Vehicle damage assessment processing method, device, equipment and storage medium

By receiving and analyzing the data of the accident owner's terminal, automatically performing monitoring video authentication and trajectory loss identification and generating documents, it solves the problem of when personnel arrive at the vehicle accident site, and realizes a rapid loss determination and claim processing process, improving efficiency and Car owner satisfaction.

CN115131702BInactive Publication Date: 2024-11-19CHINA PING AN LIFE INSURANCE CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202210737610.4
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2022-06-27
Publication Date
2024-11-19
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

After a vehicle accident, the existing technology requires traffic police and insurance company personnel to arrive at the site for damage assessment and claims processing, resulting in long wait times for car owners, low efficiency, and affecting road traffic rates.

Method used

By receiving the pending data sent by the owner terminal of the accident, performing positioning analysis and monitoring video authentication, automatically identifying the trajectory loss determination results, and generating audit documents to realize the automatic loss determination and claim settlement process without the participation of on-site personnel.

Benefits of technology

It greatly improves the efficiency of loss determination and claims settlement, saves car owners' waiting time, and improves road traffic rate and car owner experience satisfaction.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN115131702B_ABST
    Figure CN115131702B_ABST
Patent Text Reader

Abstract

The present invention relates to the technical field of data processing, and the present invention discloses a vehicle damage assessment processing method, device, equipment and storage medium, the method comprising: by receiving data to be processed, locating and parsing each data to be processed, obtaining the accident location address and the monitoring interface matching the accident location address; calling the first monitoring video associated with each monitoring interface, and according to each first monitoring video called, performing user authentication on each data to be processed, and obtaining the authentication result; according to the authentication result, determining the user information corresponding to each data to be processed; performing trajectory damage assessment identification on the first monitoring video, and identifying the damage assessment result; according to the damage assessment result and all user information, performing document generation and document review processing on each data to be processed, and obtaining the review result corresponding to each data to be processed one by one. Therefore, the present invention realizes automatic damage assessment, improves the traffic rate of the road, ensures the smooth flow of the road, and improves the driving experience satisfaction of the car owner.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a vehicle damage assessment processing method, device, equipment and storage medium. Background Art

[0002] At present, with the acceleration of social development and the improvement of people's living standards, the coverage of urban roads and highways is getting wider and wider, and the popularity of self-driving vehicles is also getting wider and wider. During peak hours, the vehicles on urban roads and highways will be crowded, and vehicle accidents are very likely to occur. Once a vehicle accident occurs, it is necessary to preserve the accident scene, the owner of the accident vehicle reports the accident, and wait for the traffic police and the insurance company to arrive at the accident scene. It often takes a long time to determine the damage and start the claims process after arriving at the accident scene. Therefore, it greatly wastes the owner's time and affects the driving routes of other vehicles on the road, greatly reducing the efficiency of damage determination and claims, and reducing the road's traffic rate. Summary of the invention

[0003] The present invention provides a vehicle damage assessment processing method, device, computer equipment and storage medium, which realize automatic damage assessment and start the claim settlement process, and quickly determine the review result of the claim settlement, without the need for relevant staff to arrive at the scene to collect accident data and assess the damage, thereby improving the damage assessment efficiency and the claim settlement efficiency, greatly saving the waiting time of the car owner, and improving the car owner's driving experience satisfaction.

[0004] A vehicle damage assessment method, comprising:

[0005] receiving at least one data to be processed, performing location analysis on each of the data to be processed, and obtaining an accident location address and at least one monitoring interface matching the accident location address;

[0006] Retrieving the first monitoring video associated with each of the monitoring interfaces, and performing user authentication on each of the to-be-processed data according to each of the retrieved first monitoring videos to obtain an authentication result;

[0007] Determining user information corresponding to each of the data to be processed according to the authentication result;

[0008] Performing trajectory damage assessment on the first surveillance video to identify a damage assessment result;

[0009] According to the damage assessment result and all the user information, documents are generated and reviewed for each of the data to be processed, and review results corresponding to each of the data to be processed are obtained.

