommended route, and the input unit 24 inputs whether or not to set it as a guide route. accept. After that, the control unit 25 causes the output unit 26 to output information that guides the set route.

[Extraction of driving evaluation model]
When the server device 1 receives the route search request information S1, the server device 1 extracts the operation evaluation model from the operation evaluation model DB 18 based on the profile information included in the route search request information S1. Here, each driving evaluation model registered in the driving evaluation model DB 18 is generated for each group of judges having a common profile such as gender and driving history, and is associated with the classification information of the profile common to the groups. There is. Therefore, the server device 1 extracts the operation evaluation model associated with the profile classification information common to the profile indicated by the profile information from the operation evaluation model DB 18.

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 18 and the classification information of the profile of the judge corresponding to the driving evaluation model. The corresponding table of FIG. 3 has each item of "gender", "driving history", "place of residence", "age", and "model ID".

Here, the driving evaluation model of the model ID "M001" includes a photographed image referred to by a judge whose gender is male, driving history is less than 5 years, residence is Tokyo, and age is 25 to 39 years old. The driving evaluation model obtained by learning the combination with the evaluation value of the driving difficulty level judged by the judge by referring to the photographed image as the teacher data is shown. Similarly, the driving evaluation model of the model ID "M002" includes a photographed image referred to by a judge whose gender is male, driving history is less than 5 years, residence is Tokyo, and age is 40 to 59 years old. The driving evaluation model obtained by learning the combination with the evaluation value of the driving difficulty level judged by the judge by referring to the photographed image as the teacher data is shown. In addition, the driving evaluation model of model ID "M251" is a photographed image referred to by a judge whose gender is female, driving history is less than 5 years, residence is Saitama prefecture, and age is 60 to 69 years old, and the judgment is made. A driving evaluation model obtained by learning a combination with an evaluation value of driving difficulty determined by a person with reference to a photographed image as teacher data is shown. In addition, the driving evaluation model of model ID "M342" is a photographed image referred to by a judge whose gender is female, driving history is 5 years or more, residence is Kanagawa prefecture, and age is 24 years or younger, and the judge is A driving evaluation model obtained by learning a combination with an evaluation value of driving difficulty determined by referring to a captured image as teacher data is shown. In addition, the driving evaluation model of model ID "M445" is a photographed image referred to by a judge who has a female gender, a driving history of 5 years or more, a place of residence of Hokkaido, and an age of 70 years or older, and a photographed image by the judge. A driving evaluation model obtained by learning a combination with an evaluation value of driving difficulty determined by referring to an image as teacher data is shown.

In this way, the driving evaluation model is generated for each group when the judges are grouped based on gender, 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 he / she often travels), age, and the like. In consideration of the above, in the present embodiment, the judges are grouped based on the profile items that affect the driving difficulty felt by the driver, and the server device 1 is a pre-generated operation evaluation for each divided group. The model is stored as the operation evaluation model DB18.

In the example of FIG. 3, the driving history was classified into two, less than 5 years and 5 years or more, the place of residence was classified by prefecture, and the age was classified by 5 stages, but each item was classified. The method is not limited to this. For example, the driving history may be divided into three or more stages, and the place of residence may be classified by a wider area (for example, 7 regions) or a more detailed area. Similarly, age may be categorized by stages other than the five stages. In addition to or in addition to the driving history, the corresponding table in FIG. 3 is provided with 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.). May be good.

The server device 1 refers to a correspondence table as shown in FIG. 3, and extracts an operation evaluation model corresponding to a group of judges (conformity group) conforming to the profile from the profile indicated by the profile information from the operation evaluation model DB 18. do. Specifically, the server device 1 refers to the correspondence table shown in FIG. 3, and is a driving evaluation model corresponding to the model ID recorded in the record corresponding to the gender, driving history, place of residence, and age included in the profile information. Is extracted from the operation evaluation model DB18. For example, if the gender indicated by the profile information is "male", the driving history is "3 years", the place of residence is "Tokyo", and the age is "45 years old", the model recorded in the second record in FIG. The driving evaluation model of the ID "M002" is extracted from the driving evaluation model DB18.

