JP7768752B2 - Educational material providing device, in-vehicle device, educational material providing method, and educational material providing program - Google Patents

Description

The present invention relates to a teaching material providing device, an in-vehicle device, a teaching material providing method, and a teaching material providing program.

Various technologies have been proposed to use camera-captured footage of vehicle driving as teaching materials for traffic safety education (see, for example, Patent Document 1).

Japanese Patent Application Laid-Open No. 2015-219497

However, with conventional technology, educational videos created by an administrator are uniformly provided to all recipients, which could reduce the educational effectiveness of the educational videos for some recipients. In other words, conventional technology leaves room for improvement in terms of providing educational videos with high educational effectiveness.

The present invention has been made in consideration of the above, and aims to provide a teaching material providing device, an in-vehicle device, a teaching material providing method, and a teaching material providing program that can provide teaching material videos with high educational effectiveness.

To solve the above problems and achieve the above objectives, the present invention provides a teaching material provision device having a control unit. The control unit detects attribute information indicating the attributes of the education recipient, and provides video captured by an in-vehicle device that corresponds to the detected attribute information as teaching material video for the education recipient.

This invention makes it possible to provide educational video materials with high educational effectiveness.

FIG. 1A is a diagram showing an overview of a learning material providing system including a learning material providing device according to an embodiment. FIG. 1B is a diagram showing an overview of a learning material providing system including a learning material providing device according to an embodiment. FIG. 2 is a block diagram showing an example of the configuration of the teaching material providing system according to the embodiment. FIG. 3 is a diagram illustrating an example of the video DB. FIG. 4 is a diagram showing an example of the teaching material DB. FIG. 5 is a diagram illustrating an example of the driver DB. FIG. 6 is a diagram showing the display of a terminal device to which educational video is provided. FIG. 7 is a flowchart showing the processing procedure executed by the teaching material providing device.

Embodiments of the educational material providing device, in-vehicle device, educational material providing method, and educational material providing program disclosed herein will be described in detail below with reference to the accompanying drawings. Note that the present invention is not limited to the embodiments described below.

<Overview of the teaching material provision system>
First, an overview of a teaching material providing system including a teaching material providing device according to an embodiment will be described with reference to Figures 1A and 1B. Figures 1A and 1B are diagrams showing an overview of a teaching material providing system including a teaching material providing device according to an embodiment.

The educational material providing system 1 according to the embodiment is a system that generates and provides educational material videos related to traffic safety using, for example, driving footage collected from vehicles. The educational material providing system 1 can collect driving footage from multiple vehicles, including, for example, transportation vehicles in the transportation industry and commercial vehicles, and generate and provide educational material videos for in-house traffic safety education.

As shown in FIG. 1A, the educational material provision system 1 according to this embodiment includes an educational material provision device 10, in-vehicle devices 100-1, 100-2, etc. mounted on vehicles V-1, V-2, etc., respectively, and a terminal device 200 (see FIG. 1B). In the following description, when vehicles V-1, V-2 and in-vehicle devices 100-1, 100-2 are not to be distinguished from one another, they will be referred to as "vehicle V" and "in-vehicle device 100," respectively.

The learning material providing device 10 is a server that performs various processes, such as providing learning material videos. For example, the learning material providing device 10 is configured as a cloud server that provides cloud services via a network such as the Internet or a mobile phone network.

The in-vehicle device 100 is a device that includes various sensors, such as a camera sensor, an acceleration sensor, and a GPS (Global Positioning System) sensor, as well as a storage device and a microcomputer. The in-vehicle device 100 has a communication function that enables communication via a network. Note that the in-vehicle device 100 may be, for example, a drive recorder.

The camera sensor described above can, for example, capture images of the surroundings of the vehicle V and output video data. Note that video data is an example of video data. Video data is not limited to video data and may include still image data, etc. Furthermore, the acceleration sensor detects the acceleration acting on the vehicle V, and the GPS sensor detects the position of the vehicle V.

The terminal device 200 (see Figure 1B) is a device used by Driver A, the training recipient. The terminal device 200 has a communication function for communicating via a network. The terminal device 200 may be, for example, a notebook PC (Personal Computer), a desktop PC, a smartphone, or a tablet device, but is not limited to these. Driver A is an example of a training recipient.

Incidentally, for example, as part of in-house training at companies and other organizations, there are efforts to provide education on traffic safety by using dangerous driving footage captured by the in-vehicle device 100 (drive recorder) as educational footage. Dangerous footage includes, for example, footage of near misses and traffic accidents.

Near-miss footage is footage of an event that may be a precursor to a traffic accident. For example, near-miss footage could be footage of a situation where the vehicle in front suddenly stops while the vehicle is traveling with insufficient distance between them, causing the vehicle to approach the vehicle in front, or footage of a situation where the vehicle is speeding and entering an intersection, causing the distance between the vehicle and another vehicle (such as an oncoming vehicle or a vehicle in front) to become extremely short.

Traffic accident footage is, for example, footage of a traffic accident occurring. For example, traffic accident footage could be footage of a vehicle colliding with a vehicle ahead because the vehicle ahead suddenly stops while the vehicle is traveling with insufficient distance between them, or footage of a vehicle speeding when entering an intersection and colliding with another vehicle.

However, if the above-mentioned dangerous footage were provided uniformly to multiple trainees (drivers), the educational effectiveness of the educational footage could be reduced for some trainees (drivers). For example, suppose Driver A tends to maintain a sufficient distance from the vehicle ahead, and is provided with educational footage (dangerous footage) of the above-mentioned incident occurring while driving with an insufficient distance from the vehicle ahead. In this case, the trainee (driver) rarely encounters situations where he or she does not maintain a sufficient distance from the vehicle ahead, resulting in wasted training. Furthermore, if a driver (trainee) tends to maintain a sufficient distance from the vehicle ahead, Driver A may perceive the educational footage (dangerous footage) of the above-mentioned incident occurring while driving with an insufficient distance from the vehicle ahead as something that does not concern him or her because it is different from his or her usual driving style, resulting in a reduced educational effectiveness of the educational footage for Driver A. Conversely, for example, if Driver A tends to frequently enter intersections at excessive speeds, Driver A will perceive the footage of the incident that occurred when entering an intersection at excessive speeds (dangerous footage) as something that could happen to him/her, and as a result the educational effect of the educational video for Driver A will be enhanced.