[0010] A vehicle damage assessment processing device, comprising:

[0011] A receiving module, configured to receive at least one piece of data to be processed, locate and analyze each piece of data to be processed, and obtain an accident location address and at least one monitoring interface matching the accident location address;

[0012] An authentication module, used to retrieve the first monitoring video associated with each of the monitoring interfaces, and perform user authentication on each of the to-be-processed data according to each of the retrieved first monitoring videos to obtain an authentication result;

[0013] A determination module, used to determine the user information corresponding to each of the data to be processed according to the authentication result;

[0014] A damage assessment module, used to perform trajectory damage assessment on the first monitoring video and identify a damage assessment result;

[0015] The audit module is used to generate and audit documents for each of the data to be processed based on the damage assessment results and all the user information, and obtain audit results that correspond one-to-one to each of the data to be processed.

[0016] A computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above-mentioned vehicle damage assessment processing method when executing the computer program.

[0017] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the above-mentioned vehicle damage assessment processing method.

[0018] The vehicle damage assessment processing method, device, computer equipment and storage medium provided by the present invention receive at least one data to be processed, locate and analyze each of the data to be processed, and obtain the accident location address and at least one monitoring interface matching the accident location address; call the first monitoring video associated with each of the monitoring interfaces, and perform user authentication on each of the data to be processed based on each of the first monitoring videos called, and obtain the authentication result; determine the user information corresponding to each of the data to be processed based on the authentication result; perform trajectory damage assessment on the first monitoring video to identify the damage assessment result; generate and review documents for each of the data to be processed based on the damage assessment result and all the user information, and obtain the review result corresponding to each of the data to be processed one by one, thereby realizing the damage assessment through location and analysis. The accident location address of the reported data sent by the terminal held by each accident vehicle owner is analyzed, the monitoring video corresponding to the accident location address is automatically retrieved, and the user information of the accident vehicle owner is determined through user authentication, and the damage assessment result is identified through trajectory damage assessment, so as to automatically generate documents and review documents based on the damage assessment result and user information, and finally determine the review result. In this way, the accident vehicle owner only needs to "shake" on the damage assessment application of the terminal to report the accident data (pending data), and there is no need for relevant staff (such as traffic police, claims personnel, etc.) to arrive at the scene and manually assess the damage. The damage is directly and automatically assessed and the claim process is initiated, and the review result of the claim is quickly determined, which improves the efficiency of damage assessment and claims settlement, greatly saves the waiting time of the car owner, and improves the traffic rate of the road, ensures the smooth flow of the road, and improves the driving experience satisfaction of the car owner. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments of the present invention will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative labor.

[0020] Figure 1 Schematic diagram of the application environment of the vehicle damage assessment processing method in one embodiment of the present invention;

[0021] Figure 2 is a flow chart of a vehicle damage assessment processing method in one embodiment of the present invention;

[0022] Figure 3 is a flow chart of step S10 of a vehicle damage assessment processing method in one embodiment of the present invention;

[0023] Figure 4 is a flow chart of step S20 of a vehicle damage assessment processing method in one embodiment of the present invention;

[0024] Figure 5 is a flow chart of step S30 of a vehicle damage assessment processing method in one embodiment of the present invention;

[0025] Figure 6 is a flow chart of step S40 of a vehicle damage assessment processing method in one embodiment of the present invention;

[0026] Figure 7 is a principle block diagram of a vehicle damage assessment processing device in one embodiment of the present invention;

[0027] Figure 8 is a schematic diagram of a computer device in one embodiment of the present invention. DETAILED DESCRIPTION

[0028] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0029] The vehicle damage assessment method provided by the present invention can be applied in the following aspects: Figure 1 In an application environment, a client (computer device or mobile terminal) communicates with a server through a network. The client (computer device or mobile terminal) includes but is not limited to various personal computers, laptops, smart phones, tablet computers, cameras, and portable wearable devices. The server can be implemented as an independent server or a server cluster consisting of multiple servers.

