JP2023064687A - Accident analysis device, accident analysis method, and program - Google Patents

Abstract

To provide an accident analysis device and the like that can favorably handle multiple case masters.SOLUTION: An accident analysis device 10 comprises: a storage unit 100 that stores an accident case DB, a first case master that associates a first tag with an accident case indicated by the accident case DB, and a second case master that associates a second tag with an accident case indicated by the accident case DB; an acquisition unit to acquire vehicle data measured by a sensor included in an accident vehicle and video data captured by a camera included in the accident vehicle; an analysis unit 102 which analyzes a situation of an accident caused by the accident vehicle on the basis of the acquired vehicle data and video data; a tag estimation unit 104 which estimates the first and second tags corresponding to the accident situation on the basis of, the accident situation analyzed by the analysis unit 102; and a search unit 106 which searches the accident case DB on the basis of, the estimated first and second tags by referring to the first and second case masters.SELECTED DRAWING: Figure 6

Description

The present invention relates to an accident analysis device, an accident analysis method, and a program.

When a traffic accident occurs, the insurance company calculates the percentage of negligence according to the circumstances of the accident. As an accident analysis device for calculating such a percentage of negligence and analyzing an accident, for example, Patent Document 1 discloses an accident analysis device that quickly compares accident situations with past accident cases. . The operator of the insurance company calculates the percentage of negligence based on the contents of the matched past accident cases (accident conditions of the past cases, percentage of negligence, etc.).

The accident analysis device described in Patent Literature 1 compares accident situations with past accident cases in the following manner. The accident analysis device described in Patent Literature 1 includes an accident case DB (database) in which items (tags) indicating the status of each case are set for each case of past accident cases. The accident analysis device described in Patent Literature 1 analyzes the accident situation to identify a tag indicating the accident situation, and compares the identified tag with the tag set for each accident case, thereby analyzing the accident situation and the past. Collate with accident cases.

JP 2020-194263 A

In an accident analysis device such as that disclosed in Patent Document 1, as a method of setting a tag for each accident case, for example, a case master in which an ID (identifier) indicating an accident case and a tag are associated is prepared separately from the accident case DB. can be considered.

A plurality of methods are conceivable as to what kind of tag is set for each accident case in the case master. For example, by increasing the granularity of the tags to be set, it becomes difficult to finely search accident cases, but the burden of setting tags to each accident case is reduced. Conversely, if the granularity of tags to be set is reduced, it becomes possible to search for accident cases in detail, but the burden of setting tags increases.

Therefore, it would be convenient for the user if the accident analysis device could suitably handle a plurality of case masters to which tags were set by different methods.

SUMMARY OF THE INVENTION In view of the above circumstances, an object of the present invention is to provide an accident analysis apparatus, an accident analysis method, and a program capable of suitably handling a plurality of case masters.

In order to achieve the above object, the accident analysis device according to the first aspect of the present invention comprises:
Accident case data indicating accident cases; a first case master that associates accident cases indicated by the accident case data with first tags; and a first case master that associates accident cases indicated by the accident case data with second tags. a storage means for storing two case masters;
Acquisition means for acquiring vehicle data measured by a sensor provided in the accident vehicle and video data captured by a camera provided in the accident vehicle;
analysis means for analyzing a situation of an accident caused by the accident vehicle based on the acquired vehicle data and the video data;
tag estimation means for estimating the first tag and the second tag corresponding to the accident situation based on the accident situation analyzed by the analysis means;
a search means for searching the accident case data based on the estimated first tag and the second tag by referring to the first case master and the second case master;
Prepare.

further comprising tag conversion means for converting the estimated first tag into the second tag;
The tag estimating means estimates the second tag by converting the estimated first tag into the second tag by the tag converting means.
You may do so.

The search means ranks each accident case indicated by the first case master based on the estimated first tag, and each accident case indicated by the second case master based on the estimated second tag. rank the
You may do so.

The search means obtains search results by integrating the accident cases ranked in the first case master and the accident cases ranked in the second case master.
You may do so.

In order to achieve the above object, the accident analysis method according to the second aspect of the present invention comprises:
an acquisition step of acquiring vehicle data measured by a sensor provided in the accident vehicle and video data captured by a camera provided in the accident vehicle;
an analysis step of analyzing a situation of an accident caused by the accident vehicle based on the obtained vehicle data and the image data;
a tag estimation step of estimating a first tag and a second tag corresponding to the accident situation based on the analyzed accident situation;
A search step of searching for accident case data indicating accident cases, wherein a first case master in which the accident case indicated by the accident case data and the first tag are associated with each other, and the accident case indicated by the accident case data and the first tag are searched. a searching step of searching for the accident case data based on the estimated first tag and the second tag by referring to a second case master in which the two tags are associated;
Prepare.

