JP2023092354A - Teaching material providing device, in-vehicle device, teaching material providing method and teaching material providing program - Google Patents

Abstract

To provide a teaching material provision device, an in-vehicle device, a method for manufacturing a teaching material, and a teaching material provision program that can provide a teaching material picture with a high teaching effect.SOLUTION: The teaching material provision device according to an embodiment has a control unit. The control unit detects attribute information showing the attribute of a teaching target person, and provides a picture according to the detected attribute information taken by an in-vehicle device, as a material picture for the teaching target person.SELECTED DRAWING: Figure 1B

Description

TECHNICAL FIELD The present invention relates to a teaching material providing apparatus, a vehicle-mounted apparatus, a teaching material providing method, and a teaching material providing program.

2. Description of the Related Art Conventionally, various techniques have been proposed that use video images of vehicle driving captured by a camera as educational materials for traffic safety education (see, for example, Patent Document 1).

JP 2015-219497 A

However, in the conventional technology, educational material videos generated by the administrator are uniformly provided to the persons to be educated, so there is a possibility that the educational effect of the educational material images may be lowered depending on the persons to be educated. In other words, the conventional technology has room for improvement in terms of providing teaching material videos with a high educational effect.

SUMMARY OF THE INVENTION It is an object of the present invention to provide a teaching material providing apparatus, an in-vehicle apparatus, a teaching material providing method, and a teaching material providing program capable of providing educational videos with a high educational effect.

In order to solve the above problems and achieve the object, the present invention has a control section in a teaching material providing apparatus. The control unit detects attribute information indicating an attribute of a person to be educated, and provides an image corresponding to the detected attribute information, which is captured by an in-vehicle device, as a teaching material image to the person to be educated.

According to the present invention, it is possible to provide teaching material videos with a high educational effect.

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

Embodiments of a teaching material providing device, a vehicle-mounted device, a teaching material providing method, and a teaching material providing program disclosed in the present application will be described in detail below with reference to the accompanying drawings. In addition, this invention is not limited by embodiment shown below.

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

The teaching material providing system 1 according to the embodiment is a system that generates and provides teaching material videos related to traffic safety using, for example, driving videos collected from vehicles. The teaching material providing system 1 can collect driving videos from a plurality of vehicles including, for example, transportation vehicles in the transportation industry and business vehicles, and generate and provide teaching materials videos for in-house traffic safety education. be.

As shown in FIG. 1A, a teaching material providing system 1 according to the present embodiment includes a teaching material providing device 10, vehicle-mounted devices 100-1, 100-2, . terminal device 200 (see FIG. 1B). In the following, when the vehicles V-1 and V-2 and the in-vehicle devices 100-1 and 100-2 are not distinguished from each other, they are referred to as "vehicle V" and "vehicle device 100" respectively. do.

The teaching material providing device 10 is a server that executes various processes such as a process of providing teaching material videos. For example, the educational material providing apparatus 10 is configured as a cloud server that provides cloud services via networks such as the Internet and mobile phone networks.

The in-vehicle device 100 is a device having various sensors such as a camera sensor, an acceleration sensor, a GPS (Global Positioning System) sensor, a storage device, a microcomputer, and the like. The in-vehicle device 100 has a communication function of communicating via a network. A drive recorder, for example, can be used as the in-vehicle device 100 .

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

A terminal device 200 (see FIG. 1B) is a device used by a driver A who is a subject of education. The terminal device 200 has a communication function of communicating via a network. As the terminal device 200, for example, a notebook PC (Personal Computer), a desktop PC, a smart phone, a tablet terminal, or the like can be used, but the terminal device 200 is not limited to these. Driver A is an example of a person to be educated.

By the way, for example, as part of in-house training at a company, there is an approach to provide education on traffic safety by using dangerous images of vehicle driving captured by the in-vehicle device 100 (drive recorder) as teaching materials. Danger videos include, for example, near-miss videos and traffic accident videos.

A near-miss video is a video of an event that may be a sign of a traffic accident, for example. As an example of a near-miss image, there is an image when the vehicle in front suddenly stops while the vehicle ahead is traveling with insufficient inter-vehicle distance, and the vehicle suddenly approaches the vehicle in front. For example, a video of a vehicle entering an intersection due to excessive speed and the inter-vehicle distance from other vehicles (an oncoming vehicle, a vehicle in front, etc.) becomes extremely short.

A traffic accident video is, for example, a video when a traffic accident occurs. For example, traffic accident images include images of when the vehicle in front of the vehicle comes to a sudden stop while driving with insufficient inter-vehicle distance between the vehicle and the vehicle in front, causing the vehicle to collide with the vehicle in front. For example, a video of a vehicle speeding into an intersection and colliding with another vehicle.

However, if, for example, the dangerous images described above are uniformly provided to a plurality of persons (drivers) to be educated as educational images, the educational effect of the educational images decreases depending on the persons (drivers) to be educated. I was afraid. That is, for example, when the driver A tends to drive with a sufficient inter-vehicle distance to the vehicle in front, an educational video ( dangerous video). In this case, it is rare that the person to be educated (driver) does not keep the distance between the vehicles, so the education is wasteful. In addition, if the driver (educated person) has a driving tendency to keep a distance between the vehicles, the driver A wakes up while driving in a state where the distance between the vehicles in front is insufficient as described above. Since the educational video of the event (dangerous video) is different from the driver's usual driving, he may feel that it is someone else's problem, and as a result, the educational effect of the educational video for the driver A is reduced. Conversely, for example, if Driver A has a driving tendency to frequently enter an intersection at excessive speed, Driver A will display a video of the event that occurred when he entered the intersection at excessive speed (dangerous As a result, the educational effect of the teaching material images for the driver A increases.