[0030] The vehicle damage assessment processing method is executed by a server.

[0031] In one embodiment, if Figure 2 As shown, a vehicle damage assessment method is provided, and its technical solution mainly includes the following steps S10-S50:

[0032] S10, receiving at least one data to be processed, performing location analysis on each of the data to be processed, and obtaining an accident location address and at least one monitoring interface matching the accident location address.

[0033] It is understandable that after the car owner downloads the damage assessment application on the terminal or client held by the car owner, he will start the damage assessment application, enter the car owner's relevant information, and obtain authorization to access the location. When a traffic accident occurs on urban roads or highways, both or multiple accident car owners only need to start the damage assessment application, "shake" the handheld terminal or click the "shake" button to automatically report the accident, and send the data to be processed. The data to be processed is the positioning data, user identification and other data related to the accident reported by the accident car owner. The data to be processed contains the terminal's positioning coordinate information and the user identification of the car owner who logs in to the damage assessment application (for example, the car owner's mobile phone number). The positioning coordinate information is the latitude and longitude coordinates of the terminal held by the car owner.

[0034] Among them, the data to be processed are received from two or more accident owners, and positioning and analysis are performed on each of the data to be processed. The process of the positioning and analysis is to locate the positioning coordinate information in the data to be processed on a road map, locate the corresponding positioning address, and merge the adjacent positioning addresses into an accident positioning address, and scan the monitoring interface in a preset range area of ​​the accident positioning address. The monitoring interface is an interface address corresponding to a monitoring camera installed on a city road or a highway.

[0035] In one embodiment, if Figure 3 As shown, in the step S10, the positioning and parsing of each of the data to be processed to obtain an accident location address and at least one monitoring interface matching the accident location address includes:

[0036] S101, performing road positioning on each of the positioning coordinate information to obtain a positioning address corresponding to each of the positioning coordinate information; the data to be processed includes the positioning coordinate information.

[0037] It can be understood that the road positioning is to locate on the road map through the longitude and latitude in the positioning coordinate information. If the located position point falls into the road of the road map, the located position point is recorded as the positioning address corresponding to the positioning coordinate information. When the located position point deviates from the road, the shortest distance of the located position point from the road is automatically used as the repositioning direction until it moves and falls into the position of the road. The fallen position is recorded as the positioning address corresponding to the deviated positioning coordinate information, wherein the road map is a map integrating all urban roads and highways, and one positioning coordinate information corresponds to one positioning address.

[0038] S102: Determine the accident location address and the road accident area according to all the location addresses.

[0039] Understandably, all the positioning addresses are grouped, and the positioning addresses whose Euclidean distance to a positioning address is less than a preset distance are divided into a group, and the overlapping areas between groups with an area greater than a preset area are merged into one group, and the merged group is averaged on the road route, that is, a location point on the road route with the shortest distance to each positioning address in the group is taken, and the location point is recorded as the accident positioning address. With the accident positioning address as the center of the circle, the circular area is extended outward until the extended circular area covers all the positioning addresses in the group and the radius exceeds the preset length of the farthest positioning address. The preset length can be set according to demand, and the circle can be determined as the road accident area, or the area where the circle overlaps with the road in the road map can be recorded as the road accident area corresponding to the group.

[0040] The accident location address is the address where the accident occurred, and the road accident area is the affected area covered by the accident on the road.

[0041] S103, scanning the monitoring interfaces in the road accident area to obtain at least one monitoring interface.

[0042] It can be understood that the road accident area is mapped to the monitoring map to scan the monitoring interfaces in the mapped area. The monitoring map is a distribution map of the monitoring interfaces corresponding to the monitoring devices or monitoring cameras that have been set up. The road accident area in the road map can also be scanned to scan the monitoring interfaces of the monitoring devices or monitoring cameras that have been marked in the road map, so that at least one of the monitoring interfaces can be scanned.