In order to achieve the above object, the program according to the third aspect of the present invention is
to the computer,
an acquisition step of acquiring vehicle data measured by a sensor provided in the accident vehicle and video data captured by a camera provided in the accident vehicle;
an analysis step of analyzing a situation of an accident caused by the accident vehicle based on the obtained vehicle data and the image data;
a tag estimation step of estimating a first tag and a second tag corresponding to the accident situation based on the analyzed accident situation;
A search step of searching for accident case data indicating accident cases, wherein a first case master in which the accident case indicated by the accident case data and the first tag are associated with each other, and the accident case indicated by the accident case data and the first tag are searched. a searching step of searching for the accident case data based on the estimated first tag and the second tag by referring to a second case master in which the two tags are associated;
to run.

According to the present invention, it is possible to provide an accident analysis device, an accident analysis method, and a program that can suitably handle a plurality of case masters.

It is a figure showing an example of an accident analysis system concerning this embodiment. FIG. 2 is a schematic diagram showing a state facing forward from inside the vehicle in the present embodiment; 1 is a functional block diagram of a drive recorder according to an embodiment; FIG. It is a figure which shows the processing flow which concerns on this Embodiment. It is a figure which shows the hardware structural example of the accident analysis apparatus which concerns on this Embodiment. 1 is a functional block diagram of an accident analysis device according to this embodiment; FIG. It is a table which shows an example of accident example DB in the accident analysis apparatus which concerns on this Embodiment. FIG. 4 is a diagram showing the relationship between an accident case DB, a first case master, and a second case master in the accident analysis device according to the present embodiment; It is a table which shows an example of the 1st case master in the accident analysis apparatus which concerns on this Embodiment. It is a table which shows an example of the 2nd example master in the accident analysis apparatus which concerns on this Embodiment. FIG. 4 is a diagram showing an example of conversion from a first tag to a second tag by a tag conversion unit of the accident analysis device according to the present embodiment; FIG. 4 is a diagram showing an example of ranking of accident cases by a search unit of the accident analysis device according to the present embodiment; It is a figure which shows an example of the screen displayed on the terminal which concerns on this Embodiment. 4 is a flow chart showing an outline of a processing procedure when the accident analysis device according to the present embodiment analyzes the circumstances of an accident and searches for an accident case; 10 is a flow chart showing an outline of a processing procedure of tag correction and re-search after tag correction when an operator designates a tag in the accident analysis apparatus according to the present embodiment;

BEST MODE FOR CARRYING OUT THE INVENTION Hereinafter, embodiments of the present invention will be described with reference to the drawings. Identical or corresponding parts in the drawings are denoted by the same reference numerals.

FIG. 1 is a diagram showing an example of an accident analysis system according to this embodiment. In the accident analysis system 1 according to the present embodiment, a drive recorder 1100 (see FIG. 2) is installed in the policyholder's vehicle 1000. ) to a cloud storage server (not shown). In the present embodiment, an example is shown in which the drive recorder 1100 connects to a cloud storage server (not shown) via a network (including a public line network) by wireless communication. A mirror-type dedicated terminal device having the function of (1) may be prepared and installed instead of the mirror 1300 .

A data storage area for this system is reserved in the cloud storage server. More specifically, a data storage area accessible by accident analysis device 10 is secured for each drive recorder 1100 mounted on vehicle 1000 .

Accident analysis device 10 uses vehicle data measured by sensors provided in vehicle 1000 (which may be referred to as “self-vehicle” for convenience in the following description) that is an accident vehicle, and a camera provided in drive recorder 1100 of vehicle 1000. It has a function of acquiring photographed video data from a cloud storage server via a network and analyzing the circumstances of an accident caused by vehicle 1000 based on the acquired vehicle data and video data. The accident analysis device 10 also has an accident case database that associates the circumstances of accidents obtained by the analysis with the circumstances of accidents that have occurred in the past and information on past accident cases (hereinafter referred to as "accident cases"). are compared to match the situation of the accident caused by the vehicle 1000 with the accident case.

In the following description, "sensors provided in vehicle 1000" are sensors provided in drive recorder 1100 mounted in vehicle 1000, not directly built in vehicle 1000. FIG. As will be described later, the drive recorder 1100 includes sensors such as a positioning sensor that acquires the absolute position of the vehicle 1000 and an acceleration sensor that measures the acceleration of the vehicle 1000 . Since the drive recorder 1100 is mounted in the vehicle 1000, various sensors provided in the drive recorder 1100 are also "sensors provided in the vehicle 1000".

The terminal 20 is, for example, a terminal operated by an operator of an insurance company, and displays an accident situation analyzed by the accident analysis device 10, an accident case corresponding to the accident situation, and an image generated by the accident analysis device 10. As the terminal 20, any information processing device having a display, such as a PC, a notebook PC, a tablet terminal, and a smart phone, can be used. The terminal 20 is communicably connected to the accident analysis device via a network. For example, when an insurance company operator receives an accident report from an insurance policyholder who drives the vehicle 1000, the operator operates the terminal 20 to grasp the accident situation, accident case, etc., and obtains the accident situation and the accident case. Calculate the percentage of fault based on the matching results.