Therefore, the teaching material providing apparatus 10 according to the present embodiment is configured to be able to provide teaching material images with high educational effect according to the driver to be educated.

Specific processing in the educational material providing apparatus 10 will be described below with reference to FIGS. 1A and 1B. Note that the educational material providing apparatus 10 also performs processing for generating educational material videos in addition to processing for providing educational material videos. Also, here, it is assumed that the driver A to be trained drives the vehicle V-1.

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

Next, the educational material providing device 10 analyzes each collected video and attaches a tag (tag information) to each video data based on the analysis result (step S2). Here, the tag is information corresponding to the content of the video, and is information indicating characteristics of the content of the video. Since the educational material providing apparatus 10 collects dangerous images, the process of step S2 can be said to be a process of analyzing the collected dangerous images and adding tags according to the contents of the dangerous images obtained from the analysis results. .

Tags include, for example, status information tags, near-miss tags, and traffic accident tags. The situation information tag is a tag of situation information indicating the driving situation (situation). , and “Ignore traffic lights” are tags. In addition, the situation information tag may include, as a tag, the date and time of driving, location, and words indicating the weather (for example, sunny, rainy, snowy, etc.), which are the driving situation. A near-miss tag is a tag that indicates the details of an event (a so-called near-miss event) that may be a sign of a traffic accident. Words such as "suddenly approaching" are tags. The traffic accident tag is a tag indicating the content of the traffic accident, and the tags are words such as "collision with a vehicle ahead", "collision with another vehicle at an intersection", and "collision with a pedestrian at an intersection". Although specific examples of the contents of the tags have been given above, these are only examples and are not limited. Moreover, the tags need not include all of the situation information tags, near-miss tags, and traffic accident tags described above, but may include some of them, or may include tags other than the above.

Next, the teaching material providing device 10 generates a teaching material video using the tagged video data (step S3). For example, the educational material providing apparatus 10 combines question information including question sentences and options corresponding to the question sentences with respect to the tagged video data to generate the educational material video.

The question sentence is a question sentence about the corresponding video, in other words, it is a sentence asking the person to be educated what can be read from the video (here, the dangerous video) in traffic safety education. The options are multiple options including at least one correct answer and are selected by the educated person.

For example, the educational material providing apparatus 10 can generate question information based on tags attached to video data. As an example, when the situation information tag of the video data is "Insufficient inter-vehicle distance to the vehicle in front" and the Hiyari-Hatto tag is "Suddenly approaching the vehicle ahead", the teaching material providing apparatus 10 may display "In the video, What is the reason for that? ], a question sentence including the content of the tag (here, the near-miss tag) is generated. In addition, the educational material providing device 10 consists of a correct answer including the content of a tag (in this case, a situation information tag) saying that "the cause is ``insufficient inter-vehicle distance to the vehicle in front''" and an arbitrarily set incorrect answer. Generate choices. Then, the educational material providing apparatus 10 combines the generated question sentences and options as question information with a video to generate a teaching material video. The educational material providing device 10 registers the generated educational material video in the educational material DB (database) 12b (see FIG. 2).

In this way, the educational material providing apparatus 10 according to this embodiment generates educational material videos in advance. In the above description, the teaching material providing apparatus 10 generates the question information, but the present invention is not limited to this.

Next, the educational material providing device 10 detects the attribute information of the person to be educated (here, the driver A) (step S4). The attribute information includes, for example, a driving tendency attribute indicating the driving tendency of the driver A and the like. Details of the attribute information will be described later with reference to FIG.

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

Specifically, the video data collected from the in-vehicle device 100-1 is tagged by the process of step S2. The educational material providing device 10 detects the attribute information (driving tendency attribute) of the driver A based on such tags. As an example, when a tag (situation information tag) of “excessive speed” is added to the video data of the in-vehicle device 100-1, the educational material providing device 10 determines that the attribute information (driving tendency attribute) of the driver A is “speed It is detected that it is a "driving tendency attribute that is likely to be exceeded." Similarly, if the video data of the in-vehicle device 100-1 is given a tag (hiyari-hatto tag) of “suddenly approaching another vehicle at an intersection”, the educational material providing device 10 detects the attribute information (driving tendency attribute) of the driver A. ) is the “driving tendency attribute that makes it easy to approach another vehicle quickly at an intersection”.

Next, the educational material providing device 10 selects and provides an educational image to the driver A, which is an image corresponding to the detected attribute information and captured by the in-vehicle device 100 (step S5). In other words, the educational material providing apparatus 10 provides the educational material video corresponding to the attribute information of the driver A to the driver A (more precisely, the terminal device 200 of the driver A).

As an example, when the attribute information (driving tendency attribute) of the driver A is "driving tendency attribute that tends to cause excessive speed", the teaching material providing device 10 Teaching material videos tagged with "speeding" (situation information tag) are selected and provided. Similarly, when the attribute information (driving tendency attribute) of the driver A is "driving tendency attribute that makes it easy to approach other vehicles quickly at an intersection", the educational material providing device 10 registers in the educational material DB 12b (see FIG. 2) A teaching material image with a tag (hiyari-hatto tag) of "suddenly approaching another vehicle at an intersection" is selected and provided from the teaching material images. The video provided as the educational video may be a video captured by the vehicle-mounted device 100-1 of the driver A, or may be a video captured by another vehicle-mounted device 100-2.