The educational material providing device 10 according to this embodiment is therefore configured to provide educational material videos with high educational effectiveness tailored to the driver being trained.

The specific processing performed by the educational material providing device 10 will be described below using Figures 1A and 1B. In addition to providing educational material videos, the educational material providing device 10 also generates educational material videos. Here, it is assumed that driver A, the training target, drives vehicle V-1.

As shown in FIG. 1A, the educational material providing device 10 first collects video captured by an in-vehicle device 100, such as a drive recorder, mounted on a vehicle V (step S1). For example, the educational material providing device 10 collects video (video data) from multiple in-vehicle devices 100-1, 100-2, etc. Here, the educational material providing device 10 collects dangerous video captured by the in-vehicle device 100, but this is not limited to this, and the educational material providing device 10 may also collect video other than dangerous video.

Next, the learning material providing device 10 analyzes each of the collected videos and assigns tags (tag information) to each piece of video data based on the analysis results (step S2). Here, a tag is information that corresponds to the content of the video and indicates the characteristics of the video content. Note that, because the learning material providing device 10 collects dangerous videos, the processing of step S2 can also be said to be a process of analyzing the collected dangerous videos and assigning tags that correspond to the content of the dangerous videos obtained from the analysis results.

Tags include, for example, situation information tags, near miss tags, and traffic accident tags. Situation information tags are tags for situation information that indicate the driving situation (situation), such as "insufficient distance from the vehicle ahead," "speeding," "sudden braking," "sudden acceleration," "abrupt steering," and "running a red light." Situation information tags may also include tags for the driving situation, such as the date, time, location, and weather (e.g., sunny, rainy, snowy, etc.). Near miss tags are tags that indicate the details of events that may be precursors to traffic accidents (so-called near misses), such as "rapidly approaching a vehicle ahead," "rapidly approaching another vehicle at an intersection," and "rapidly approaching a pedestrian at an intersection." Traffic accident tags are tags that indicate the details of a traffic accident, such as "contact with a vehicle ahead," "contact with another vehicle at an intersection," and "contact with a pedestrian at an intersection." While specific examples of tag content have been given above, these are merely examples and are not limiting. Furthermore, the tags do not need to include all of the situation information tags, near miss tags, and traffic accident tags described above; they may include some of them, or may include tags other than those listed above.

Next, the learning material providing device 10 generates learning material videos using the tagged video data (step S3). For example, the learning material providing device 10 generates learning material videos by combining the tagged video data with question information including a question statement and options corresponding to the question statement.

The question is a question about the corresponding video; in other words, it is a sentence that asks the recipient what they can read from the video (here, dangerous video) in traffic safety education. The options are multiple options, each with at least one correct answer, and are selected by the recipient.

For example, the learning material providing device 10 can generate question information based on tags assigned to video data. As an example, if the situation information tag of the video data is "insufficient distance from the vehicle ahead" and the near-miss tag is "rapid approach to the vehicle ahead," the learning material providing device 10 generates a question statement containing the content of the tag (here, the near-miss tag), such as "What is the cause of the 'rapid approach to the vehicle ahead' in the video?" The learning material providing device 10 also generates answer choices consisting of a correct answer containing the content of the tag (here, the situation information tag), such as "The cause is 'insufficient distance from the vehicle ahead'," and an arbitrarily set incorrect answer. The learning material providing device 10 then combines the generated question statement and answer choices with the video as question information to generate a learning material video. The learning material providing device 10 then registers the generated learning material video in the learning material DB (database) 12b (see Figure 2).

In this way, the learning material providing device 10 according to this embodiment generates learning material videos in advance. Note that, although the learning material providing device 10 generates the question information in the above description, this is not limited to this; for example, the question information may be generated by input operations by an administrator of the learning material providing device 10.

Next, the educational material providing device 10 detects attribute information of the training subject (here, driver A) (step S4). The attribute information includes, for example, driving tendency attributes that indicate driver A's driving tendencies. Details of the attribute information will be described later using Figure 5.

The educational material providing device 10 detects attribute information (e.g., driving tendency attributes) based on video captured by an in-vehicle device 100-1 mounted on a vehicle V-1 driven by driver A, for example.

Specifically, tags are assigned to the video data collected from the in-vehicle device 100-1 by the processing of step S2. The educational material providing device 10 detects driver A's attribute information (driving tendency attribute) based on these tags. As an example, if the video data from the in-vehicle device 100-1 is assigned a tag (situation information tag) called "speeding," the educational material providing device 10 detects that driver A's attribute information (driving tendency attribute) is a "driving tendency attribute that makes it easy to speed." Similarly, if the video data from the in-vehicle device 100-1 is assigned a tag (near miss tag) called "rapidly approaching another vehicle at an intersection," the educational material providing device 10 detects that driver A's attribute information (driving tendency attribute) is a "driving tendency attribute that makes it easy to quickly approach another vehicle at an intersection."

Next, the educational material providing device 10 selects and provides, as educational material video for driver A, video captured by the in-vehicle device 100 that corresponds to the detected attribute information (step S5). In other words, the educational material providing device 10 provides educational material video that corresponds to driver A's attribute information to driver A (or more precisely, to driver A's terminal device 200).