[0043] The present invention realizes road positioning for each of the positioning coordinate information to obtain a positioning address corresponding to the positioning coordinate information in each of the data to be processed; according to all the positioning addresses, the accident positioning address and the road accident area are determined; the monitoring interface in the road accident area is scanned to obtain at least one of the monitoring interfaces, so that the accident positioning address and the road accident area can be quickly and accurately positioned, and the corresponding monitoring interface can be automatically scanned without manually calling the corresponding monitoring interface, thereby saving labor costs and time, and improving the accuracy and correctness of determining the accident positioning address and the road accident area, as well as improving the efficiency of positioning.

[0044] S20, retrieve the first monitoring video associated with each of the monitoring interfaces, and perform user authentication on each of the to-be-processed data according to the retrieved first monitoring videos to obtain an authentication result.

[0045] It can be understood that the retrieval process is to determine the time range that needs to be retrieved according to the reporting time in the data to be processed, that is, the process of obtaining the monitoring video stored or collected by the monitoring interface within the time period before and after the reporting time, and determining the video as the first monitoring video associated with the monitoring interface. The user authentication process is to extract images related to the owner from all the first monitoring videos, such as: faces, license plates and vehicle models, which will be associated with the owner's information, identify the information in the image, and determine the list of possible owners in the accident based on the information in the identified image, as well as the process of comparing the corresponding information of the list with the owner information in the data to be processed, and judging whether the owner information has been authenticated. The authentication result reflects the result of whether the owner information in each of the data to be processed has been authenticated.

[0046] In one embodiment, if Figure 4 As shown, in step S20, that is, performing user authentication on each of the to-be-processed data according to each of the first surveillance videos retrieved to obtain an authentication result, including:

[0047] S201, performing vehicle owner recognition on all the first surveillance videos to identify vehicle owner results in the first surveillance videos.

[0048] It can be understood that the vehicle owner identification is to capture the faces and license plates in all the first surveillance videos, capture face images and license plate images, perform face recognition on the face images through a face recognition model to identify the face recognition result, perform license plate number recognition on the license plate image through a license plate number recognition model to identify the license plate recognition result, and the face recognition result and the license plate recognition result can be merged to obtain the vehicle owner result, or the face recognition result and the license plate recognition result can be combined in pairs, and the combined results are matched with the vehicle owner to match the combination in which the degree of matching between the vehicle owner and the license plate is greater than or equal to a preset threshold, and the matched combinations are summarized to obtain the vehicle owner result. The vehicle owner result reflects the result of the association matching between the vehicle owner and the license plate in all the first surveillance videos, that is, the result of the correct matching relationship of the vehicle owner driving the vehicle with the license plate.

[0049] In one embodiment, the step S201, i.e., performing vehicle owner identification on all the first surveillance videos to identify the vehicle owner in the first surveillance videos, includes:

[0050] The first surveillance video is used to capture a face, and face recognition is performed on the captured face image to obtain a face recognition result.

[0051] It can be understood that the face capture process is to perform frame processing on the first surveillance video to obtain image frames, then perform face target recognition on the face in the image frame to identify the face area, then extract the image of the identified face area, and record the extracted image as the face image. The face recognition process is to extract face features from the face image to extract a face feature map, and obtain feature vector values ​​of various face dimensions based on the extracted face feature map, for example: vector values ​​of facial feature positioning point features, vector values ​​of eye features, and vector values ​​of nose features. The vector values ​​of the features, the vector values ​​of the mouth features, the vector values ​​of the facial texture features and the vector values ​​of the facial contour features are compared with the feature vector values ​​of each facial dimension and the feature vectors of the facial photos of all drivers with a driver's license, and the driver's facial photo corresponding to the highest similarity greater than or equal to a preset threshold is compared, so that the facial image is associated with the identified driver as the face recognition result of the facial image, and the unrecognized facial image (the facial image with the highest similarity less than the preset threshold) is not processed, not associated with the driver, and its face recognition result is empty.