FIG. 2 shows a state in which the front of vehicle 1000 is viewed inside vehicle 1000 . The drive recorder 1100 includes a camera and, as shown, is attached to the front portion or windshield of the vehicle 1000 so as to capture at least an image of the direction in which the vehicle 1000 is traveling. The camera may be capable of photographing the lateral direction and the rear of the vehicle 1000 . As shown in FIG. 2, the vehicle 1000 is equipped with a known automatic diagnostic system 1400 (for example, OBD (On-Board Diagnostic system-II)). Assume that it is connected to the recorder 1100 .

FIG. 3 shows a functional block diagram of drive recorder 1100 according to the present embodiment. The drive recorder 1100 mounted on the vehicle 1000 includes a communication unit 1120, a positioning unit 1130, a recording unit 1140, a recording unit 1150, an acceleration measurement unit 1160, an automatic diagnosis data acquisition unit 1170, a control unit 1180, and a data storage unit 1200 .

The control unit 1180 is composed of processors such as a CPU (Central Processing Unit) and a GPU (Graphical processing unit), and causes each component to execute processing related to the customer service.

The communication unit 1120 has a function of transmitting data to a cloud storage server by wireless packet communication using a public line network, for example.

When instructed by control unit 1180 , positioning unit 1130 acquires the absolute position (for example, latitude and longitude) of vehicle 1000 by GPS (Global Positioning System), for example, and stores it in data storage unit 1200 .

The recording unit 1140 stores, in the data storage unit 1200, moving image data (video data) shot by a camera installed in the drive recorder 1100, for example. Recording unit 1150 stores sound data input from the microphone in data storage unit 1200 . Recording unit 1150 may be integrated with recording unit 1140 . Recording unit 1140 continuously records and stores data in data storage unit 1200 when instructed to operate by control unit 1180 , for example. It is assumed that the control unit 1180 can extract both video data for a certain period of time before a specific time and video data for a certain period of time after the specific time. The same is true for the recording unit 1150 . Recording unit 1140 can capture a moving image of the exterior of vehicle 1000 and a moving image of the interior of vehicle 1000 .

Acceleration measuring section 1160 measures the value of acceleration using, for example, an acceleration sensor, and outputs it to control section 1180 . Automatic diagnostic data acquisition section 1170 acquires automatic diagnostic data from automatic diagnostic system 1400 mounted inside vehicle 1000 when instructed by control section 1180 .

The data storage unit 1200 is composed of storage devices such as memory, HDD (Hard Disk Drive) and/or SSD (Solid State Drive). ), telephone numbers, etc., and also stores data acquired by each component according to instructions from the control unit 1180 .

Next, in the accident analysis system shown in FIG. 1, details of processing from occurrence of an accident to transmission of data related to the accident to the cloud storage server will be described with reference to FIG.

Control unit 1180 of drive recorder 1100 mounted on vehicle 1000 continuously causes acceleration measurement unit 1160 to measure acceleration, and determines whether the measured acceleration is equal to or greater than a predetermined threshold. do. Here, it is assumed that the control unit 1180 detects an acceleration equal to or greater than the threshold ( FIG. 4 : step S100).

When an acceleration equal to or greater than the threshold is detected, the control unit 1180 reads equipment data from the data storage unit 1200, and extracts vehicle data including impact event data, video data, etc. (step S101). The impact event data includes the date and time obtained from the clock, position data obtained by positioning section 1130 , detected acceleration, and automatic diagnosis data obtained by automatic diagnosis data obtaining section 1170 . The video data includes video data captured by recording unit 1140 and sound data recorded by recording unit 1150 . As described above, the video data and the like include video data and the like for a certain period of time before the point at which acceleration equal to or greater than the threshold is detected, and video data and the like for a certain period of time after that point. The automatic diagnosis data includes data representing the presence or absence of damage to each of the engine, battery, fuel system, and the like. The device data and impact event data are referred to as vehicle data.

Then, the control unit 1180 transmits the extracted data (vehicle data (equipment data, impact event data), video data, etc.) to the cloud storage server to the communication unit 1120 (step S102). After that, the control unit 1180 ends the subsequent processing (step S103).

When the cloud storage server receives the extracted data from the drive recorder 1100, it stores it in a data storage area specified by, for example, the vehicle registration number or telephone number included in the device data (step S103).

Next, with reference to FIGS. 5 to 14, the analysis of the accident situation and the comparison between the accident situation and the accident case by the accident analysis device 10 in the accident analysis system shown in FIG. 1 will be described.

As described above, the accident analysis device 10 acquires vehicle data and video data from the cloud storage server via the network, and analyzes the accident caused by the vehicle 1000 based on the acquired vehicle data and video data. It has a function of analyzing the situation and comparing the situation of the accident caused by the vehicle 1000 with the accident case. Further, the accident analysis device 10 maps the position of the vehicle 1000 and the positions of the other vehicles obtained by analyzing the circumstances of the accident on the map data, thereby generating an image showing the circumstances of the accident caused by the vehicle 1000. has a function to generate The image showing the circumstances of the accident caused by the vehicle 1000 may be of any kind, and may be, for example, a bird's-eye view or a moving image.

