Operation evaluation model generation device

Abstract

To generate an operation evaluation model taking difference of feelings generated due to operation experience, a living area or the like into consideration.SOLUTION: An operation evaluation model generation device comprises a first storage unit for storing image information on a location where a mobile body travels and a second storage unit for storing evaluation information on operation evaluated by a determination person for the image information, in association with a profile of the determination person. Then, on the basis of the evaluation information and the profile of the determination person, an operation evaluation model corresponding to the profile of the determination person is generated.SELECTED DRAWING: Figure 3

Description

[Technical field]

[0001] The present invention relates to a method for generating a model for making an assessment regarding driving. [Background technology]

[0002] Conventionally, there has been known a system that aggregates data from a plurality of vehicles in a server device and distributes information on the learning results obtained by the server device through machine learning. For example, Patent Document 1 discloses a system that collects conditions such as the weather and time of day when each vehicle is traveling as environmental data, and learns for each condition indicated by the environmental data. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2015-133552 A Summary of the Invention [Problem to be solved by the invention]

[0004] Regarding situation recognition and judgment while driving, there are individual differences based on the driver's experience, etc., and recognition and judgment may differ depending on the driver. In this regard, Patent Document 1 does not take such individual differences into consideration at all.

[0005] The above is an example of a problem to be solved by the present invention. The present invention aims to generate a driving evaluation model that takes into account differences in sensations due to driving experience, living area, etc. [Means for solving the problem]

[0006] The invention described in claim 1 is a driving evaluation model generation device that includes evaluation information regarding driving evaluated by an evaluator based on image information of a location where a moving body is traveling, and a generation unit that generates a driving evaluation model corresponding to the profile of the evaluator based on the profile of the evaluator associated with the evaluation information. [Brief description of the drawings]

[0007] [Figure 1] 1 shows a configuration of a learning system according to an embodiment of the present invention. [Diagram 2] 13 shows an example of stored data in the teacher data management unit. [Diagram 3] 4 is a flowchart of a first embodiment of a learning process. [Figure 4] 13 is a flowchart of a second embodiment of the learning process. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0008] In one preferred embodiment of the present invention, a driving evaluation model generation device includes a first memory unit that stores image information of locations where a moving body is traveling, a second memory unit that stores evaluation information regarding driving evaluated by an evaluator based on the image information in association with a profile of the evaluator, and a generation unit that generates a driving evaluation model corresponding to the profile of the evaluator based on the evaluation information and the profile of the evaluator.

[0009] The driving evaluation model generation device includes a first storage unit that stores image information of a location where a moving object travels, and a second storage unit that stores evaluation information on driving evaluated by an evaluator for the image information in association with the profile of the evaluator. Then, a driving evaluation model corresponding to the profile of the evaluator is generated based on the evaluation information and the profile of the evaluator. In this way, a driving evaluation model can be generated for each profile of the evaluator.

[0010] In one aspect of the driving evaluation model generation device, the generation unit extracts, for each group of evaluators who share the same profile, evaluation information by the evaluators who belong to the group from the storage unit, analyzes the tendency of the extracted evaluation information, and generates the driving evaluation model. This makes it possible to generate a driving evaluation model suitable for a group of evaluators who share a common profile. In a preferred example, when the number of evaluators who have presented the same evaluation information is equal to or greater than a predetermined ratio of the number of evaluators who belong to the group, the generation unit reflects the evaluation information in the driving evaluation model of the group.

[0011] In another aspect of the driving evaluation model generation device, the generation unit extracts profiles of evaluators belonging to each group of evaluators who have the same evaluation information from the storage unit, analyzes the tendency of the extracted profiles, and determines a profile for the group. In this aspect, a profile is determined for a group of evaluators who have the same evaluation information, and a corresponding driving evaluation model is generated. In a preferred example, when the number of evaluators who have the same profile is equal to or greater than a predetermined ratio of the number of evaluators who belong to the group, the generation unit sets the profile as the profile for the group.

[0012] In another aspect of the driving evaluation model generation device, the profile includes at least one of the age, sex, residential area, and driving history of the assessor. In another aspect, the generation unit updates the driving evaluation model every time the evaluation information or the profile stored in the storage unit is updated. This makes it possible to always generate a driving evaluation model using the latest information.