[0052] The frame segmentation process is to segment each frame in the input video or to segment each frame at intervals of a preset frame. The face image is an image containing a face in the first surveillance video. The face features are features related to the face. The face features include features of facial features, eye features, nose features, mouth features, and facial contour features.

[0053] The license plate is captured from the first surveillance video, and the license plate number is recognized on the captured license plate image to obtain a license plate recognition result.

[0054] It can be understood that the process of license plate capture is to perform the frame segmentation processing on the input first surveillance video, divide the image frames, perform license plate target recognition on the license plate in the image frames, identify the license plate area with license plate features, and then extract the image of the identified license plate area, and record the extracted image as the license plate image. The process of license plate number recognition is to extract text features and digital features of the license plate image, and recognize the text and numbers in the license plate image based on the extracted text features and digital features, identify the license plate number of the license plate image, and use it as the license plate recognition result of the license plate image, which represents the license plate number result in the license plate image.

[0055] The license plate features are features related to the license plate, such as the background color of the license plate, the number of digits, the license plate number rule, the number format, and the like.

[0056] The face recognition result and the license plate recognition result are matched and identified to identify the owner of the vehicle.

[0057] It can be understood that the process of car owner matching and identification is to combine the face recognition results and the license plate recognition results in pairs, search the car owner database to see whether there is an association relationship consistent with the combined result, retain the association relationship consistent with the combined result, and record the combined result as one of the car owner results. The car owner result reflects the results of all the associations between the car owner and the license plate in the first surveillance video, that is, the results of the correct matching relationship of the car owner driving the vehicle with the license plate. The car owner result also represents the set of associations between the car owner and the license plate number in the first surveillance video.

[0058] The car owner database stores a collection of all car owners and their associated license plate numbers.

[0059] The present invention realizes face capture on the first monitoring video and face recognition on the captured face image to obtain a face recognition result; license plate capture on the first monitoring video and license plate number recognition on the captured license plate image to obtain a license plate recognition result; owner matching recognition is performed on the face recognition result and the license plate recognition result to identify the owner result. In this way, the face and license plate number in the first monitoring video can be automatically identified, and the owner result for the possible association between the owner and the license plate number in the accident can be automatically identified through owner matching recognition, without manual identification, and the identified owner result is more accurate and correct, providing a data basis for user authentication of subsequent accidents.

[0060] S202, searching for vehicle information and insurance policy information corresponding to the owner information in the data to be processed.

[0061] It can be understood that the data packet to be processed contains the owner information, which is the unique information of the "shake" terminal, such as a mobile phone number. The vehicle information and insurance policy information corresponding to the owner information are searched in the cloud server. The vehicle information is the relevant information of the vehicle bound to the owner information, such as the vehicle's license plate number, motor vehicle number, etc. The insurance policy information is the information contained in the insurance policy bound to the owner information, such as the name, ID number, policy number, etc. in the insurance policy bound to the owner information. The cloud server is a cross-database storage that stores all owner information and vehicle information corresponding to the owner information one by one, as well as a collection of insurance policy information. All different databases that provide insurance policy information can be accessed in the cloud server.

[0062] S203, according to the vehicle owner result, user authentication is performed on the vehicle information and the insurance policy information to obtain the authentication result; the authentication result reflects whether the vehicle owner information in each of the data to be processed has passed the authentication.

[0063] It can be understood that the process of user authentication of the vehicle information and the insurance policy information is to combine the license plate number in the vehicle information and the name in the insurance policy information, compare the combined result with the car owner result one by one, and determine whether the combined result can be found in the car owner result. If it can be found in the car owner result, the owner information corresponding to the searchable combination is marked as the authenticated owner information. If it cannot be found in the car owner result, the owner information corresponding to the unfound combination is marked as the unauthenticated owner information. The authentication result reflects the result of whether the owner information in each of the data to be processed is authenticated.