As an example, if driver A's attribute information (driving tendency attribute) is a "driving tendency attribute that tends to exceed the speed limit," the educational material providing device 10 selects and provides educational material video tagged with "speeding" (situation information tag) from educational material videos registered in educational material DB 12b (see FIG. 2). Similarly, if driver A's attribute information (driving tendency attribute) is a "driving tendency attribute that tends to quickly approach other vehicles at intersections," the educational material providing device 10 selects and provides educational material video tagged with "suddenly approach other vehicles at intersections" (near miss tag) from educational material videos registered in educational material DB 12b (see FIG. 2). Note that the video provided as educational material may be video captured by driver A's in-vehicle device 100-1 or may be video captured by another in-vehicle device 100-2.

Then, when an input operation to start traffic safety education is performed on the terminal device 200 to which the educational video has been provided, the educational video is displayed on the display 201, and traffic safety education is provided to Driver A by having Driver A answer the above-mentioned question information, etc.

In this way, the educational material providing device 10 according to this embodiment provides educational material video that is video of the in-vehicle device 100 according to the attribute information of the driver A, who is the training target. As a result, in this embodiment, educational material video with high educational effectiveness according to the driver A, who is the training target, can be provided. In other words, by being provided with educational material video according to the attribute information, driver A is more likely to experience the content of the educational material video happening to him/her, and as a result, the educational effectiveness of the educational material video for driver A can be improved.

In more detail, the educational material providing device 10 according to this embodiment uses attribute information (driving tendency attributes) for each driver to provide a relatively large number of educational material videos relating to situations in which Driver A is prone to fall into or things he or she is not careful about. This makes it possible to effectively educate Driver A about dangers that he or she should be particularly careful of.

In the above description, the educational material providing device 10 provides educational material videos to the terminal device 200, but this is not limited to this. In other words, if the in-vehicle device 100 (in-vehicle device 100-1) has a display, the educational material providing device 10 may provide educational material videos to the in-vehicle device 100 (in-vehicle device 100-1). This makes it possible to provide traffic safety education to driver A, for example, before (or after) driving in vehicle V-1.

<Overall configuration of the teaching material provision system>
2 is a block diagram showing an example of the configuration of the educational material providing system 1 according to the embodiment. Note that in FIG. 2, only components necessary for explaining the features of the embodiment are shown, and descriptions of general components are omitted.

In other words, the components shown in Figure 2 are conceptual functional components and do not necessarily need to be physically configured as shown. For example, the specific form of distribution and integration of each block is not limited to that shown, and all or part of them can be functionally or physically distributed and integrated in any unit depending on various loads, usage conditions, etc.

Furthermore, in the explanation using Figure 2, the explanation of components that have already been explained may be simplified or omitted.

As shown in FIG. 2, the teaching material provision system 1 according to the embodiment includes a teaching material provision device 10, an in-vehicle device 100, and a terminal device 200. Note that for simplicity of illustration, FIG. 2 shows one in-vehicle device 100 and one terminal device 200, but there may be multiple in-vehicle devices 100 and multiple terminal devices 200.

<Configuration of the in-vehicle device>
The in-vehicle device 100 includes a communication unit 101, various sensors 102, a display 103, a storage unit 104, and a control unit 105. The control unit 105 is an example of an in-vehicle device control unit.

The communication unit 101 is a communication interface that connects to the communication network N for two-way communication, and transmits and receives information between the teaching material providing device 10 and the terminal device 200, etc.

As described above, the various sensors 102 include, for example, a camera sensor, an acceleration sensor, and a GPS sensor. The camera sensor outputs captured video data to the control unit 105. The acceleration sensor outputs a signal indicating the acceleration acting on the vehicle V, and the GPS sensor outputs a signal indicating the position of the vehicle V to the control unit 105. Note that the various sensors 102 are not limited to the camera sensors and acceleration sensors described above, and may include other types of sensors, such as a microphone sensor, in addition to or instead of the camera sensors, etc.

The display 103 displays images captured by a camera sensor, etc. Furthermore, when educational material images are provided from the educational material providing device 10 as described above, the display 103 displays the provided educational material images.

The storage unit 104 is configured with a storage device such as a non-volatile memory, data flash, or hard disk drive. The storage unit 104 stores video data 104a captured by the camera sensor, various programs, and the like. Note that the video data 104a may or may not include dangerous video.

The control unit 105 includes an acquisition unit 105a, a processing unit 105b, and an output unit 105c, and includes, for example, a computer having a CPU (Central Processing Unit), ROM (Read Only Memory), RAM (Random Access Memory), input/output ports, etc., and various other circuits.

The computer's CPU functions as the acquisition unit 105a, processing unit 105b, and output unit 105c of the control unit 105, for example, by reading and executing programs stored in ROM.

Furthermore, at least some or all of the acquisition unit 105a, processing unit 105b, and output unit 105c of the control unit 105 can be configured using hardware such as an ASIC (Application Specific Integrated Circuit) or FPGA (Field Programmable Gate Array).

The acquisition unit 105a of the control unit 105 acquires the outputs of the various sensors 102. For example, the acquisition unit 105a acquires video data captured by a camera sensor and registers it as video data 104a in the memory unit 104. The acquisition unit 105a acquires a signal indicating the acceleration acting on the vehicle from the acceleration sensor and outputs it to the processing unit 105b. The acquisition unit 105a acquires a signal indicating the vehicle's position from the GPS sensor and outputs it to the processing unit 105b.

When the processing unit 105b detects, for example, sudden braking, sudden acceleration, sudden steering (abrupt steering), or an impact due to a collision accident from the output of the acceleration sensor, it stores information indicating the detected content in the memory unit 104, linking it to the video data captured at the time of detection as event information.