[0013] In another preferred embodiment of the present invention, a driving evaluation model generation method executed by a driving evaluation model generation device includes a first acquisition step of acquiring image information of a place where a moving body travels, a second acquisition step of acquiring evaluation information on driving evaluated by an evaluator for the image information in association with a profile of the evaluator, and a generation step of generating a driving evaluation model corresponding to the profile of the evaluator based on the evaluation information and the profile of the evaluator. This method also allows the generation of a driving evaluation model for each profile of the evaluator.

[0014] In another preferred embodiment of the present invention, a program executed by an apparatus including a computer causes the computer to execute a first acquisition step of acquiring image information of a place where a moving object travels, a second acquisition step of acquiring evaluation information on driving evaluated by an evaluator for the image information in association with a profile of the evaluator, and a generation step of generating a driving evaluation model corresponding to the profile of the evaluator based on the evaluation information and the profile of the evaluator. By executing this program on a computer, the above driving evaluation model generation device can be realized. This program can be stored in a storage medium and handled. EXAMPLES

[0015] Hereinafter, preferred embodiments of the present invention will be described with reference to the drawings. [System Configuration] 1 shows the configuration of a learning system which is one embodiment of a driving evaluation model generating device of the present invention. The learning system 10 is realized by a device equipped with a computer, such as a server device. As shown in the figure, the learning system 10 includes an image data storage unit 11, a teacher data management unit 12, a learning data control unit 13, a machine learning unit 14, and a driving evaluation model database (hereinafter, "database" will be abbreviated as "DB").

[0016] Image data captured by a vehicle camera is stored in the image data storage unit 11. In a typical example, the image data is captured by an on-board camera while the vehicle is traveling, and is supplied to the learning system 10 configured as a server by wireless communication via the Internet. The image data is an image including the environment in which the vehicle is traveling, specifically, the road ahead of the vehicle and its surroundings. The image data is stored in the image data storage unit 11 in association with an image data ID, which is its identification information.

[0017] The teacher data management unit 12 stores the results of the evaluation of the driving environment indicated by the image data by the assessor as a teacher. FIG. 2 shows an example of the stored data of the teacher data management unit 12. The teacher data management unit 12 stores a plurality of teacher data. One piece of stored data is composed of an image data ID, a profile, environmental information, and a judgment value. The teacher data stored in the teacher data management unit 12 is used for learning by the machine learning unit 14 described later. The teacher data can be generated from, for example, probe data transmitted from a vehicle that is actually traveling or a car navigation device mounted on the vehicle. In addition, the image data may be shown to the assessor by a questionnaire method to have the assessor evaluate the driving, and at the same time, the profile of the assessor and environmental information at that time may be obtained to generate the teacher data.

[0018] "Image data ID" is identification information of the image data to be judged by the judge. "Profile" is the profile of the teacher when performing machine learning of driving evaluation, and actually indicates the profile of the judge who makes the judgment on the image data. The profile includes a teacher identifier, gender, year of birth, place of residence, and driving history.

[0019] The "teacher identifier" is identification information that uniquely identifies the teacher, and specifically, is the ID of the judge. "Gender" is the gender of the judge, and "Year of birth" is the year the judge was born. Note that age may be used instead of the year of birth. "Place of residence" indicates the area in which the judge resides, and in this example, the prefecture is used. "Driving history" is the driving history of the judge, and in this example, the number of years of driving experience is used.

[0020] "Environment information" is information indicating the environment when each image data was captured, and includes weather, road type, and time period. "Weather" is the weather when the image data was captured, and sunny, cloudy, rainy, snowy, etc. are used. "Road type" is the type of road included in the image data, i.e., the type of road the vehicle was traveling on when the image was captured, and expressways, national roads, prefectural roads, narrow streets, etc. are used. "Time period" indicates the time period when the image data was captured.

[0021] The "judgment value" is the result of the judge's evaluation of the image data, and is the result of the judge's evaluation of the driving environment shown by the image data. In this example, the judgment value is assigned two values, "difficult to drive" and "easy to drive", but the ease of driving may be classified into three or five levels, and three or five judgment values ​​may be used.

[0022] In the example shown in Figure 2, the results of three judges with teacher identifiers "K1116," "H1117," and "T1110" judging the drivability of two pieces of image data with image data IDs "107" and "108" are stored as teacher data.