[0064] The present invention realizes that the owner of the vehicle in all the first monitoring videos is identified, and the owner result in the first monitoring video is identified; the vehicle information and insurance policy information corresponding to the owner information in the data to be processed are searched; according to the owner result, the vehicle information and the insurance policy information are authenticated by the user to obtain the authentication result. In this way, the owner of the vehicle can be automatically identified and the user can be authenticated automatically for the first monitoring video to obtain the authentication result of the owner information. Without manual authentication, the owner who has reported an accident can be authenticated automatically through the video at the scene, thereby accurately authenticating the accident owner and improving the accuracy and correctness of user authentication.

[0065] S30: Determine user information corresponding to each piece of data to be processed according to the authentication result.

[0066] It is understandable that when it is detected that there is no unauthenticated owner information in the authentication result, the user information associated with the authenticated owner information in the authentication result is retrieved; when it is detected that there is unauthenticated owner information in the authentication result, further owner authentication is performed on the unauthenticated owner information, and the owner authentication can be performed by taking a full-range video of the accident location address by a drone, and then the authentication result is updated, thereby retrieving the user information associated with the authenticated owner information in the updated authentication result.

[0067] The user information is the relevant information of the accident vehicle owner corresponding one-to-one to the data to be processed.

[0068] In one embodiment, if Figure 5 As shown, in the step S30, that is, determining the user information corresponding to each of the data to be processed according to the authentication result, includes:

[0069] S301, when it is detected that the authentication result contains information of the owner that has not passed the authentication, searching for a video acquisition device that is closest to the accident location address.

[0070] It is understandable that if there is information of the owner who has not passed the authentication in the authentication result, the accident location address is used as the center of the circle on the road map, and the radius is continuously expanded to scan. When the mark of the video acquisition device is scanned, the scanned video acquisition device is determined as the nearest video acquisition device. The video acquisition device is a device that can move and shoot videos, and the video acquisition device can be a drone.

[0071] S302, planning a moving route for the video acquisition device to the accident location address, and starting the video acquisition device to move along the moving route.

[0072] It can be understood that the process of planning the moving route of the video acquisition device to the accident location address is to apply navigation technology to identify the highest point of the terrain in the straight-line distance between the mark point of the video acquisition device and the accident location address, and set the preset height exceeding the highest point of the terrain as the height at which the video acquisition device rises. The moving route is the rising height, and the straight-line route from the mark point of the video acquisition device and the accident location address, and then the descending route from the rising height, and the video acquisition device is started to move according to the moving route. During the movement, the process of descending from a high altitude will continuously identify the accident vehicle (i.e., a vehicle parked on the roadside or stationary), so that the accident vehicle is distributed exactly in the middle position of the collected image, and the area occupied by the accident vehicle accounts for a preset proportion of the collected image, such as 80%, and the point where it stops at this moment is the best visual point.

[0073] The highest point of the terrain is the highest altitude among the altitudes of each point between the two points. The height at which the video acquisition device rises is obtained by adding the preset height to the difference between the highest altitude and the altitude of the video acquisition device.

[0074] S303, obtaining a second monitoring video of the video acquisition device; the second monitoring video is obtained by the video acquisition device performing all-round collection at the accident location address.

[0075] Understandably, the video acquisition device can transmit the acquired second surveillance video to the cloud server through a wireless network. The wireless network can be a wireless router accessing the Internet network and then transmitting it to the cloud server, or transmitting it to the cloud server through a 4G or 5G network. The second surveillance video is obtained by the video acquisition device through all-round acquisition at the accident location address. The all-round acquisition is centered on the best visual point, and video is acquired from the positions in front of, behind, left, right, upper left, upper right, lower left, and lower right of this center point towards the center point direction, that is, on the same plane as the best visual point. When the clarity of the acquired video is lower than the preset clarity threshold, it is moved up and down in the vertical direction to achieve a clarity reaching the preset clarity threshold. For example: the best visual point is the center point of the character "田" (field), the all-round acquisition positions are the intersections of the character "田", and the cameras all acquire towards the center point direction and autofocus on the center point position. In this way, videos of the accident scene can be acquired from all directions, and the real picture of the accident scene can be quickly acquired, providing a data basis for subsequent loss assessment.