The processing unit 105b, based on the output of the GPS sensor, stores, for example, vehicle location information linked to video data in the storage unit 104. Furthermore, when the processing unit 105b detects excessive vehicle speeds based on the output of the GPS sensor, it stores information indicating the detected content (here, speeding) linked to the video data captured at the time of detection as event information in the storage unit 104. Specifically, the processing unit 105b calculates the vehicle's travel distance in a given travel time from the vehicle's location information output from the GPS sensor, and calculates the vehicle speed by dividing the calculated travel distance by the given travel time. The processing unit 105b then compares the calculated vehicle speed with the speed limit included in the map information for the location (place) where the vehicle is traveling, and detects excessive speeding if the vehicle speed exceeds the speed limit. The map information may be information previously stored in the storage unit 104, or information obtained from an external server (not shown). The processing unit 105b may also perform processing to prohibit overwriting of video data for a predetermined period of time before and after the detection of sudden braking, speeding, etc.

In addition, when a signal (vehicle signal) from a sensor mounted on the vehicle, such as a brake sensor, is input to the in-vehicle device 100, the processing unit 105b may detect sudden braking of the vehicle, etc., based on the vehicle signal. In more detail, the vehicle signal may be the output of a brake sensor, accelerator sensor, steering angle sensor, vehicle speed sensor, etc., and the processing unit 105b may detect sudden braking, sudden acceleration, abrupt steering, speeding, etc., of the vehicle based on the vehicle signal.

The output unit 105c transmits the captured video (video data) to the learning-material providing device 10 via the communication unit 101. For example, the output unit 105c may transmit video data linked to event information such as sudden braking to the learning-material providing device 10. In other words, video data linked to event information such as sudden braking or speeding is presumed to be dangerous video data, including near-miss video and traffic accident video. Therefore, when the output unit 105c transmits video data linked to event information, the learning-material providing device 10 can collect dangerous video. The timing of transmitting the video data may be, for example, the timing when event information is linked to the video data, the timing when a request to transmit the video data is received from the learning-material providing device 10, or any other timing.

Furthermore, when educational video is provided (transmitted) from the educational video providing device 10, the output unit 105c receives the educational video via the communication unit 101. The output unit 105c then outputs and displays the received educational video on the display 103, providing it to the driver. As already mentioned, this makes it possible to provide traffic safety education within the vehicle V.

<Configuration of the teaching material providing device>
Next, a description will be given of the configuration of the learning material providing device 10. As shown in FIG.

The communication unit 11 is a communication interface that connects to the communication network N for two-way communication, and transmits and receives information between the in-vehicle device 100, the terminal device 200, etc.

The memory unit 12 is composed of a storage device such as a non-volatile memory, data flash, or hard disk drive. The memory unit 12 includes a video DB 12a, a teaching material DB 12b, and a driver DB 12c.

Video DB 12a stores information related to videos. Here, we will explain video DB 12a using Figure 3. Figure 3 is a diagram showing an example of video DB 12a.

As shown in Figure 3, video DB 12a includes items such as "Video ID," "Driver ID," "Video," "Date and Time," "Location," and "Event," with data for each item associated with the "Video ID." In other words, corresponding data such as "Video" and "Date and Time" are stored in a data record identified by a "Video ID."

"Video ID" is identification information that identifies the video data. "Driver ID" is identification information that identifies the driver. For example, "Driver ID" includes information about the driver of the vehicle V that is equipped with the in-vehicle device 100 that captured the corresponding video data.

"Video" is video data captured by the in-vehicle device 100. Note that in the example shown in Figure 3, for convenience, "video" is abstractly described as "C1," but specific information is stored in "C1." Below, other information may also be abstractly described.

"Date and time" is information indicating the date and time when the corresponding video was captured. "Location" is information indicating the location (place) where the corresponding video was captured.

"Event" is information related to an event that occurred in the corresponding video; more specifically, it is event information related to an event (phenomenon) that occurred while the video was being captured. As described above, event information is linked to video data by the in-vehicle device 100. Therefore, information indicating, for example, sudden braking, sudden acceleration, abrupt steering, a collision, speeding, etc. is registered in "Event."

In the example shown in Figure 3, the video data identified by video ID "A01" is video data captured while the driver identified by driver ID "B01" was driving, and indicates that the video is "C1," the date and time is "D1," the location is "E1," and the event is "F1."

Returning to the explanation of Figure 2, the teaching material DB 12b stores information about teaching material videos. Here, we will explain the teaching material DB 12b using Figure 4. Figure 4 is a diagram showing an example of the teaching material DB 12b.

As shown in Figure 4, the learning material DB 12b contains items such as "learning material ID," "video ID," "driver ID," "situation information tag," "near miss tag," "traffic accident tag," and "problem information," and data for each item is associated with a "learning material ID." In other words, corresponding data such as "situation information tag" and "near miss tag" is stored in a data record identified by a "learning material ID."

The "teaching material ID" is identification information that identifies the teaching material video. The "video ID" is identification information that identifies the video data, and more specifically, is identification information that identifies the video data set as the teaching material video. In this way, by registering the "video ID" in the teaching material DB 12b, the teaching material video identified by the "teaching material ID" is linked (associated) with the video data in the video DB 12a by the "video ID."

The "driver ID" is identification information that identifies the driver, and more specifically, the identification information of the driver of the vehicle V (more precisely, the in-vehicle device 100) that captured the video data set as the educational video. In this way, by registering the "driver ID" in the educational video DB 12b, the educational video identified by the "educational video ID" is linked (associated) with the driver data in the video DB 12a and the driver DB 12c by the "driver ID."

"Situation information tag" is information related to the situation information tag described above, and more specifically, information related to the tag of the driving situation when the video set as the educational video was captured (situation information tag). Tags registered as "situation information tag" include, for example, "insufficient distance from the vehicle ahead," "excessive speed," "sudden braking," "sudden acceleration," "abrupt steering," and "running a red light." Note that the number of tags registered as "situation information tag" may be one or more.