Then, in the terminal device 200 to which the educational image is provided, when an input operation for starting traffic safety education is performed, the educational image is displayed on the display 201, and the driver A answers the above-described problem information, etc. Traffic safety education for driver A is provided.

As described above, the educational material providing apparatus 10 according to the present embodiment provides the image of the in-vehicle apparatus 100 corresponding to the attribute information of the driver A who is the subject of education as the educational material image. As a result, in this embodiment, it is possible to provide a highly effective teaching material video suitable for the driver A who is to be educated. That is, since the instructional video corresponding to the attribute information is provided to the driver A, there is a high possibility that the contents of the educational video may occur to the driver A. As a result, the educational effect of the educational video for the driver A is improved. can be made

Specifically, the educational material providing device 10 according to the present embodiment uses the attribute information (driving tendency attribute) for each driver, so that, for example, the educational material video relating to situations in which the driver A is likely to fall into and things that the driver A is not careful about is compared. can provide a lot. As a result, it becomes possible to effectively educate the driver A about dangers and the like to which he/she should be particularly careful.

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

<Overall configuration of educational material provision system>
FIG. 2 is a block diagram showing a configuration example of the educational material providing system 1 according to the embodiment. It should be noted that FIG. 2 shows only the constituent elements necessary for explaining the features of the embodiment, and omits the description of general constituent elements.

In other words, each component illustrated in FIG. 2 is functionally conceptual and does not necessarily need to be physically configured as illustrated. For example, the specific form of distribution/integration of each block is not limited to the one shown in the figure. It is possible to integrate and configure.

In addition, in the description using FIG. 2, the description of components that have already been described may be simplified or omitted.

As shown in FIG. 2 , the teaching material providing system 1 according to the embodiment includes a teaching material providing device 10 , an in-vehicle device 100 and a terminal device 200 . In FIG. 2, one in-vehicle device 100 and one terminal device 200 are shown for simplification of illustration, but there may be a plurality of in-vehicle devices 100, terminal devices 200, and the like.

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

The communication unit 101 is a communication interface that is connected to the communication network N so as to enable two-way communication, and transmits and receives information to and from the educational material providing device 10 and the terminal device 200 and the like.

Various sensors 102 include, for example, a camera sensor, an acceleration sensor, a GPS sensor, etc., as described above. The camera sensor outputs captured moving image 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 . 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 microphone sensors in addition to or instead of the camera sensors.

A display 103 displays an image captured by the camera sensor. Further, when the educational material video is provided from the educational material providing apparatus 10 as described above, the display 103 displays the provided educational material video.

The storage unit 104 is, for example, a storage unit configured by a storage device such as a nonvolatile 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 image data 104a may or may not include a dangerous image.

The control unit 105 includes an acquisition unit 105a, a processing unit 105b, and an output unit 105c. Including computers and various circuits that have

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

At least one or all of the acquisition unit 105a, the processing unit 105b, and the output unit 105c of the control unit 105 may be configured by hardware such as ASIC (Application Specific Integrated Circuit) or FPGA (Field Programmable Gate Array). can.

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

When detecting, for example, sudden braking, sudden acceleration, sudden steering, or an impact due to a contact accident, the processing unit 105b outputs information indicating the details of the detection from the output of the acceleration sensor. The event information is associated with the captured video data and stored in the storage unit 104 .

The processing unit 105b stores, for example, vehicle position information in the storage unit 104 in association with the image data based on the output of the GPS sensor. Further, when the processing unit 105b detects that the vehicle is overspeeding from the output of the GPS sensor, the processing unit 105b adds information indicating the content of the detection (here, overspeeding) to the video data captured when the detection was made as event information. The information is linked and stored in the storage unit 104 . Specifically, the processing unit 105b calculates the travel distance of the vehicle in a certain predetermined travel time from the vehicle position information output from the GPS sensor, and divides the calculated travel distance by the predetermined travel time to calculate the vehicle speed. Then, the processing unit 105b compares the calculated vehicle speed with the speed limit included in the map information of the position (location) where the vehicle is traveling, and detects excessive speed when the vehicle speed exceeds the speed limit. do. Note that the map information may be information stored in the storage unit 104 in advance, or may be information acquired from an external server (not shown). In addition, the processing unit 105b may perform a process of prohibiting overwriting of video data for a predetermined period of time before and after detection of sudden braking, excessive speed, or the like.

For example, 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 based on the vehicle signal. More specifically, for example, the vehicle signal is the output of a brake sensor, an accelerator sensor, a steering angle sensor, a vehicle speed sensor, etc., and the processing unit 105b detects sudden braking, sudden acceleration, sudden steering, excessive speed, etc. of the vehicle based on the vehicle signal. may be detected.