[Route search processing]
Next, the route search process using the driving evaluation model will be described. FIG. 4 is an example of a flowchart showing the procedure of the route search process using the operation evaluation model.

First, the terminal device 2 determines whether or not there is an input instructing the route search (step S101). Then, when there is an input instructing the route search (step S101; Yes), the terminal device 2 stores the destination information specified in the above input, the current position information output by the GPS receiver 32 or the like, and the storage. The route search request information S1 including the profile information stored in the unit 22 is transmitted to the server device 1 (step S102). On the other hand, when there is no input instructing the route search (step S101; No), the terminal device 2 subsequently monitors in step S101 whether or not there is an input instructing the route search.

After the route search request information S1 is transmitted by the terminal device 2, the server device 1 receives the route search request information S1 from the terminal device 2 (step S201). Then, the server device 1 refers to the profile information included in the route search request information S1 and extracts the operation evaluation model to be applied from the operation evaluation model DB 18 (step S202).

Then, the server device 1 is a route search from the current position (that is, the departure point) of the server device 1 specified by the route search request information S1 to the destination, and is an evaluation value of the driving difficulty level calculated from the driving evaluation model. Is started (step S203). In this case, the server device 1 extracts the captured image corresponding to the road (that is, the link on the map data 16) constituting the route from the captured image DB 17, and inputs the extracted captured image into the driving evaluation model to target the target. The evaluation value of the driving difficulty corresponding to the road is calculated (step S204). At this time, the server device 1 may set the cost (link cost) for each road to a value proportional to the calculated evaluation value of the driving difficulty level, and calculates it in consideration of the required time in a normal route search. It may be set to a value obtained by adding a value corresponding to the above-mentioned evaluation value to the link cost to be performed. In this case, the evaluation value of the driving difficulty level may be set so as to be higher as the road is harder to drive.

Then, the server device 1 determines 1 or a predetermined number of recommended routes having the lowest total link cost for each road (step S205). In this case, the server device 1 totals the link costs of all the roads constituting the candidate route for each candidate route that is a candidate for the recommended route from the departure point to the destination, and the total link cost is the lowest 1 or Determine a predetermined number of recommended routes. As a result, the server device 1 can suitably determine a route composed of roads, which is presumed to be less difficult for the driver to drive, as a recommended route. Then, the server device 1 transmits the recommended route information S2 regarding the determined recommended route to the terminal device 2 that is the source of the route search request information S1 (step S206).

On the other hand, after transmitting the route search request information S1, the terminal device 2 receives the recommended route information S2 transmitted by the server device 1 in step S206 (step S103). Then, the terminal device 2 determines the recommended route selected by the user as the guide route, and starts the guidance for traveling along the determined guide route (step S104).

As described above, the server device 1 according to the present embodiment receives profile information about the driver who drives the vehicle and information on the departure point and the destination of the vehicle from the terminal device 2. The server device 1 calculates an evaluation value of the driving difficulty level based on the driving evaluation model corresponding to the profile information for each of the roads constituting the plurality of routes from the starting point to the destination. Then, the server device 1 determines the recommended route based on the calculated evaluation value of the driving difficulty level. In this way, since the server device 1 performs the route search based on the evaluation value of the driving difficulty calculated from the driving evaluation model suitable for the driver of the vehicle, the server device 1 executes the route search in consideration of the individual difference of the driver. can do.

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

(Modification example 1)
The terminal device 2 may execute a part or all of the route search process executed by the server device 1.