[0076] S304. Identify and authenticate the unauthenticated vehicle owners in the second surveillance video, and update the authentication result.

[0077] Understandably, the identification of unauthenticated vehicle owners is a process of performing face recognition and license plate number recognition on each frame of the image in the second surveillance video, removing the combinations of authenticated vehicle owners from the recognized results to obtain the final unauthenticated vehicle owner identification result. Then, the unauthenticated vehicle owners are authenticated. The process of authenticating unauthenticated vehicle owners is to perform corresponding comparison and authentication on the vehicle information and the policy information according to the unauthenticated vehicle owner identification result, that is, to compare one by one the remaining unauthenticated vehicle owner information in the vehicle information and the policy information with the combinations in the unauthenticated vehicle owner identification result to determine whether there is a consistent situation, and change the unauthenticated vehicle owner information with a consistent situation from unauthenticated to authenticated, so as to add the changed authenticated vehicle owner information to the authentication result to achieve the update of the authentication result.

[0078] S305. Retrieve the user information associated with the vehicle owner information authenticated in the authentication result.

[0079] Understandably, retrieve the user information associated with the vehicle owner information marked as authenticated in the authentication result in the cloud server. The user information is the relevant information of the accident vehicle owner corresponding one-to-one to the data to be processed.

[0080] The present invention realizes that when it is detected that the authentication result contains unauthenticated owner information, the video acquisition device closest to the accident location address is searched; a moving route of the video acquisition device to the accident location address is planned, and the video acquisition device is started to move according to the moving route; a second monitoring video of the video acquisition device is obtained; unauthenticated owner identification and unauthenticated owner authentication are performed on the second monitoring video, and the authentication result is updated; the user information associated with the authenticated owner information in the authentication result is retrieved, so that when unauthenticated owner information exists, the video acquisition device is automatically started to capture the second monitoring video, and the authentication result is updated through unauthenticated owner identification and unauthenticated owner authentication, thereby retrieving the updated user information, and all owner information can be authenticated more accurately, without the need for manual on-site verification of unauthenticated owners, thereby reducing verification costs and improving vehicle damage assessment efficiency.

[0081] S40, performing trajectory damage assessment on the first monitoring video to identify a damage assessment result.

[0082] It can be understood that the trajectory damage assessment identification is to simulate the vehicle trajectory of the vehicle in the first monitoring video, simulate the driving process of the vehicle in the accident, and analyze the simulated driving process in various dimensions related to damage assessment to analyze the identification process of the damage assessment result.

[0083] Among them, the damage assessment result is the result of determining the responsible party and the extent of the accident. The damage assessment result reflects the type of responsibility of the car owner in the accident and the type of damage to the vehicle.

[0084] In one embodiment, if Figure 6 As shown, in step S40, that is, performing trajectory damage assessment on the first monitoring video and identifying the damage assessment result, the step includes:

[0085] S401, based on all the user information, simulate the vehicle trajectory of all the first monitoring videos to construct a vehicle trajectory model.

[0086] It can be understood that according to the association between the owner and the license plate number in all the user information, all the vehicles in the first surveillance video are marked with license plate numbers or owners, and then the vehicle trajectory simulation is performed according to the moving trajectory of the marked vehicle. The process of the vehicle trajectory simulation is to convert the shooting perspective of the first surveillance video into a plane path, simulate the moving position of the marked vehicle on the plane path according to the movement of the perspective, and convert the length, width and height of the vehicle into plane dimensions through the image ratio, so as to construct a vehicle trajectory model. The vehicle trajectory model is a model of the moving trajectory of the marked vehicle when the size of the vehicle remains unchanged.