The output unit 105c transmits the imaged video (video data) to the educational material providing apparatus 10 via the communication unit 101. FIG. For example, the output unit 105c may transmit video data linked with event information such as sudden braking to the educational material providing device 10 . That is, video data linked with event information such as sudden braking or excessive speed is presumed to be dangerous video data including near-miss video and traffic accident video. Therefore, when the output unit 105c transmits the video data linked with the event information, the educational material providing device 10 can collect the dangerous video. The transmission timing of the video data may be, for example, the timing at which the event information is associated with the video data, or the timing at which the transmission request for the video data is received from the educational material providing device 10. Any timing may be set.

Further, when a teaching material video is provided (transmitted) from the teaching material providing apparatus 10, the output unit 105c receives the teaching material video via the communication unit 101. FIG. Then, the output unit 105c outputs and displays the received teaching material image on the display 103, and provides it to the driver. As already described, traffic safety education can be provided in the vehicle V by this means.

<Configuration of Teaching Material Providing Device>
Next, the configuration of the educational material providing device 10 will be described. As shown in FIG. 2 , the educational material providing device 10 includes a communication section 11 , a storage section 12 and a control section 13 .

The communication unit 11 is a communication interface that connects to the communication network N so as to allow two-way communication, and transmits and receives information to and from the in-vehicle device 100, the terminal device 200, and the like.

Also, the storage unit 12 is a storage unit configured by a storage device such as a nonvolatile memory, a data flash, or a hard disk drive, for example. The storage unit 12 includes a video DB 12a, a teaching material DB 12b, and a driver DB 12c.

The video DB 12a stores information about videos. Here, the video DB 12a will be described with reference to FIG. FIG. 3 is a diagram showing an example of the video DB 12a.

As shown in FIG. 3, the image DB 12a includes items such as "image ID", "driver ID", "image", "date and time", "position", and "event". Data for each item is associated. That is, corresponding data such as "video" and "date and time" are stored in the data record specified by the "video ID".

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

“Video” is video data captured by the in-vehicle device 100 . In the example shown in FIG. 3, for the sake of convenience, "video" is abstractly described as "C1", but concrete information is stored in "C1". Other information may also be abstractly described below.

"Date and time" is information indicating the date and time when the corresponding video was captured. “Position” is information indicating the position (place) where the corresponding video was captured.

"Event" is information about an event that occurred in the corresponding video, and more specifically, event information about an event that occurred during driving when the video was captured. The event information is the event information linked to the video data by the in-vehicle device 100 as described above. Therefore, information indicating, for example, abrupt braking, abrupt acceleration, abrupt steering, a contact accident, excessive speed, etc. is registered in the "event".

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

Returning to the description of FIG. 2, the teaching material DB 12b stores information on teaching material videos. Here, the teaching material DB 12b will be described with reference to FIG. FIG. 4 is a diagram showing an example of the teaching material DB 12b.

As shown in FIG. 4, the teaching material DB 12b stores "learning material ID", "video ID", "driver ID", "situation information tag", "hiyari hatto tag", "traffic accident tag", "problem information", and the like. , and the data of each item is associated with the "learning material ID". In other words, the corresponding data such as the "situation information tag" and the "near-miss tag" are stored in the data record specified by the "learning material ID".

“Teaching material ID” is identification information for identifying the teaching material video. "Video ID" is identification information for identifying video data, and more specifically, identification information for identifying video data set as educational video. By registering the "video ID" in the teaching material DB 12b in this way, 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".

"Driver ID" is identification information for identifying the driver, and more specifically, identification information for the driver of the vehicle V (more precisely, the in-vehicle device 100) that captures the video data set as the educational video. By registering the "driver ID" in the teaching material DB 12b in this way, the teaching material video identified by the "teaching material ID" is associated with the driver data in the video DB 12a and the driver DB 12c by the "driver ID". be (associated with).

The "situation information tag" is information about the above-described situation information tag, and more specifically, information about a driving situation tag (situation information tag) when a video set as a teaching video is captured. The "situation information tag" registers tags such as "insufficient distance between vehicles ahead", "speeding", "sudden braking", "sudden acceleration", "sudden steering", and "ignoring traffic lights", for example. . The number of tags registered in the "status information tag" may be one or plural.

The "near-miss tag" is information related to the above-described near-miss tag, and more specifically, information related to the near-miss tag while driving in which the image set as the teaching material image was captured. For example, tags such as "suddenly approaching a vehicle ahead", "suddenly approaching another vehicle at an intersection", and "suddenly approaching a pedestrian at an intersection" are registered as the "near-miss tag". The number of tags registered in the "near-miss tag" may be one or more.

The "traffic accident tag" is information related to the traffic accident tag described above, and more specifically, information related to the tag of the traffic accident while driving in which the video set as the educational video was captured. In the "traffic accident tag", for example, tags such as "collision with a vehicle ahead", "collision with another vehicle at an intersection", and "collision with a pedestrian at an intersection" are registered. The number of tags registered in the "traffic accident tag" may be one or plural. In addition, since near-miss incidents are a sign of traffic accidents, either "near-miss incident tags" or "traffic accident tags" are registered in one educational video. It is not limited.

The teaching material images in the image DB 12a are classified according to the degree of risk in driving the vehicle by the "near-miss tag" and "traffic accident tag". In other words, near-miss incidents are events that are predictors of traffic accidents, so the degree of danger in driving a vehicle is lower than the degree of danger in traffic accidents. Conversely, the risk of traffic accidents is higher than the risk of near misses. Therefore, it can be said that the educational videos are classified according to the degree of danger in driving a vehicle by attaching the "near-miss tag" and the "traffic accident tag" to the educational videos.