"Near miss tag" is information related to the near miss tag mentioned above, and more specifically, information related to the tag of a near miss that occurred while driving when the video set as the educational video was captured. Tags such as "rapid approach to a vehicle ahead," "rapid approach to another vehicle at an intersection," and "rapid approach to a pedestrian at an intersection" are registered in the "Near miss tag." The number of tags registered in the "Near miss tag" may be one or more.

"Traffic accident tag" is information related to the traffic accident tag mentioned above, and more specifically, information related to the tag of a traffic accident that occurred while driving and resulted in the video set as the educational video. Tags such as "contact with a vehicle ahead," "contact with another vehicle at an intersection," and "contact with a pedestrian at an intersection" are registered as "traffic accident tags." Note that the number of tags registered as "traffic accident tags" may be one or more. Furthermore, since near misses are events that may be precursors to traffic accidents, either a "near miss tag" or a "traffic accident tag" will be registered for each educational video, but this is not limited to this.

These "near miss tags" and "traffic accident tags" allow the educational videos in video DB 12a to be classified according to the level of risk associated with driving a vehicle. In other words, because near misses are events that are precursors to traffic accidents, the level of risk associated with driving a vehicle is lower than the level of risk associated with traffic accidents. Conversely, the level of risk associated with traffic accidents is higher than the level of risk associated with near misses. Therefore, by assigning "near miss tags" and "traffic accident tags" to educational videos, the educational videos can be classified according to the level of risk associated with driving a vehicle.

"Question information" is information about questions provided to the training recipient (driver), and more specifically, is information about questions that are combined with video set as educational video. "Question information" includes information indicating the question statement and information indicating the options corresponding to the question statement.

In the example shown in Figure 4, the educational video data identified by educational video ID "J01" indicates that the video data identified by video ID "A01" has been set as educational video, and that this educational video is video captured while the driver identified by driver ID "B01" was driving. Furthermore, the educational video data identified by educational video ID "J01" indicates that the situation information tag is "K1", the near-miss tag is "L1", and the problem information is "N1".

Furthermore, the educational material video data identified by educational material ID "J02" has a corresponding video ID of "A02", a corresponding driver ID of "B02", a situation information tag of "K2", a traffic accident tag of "M2", and question information of "N2".

Returning to the explanation of Figure 2, driver DB 12c stores information about drivers. For example, driver DB 12c stores attribute information about drivers. Here, driver DB 12c will be explained using Figure 5. Figure 5 is a diagram showing an example of driver DB 12c.

As shown in Figure 5, driver DB12c includes items such as "driver ID," "driving tendency attribute," "driving area attribute," "age attribute," and "affiliation attribute," with data for each item associated with the "driver ID." In other words, corresponding data such as "driving tendency attribute" and "driving area attribute" is stored in a data record identified by the "driver ID."

"Driver ID" is identification information that identifies the driver. "Driving tendency attributes" is attribute information that indicates the driver's driving tendencies. Note that driving tendencies may also include near miss experiences and accident experiences.

The "driving tendency attribute" registers driving tendency attribute information such as "tends to keep insufficient distance from the vehicle ahead," "tends to exceed the speed limit," "tends to brake suddenly," "tends to accelerate suddenly," "tends to steer sharply," and "tends to run red lights." If the driver has experienced a near miss, the "driving tendency attribute" registers driving tendency attribute information such as "tends to quickly approach the vehicle ahead," "tends to quickly approach other vehicles at intersections," and "tends to quickly approach pedestrians at intersections." If the driver has experienced an accident, the "driving tendency attribute" registers driving tendency attribute information such as "collided with the vehicle ahead," "collided with other vehicles at intersections," and "collided with pedestrians at intersections." The above-mentioned driving tendency attribute information is registered, for example, from information (event information) contained in the video data of the in-vehicle device 100 or detected by video analysis (more precisely, detected based on tags), as will be described later.

"Driving area attributes" are information indicating attributes related to the area in which the driver drives the vehicle. Driving areas include, for example, routes and regions frequently traveled by the driver's vehicle, but are not limited to these. Note that "driving area attributes" may be registered based on information (location information) included in the video data of the in-vehicle device 100, or may be registered through input operations by the driver, administrator, etc.

The "age attribute" is information that indicates the attribute that indicates the driver's age. For example, the "age attribute" may register information that classifies the driver's age by age group, such as "20s" or "30s," but is not limited to this.

"Affiliation attribute" is information that indicates the attributes that indicate the affiliation of the driver. For example, "Affiliation attribute" may include, but is not limited to, information such as the company the driver belongs to, the group the driver belongs to, or the school the driver belongs to. Furthermore, the above-mentioned "age attribute" and "affiliation attribute" are registered by input operations by the driver, manager, etc., but are not limited to these.

In the example shown in Figure 5, the data for the driver identified by driver ID "B01" indicates that the driving tendency attribute is "P1", the driving area attribute is "Q1", the age attribute is "R1", and the affiliation attribute is "T1". Note that in the example shown in Figure 5, the data for the driver identified by driver ID "B03" does not have any driving tendency attribute information registered. This indicates that no driving tendency attribute information was detected for the driver with driver ID "B03", or in other words, it was not possible to detect driving tendency attribute information; this will be discussed later.

Returning to the explanation of Figure 2, the control unit 13 includes a collection unit 13a, an analysis unit 13b, a generation unit 13c, a detection unit 13d, and a provision unit 13e, and includes, for example, a computer having a CPU, ROM, RAM, a hard disk drive, input/output ports, etc., and various circuits. The computer's CPU, for example, reads and executes various programs stored in ROM, thereby functioning as the collection unit 13a, analysis unit 13b, generation unit 13c, detection unit 13d, and provision unit 13e of the control unit 13. The various programs include the teaching material provision program according to this embodiment.