FIG. 5 is a configuration example of the route search system according to this modified example. In the example of FIG. 5, the terminal device 2 stores map data 20 including road data, facility information, and the like, and transmits the profile information “Sa” stored in the storage unit 22 to the server device 1. In this case, the server device 1 extracts the driving evaluation model from the driving evaluation model DB 18 based on the profile indicated by the profile information Sa. Then, the server device 1 transmits the extracted operation evaluation model information (also referred to as “extracted model information Sb”) to the terminal device 2. When the terminal device 2 receives the input of the destination and executes the route search, the terminal device 2 determines the recommended route by executing steps S203 to S205 of FIG. In this case, the terminal device 2 receives the captured image of each road on the route required in step S204 from the server device 1 as the route image information “Sc”. In this case, for example, the terminal device 2 transmits a request signal specifying a link ID or the like of the road on which the captured image is required to the server device 1, and the server device 1 corresponds to the link ID or the like included in the received request signal. The captured image to be captured is extracted from the captured image DB 17 and transmitted as the route image information Sc.

As described above, according to the present modification, the terminal device 2 can suitably execute the route search process according to the embodiment in place of the server device 1. In this modification, the terminal device 2 is an example of the "route search device" in the present invention, and the control unit 25 of the terminal device 2 is the "first acquisition unit" and "second acquisition unit" in the present invention. , "Third acquisition unit", "routing unit", and an example of a computer that executes a program.

(Modification 2)
The evaluation value of the driving difficulty calculated based on the driving evaluation model may be included in the map data in advance.

FIG. 6 shows the configuration of the route search system according to this modified example. In the example of FIG. 6, the terminal device 2 includes information (also referred to as “driving evaluation information Ie”) in which the evaluation value of the driving difficulty calculated based on each driving evaluation model is associated with each road in the map data 20. It has been. In this case, the evaluation value of the driving difficulty of each road is recorded in the map data 20 for each model ID of each driving evaluation model, for example. Further, in the configuration example of FIG. 6, the terminal device 2 stores the corresponding table of FIG. 3 in advance. Then, when the terminal device 2 executes the route search, for example, after specifying the model ID of the driving evaluation model corresponding to the profile information with reference to the corresponding table of FIG. 3, the driving difficulty level of each road constituting the route is specified. The evaluation value of is obtained by referring to the map data 20 from the specified model ID and the link ID of the target road. Also in this aspect, the terminal device 2 can calculate the cost of each route based on the evaluation value of the driving difficulty level and determine the recommended route.

Instead of the example of FIG. 6, in the configuration in which the server device 1 executes the route search, the operation evaluation information Ie may be included in the map data included in the server device 1. Even in this case, the server device 1 identifies the model ID of the driving evaluation model corresponding to the profile information received from the terminal device 2 with reference to the corresponding table in FIG. The evaluation value of the driving difficulty level is acquired by referring to the map data from the specified model ID and the link ID of the target road. Also in this aspect, the server device 1 can calculate the cost of each route based on the evaluation value of the driving difficulty level and determine the recommended route.

(Modification example 3)
The driving evaluation model may be further classified and generated based on the driving environment of the vehicle.

In this case, in the corresponding table of FIG. 3, in addition to the items related to the profile such as gender, driving history, place of residence, and age, items related to the driving environment such as weather, road type, and time zone are further provided. Then, the driving evaluation model is generated in advance for each classification based on the items related to the driving environment and stored in the driving evaluation model DB18. In this case, the driving evaluation model corresponding to each driving environment evaluates the photographed image and the driving difficulty level 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 the combination with the value as teacher data.

Then, for example, when the terminal device 2 receives an input instructing a route search, the terminal device 2 recognizes the current traveling environment of the vehicle by referring to the output of the sensor unit 23 such as a raindrop sensor (not shown) or the map DB 20. .. Then, the terminal device 2 includes the recognized information indicating the traveling environment in the route search request information S1 and transmits the information to the server device 1. In this case, the server device 1 selects a driving evaluation model that matches the profile information and the information indicating the driving environment included in the route search request information S1, and uses the driving evaluation model to determine the driving difficulty required for the route search. Calculate the evaluation value. As described above, according to the present modification, the server device 1 can determine a route that is easy to drive as a recommended route in consideration of the current traveling environment of the vehicle.

(Modification example 4)
The target 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 a good view.