"Problem information" is problem information provided to a person (driver) to be educated, and more specifically, is problem information combined with a video set as an educational video. The “problem information” includes information indicating a question sentence and information indicating options corresponding to the question sentence.

In the example shown in FIG. 4, the educational video data identified by the educational material ID "J01" is the video data identified by the video ID "A01" set as the educational video. This indicates that the image is captured while the driver identified by the ID "B01" is driving. In addition, the teaching material video data identified by the teaching material ID "J01" indicates that the situation information tag is "K1", the near miss tag is "L1", and the problem information is "N1".

The teaching material video data identified by the teaching material ID "J02" has a corresponding video ID of "A02", a corresponding driver ID of "B02", a situation information tag of "K2", and a traffic accident tag of "M2". ”, indicating that the problem information is “N2”.

Returning to the description of FIG. 2, the driver DB 12c stores information about drivers. For example, the driver DB 12c stores driver attribute information. Here, the driver DB 12c will be described with reference to FIG. FIG. 5 is a diagram showing an example of the driver DB 12c.

As shown in FIG. 5, the driver DB 12c includes items such as "driver ID", "driving tendency attribute", "driving area attribute", "age attribute", and "affiliation attribute". Data of each item is associated with "Person ID". In other words, corresponding data such as "driving tendency attribute" and "driving area attribute" are stored in the data record specified by the "driver ID".

“Driver ID” is identification information that identifies the driver. The “driving tendency attribute” is attribute information indicating the driving tendency of the driver. Note that the driving tendency may include near-miss experience, accident experience, and the like.

The "driving tendency attributes" include, for example, "prone to short distance between vehicles ahead", "prone to excessive speed", "prone to sudden braking", "prone to sudden acceleration", "prone to sudden steering", " Driving tendency attribute information such as "easy to ignore traffic lights" is registered. If the driver has experienced a near-miss, the "driving tendency attribute" may include, for example, "easily approaching a vehicle in front", "easily approaching another vehicle at an intersection", and "having a sudden approach to a pedestrian at an intersection". Driving tendency attribute information such as "easy to approach" is registered. In addition, if the driver has had an accident, the "driving tendency attribute" may include, for example, "hitting a vehicle ahead", "hitting another vehicle at an intersection", and "hitting a pedestrian at an intersection". Driving tendency attribute information is registered. The attribute information of the driving tendency described above is, for example, information (event information) included in the video data of the in-vehicle device 100, or detected by video analysis (more precisely, detected based on the tag) and registered. but more on that later.

"Driving area attribute" is information indicating an attribute related to the area where the driver travels in the vehicle. The travel area includes, for example, routes and areas where the vehicle driven by the driver often travels, but is not limited to this. Note that the "driving area attribute" may be registered based on information (position information) included in the video data of the in-vehicle device 100, or may be registered by an input operation by the driver, administrator, or the like.

"Age attribute" is information indicating an attribute indicating the age of the driver. In the "age attribute", information classified by age group such as "twenties" and "thirties" is registered, but the information is not limited to this.

"Affiliation attribute" is information indicating an attribute indicating the driver's affiliation. Information such as the company to which the driver belongs, the group to which the driver belongs, the school, etc. is registered in the "affiliation attribute", but the information is not limited to this. Moreover, although the above-described "age attribute" and "affiliation attribute" are registered by an input operation of a driver, administrator, or the like, the registration is not limited to this.

In the example shown in FIG. 5, the data of the driver identified by the driver ID "B01" has a driving tendency attribute of "P1", a driving area attribute of "Q1", an age attribute of "R1", and an affiliation attribute of It indicates that it is "T1". In the example shown in FIG. 5, the data of the driver identified by the driver ID "B03" does not include information on driving tendency attributes. This indicates that the driving tendency attribute information was not detected for the driver with the driver ID "B03", in other words, the driving tendency attribute information could not be detected. will be described later.

Returning to the description of FIG. 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. , computers with input/output ports, and various circuits. The CPU of the computer functions as a collection unit 13a, an analysis unit 13b, a generation unit 13c, a detection unit 13d, and a provision unit 13e of the control unit 13 by reading and executing various programs stored in the ROM, for example. Various programs include the teaching material providing program according to the present embodiment.

At least one or all of the collecting unit 13a, the analyzing unit 13b, the generating unit 13c, the detecting unit 13d, and the providing unit 13e of the control unit 13 can be configured by hardware such as ASIC and FPGA.

The collection unit 13a collects images (including dangerous images) captured by the in-vehicle device 100, and registers the collected images (image data) in the image DB 12a. In addition, when the video data includes date and time information when the video was captured, position information, and event information, the collection unit 13a registers these information in the video DB 12a. Also, the collection unit 13a collects images from a plurality of in-vehicle devices 100, that is, collects a plurality of images, but is not limited to this.