[0023] Returning to FIG. 1, the learning data control unit 13 generates learning data based on the image data stored in the image data accumulation unit 11 and the teacher data stored in the teacher data management unit 12, and supplies the data to the machine learning unit 14. The "learning data" is data input to the machine learning unit 14 and used for machine learning, and includes teacher data and learning data. Here, the "teacher data" is a judgment value stored in the teacher data management unit 12, and the "learning data" is image data corresponding to the judgment value. That is, the learning data is data that links image data with the judgment value of the judge for the image data. As will be described in detail later, the learning data control unit 13 groups the judges who are teachers according to the commonality of their profiles. That is, a plurality of teachers are grouped according to the commonality of their profiles to generate a teacher model, and learning data is generated for each teacher model and supplied to the machine learning unit 14.

[0024] The machine learning unit 14 performs supervised learning using the learning data supplied from the learning data control unit 13. Then, the machine learning unit 13 generates, as a learning result, a model (hereinafter referred to as a "driving evaluation model") for determining whether or not the driving environment indicated by the image data is easy to drive in. That is, the driving evaluation model is a pattern classifier obtained by supervised machine learning, and is, for example, a learning result obtained by learning to which a neural network is applied.

[0025] Here, as described above, the learning data control unit 13 generates learning data for each teacher model and supplies it to the machine learning unit 14, so that the machine learning unit 14 generates a learning result for each teacher model and stores it as a driving evaluation model in the driving evaluation model DB 15. For example, in the case of learning by deep learning, the driving evaluation model is composed of network data, a teacher model (a profile of the teacher used to create the teacher model), environmental data (parameters of environmental information used during learning), etc.

[0026] In the above configuration, the image data storage unit 11 is an example of a first memory unit of the present invention, the teacher data management unit 12 is an example of a second memory unit of the present invention, and the learning data control unit 13 and the machine learning unit 14 are examples of a generation unit of the present invention.

[0027] [Learning process] Next, the learning process performed by the learning system 10 will be described. (First embodiment) In the learning process of the first embodiment, a teacher model is set by specifying a profile of a teacher (evaluator), and a driving evaluation model corresponding to the teacher model is created.

[0028] Fig. 3 is a flowchart of the learning process according to the first embodiment. This process is mainly executed by the learning data control unit 13 and the machine learning unit 14 of the learning system 10 shown in Fig. 1. When the learning system 10 is configured with a computer device such as a server, the learning process is realized by the computer device executing a program prepared in advance.

[0029] First, the learning data control unit 13 creates a teacher model by grouping teachers based on the commonality of their profiles from the teacher data stored in the teacher data management unit 12 (step S11). As shown in FIG. 2, the teacher data management unit 12 stores profiles of different teachers (evaluators). In the example of FIG. 2, gender, year of birth, place of residence, and driving history are stored as profiles. The learning data control unit 13 creates a group of evaluators who have one or more of these profiles in common. For example, a group called "males residing in Saitama Prefecture" is created for evaluators whose gender is male and whose place of residence is Saitama Prefecture, and this is used as the teacher model.

[0030] Next, the learning data control unit 13 acquires image data and judgment values ​​for all teachers (judges) belonging to the teacher model created in step S11 (step S12). Specifically, for all teacher data belonging to the teacher model "male residing in Saitama Prefecture", judgment values ​​are acquired from the teacher data management unit 12, and image data corresponding to the image data ID is acquired from the image data storage unit 11. Then, the learning data control unit 13 saves the acquired image data and judgment values ​​as learning data for the teacher model (step S13). In this way, learning data corresponding to the teacher model created in step S11 is prepared.

[0031] The learning data created in this way is supplied to the machine learning unit 14, and the machine learning unit 14 executes machine learning using the learning data (step S14). Then, the machine learning unit 14 stores the learning result obtained by the machine learning (step S15). Specifically, the learning result obtained by the machine learning becomes a driving evaluation model corresponding to the teacher model created in step S11. That is, in the above example, a driving evaluation model of the teacher model "male residing in Saitama Prefecture" is obtained as the learning result. Then, the machine learning unit 14 stores this driving evaluation model in the driving evaluation model DB15.

[0032] In step S13, when image data and judgment values ​​are obtained for a teacher (judge) belonging to a teacher model to generate learning data, different judgment values ​​may be obtained from judges belonging to the same teacher model. For example, a case may be considered in which judgment values ​​for the same image data by a judge belonging to the teacher model "male living in Saitama Prefecture" are divided into "easy to drive" and "difficult to drive". In this case, the obtained image data and judgment value cannot be used as is for machine learning processing in which image data and judgment values ​​are input one-to-one as learning data. Therefore, the learning data control unit 13 unifies judgment values ​​corresponding to the same image data into one by the following method.