In this case, each driving evaluation model registered in the driving evaluation model DB 18 uses teacher data as a combination of a photographed image taken on the road and an evaluation value of good visibility judged by a judge who referred to the photographed image. It is generated by learning as. Then, each of these driving evaluation models is generated for each group of judges having a common profile such as gender and age, and is associated with the common profile classification information, as in the embodiment, and the driving evaluation model DB18 Is remembered in. Then, in the route search process of FIG. 4, the terminal device 2 transmits the route search request information S1 including the profile information to the server device 1 in step S102, as in the embodiment. In this case, in step S202, the server device 1 extracts from the operation evaluation model DB 18 an operation evaluation model that matches the profile indicated by the profile information included in the route search request information S1 received from the terminal device 2. Then, in step S203, the server device 1 starts a route search using the evaluation value of the good view calculated from the operation evaluation model as the cost. In this case, the evaluation value of the good view calculated from the driving evaluation model is set so that the worse the view is, the higher the value is. Then, the server device 1 determines the recommended route by executing steps S204 and S205, and transmits the recommended route information S2 regarding the determined recommended route to the terminal device 2 in step S206.

According to this modification, the server device 1 can determine a route composed of roads having a good view as a suitable recommended route from the viewpoint of tourism or safety. Here, the route composed of roads having a good view corresponds to, for example, a route composed of roads having an excellent landscape in a tourist spot from the viewpoint of tourism, and from a distance from the viewpoint of safe driving. However, routes consisting of safe roads that are relatively easy to find pedestrians are applicable. The terminal device 2 may receive an input from the input unit 24 that allows the user to select which index of driving difficulty and good view is used to execute the route search. In this case, the terminal device 2 includes the information specifying which index of the driving difficulty level and the good view is to be used in the route search request information S1 based on the received input, and transmits the information to the server device 1.

1 Server device 2 Terminal device 11, 21 Communication unit 12, 22 Storage unit 15, 25 Control unit 16, 20 Map data 17 Captured image DB
18 Driving evaluation model DB
23 Sensor unit 24 Input unit 26 Output unit

Claims (18)