The accident analysis device 10 may be composed of one or more physical information processing devices such as a mainframe, a workstation, or a personal computer (PC), or may be a virtual information processing device that operates on a hypervisor. information processing apparatus, or a cloud server.

FIG. 5 is a diagram showing a hardware configuration example of the accident analysis device 10. As shown in FIG. The accident analysis device 10 includes a processor 11 such as a CPU (Central Processing Unit) or a GPU (Graphical Processing Unit), a memory, a storage device 12 such as a HDD (Hard Disk Drive) and/or an SSD (Solid State Drive), wired or wireless. It has a communication IF (Interface) 13 for communication, an input device 14 for receiving input operations, and an output device 15 for outputting information. The input device 14 is, for example, a keyboard, touch panel, mouse and/or microphone. The output device 15 is, for example, a display and/or a speaker.

FIG. 6 is a functional block diagram of the accident analysis device 10 according to this embodiment. Accident analysis device 10 includes storage unit 100 , acquisition unit 101 , analysis unit 102 , generation unit 103 , tag estimation unit 104 , tag conversion unit 105 , search unit 106 , and output unit 107 . The storage unit 100 can be implemented using the storage device 12 included in the accident analysis device 10 . The acquisition unit 101, the analysis unit 102, the generation unit 103, the tag estimation unit 104, the tag conversion unit 105, the search unit 106, and the output unit 107 are stored by the processor 11 of the accident analysis device 10. It can be realized by executing a program stored in the device 12 . Also, the program can be stored in a storage medium. The storage medium storing the program may be a non-transitory computer readable medium. The non-temporary storage medium is not particularly limited, but may be a storage medium such as a USB memory or CD-ROM, for example.

The storage unit 100 stores an accident case DB, a first case master, a second case master, and a map data DB. The storage unit 100 corresponds to storage means.

The accident case DB is a database showing past accident cases. The accident case DB is, for example, a database of judicial precedents of automobile accidents. For example, as shown in FIG. 7, the accident case DB includes case IDs for individually identifying accident cases, details of the accident cases, fault ratios in the accident cases, and correction elements. Here, the percentage of fault is the basic percentage of fault, which can be modified according to the modifiers. The corrective element is an element that corrects the percentage of fault according to the circumstances of the accident. The percentage of fault can then be corrected. The accident case DB corresponds to accident case data.

Details will be described below, but the relationship between the accident case DB, the first case master, and the second case master is as shown in FIG.

The first case master is a master that associates an accident case indicated by the accident case DB with a first tag corresponding to the content of the accident case. The first tag has a finer granularity than the second tag, which will be described later. Therefore, the burden of setting a tag for each accident case is greater than for the second tag.

The second case master is a master that associates an accident case indicated by the accident case DB with a second tag corresponding to the content of the accident case. The second tag has a coarser granularity than the first tag. Therefore, the burden of setting a tag for each accident case is smaller than that for the first tag.

The first case master is, for example, as shown in FIG. 9, and the second case master is, for example, as shown in FIG. In the examples shown in FIGS. 9 and 10, for both the first case master and the second case master, the case ID of the accident case DB shown in FIG. 7 is used to refer to the accident cases contained in the accident case DB. . Between the first case master shown in FIG. 9 and the second case master shown in FIG. 10, the granularity of the road-related tags is finer in the first case master. Further, in the first case master shown in FIG. 9 and the second case master shown in FIG. 10, the number of accident cases with tags set is larger in the second case master than in the first case master. This is based on the assumption that the first case master, which has finer granularity of tags, has a larger tag setting burden, and thus the degree of progress of tag setting is lower than that of the second case master.

In addition to those shown in FIG. 9, examples of the first tag included in the first case master include the priority relationship between roads, whether a right-turning vehicle cannot approach the center, whether a left-turning vehicle cannot approach the left edge, and a tag indicating the color of a signal when an object enters, the speed of the own vehicle and the object when entering, the presence or absence of an accident, the presence or absence of an injury, and the like. On the other hand, in addition to the tags shown in FIG. 10, examples of the second tag included in the second case master include the movement of the own vehicle, the vehicle speed at the time of collision, the color of the signal when the own vehicle and the object enter, and the like.

The accident case DB, the first case master, and the second case master are stored in the storage unit 100, for example, by manual data registration by the administrator of the accident analysis device 10. FIG. Alternatively, accident case data distributed by a third-party vendor that handles accident cases may be stored in the storage unit 100 as an accident case DB, and the administrator may manually input only the first case master and the second case master. . Alternatively, a third party may distribute the accident case DB and the second case master, and the administrator may manually input only the first case master.

Since the granularity and contents of the tags set differ between the first case master and the second case master, tags are set from different viewpoints between the first case master and the second case master.

Please refer to FIG. 6 again. The map data DB includes various data such as road data, road width, direction of travel, road type, traffic signs (stop, no entry, etc.), speed limit, position of traffic lights, number of intersecting roads at intersections, and the like.