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

Specifically, for example, when the collected video data includes event information such as “sudden braking”, “sudden acceleration”, “sudden steering”, and “excessive speed”, the analysis unit 13b converts such event information into the situation information. Assign as a tag. For example, when the image analysis detects "insufficient inter-vehicle distance to the vehicle in front" or "signal disregard", the analysis unit 13b attaches the detected content as a situation information tag. For example, when video data includes information such as "date and time" and "position", the analysis unit 13b adds the content of such information as a status information tag. Further, when the weather during driving is detected by, for example, video analysis, the analysis unit 13b attaches the detected content (for example, fine weather, rain, snow, etc.) as a situation information tag. For example, when the video analysis detects "suddenly approaching a vehicle ahead", "suddenly approaching another vehicle at an intersection", or "suddenly approaching a pedestrian at an intersection", the analysis unit 13b analyzes the detected content. Attached as a near-miss tag. Further, the analysis unit 13b, for example, based on the event information of the video data and video analysis, when "contact with a vehicle in front", "contact with another vehicle at an intersection", "contact with a pedestrian at an intersection", etc. are detected, Attach the detected content as a traffic accident tag. Then, the analysis unit 13b associates the tags with the tagged video data and registers them in the teaching material DB 12b.

The generation unit 13c generates a teaching material video using the tagged video data. Specifically, the generation unit 13c generates question information using tags, and combines the question information with a video to generate a teaching material video. Note that the generation unit 13c associates the question information with the video data corresponding to the question information and registers them in the teaching material DB 12b.

For example, the generating unit 13c generates problem information based on tags. Specifically, the generating unit 13c generates question sentences and options using the contents (words) included in the situation information tag, the near-miss tag, and the traffic accident tag of the video data. Then, the generation unit 13c combines the question information including the question sentences and options with the video to generate the teaching material video.

As described above, the educational material providing apparatus 10 according to the present embodiment collects a plurality of images including dangerous images from the in-vehicle apparatus 100, generates a plurality of educational materials using the collected images, and generates a plurality of educational materials. is stored in advance in the teaching material DB 12b. As a result, in the present embodiment, it is possible to deal with, for example, a case where the attribute information of the driver, who is the object of education, is diverse. becomes possible.

The detection unit 13d detects attribute information of a driver to be trained. For example, the detection unit 13d detects, as attribute information, driving tendency attribute information indicating the driving tendency of the driver. Driving tendency attribute information is an example of driving tendency information.

Specifically, the detection unit 13d searches the educational material DB 12b for images captured by the in-vehicle device 100 of the vehicle V driven by, for example, the driver (educated person), and detects the tags attached to the corresponding image data. to confirm. Then, the detection unit 13d detects the driving tendency attribute information based on the tag attached to the video data corresponding to the driver (education subject). As an example, when a tag (situation information tag) of “insufficient inter-vehicle distance to the vehicle in front” is added to the video data corresponding to the driver, the detection unit 13d determines that the driving tendency attribute of the driver is “to the vehicle in front”. It is detected that it is a driving tendency attribute that tends to be short of inter-vehicle distance. 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 more. That is, when a plurality of tags are attached to the video data, the number of pieces of attribute information becomes plural according to the tags.

Further, the detection unit 13d detects (specifies) the travel area of the corresponding driver based on the position information included in the video data, and stores information indicating the detected travel area (travel area attribute information) in the driver DB 12c. Register in "Driving Area Attribute".

As described above, the detection unit 13d according to the present embodiment detects attribute information based on the image captured by the in-vehicle device 100 mounted on the vehicle V driven by the driver. As a result, the attribute information of the driver can be detected easily and accurately.

Here, the video data of the driver (person to be trained) may not be registered in the teaching material DB 12b. In other words, no image data is collected because there is no danger image in the in-vehicle device 100 of the vehicle V driven by the driver (educated person), or the educated person does not drive during the predetermined image collection period. Therefore, the video data may not be registered in the teaching material DB 12b because the video data has not been collected. In such a case, the detection unit 13d cannot detect the driving tendency attribute from the video data, and therefore does not register the "driving tendency attribute information" in the driver DB 12c. It is processed as if the detection of was not possible.

The providing unit 13e provides a teaching material image to the driver (education target person) based on the attribute information of the driver. For example, the providing unit 13e provides a video corresponding to the detected attribute information of the driver and captured by the in-vehicle device 100 as a teaching video for the driver. In other words, the providing unit 13e provides the driver with the teaching material image that matches the driver's attribute information.

As a result, in this embodiment, it is possible to provide teaching material images with high educational effects according to the driver (person to be educated). In other words, the driver is more likely to feel that the content of the teaching video is likely to happen to him/herself by being provided with the teaching video corresponding to his/her attributes. As a result, it is possible to improve the educational effect of the instructional video for the driver.

Specifically, the providing unit 13e provides a video image corresponding to the driving tendency information, which is one of the attribute information, as the educational video image. For example, the providing unit 13e searches the teaching material DB 12b based on the driving tendency attribute information of the driver, selects and provides the teaching material video corresponding to the driving tendency attribute information. As an example, when the driving tendency attribute of the driver is "driving tendency attribute that tends to cause insufficient inter-vehicle distance to the vehicle in front", the providing unit 13e searches the teaching material DB 12b based on the driving tendency attribute, Insufficient inter-vehicle distance” tag (situation information tag) is attached to select and provide teaching material videos. As a result, the providing unit 13e can provide a highly effective teaching material image that matches the driving tendency of the driver (educated person).

Here, the instructional video provided to the driver (educated person) will be described with reference to FIG. FIG. 6 is a diagram showing the display 201 of the terminal device 200 provided with the teaching material video.

As shown in FIG. 6 , the providing unit 13 e provides the educational material video to the terminal device 200 and displays it in the display field 300 of the display 201 . The teaching material video includes a video (danger video) 310 captured by the in-vehicle device 100 and problem information 320 . The question information 320 includes a display column 321 in which question sentences are displayed and a display column 322 in which options are displayed. Then, the driver (educated person) selects an option and answers, and traffic safety education is provided to the driver.