The first acquisition unit that acquires the driver information about the driver who drives the moving body and the information on the starting point and the destination of the moving body, and the first acquisition unit.
Evaluation information output from the driving evaluation model by inputting captured images corresponding to each of the roads constituting the plurality of routes from the starting point to the destination into the driving evaluation model corresponding to the driver information. The second acquisition department to acquire
A route determination unit that determines a recommended route from the plurality of routes based on the evaluation information,
A route search device including. A transmission unit that transmits information on the recommended route to the terminal device that moves together with the moving body is further provided.
The route search device according to claim 1, wherein the first acquisition unit receives the driver information and information on the departure place and the destination from the terminal device. The second acquisition unit acquires the driver evaluation model corresponding to the driver information by transmitting the driver information to a server device that stores a plurality of operation evaluation models, and based on the operation evaluation model. The route search device according to claim 1, which calculates evaluation information for each of the roads. The route search device according to claim 2 or 3, wherein the evaluation information is information indicating a driving difficulty level or information indicating a good view. The first acquisition unit that acquires the driver information about the driver who drives the moving body and the information on the starting point and the destination of the moving body, and the first acquisition unit.
A second acquisition unit that acquires evaluation information based on a driving evaluation model corresponding to the driver information for each of the roads constituting the plurality of routes from the departure point to the destination.
A route determination unit that determines a recommended route from the plurality of routes based on the evaluation information,
With
The driving evaluation model is for each group of the judges classified according to the commonality of the profiles based on the photographed image around the moving body and the evaluation information regarding the driving evaluated by the judge having the profile based on the photographed image. A route search device that is a driving evaluation model in a conforming group that matches the driver information from the driving evaluation model learned in. For each road, a storage unit that stores map data associated with evaluation information based on a plurality of driving evaluation models is further provided.
The route search device according to claim 5, wherein the second acquisition unit acquires evaluation information based on a driving evaluation model corresponding to the driver information for each of the roads from the map data. A transmission unit that transmits information on the recommended route to the terminal device that moves together with the moving body is further provided.
The route search device according to claim 5 or 6, wherein the first acquisition unit receives the driver information and information on the departure place and the destination from the terminal device. The second acquisition unit acquires the driver evaluation model corresponding to the driver information by transmitting the driver information to a server device that stores a plurality of operation evaluation models, and based on the operation evaluation model. The route search device according to claim 5 or 6, which calculates evaluation information for each of the roads. The route search device according to claim 7 or 8, wherein the evaluation information is information indicating a driving difficulty level or information indicating a good view. The first acquisition unit that acquires the driver information about the driver who drives the moving body and the information on the starting point and the destination of the moving body, and the first acquisition unit.
A second acquisition unit that acquires captured images taken on each of the roads constituting the plurality of routes, and
A third acquisition unit that acquires evaluation information based on a driving evaluation model corresponding to the driver information for each of the roads constituting the plurality of routes from the departure point to the destination.
A route determination unit that determines a recommended route from the plurality of routes based on the evaluation information,
With
The third acquisition unit is a route search device that acquires evaluation information for each of the roads by inputting the captured image acquired by the second acquisition unit into the driving evaluation model. A transmission unit that transmits information on the recommended route to the terminal device that moves together with the moving body is further provided.
The route search device according to claim 10, wherein the first acquisition unit receives the driver information and information on the departure place and the destination from the terminal device. The third acquisition unit acquires the driver evaluation model corresponding to the driver information by transmitting the driver information to a server device that stores a plurality of operation evaluation models, and based on the operation evaluation model. The route search device according to claim 10, which calculates evaluation information for each of the roads. The route search device according to claim 11 or 12, wherein the evaluation information is information indicating a driving difficulty level or information indicating a good view. It is a control method executed by the route search device.
The first acquisition step of acquiring the driver information about the driver who drives the moving body and the information of the starting point and the destination of the moving body, and
Evaluation information output from the driving evaluation model by inputting captured images corresponding to each of the roads constituting the plurality of routes from the starting point to the destination into the driving evaluation model corresponding to the driver information. The second acquisition process to acquire
A route determination step of determining a recommended route from the plurality of routes based on the evaluation information, and
Control method having. A program that a computer runs
The first acquisition unit that acquires the driver information about the driver who drives the moving body and the information on the starting point and the destination of the moving body, and the first acquisition unit.
Evaluation information output from the driving evaluation model by inputting captured images corresponding to each of the roads constituting the plurality of routes from the starting point to the destination into the driving evaluation model corresponding to the driver information. The second acquisition department to acquire
A program that causes the computer to function as a route determination unit that determines a recommended route from the plurality of routes based on the evaluation information. It is a control method executed by the route search device.
The first acquisition step of acquiring the driver information about the driver who drives the moving body and the information of the starting point and the destination of the moving body, and
A second acquisition step of acquiring evaluation information based on a driving evaluation model corresponding to the driver information for each of the roads constituting the plurality of routes from the starting point to the destination.
A route determination step of determining a recommended route from the plurality of routes based on the evaluation information, and
Have,
The driving evaluation model is for each group of the judges classified according to the commonality of the profiles based on the photographed image around the moving body and the evaluation information regarding the driving evaluated by the judge having the profile based on the photographed image. A control method that is a driving evaluation model in a conforming group that matches the driver information from the driving evaluation model learned in. A program that a computer runs
The first acquisition unit that acquires the driver information about the driver who drives the moving body and the information on the starting point and the destination of the moving body, and the first acquisition unit.
A second acquisition unit that acquires evaluation information based on a driving evaluation model corresponding to the driver information for each of the roads constituting the plurality of routes from the departure point to the destination.
Based on the evaluation information, the computer is made to function as a route determination unit that determines a recommended route from the plurality of routes.
The driving evaluation model is for each group of the judges classified according to the commonality of the profiles based on the photographed image around the moving body and the evaluation information regarding the driving evaluated by the judge having the profile based on the photographed image. A program that is a driving evaluation model in a conforming group that matches the driver information from the driving evaluation model learned in. A storage medium in which the program according to claim 15 or 17 is stored.

Images