Furthermore, at least some or all of the collection unit 13a, analysis unit 13b, generation unit 13c, detection unit 13d, and provision unit 13e of the control unit 13 can be configured using hardware such as an ASIC or FPGA.

The collection unit 13a collects video (including dangerous video) captured by the in-vehicle devices 100 and registers the collected video (video data) in the video DB 12a. Furthermore, if the video data includes information on the date and time the video was captured, location information, and event information, the collection unit 13a registers this information in the video DB 12a. Furthermore, the collection unit 13a collects video from multiple in-vehicle devices 100, i.e., collects multiple videos, but this is not limited to this.

The analysis unit 13b analyzes the collected and input video and assigns tags to the video data based on the analysis results. The tags assigned here include the situation information tags, near miss tags, and traffic accident tags described above.

Specifically, for example, if the collected video data contains event information such as "sudden braking," "sudden acceleration," "abrupt steering," or "speeding," the analysis unit 13b assigns such event information as a situation information tag. Furthermore, if the video analysis detects, for example, "insufficient distance from the vehicle ahead" or "running a red light," the analysis unit 13b assigns the detected information as a situation information tag. Furthermore, if the video data contains information such as "date and time" and "location," the analysis unit 13b assigns the information as a situation information tag. Furthermore, if the video analysis detects, for example, the weather during driving, the analysis unit 13b assigns the detected information (for example, sunny, rainy, snowy, etc.) as a situation information tag. Furthermore, if the video analysis detects, for example, "sudden approach to a vehicle ahead," "sudden approach to another vehicle at an intersection," or "sudden approach to a pedestrian at an intersection," the analysis unit 13b assigns the detected information as a near miss tag. Furthermore, if the analysis unit 13b detects, for example, "contact with a vehicle ahead," "contact with another vehicle at an intersection," or "contact with a pedestrian at an intersection" based on event information in the video data or video analysis, it assigns the detected content as a traffic accident tag. The analysis unit 13b then associates the tag with the video data to which it has been assigned and registers it in the teaching material DB 12b.

The generation unit 13c generates educational video using the tagged video data. More specifically, the generation unit 13c generates question information using the tags and combines the question information with the video to generate the educational video. The generation unit 13c associates the question information with the video data corresponding to the question information and registers them in the educational video DB 12b.

For example, the generation unit 13c generates question information based on tags. Specifically, the generation unit 13c generates question sentences and answer choices using the content (wording) contained in the situation information tag, near-miss tag, and traffic accident tag of the video data. The generation unit 13c then combines the question information, including the question sentences and answer choices, with the video to generate the educational video.

In this way, the educational material providing device 10 according to this embodiment collects multiple videos, including dangerous videos, from the in-vehicle device 100, generates multiple educational material videos using the collected videos, and pre-stores the multiple generated educational material videos in the educational material DB 12b. This makes it possible for this embodiment to accommodate, for example, cases where the attribute information of the driver being trained varies widely, i.e., it becomes possible to provide educational material videos according to the attribute information.

The detection unit 13d detects attribute information of the driver who is the training target. For example, the detection unit 13d detects driving tendency attribute information that indicates the driver's driving tendencies as attribute information. Note that driving tendency attribute information is an example of driving tendency information.

Specifically, the detection unit 13d searches the teaching material DB 12b for video captured by the in-vehicle device 100 of the vehicle V driven by the driver (trainee), for example, and checks the tags attached to the corresponding video data. The detection unit 13d then detects driving tendency attribute information based on the tags attached to the video data corresponding to the driver (trainee). As an example, if the video data corresponding to the driver is attached with a tag (situation information tag) of "insufficient distance from preceding vehicle," the detection unit 13d detects that the driver's driving tendency attribute is "driving tendency attribute that tends to keep insufficient distance from preceding vehicle." The detection unit 13d registers the detected driving tendency attribute information in the "driving tendency attribute" of the driver DB 12c.

Note that the number of pieces of attribute information detected here may be one or multiple. In other words, if multiple tags are attached to the video data, the number of pieces of attribute information will be multiple depending on the tags.

In addition, the detection unit 13d detects (identifies) the driving area of the corresponding driver based on the location information included in the video data, and registers information indicating the detected driving area (driving area attribute information) in the "driving area attribute" field of the driver DB 12c.

In this way, the detection unit 13d according to this embodiment detects attribute information based on video captured by the in-vehicle device 100 installed in the vehicle V driven by the driver. This makes it possible to easily and accurately detect the driver's attribute information.

Here, there are cases where the video data of the driver (trainee) is not registered in the teaching materials DB 12b. That is, the video data may not be registered in the teaching materials DB 12b for reasons such as the absence of dangerous video in the in-vehicle device 100 of the vehicle V driven by the driver (trainee), so video data is not collected, or the training recipient has not driven during the specified video collection period, so video data is not collected. In such cases, the detection unit 13d cannot detect driving tendency attributes from the video data, so it does not register "driving tendency attribute information" in the driver DB 12c. In other words, it processes the data as if it were impossible to detect driving tendency attribute information for the driver (trainee).

The provision unit 13e provides educational video to the driver (trainee) based on the driver's attribute information. For example, the provision unit 13e provides the driver with video captured by the in-vehicle device 100 as educational video, which video corresponds to the detected driver's attribute information. In other words, the provision unit 13e provides the driver with educational video that is in line with the driver's attribute information.

As a result, in this embodiment, it is possible to provide educational videos with a high educational effect that are tailored to the driver (the person being educated). In other words, by being provided with educational videos tailored to the driver's attributes, the driver is more likely to perceive the content of the educational video as something that could happen to them, which in turn makes them more likely to perceive it as something that could happen to them, thereby improving the educational effect of the educational video for the driver.