As described above, in FIG. 6, the storage unit 100 is implemented using the storage device 12 provided in the accident analysis device 10. It may be realized by a server.

The acquisition unit 101 has a function of acquiring vehicle data and image data measured and photographed by the vehicle 1000 (accident vehicle) from a cloud storage server. The acquisition unit 101 also has a function of acquiring information (hereinafter referred to as “operation information”) regarding the operation of the terminal 20 by the operator. Acquisition unit 101 corresponds to acquisition means.

Analysis unit 102 has a function of analyzing the circumstances of an accident caused by vehicle 1000 based on the vehicle data and video data acquired by acquisition unit 101 . The analysis unit 102 corresponds to analysis means. The accident situation analyzed by the analysis unit 102 includes at least the road situation of the accident caused by the vehicle 1000 (whether the road is a general road or an expressway, whether the road is a single road or an intersection), and whether the vehicle 1000 crosses an intersection. It may include the color of the traffic light when passing, the priority relationship when passing through the intersection, and whether the vehicle speed of the vehicle 1000 exceeds the speed limit.

Vehicle data of vehicle 1000 includes at least information indicating the absolute position of vehicle 1000 measured by the GPS of positioning unit 1130. Analysis unit 102 provides information indicating the absolute position of vehicle 1000 (positioning unit 1130) and information indicating the relative positional relationship between the vehicle 1000 and the other vehicle obtained by analyzing the image of the other vehicle shown in the image data. may be estimated. Also, the analysis unit 102 may estimate the absolute positions of the vehicle 1000 and other vehicles in chronological order. Further, the analysis unit 102 uses SfM (Structure from Motion) technology to more accurately estimate the absolute position of the own vehicle based on the information indicating the absolute position measured by GPS and the data of each frame of the video data. may

Further, the analysis unit 102 compares the image size of a portion of the video data in which the other vehicle is shown with data indicating the correspondence relationship between the image size and the distance, and determines the relative positions of the vehicle 1000 and the other vehicle. The situation of the accident may be analyzed by estimating the distance between the vehicle 1000 and the other vehicle, which is one of the information indicating the relationship.

Further, the analysis unit 102 compares the difference between the coordinates of the location where the other vehicle is shown in the image data and the center coordinates of the image data, and the data indicating the correspondence relationship between the coordinates and the angle, and The situation of the accident may be analyzed by estimating the angular difference between the traveling direction of the vehicle 1000 and the direction in which other vehicles are present, which is one of the information indicating the relative positional relationship with the vehicle. .

The generation unit 103 refers to the map data DB of the storage unit 100 and maps the absolute position of the vehicle 1000 and the absolute positions of the other vehicles on the map data based on the analysis result of the analysis unit 102, thereby enabling the vehicle 1000 to wake up. It has a function to generate an image showing the accident situation. The image may include a bird's-eye view or a moving image. For example, the generation unit 103 may generate a moving image in which images showing the circumstances of the accident are arranged in chronological order.

The tag estimation unit 104 estimates the first tag and the second tag representing the accident situation analyzed by the analysis unit 102 . For example, the tag estimation unit 104 estimates a tag related to road conditions among the first tag and the second tag based on the road conditions analyzed by the analysis unit 102 . As will be described later, part or all of the second tag may be estimated by converting the estimated first tag using the tag conversion unit 105 . The tag estimation unit 104 corresponds to tag estimation means.

The tag converting section 105 converts the first tag estimated by the tag estimating section 104 into a second tag. For example, as shown in FIG. 11, when the first tags estimated by the tag estimation unit 104 are "road type: general road" and "road shape: intersection", the tag conversion unit 105 converts these two first tags. Convert the tag into one secondary tag "Road type: Intersection". The tag conversion unit 105 corresponds to tag conversion means.

In addition to the above, for example, when the estimated first tags are "road type: intersection" and "relative position: left of own vehicle/right of object", the tag conversion unit 105 converts these two first tags to It is conceivable to set one second tag "accident type: head-to-head/side-collision/contact". In this case, the first tag "road type: intersection" is used to convert to the second tag "road type: intersection", and is used to convert to the second tag "accident type: crossing, side collision, contact". will also be used. That is, one primary tag can be used to transform two or more secondary tags.

The search unit 106 refers to the first case master and the second case master in the storage unit 100 and searches for accident cases based on the first tag and the second tag estimated by the tag estimation unit 104 . Since the tag estimated by the tag estimation unit 104 is a tag representing the accident situation, the search unit 106 can match the accident situation with the accident case. The search unit 106 corresponds to search means.

In addition, the search unit 106 not only searches for accident cases, but also searches for the estimated tag (first tag or second tag) and each accident case of the case master (first case master or second case master). Each accident case in the case master may be ranked according to the degree of matching with the set tag, and the result obtained by ranking may be used as the search result. Alternatively, the search result may be obtained by integrating the results obtained by ranking the respective accident cases. Description will be made below with reference to FIG.