Continuing with the description of FIG. 2, the providing unit 13e, as described above, attaches tag information (for example, situation information tag, near-miss tag, traffic accident tag) corresponding to attribute information (for example, driving tendency attribute information) to video is provided as a teaching video. Specifically, a tag is attached in advance to the image of the in-vehicle device 100, and the providing unit 13e selects and provides an educational material image from the educational material DB 12b based on the attribute information and the tag corresponding to the attribute information. More specifically, the providing unit 13e selects and provides teaching material videos whose attribute information matches tags corresponding to the attribute information. Accordingly, the providing unit 13e can reliably select and provide an image corresponding to the attribute information of the driver with high accuracy.

Further, the providing unit 13e provides teaching material images of the degree of risk corresponding to the attribute information. That is, the teaching videos include near-miss videos and videos of traffic accidents, and the teaching videos are classified according to the degree of danger in driving a vehicle as described above. If the attribute information (for example, driving tendency attribute information) includes information that is less dangerous than a traffic accident (for example, information about a near-miss such as "easily approaching a vehicle in front"), the attribute information selects and provides a teaching material video (that is, a teaching video to which a near-miss tag is attached) with a degree of risk corresponding to the Similarly, when the attribute information (driving tendency attribute information) includes information with a higher degree of danger than a near-miss (for example, information about a traffic accident such as "contact with a vehicle in front"), the attribute information (ie, the educational video attached with the traffic accident tag) is selected and provided.

As a result, in the present embodiment, it is possible to provide an educational video that matches the degree of risk of driving included in the driver's attribute information, and as a result, the educational effect of the educational video for the driver is further improved. be able to.

Further, the providing unit 13e may provide, as a teaching material video, a video corresponding to situation information indicating the vehicle driving situation of the driver (educated person). As the situation information, for example, information such as vehicle position, weather, speed, date and time during driving can be used, but the information is not limited to these.

For example, when the situation information tag of the video data corresponding to the driver (educated person) includes situation information such as vehicle position, weather, speed, date and time, the providing unit 13e provides the video corresponding to the situation information. It is provided as an educational video. Specifically, when situation information is included in the video data of the driver (educated person), the providing unit 13e provides a teaching material video (for example, the driver (educated person)) to which a situation information tag corresponding to the situation information is added. A video (dangerous video) captured by another driver different from the driver is selected and provided.

As a result, in this embodiment, it is possible to provide teaching material images corresponding to situations in which the driver (educated person) has driven in the past and an image (dangerous image) was captured. It is possible to further improve the educational effect of the teaching material video.

Further, as described above, there are cases where it is impossible to detect the driving tendency attribute information of the driver (educated person). In such a case, the providing unit 13e provides, as teaching material images, images selected corresponding to similar drivers having attribute information similar to that of the driver (education subject).

For example, the providing unit 13e determines that at least one of the “driving area attribute”, the “age attribute”, and the “affiliation attribute” is similar to the driver whose driving tendency attribute information is not detected. identify similar drivers who Then, the providing unit 13e selects the image (dangerous image) of the in-vehicle device 100 of the identified similar driver and provides it as a teaching material image. Note that the similarity of attribute information includes the case where all the contents of the attribute information match, the case where part of the contents match, and the case where the contents of the attribute information are within a predetermined allowable range. It is not limited to this. Also, the predetermined allowable range can be set arbitrarily.

As a result, in this embodiment, even if the driving tendency attribute information is not detected, it is possible to provide educational videos with high educational effects according to the driver (educated person). That is, for a driver (education subject) whose driving tendency attribute information was not detected, a teaching material video (dangerous video) of a similar driver whose attribute information (for example, driving area, age, affiliation, etc.) is relatively close. Since it is provided, the driver (person to be educated) has a high possibility that the contents of the educational video will occur to him/herself, and as a result, the educational effect of the educational video for the driver can be improved.

Although the providing unit 13e provides the educational material video to the terminal device 200, the present invention is not limited to this. That is, the providing unit 13e may provide the teaching material image to the in-vehicle device 100 of the driver (educated person).

<Control processing of educational 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. FIG. 7 is a flowchart showing a processing procedure executed by the educational material providing apparatus 10. As shown in FIG. In the following description, a case where the number of instructional videos to be provided to the driver (hereinafter referred to as the "specified number") is three (three types) will be described as an example, but the present invention is not limited to this. The specified number can be set arbitrarily.

As shown in FIG. 7, the control unit 13 of the educational material providing device 10 collects images from the in-vehicle device 100 of the vehicle V (step S10). Next, the control unit 13 analyzes the collected video and attaches a tag to the video data based on the analysis result (step S11).

Next, the control unit 13 generates a teaching material video using the tagged video data (step S12). For example, the control unit 13 combines the question information with the tagged video data to generate the teaching material video. Note that the control unit 13 registers the generated educational material video in the educational 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 (for example, driving tendency attribute) based on an image captured by the in-vehicle device 100 of the vehicle V driven by the driver (educated person).

Next, the control unit 13 determines whether or not there is a teaching material image corresponding to the attribute information of the driver (educated person) (step S14). In other words, the process of step S14 can be said to be a process of detecting driving tendency attribute information in the driver's attribute information and determining whether or not there is an educational video corresponding to the detected driving tendency attribute information.