[0033] The learning data control unit 13 basically determines one judgment value by majority vote. That is, the learning data control unit 13 counts the number of occurrences of judgment values ​​for the same image data, and adopts the judgment value that occurs most frequently as the judgment value for that image data. In the above example, the number of judgment values ​​"difficult to drive" and "easy to drive" for the same image by judges belonging to the teacher model "male living in Saitama Prefecture" is counted, and the judgment value with the larger number is adopted as the judgment value for that image data.

[0034] In addition, a reliability judgment may be added to the majority voting method described above to determine a single judgment value for the same image data. Specifically, if there is not much difference in the number of occurrences of different judgment values, the accuracy may be insufficient, so the image data and the judgment value for it may not be adopted as learning data.

[0035] Alternatively, the most frequent occurrence count may be compared to the occurrence counts of other judgment values ​​to determine whether there is a difference in the most frequent occurrence count that is deemed superior, based on the ratio of the occurrence counts, and the judgment value of the most frequent occurrence count may be adopted only when such a difference is found. For example, the judgment value of the most frequent occurrence count may be adopted when conditions such as the most frequent occurrence count being 70% or more of the total, or the most frequent occurrence count being 10% or more greater than the second most frequent occurrence count are satisfied.

[0036] In this way, in the first embodiment, a teacher model is set by first specifying a profile, and then machine learning is performed using the learning data of a teacher (evaluator) belonging to the teacher model to generate a driving evaluation model corresponding to the teacher model. Therefore, various teacher models can be set by specifying an arbitrary profile, and a driving evaluation model corresponding to the teacher model can be created.

[0037] There are various examples of teacher models that are set based on the commonality of profiles. For example, teacher models such as "male" and "female" can be set based on gender. Teacher models such as "young", "youth", "middle-aged", and "elderly" or teacher models such as "20s" to "80s" can be set based on the year of birth or age. Regarding the place of residence, in addition to teacher models for each prefecture, teacher models such as "urban area" and "suburban area" can also be set. Regarding driving experience, teacher models such as "novice" and "veteran" can be set according to the number of years. Of course, it is also possible to combine multiple of these to create one teacher model.

[0038] (Second Example) In the learning process of the second embodiment, teachers having the same judgment value, which is the evaluation result of the drivability for image data, are grouped, a teacher model for them is determined, and a driving evaluation model corresponding to the teacher model is created.

[0039] Fig. 4 is a flowchart of the learning process according to the second embodiment. This process is mainly executed by the learning data control unit 13 and the machine learning unit 14 of the learning system shown in Fig. 1. When the learning system 10 is configured with a computer device such as a server, the learning process is realized by the computer device executing a program prepared in advance.

[0040] First, the learning data control unit 13 groups teacher data having the same judgment value from among the teacher data stored in the teacher data management unit 12 (step S21). For example, the learning data control unit 13 forms one group from teacher data having a judgment value of "difficult to drive" (hereinafter, for convenience of explanation, referred to as the group "difficult to drive").

[0041] Next, the learning data control unit 13 analyzes the profiles of the teachers (judges) belonging to the group "difficult to drive" and determines the teacher model for this group (step S22). For example, if the majority of the judges belonging to the group "difficult to drive" are women with short driving histories, this group can be considered to be a group of "women with short driving histories", so the learning data control unit 13 determines the teacher model for this group to be "women with short driving histories". As another example, if the majority of the judges belonging to the group "difficult to drive" are elderly, the learning data control unit 13 determines the teacher model for this group to be "elderly". In this way, the learning data control unit 13 groups teacher data with common judgment values ​​and sets a teacher model for the group by analyzing the profiles.

[0042] Next, the learning data control unit 13 acquires image data and judgment values ​​of all teachers (judges) belonging to the teacher model determined in step S22 (step S23). In the first example above, the learning data control unit 13 extracts all teacher data belonging to the teacher model "female with short driving history" from the teacher data management unit 12 and acquires the image data and judgment values. Then, the learning data control unit 13 saves the acquired image data and judgment values ​​as learning data for that teacher model (step S24). In this way, learning data corresponding to the teacher model determined in step S22 is prepared.