First, for each of the first case master and the second case master, the search unit 106 determines the degree of matching between the estimated tag and the tag set for each accident case in the case master, as shown in the upper part of FIG. Rank each accident case as follows: Here, among the case IDs of the second case master shown in FIG. 12, shaded ones indicate accident cases that also exist in the first case master. Note that accident cases with zero matching with the estimated tags are excluded from the ranking.

As the "matching degree", for example, a simple matching coefficient may be used, or another index may be used. For example, a different score may be determined in advance for each tag, and the total score of matching tags may be used as the "coincidence".

Next, the search unit 106 integrates the ranking results for each of the first case master and the second case master. Specifically, for example, based on the ranking result of the second case master, the ranking in the first case master is applied to the accident cases that exist in the first case master among the accident cases in the second case master. Integrate the ranking results by For example, in the case shown in FIG. 12, the rankings of case IDs 002, 017, 008, and 010 for the first case master are from first to fourth, respectively, while for the second case master, case IDs 002, 017, 008, The ranking of 010 is 2nd, 1st, 3rd and 5th respectively. In this case, the order magnitude relationship for the first case master is prioritized at the time of integration, and the orders of case IDs 002, 017, 008, and 010 at the time of integration are 1st, 2nd, 3rd, and 5th, respectively.

The reason why the ranking in the first case master is applied at the time of integration is that the granularity of tags in the first case master is finer, so the ranking is likely to be more appropriate.

Further, although the details will be described later, the search unit 106 also has a function of re-searching based on the operation information acquired by the acquisition unit 101 when the operator operates the terminal 20 to correct the tag.

The output unit 107 outputs information indicating the accident situation analyzed by the analysis unit 102, information indicating the tag estimated by the tag estimation unit 104, information indicating the search result by the search unit 106, and the accident situation generated by the generation unit 103. It has a function of outputting the displayed image to the terminal 20 . Since the search results obtained by the search unit 106 include only case IDs and rankings, the output unit 107 refers to the accident case DB, and based on the case IDs, the detailed information of the accident cases ("contents" shown in FIG. 7). , “percentage of fault”, “correction factor”, etc.) and includes the detailed information in the information showing the search results.

Based on the output from the output unit 107, a screen as shown in FIG. 13 is displayed on the terminal 20, for example. The screen shown in FIG. 13 includes at least an image and information indicating the accident situation analyzed by the analysis unit 102 (the image is generated by the generation unit 103), the first tag and the second tag estimated by the tag estimation unit 104, and search results by the search unit 106 . Also, the output unit 107 can display a screen described below based on the operation information acquired by the acquisition unit 101 .

The operator who operates the terminal 20 can check the video recorded by the drive recorder 1100 of the vehicle 1000 at the time of the accident by selecting the button "Watch the video of the accident" on the screen. This is realized by having the output unit 107 display a moving image based on the operation information indicating that "watch the moving image when the accident occurred" is selected.

In addition, the operator who operates the terminal 20 can check the details of each accident case listed in the search results, correction factors for the percentage of fault, and the like by selecting "view details" in the search results. The operator compares the accident situation with the details of the accident case and calculates the percentage of fault based on the accident case. This is realized by having the output unit 107 display the detailed contents of the accident case based on the operation information indicating that "view details" has been selected.

Also, the operator who operates the terminal 20 can correct the tag by selecting the "correct tag" button on the screen. Note that "correction of tags" includes correcting estimated tags, deleting part of estimated tags, adding new tags, and the like. When the tag is corrected, the terminal 20 displays the result of searching again with the corrected tag. For example, when the tag estimation unit 104 cannot estimate the tag, or when the tag estimated by the tag estimation unit 104 is not appropriate, the operator checks the video, corrects the appropriate tag, and searches again. can be done. This is because the search unit 106 searches based on the corrected tag based on the operation information indicating that “correct tag” is selected and then the tag is corrected, and the output unit 107 outputs the corrected tag search result. It is realized by displaying the result.

Note that the functions of the accident analysis device 10 may be implemented in cooperation with the terminal 20, so there may be functions provided on the terminal 20 side. Alternatively, the accident analysis device 10 and the terminal 20 may be integrated into one information processing device.

Next, a processing procedure for analyzing an accident situation and retrieving an accident case by the accident analysis device 10 will be described with reference to FIG. 14 . FIG. 14 is a flow chart showing an outline of a processing procedure when the accident analysis device 10 analyzes the circumstances of an accident and searches for an accident case. In the following description, it is assumed that vehicle data and video data each include time information or synchronization information. That is, in the present embodiment, when analyzing video data at a certain point in time, analysis can be performed using vehicle data corresponding to that point in time. Conversely, when analyzing vehicle data at a certain point in time, Analysis can be performed using the video data corresponding to that point in time.