Specifically, the providing unit 13e provides, as educational video, video corresponding to driving tendency information, which is one type of attribute information. For example, the providing unit 13e searches the educational video DB 12b based on the driver's driving tendency attribute information, and selects and provides educational video corresponding to the driving tendency attribute information. As one example, if the driver's driving tendency attribute is a "driving tendency attribute that tends to keep a short distance from the vehicle ahead," the providing unit 13e searches the educational video DB 12b based on this driving tendency attribute, and selects and provides educational video that has been tagged with a "short distance from the vehicle ahead" tag (situation information tag). This allows the providing unit 13e to provide educational video that is highly effective in education and is in line with the driving tendencies of the driver (trainee).

Here, we will explain the educational video provided to the driver (trainee) with reference to Figure 6. Figure 6 is a diagram showing the display 201 of the terminal device 200 to which the educational video is provided.

As shown in FIG. 6, the providing unit 13e provides educational video to the terminal device 200 and displays it in the display field 300 of the display 201. The educational video includes video (dangerous video) 310 captured by the in-vehicle device 100 and question information 320. The question information 320 includes a display field 321 in which a question statement is displayed and a display field 322 in which options are displayed. Traffic safety education is then provided to the driver (the person being educated) by having them select an option and answer the question.

Continuing with the explanation of Figure 2, as described above, the provision unit 13e provides, as educational video, video to which tag information (e.g., situation information tag, near miss tag, traffic accident tag) corresponding to attribute information (e.g., driving tendency attribute information) has been assigned. Specifically, tags are assigned in advance to the video in the in-vehicle device 100, and the provision unit 13e selects and provides educational video from the educational video DB 12b based on the attribute information and the tag corresponding to the attribute information. More specifically, the provision unit 13e selects and provides educational video in which the attribute information matches the tag corresponding to the attribute information. This allows the provision unit 13e to reliably and accurately select and provide video that corresponds to the driver's attribute information.

The providing unit 13e also provides educational video with a risk level corresponding to the attribute information. That is, the educational video includes near miss videos and traffic accident videos, and the educational video is classified according to the risk level of vehicle driving as described above. When the attribute information (e.g., driving tendency attribute information) includes information with a lower risk level than traffic accidents (e.g., information related to near misses, such as "prone to suddenly approaching a vehicle ahead"), the providing unit 13e selects and provides educational video with a risk level corresponding to the attribute information (i.e., educational video with a near miss tag attached). Similarly, when the attribute information (driving tendency attribute information) includes information with a higher risk level than near misses (e.g., information related to traffic accidents, such as "collided with a vehicle ahead"), the providing unit 13e selects and provides educational video with a risk level corresponding to the attribute information (i.e., educational video with a traffic accident tag attached).

As a result, in this embodiment, it is possible to provide educational videos that are in line with the driving risk level contained in the driver's attribute information, thereby further improving the educational effect of the educational videos on drivers.

The providing unit 13e may also provide, as educational video, video corresponding to situational information indicating the vehicle driving situation of the driver (trainee). Incidentally, the situational information may include, but is not limited to, information such as the vehicle's position during driving, weather, speed, date and time, etc.

For example, if the situation information tag of the video data corresponding to the driver (trainee) includes situation information such as vehicle position, weather, speed, date and time, the providing unit 13e provides video corresponding to such situation information as educational video. In more detail, if the video data of the driver (trainee) includes situation information, the providing unit 13e selects and provides educational video (for example, video (dangerous video) captured by a driver other than the driver (trainee)) that has been assigned a situation information tag that also corresponds to such situation information.

As a result, in this embodiment, educational video can be provided that corresponds to the situation in which the driver (trainee) drove in the past and video (dangerous video) was captured, thereby further improving the educational effect of the educational video on the driver.

Furthermore, as mentioned above, there are cases where it is impossible to detect driving tendency attribute information for a driver (trainee). In such cases, the providing unit 13e provides, as educational video, video selected corresponding to a similar driver who has attribute information similar to that of the driver (trainee).

For example, for a driver for whom driving tendency attribute information has not been detected, the providing unit 13e identifies a similar driver who has similar at least one of the "driving area attribute," "age attribute," and "affiliation attribute" attributes from the driver's attribute information. The providing unit 13e then selects video (dangerous video) from the in-vehicle device 100 of the identified similar driver and provides it as educational video. Note that the similarity of attribute information described above includes, but is not limited to, cases where the entire content of the attribute information matches, cases where only part of the content matches, and cases where the content of the attribute information is within a predetermined tolerance range. The predetermined tolerance range can be set arbitrarily.

As a result, in this embodiment, even if driving tendency attribute information is not detected, it is possible to provide educational video with a high educational effect tailored to the driver (trainee). In other words, a driver (trainee) for whom driving tendency attribute information is not detected is provided with educational video (dangerous video) of a similar driver with relatively similar attribute information (e.g., driving area, age, affiliation, etc.). This means that the driver (trainee) will likely perceive the content of the educational video as something that could happen to them, thereby improving the educational effect of the educational video for the driver.

Note that the providing unit 13e provides the educational video to the terminal device 200, but this is not limited to this. In other words, the providing unit 13e may also provide the educational video to the in-vehicle device 100 of the driver (trainee).

<Control process of the teaching material providing device>
Next, an example of a specific processing procedure in the educational material providing device 10 will be described with reference to Fig. 7. Fig. 7 is a flowchart showing the processing procedure executed by the educational material providing device 10. Note that, in the following, an example will be described in which the number of educational material videos provided to the driver (hereinafter referred to as "prescribed number") is three (three types), but the present invention is not limited to this, and the prescribed number can be set arbitrarily.

As shown in FIG. 7, the control unit 13 of the teaching material providing device 10 collects video from the in-vehicle device 100 of the vehicle V (step S10). Next, the control unit 13 analyzes the collected video and assigns tags to the video data based on the analysis results (step S11).