[0043] The learning data thus created is supplied to the machine learning unit S14, and the machine learning unit 14 executes machine learning using the learning data (step S25). Then, the machine learning unit 14 stores the learning result obtained by the machine learning (step S26). Specifically, the learning result obtained by the machine learning becomes a driving evaluation model corresponding to the teacher model determined in step S22. That is, in the above example, a driving evaluation model of the teacher model "female with short driving history" is obtained as the learning result. Then, this driving evaluation model is stored in the driving evaluation model DB15.

[0044] In this way, in the second embodiment, first, teachers with matching judgment values, i.e., evaluation results for drivability, are grouped, and a teacher model for the group is set by analyzing their profiles. Then, a driving evaluation model corresponding to the teacher model is generated by performing machine learning using learning data of teachers (evaluators) belonging to the teacher model. That is, the teacher model is set by analyzing what kind of profile the evaluators with matching evaluations of drivability in a certain driving environment have, so that a teacher model composed of evaluators with matching evaluations can be flexibly set, and a driving evaluation model for it can be generated.

[0045] [Variations] In the above embodiment, the teacher model is set by one or more profiles, but the teacher model may be set by adding environmental information. For example, the teacher model "women with short driving experience" may be set as separate teacher models by adding weather, which is one of the environmental information, to "women with short driving experience (fine weather)", "women with short driving experience (rainy weather)", "women with short driving experience (snowy weather)", etc. In this case, learning data may be created from teacher data obtained under weather conditions corresponding to each teacher model, and a driving evaluation model may be generated by performing machine learning. [Explanation of symbols]

[0046] 10 Learning System 11 Image data storage unit 12 Teacher Data Management Department 13 Learning data control section 14 Machine Learning Department 15 Driving evaluation model database

Claims

1. A first storage unit that stores image information of a location where the moving object travels; a second storage unit that stores evaluation information regarding the driving evaluated by an evaluator for the image information in association with a profile of the evaluator; A generation unit that generates a driving evaluation model corresponding to the profile of the evaluator based on the evaluation information and the profile of the evaluator; A driving evaluation model generating device comprising:

2. A driving evaluation model generating device as described in claim 1, wherein the generation unit extracts evaluation information by evaluators belonging to each group who have a common profile from the second memory unit, analyzes trends in the extracted evaluation information, and generates the driving evaluation model.

3. A driving evaluation model generation device as described in Claim 2, wherein the generation unit reflects the evaluation information in the driving evaluation model of the group when the number of evaluators who presented the same evaluation information is equal to or greater than a predetermined percentage of the number of evaluators belonging to the group.

4. A driving evaluation model generating device as described in claim 1, wherein the generation unit extracts profiles of evaluators belonging to each group of evaluators who have common evaluation information from the second memory unit, analyzes trends in the extracted profiles, and determines a profile for the group.

5. A driving evaluation model generation device as described in Claim 4, wherein the generation unit sets the profile as the profile of the group when the number of evaluators having the same profile is equal to or greater than a predetermined percentage of the number of evaluators belonging to the group.

6. A driving evaluation model generating device as described in any one of claims 1 to 5, characterized in that the profile includes at least one of the judge's age, gender, residential area, and driving history.

7. A driving evaluation model generating device as described in any one of claims 1 to 6, characterized in that the generation unit updates the driving evaluation model each time the evaluation information or the profile stored in the second memory unit is updated.

8. A driving evaluation model generation method executed by a driving evaluation model generation device, comprising: A first acquisition step of acquiring image information of a location where a moving object travels; A second acquisition step of acquiring evaluation information on the driving evaluated by an evaluator with respect to the image information in association with a profile of the evaluator; A generation step of generating a driving evaluation model corresponding to the profile of the evaluator based on the evaluation information and the profile of the evaluator; A driving evaluation model generation method comprising:

9. A program executed by an apparatus having a computer, A first acquisition step of acquiring image information of a location where the moving object is traveling; a second acquisition step of acquiring evaluation information on the driving evaluated by an evaluator with respect to the image information in association with a profile of the evaluator; A generation step of generating a driving evaluation model corresponding to the profile of the evaluator based on the evaluation information and the profile of the evaluator; A program for causing the computer to execute the above.

10. A storage medium storing the program described in claim 9.

Images