First, the acquisition unit 101 of the accident analysis device 10 acquires the vehicle data of the vehicle 1000 that caused the accident and the image data at the time of the accident (steps S10 and S11). Specifically, the accident analysis device 10 acquires the vehicle data and the video data from the cloud storage server via the network. In addition, for example, it is recorded in a non-temporary storage medium such as an SD card or USB memory, and by connecting the recording medium to the accident analysis device 10, the vehicle data and video data are imported into the accident analysis device 10. You may do so. The processing of steps S10 and S11 corresponds to the acquisition step.

Next, analysis unit 102 of accident analysis device 10 analyzes the circumstances of the accident caused by vehicle 1000 based on the vehicle data acquired in step S10 and the video data acquired in step S11 (step S12). The processing of step S12 corresponds to the analysis step.

Next, the tag estimation unit 104 of the accident analysis device 10 estimates the first tag and the second tag indicating the accident situation based on the analysis result in step S12 (step S13). As described above, in estimating some or all of the second tags, the second tags may be estimated by converting the estimated first tags into second tags by the tag conversion unit 105 . The processing of step S13 corresponds to the tag estimation step.

Next, the search unit 106 of the accident analysis device 10 refers to the first case master and ranks the accident cases based on the first tags estimated in step S13 (step S14). Similarly, the search unit 106 refers to the second case master and ranks the accident cases based on the second tags estimated in step S13 (step S15). The search unit 106 integrates the results of ranking in steps S14 and S15 to obtain a search result (step S16). The processing from step S14 to step S16 corresponds to the search step.

Next, the generation unit 103 of the accident analysis device 10 generates an image showing the circumstances of the accident based on the analysis result obtained in step S12 (step S17). Note that the process of step S17 may be performed between the processes of steps S12 to S16, or may be performed in parallel with these processes.

Then, the output unit 107 of the accident analysis device 10 outputs information indicating the analysis result (accident situation) obtained in step S12, information indicating the tag estimated in step S13, and search results obtained in steps S14 to S16. and the image representing the circumstances of the accident generated in step S17 are output to the terminal 20 (step S18), and the accident analysis device 10 terminates the analysis and search processing.

Note that these processes may be performed in any order as long as there is no contradiction in the processes.

Next, the re-search processing procedure by the accident analysis device 10 when the operator corrects the tag will be described with reference to FIG. 15 . Since the procedure shown in FIG. 15 is a re-search, it is executed at the timing when the operator operates the terminal 20 to correct the tag after the procedure shown in FIG. 14 is performed and the search results are displayed.

First, the acquisition unit 101 of the accident analysis device 10 acquires operation information indicating that the operator has operated the terminal 20 to correct the tag (step S20).

Next, the search unit 106 of the accident analysis device 10 identifies the modified tag based on the operation information (step S21).

Next, the search unit 106 searches again for accident cases including the tag identified in step S21 from the search results while maintaining the ranking order (step S22). For example, consider a case where the original search result is the post-integration shown in FIG. In this case, assume that the accident cases including the corrected tag are three accident cases with case IDs of 017, 032, and 010, respectively. The rankings of these three accident cases before tag correction are 2nd, 4th, and 5th, respectively. In this case, the search unit 106 ranks the accident cases with case IDs 017, 032, and 010 as first, second, and third, respectively. Since the rankings before tag correction were 2nd, 4th, and 5th respectively, the rankings after tag correction are 1st, 2nd, and 3rd, respectively.

Then, the output unit 107 of the accident analysis device 10 outputs to the terminal 20 the information indicating the re-search result after tag correction obtained in step S22 (step S23), and the accident analysis device 10 ends the re-search process. do.

According to the embodiment described above, the accident analysis device 10 estimates two types of tags, the first tag and the second tag, from the accident situation, and based on these tags, the past accident case is identified as the first case. Search is performed from two case masters, the master and the second case master. Therefore, according to the accident analysis device 10, a plurality of case masters can be suitably handled.

(Modification)
The present invention is not limited to the above embodiments, and various modifications and applications are possible. For example, the vehicle 1000, the drive recorder 1100, the cloud storage server, the accident analysis device 10, and the terminal 20 may not have all the technical features shown in the above embodiments, and at least one In order to solve the problem, a part of the configuration described in the above embodiment may be provided. Moreover, at least a part of each of the following modified examples may be combined.

In the above embodiment, the search unit 106 obtains search results by integrating the results of ranking based on the first tag and the results of ranking based on the second tags. It may be the result. In this case, two types of search results based on the first tag and the second tag are displayed in the search results shown in FIG.

In the above-described embodiment, the first case master has tags with fine granularity, and the second case master has tags with coarse granularity. In addition, for example, the first case master may be set with tags specialized for accident cases of a specific type, and the second case master may be set with tags related to general accident cases. For example, by setting a tag specific to four-wheeled vehicle to four-wheeled vehicle in the first case master, accident cases of four-wheeled vehicle to four-wheeled vehicle can be searched with high accuracy. It will also be possible to search for typical accident cases.

In the above embodiment, two case masters, the first case master and the second case master, were handled, but three or more case masters can be handled in the same way.