The control unit 13 then generates a teaching material video using the tagged video data (step S12). For example, the control unit 13 generates the teaching material video by combining question information with the tagged video data. The control unit 13 then registers the generated teaching material video in the teaching material DB 12b.

Next, the control unit 13 detects attribute information of the driver to be trained (step S13). For example, the control unit 13 detects attribute information (e.g., driving tendency attributes) based on video captured by the in-vehicle device 100 of the vehicle V driven by the driver (trainee).

Next, the control unit 13 determines whether there is any educational video that corresponds to the attribute information of the driver (trainee) (step S14). In other words, the processing of step S14 is a process in which driving tendency attribute information is detected in the driver's attribute information, and whether there is any educational video that corresponds to the detected driving tendency attribute information.

If the control unit 13 determines that there is no educational video corresponding to the attribute information (e.g., driving tendency attribute) (step S14, No), in other words, if it is unable to detect driving tendency attribute information, it selects educational video corresponding to similar drivers who have attribute information similar to that of the driver (trainee) for the number that is insufficient compared to the specified number (step S15). As mentioned above, since the specified number is three, three educational video clips are selected here.

On the other hand, if the control unit 13 determines that there is educational video corresponding to the attribute information (e.g., driving tendency attribute) (step S14, Yes), in other words, if driving tendency attribute information is detected, it selects as educational video the video that corresponds to the detected attribute information (driving tendency attribute) and that was captured by the in-vehicle device 100 (step S16).

When selecting educational videos, the control unit 13 may select educational videos in descending order of the number of detected attribute information (driving tendency attributes) (i.e., the number of detections). As an example, if information indicating attribute contents a, b, c, and d is detected five times, three times, two times, and once respectively in the attribute information, videos corresponding to attribute contents a, b, and c in descending order of the number of detections may be selected as educational videos. Examples of the attribute contents a, b, c, and d mentioned above include "tends to keep insufficient distance from the vehicle ahead," "tends to approach the vehicle ahead suddenly," and "collisions with the vehicle ahead."

Next, the control unit 13 determines whether the specified number of educational videos have been selected (step S17). If the control unit 13 determines that the specified number of educational videos have not been selected (step S17, No), the control unit 13 proceeds to step S15 and selects educational videos corresponding to similar drivers for the number that is short of the specified number. That is, for example, the control unit 13 selects one educational video corresponding to a similar driver if there is one short of the specified number, and selects two educational videos corresponding to similar drivers if there are two short of the specified number.

Then, the control unit 13 provides the educational video selected in steps S15 and S16 to the driver (step S18). On the other hand, if the control unit 13 determines that the specified number of educational videos have been selected (step S17, Yes), it proceeds to step S18 and provides the educational video selected in step S16 to the driver.

As described above, the educational material providing device 10 according to the embodiment has a control unit 13. The control unit 13 detects attribute information indicating the attributes of the educational recipient, and provides the educational material video to the educational recipient, which video corresponds to the detected attribute information and is captured by the in-vehicle device 100. This makes it possible to provide educational material video with high educational effectiveness.

The educational video generated in the above-described embodiment may be masked to conceal vehicle license plates, people, etc. that appear in the video, for example, for the purpose of protecting personal information. Masking is a process in which areas of vehicle license plates or people in the video are filled in or pixelated. This makes it possible, for example, to repurpose the generated educational video for educational video from other companies, thereby improving the versatility of the educational video.

Further advantages and modifications may readily occur to those skilled in the art. Therefore, the invention in its broader aspects is not limited to the specific details and representative embodiments shown and described above. Accordingly, various modifications may be made without departing from the spirit or scope of the general inventive concept as defined by the appended claims and their equivalents.

REFERENCE SIGNS LIST 1 Teaching material providing system 10 Teaching material providing device 13 Control unit 100 In-vehicle device 105 Control unit

Claims (9)

A teaching material providing device that provides a vehicle driving video captured by an in-vehicle device to a training target ,
Detecting a driving risk level from attribute information of the training recipient;
providing the training subject with a training video corresponding to the detected driving risk level from among a plurality of training video clips obtained by classifying the vehicle driving video clips according to driving risk levels ;
A teaching material providing device having a control unit . The control unit
detecting the attribute information based on an image captured by an in-vehicle device mounted on a vehicle driven by the training target person;
The teaching material providing device according to claim 1 . The control unit
detecting driving tendency information indicating the driving tendency of the training recipient as the attribute information;
providing a video according to the detected driving tendency information as the educational video;
3. The teaching material providing device according to claim 1. The control unit
If the driving tendency information of the training target cannot be detected, a video selected corresponding to a similar driver having the attribute information similar to that of the training target is provided as the training video.
4. The teaching material providing device according to claim 3. The control unit
providing, as the educational video, a video corresponding to situation information indicating a driving situation of the vehicle;
5. The teaching material providing device according to claim 1. The control unit
Add tag information to the input video according to the content of the video,
providing a video to which the tag information corresponding to the attribute information is assigned as the teaching material video;
6. The teaching material providing device according to claim 1. An in-vehicle device having an in-vehicle device control unit,
The in-vehicle device control unit
The captured image is transmitted to the educational material providing device,
receiving, from the educational material providing device, a video corresponding to the driving risk level detected from the attribute information of the training recipient as a training material video for the training recipient and providing the video to the training recipient;
In-vehicle device. A teaching material providing method executed by a teaching material providing device,
Detect driving risk from the attribute information of the training target,
providing the training subject with a training video corresponding to the detected driving risk level from among a plurality of training video images obtained by classifying vehicle driving videos captured by an in-vehicle device according to driving risk level ;
Method of providing teaching materials. On the computer,
Detect driving risk from the attribute information of the training target,
providing the training subject with a training video corresponding to the detected driving risk level from among a plurality of training video images obtained by classifying vehicle driving videos captured by an in-vehicle device according to driving risk level ;
A program that provides instructional materials to help you carry out the steps.