When it is determined that there is no teaching material video corresponding to the attribute information (for example, driving tendency attribute) (step S14, No), in other words, when the driving tendency attribute information cannot be detected, the control unit 13 The number of instructional videos corresponding to the similar driver having attribute information similar to that of the driver (education subject) is selected (step S15). As described above, since the specified number is 3, three teaching material videos are selected here.

On the other hand, if the control unit 13 determines that there is a teaching material video corresponding to the attribute information (for example, driving tendency attribute) (step S14, Yes), in other words, if the driving tendency attribute information is detected, the detected attribute A video corresponding to the information (driving tendency attribute) and captured by the in-vehicle device 100 is selected as a teaching video (step S16).

Note that, 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) (that is, the number of times of detection). As an example, when information indicating attribute contents a, b, c, and d in the attribute information is detected five times, three times, two times, and once, respectively, the attribute contents a, b, and c may be selected as the teaching material video. The attribute contents a, b, c, and d described above are, for example, "the distance between the vehicle ahead and the vehicle in front is likely to be insufficient", "the vehicle ahead is likely to approach suddenly", and "the vehicle in front is likely to come into contact".

Next, the control unit 13 determines whether or not a prescribed number of teaching material videos have been selected (step S17). If the control unit 13 determines that the prescribed number of teaching material images have not been selected (step S17, No), the control unit 13 proceeds to step S15 to correspond to the number of similar drivers that is short of the prescribed number. Select a teaching material video. That is, for example, the control unit 13 selects one teaching material video corresponding to the similar driver when one video is short of the prescribed number, and selects one educational video corresponding to the similar driver when two videos are short of the prescribed number. Select two instructional videos.

Then, the control unit 13 provides the driver with the teaching material video selected in steps S15 and S16 (step S18). On the other hand, if the controller 13 determines that the prescribed number of teaching material images have been selected (step S17, Yes), the control unit 13 proceeds to step S18 to provide the driver with the teaching material images selected in step S16.

As described above, the educational material providing device 10 according to the embodiment has the control unit 13 . The control unit 13 detects attribute information indicating attributes of the person to be educated, and provides an image corresponding to the detected attribute information, which is captured by the in-vehicle device 100, as a teaching material image to the person to be educated. As a result, it is possible to provide teaching material videos with a high educational effect.

The teaching material video generated in the above-described embodiment may be subjected to a masking process for concealing the vehicle number, person, etc. appearing in the video for the purpose of protecting personal information, for example. The masking process is, for example, a process of painting or mosaicing a vehicle number or person area in an image. As a result, for example, the generated teaching material video can be diverted to teaching material videos of other companies other than one's own company, and the versatility of teaching material videos can be improved.

Further effects and modifications can be easily derived by those skilled in the art. Therefore, the broader aspects of the invention are not limited to the specific details and representative embodiments so shown and described. Accordingly, various changes may be made without departing from the spirit or scope of the general inventive concept defined by the appended claims and equivalents thereof.

1 Teaching Material Providing System 10 Teaching Material Providing Device 13 Control Unit 100 In-Vehicle Device 105 Control Unit

Claims (10)

A teaching material providing device having a control unit,
The control unit
Detect attribute information that indicates the attributes of the person to be educated,
Providing a video corresponding to the detected attribute information, which is captured by an in-vehicle device, as a teaching video for the education subject,
Educational material providing device. The control unit
Detecting the attribute information based on an image captured by an in-vehicle device mounted on a vehicle driven by the education subject;
The educational material providing device according to claim 1 . The control unit
Detecting driving tendency information indicating the driving tendency of the person to be educated as the attribute information,
providing a video corresponding to the detected driving tendency information as the educational video;
3. The educational material providing device according to claim 1 or 2. The control unit
If the driving tendency information cannot be detected for the person to be educated, a video selected corresponding to a similar driver having the attribute information similar to that of the person to be educated is provided as the teaching material video.
The educational material providing device according to claim 3. The control unit
providing a video as the educational video according to the situation information indicating the driving situation of the vehicle;
A teaching material providing device according to any one of claims 1 to 4. The control unit
Attach tag information according to the content of the video to the input video,
Providing a video attached with the tag information corresponding to the attribute information as the educational video;
A teaching material providing device according to any one of claims 1 to 5. The educational videos are classified according to the degree of danger in driving a vehicle,
The control unit
providing the teaching material video of the degree of risk corresponding to the attribute information;
A teaching material providing device according to any one of claims 1 to 6. An in-vehicle device having an in-vehicle device control unit,
The in-vehicle device control unit
Transmit the captured video to the educational material providing device,
receiving a video corresponding to attribute information indicating an attribute of a person to be educated from the teaching material providing device as a teaching material video for the person to be educated, and providing the person to be educated;
In-vehicle device. A teaching material providing method executed by a teaching material providing device,
Detect attribute information that indicates the attributes of the person to be educated,
Providing a video corresponding to the detected attribute information, which is captured by an in-vehicle device, as a teaching video for the education subject,
How to provide teaching materials. to the computer,
Detect attribute information that indicates the attributes of the person to be educated,
Providing a video corresponding to the detected attribute information, which is captured by an in-vehicle device, as a teaching video for the education subject,
A program that provides instructional materials to guide you through the process.

Images