In the above embodiment, drive recorder 1100 is installed in vehicle 1000 of the policyholder, but this is just an example. Instead of the drive recorder 1100, a smartphone owned by the policyholder may be used. External video data and internal video data may be captured by cameras mounted on the back and front of the smartphone.

In the above embodiment, drive recorder 1100 includes various sensors, but vehicle 1000 may incorporate various sensors instead of drive recorder 1100 . In this case, vehicle 1000 has the same configuration as communication unit 1120, positioning unit 1130, automatic diagnostic data acquisition unit 1170, control unit 1180, acceleration measurement unit 1160, and data storage unit 1200 in the above embodiment. Then, accident analysis device 10 obtains video data from drive recorder 1100 and vehicle data from vehicle 1000 .

The accident analysis system 1 can be realized using a normal computer without using a dedicated device. For example, the accident analysis system 1 that executes the above-described processes may be configured by installing a program for executing any of the above-described processes in a computer from a recording medium that stores the program. Also, one accident analysis system 1 may be configured by a plurality of computers operating in cooperation.

Any method may be used to supply the program to the computer. For example, it may be supplied via a communication line, communication network, communication system, or the like.

In addition, when an OS (Operation System) provides some of the functions described above, the parts other than the functions provided by the OS may be provided by a program.

The embodiments described above are for facilitating the understanding of the present invention, and are not intended to limit and interpret the present invention. Flowcharts, sequences, elements included in the embodiments, their arrangement, materials, conditions, shapes, sizes, and the like described in the embodiments are not limited to those illustrated and can be changed as appropriate. Also, it is possible to partially replace or combine the configurations shown in different embodiments.

DESCRIPTION OF SYMBOLS 1... Accident analysis system 10... Accident analysis apparatus 11... Processor 12... Storage device 13... Communication interface 14... Input device 15... Output device 20... Terminal 100... Storage part 101... Acquisition part, 102... analysis unit, 103... generation unit, 104... tag estimation unit, 105... tag conversion unit, 106... search unit, 107... output unit, 1000... vehicle, 1100... drive recorder, 1120... communication unit, 1130... positioning unit , 1140...Recording unit 1150...Recording unit 1160...Acceleration measuring unit 1170...Automatic diagnosis data acquisition unit 1180...Control unit 1200...Data storage unit 1300...Mirror 1400...Automatic diagnosis system.

Claims (6)

Accident case data indicating accident cases; a first case master that associates accident cases indicated by the accident case data with first tags; and a first case master that associates accident cases indicated by the accident case data with second tags. a storage means for storing two case masters;
Acquisition means for acquiring vehicle data measured by a sensor provided in the accident vehicle and video data captured by a camera provided in the accident vehicle;
analysis means for analyzing a situation of an accident caused by the accident vehicle based on the acquired vehicle data and the video data;
tag estimation means for estimating the first tag and the second tag corresponding to the accident situation based on the accident situation analyzed by the analysis means;
a search means for searching the accident case data based on the estimated first tag and the second tag by referring to the first case master and the second case master;
Accident analysis device with. further comprising tag conversion means for converting the estimated first tag into the second tag;
The tag estimating means estimates the second tag by converting the estimated first tag into the second tag by the tag converting means.
The accident analysis device according to claim 1, characterized in that: The search means ranks each accident case indicated by the first case master based on the estimated first tag, and each accident case indicated by the second case master based on the estimated second tag. rank the
3. The accident analysis device according to claim 1 or 2, characterized in that: The search means obtains search results by integrating the accident cases ranked in the first case master and the accident cases ranked in the second case master.
4. The accident analysis device according to claim 3, characterized in that: an acquisition step of acquiring vehicle data measured by a sensor provided in the accident vehicle and video data captured by a camera provided in the accident vehicle;
an analysis step of analyzing a situation of an accident caused by the accident vehicle based on the obtained vehicle data and the image data;
a tag estimation step of estimating a first tag and a second tag corresponding to the accident situation based on the analyzed accident situation;
A search step of searching for accident case data indicating accident cases, wherein a first case master in which the accident case indicated by the accident case data and the first tag are associated with each other, and the accident case indicated by the accident case data and the first tag are searched. a searching step of searching for the accident case data based on the estimated first tag and the second tag by referring to a second case master in which the two tags are associated;
an accident analysis method comprising: to the computer,
an acquisition step of acquiring vehicle data measured by a sensor provided in the accident vehicle and video data captured by a camera provided in the accident vehicle;
an analysis step of analyzing a situation of an accident caused by the accident vehicle based on the obtained vehicle data and the image data;
a tag estimation step of estimating a first tag and a second tag corresponding to the accident situation based on the analyzed accident situation;
A search step of searching for accident case data indicating accident cases, wherein a first case master in which the accident case indicated by the accident case data and the first tag are associated with each other, and the accident case indicated by the accident case data and the first tag are searched. a searching step of searching for the accident case data based on the estimated first tag and the second tag by referring to a second case master in which the two tags are associated;
program to run.

Images