[0087] S402, performing damage assessment analysis on the vehicle trajectory model to obtain the damage assessment result.

[0088] It can be understood that the damage assessment analysis process is a process of performing a speed simulation analysis on the vehicles in the vehicle trajectory model, a collision simulation analysis on the vehicles in the vehicle trajectory model, and a movement compliance analysis on the vehicles in the vehicle trajectory model, and combining all analysis results to determine the damage assessment result, which reflects the type of responsibility of the vehicle owner in the accident and the type of damage to the vehicle.

[0089] The present invention realizes the construction of a vehicle trajectory model by simulating the vehicle trajectory of all the first monitoring videos based on all the user information; performing damage assessment analysis on the vehicle trajectory model and analyzing the damage assessment result. In this way, the vehicle trajectory model can be automatically constructed and the damage assessment can be automatically performed without manual damage assessment, thereby improving the efficiency and accuracy of damage assessment.

[0090] In one embodiment, the step S402, i.e., performing damage assessment analysis on the vehicle trajectory model to obtain the damage assessment result, includes:

[0091] A vehicle speed simulation analysis is performed on the vehicles in the vehicle trajectory model to obtain a vehicle speed analysis result.

[0092] It can be understood that the vehicle speed simulation analysis is to mark the moving speed of the three-dimensional center of the marked vehicle in the vehicle trajectory model at each point on the moving trajectory, and a curve graph of time and speed for each marked vehicle can be obtained, and the curve graph is recorded as the vehicle speed analysis result, or the vehicle speed analysis result in time and acceleration. The vehicle speed analysis result reflects the time-moving speed / acceleration curve graph of each accident vehicle.

[0093] A collision simulation analysis is performed on the vehicles in the vehicle trajectory model to obtain a collision analysis result.

[0094] It can be understood that the collision simulation analysis is to determine whether there is any overlapping volume of each marked vehicle according to the movement trajectory in the vehicle trajectory model when the marked vehicle does not change its size, and the overlapping volume is associated with the two vehicles, so as to summarize the overlapping volume at all time points and record it as the collision analysis result, which reflects the result of the overlapping volume between the vehicles on the timeline.

[0095] Performing a mobile compliance analysis on the vehicles in the vehicle trajectory model to obtain a compliance analysis result.

[0096] It can be understood that the vehicle trajectory model also includes the headlight lighting records of each marked vehicle, that is, the headlight conditions at each trajectory point are recorded, and the mobile compliance analysis is to analyze whether the driving of each marked vehicle is compliant based on the headlight lighting records of two vehicles in a preset time period before the overlapping volume appears in the collision analysis result, thereby outputting the compliance identification of each marked vehicle at each trajectory point, thereby determining the compliance analysis result, and the compliance analysis result reflects the collection of driving compliance records of each vehicle on the timeline.

[0097] The preset time period can be set according to the requirements, for example, 5S or 10S.

[0098] The damage assessment result is determined based on the vehicle speed analysis result, the collision analysis result and the compliance analysis result.

[0099] It can be understood that on the time axis of the vehicle speed analysis results, the collision analysis results and the compliance analysis results, the speed / acceleration, overlapping volume and compliance record of each vehicle determine the responsibility type of each vehicle, that is, determine whether each vehicle is the active party or the passive party, and according to the range of the overlapping volume of each vehicle, determine the damage type of each vehicle, that is, determine the damage types such as minor scratches, moderate dents, and severe dents, so as to summarize all responsibility types and damage types, perform probability analysis of the responsibility types on the summarized results, remove duplicates and take the damage type with the greatest degree, and output the damage assessment result.

[0100] The present invention realizes obtaining a vehicle speed analysis result by performing a vehicle speed simulation analysis on the vehicles in the vehicle trajectory model; obtaining a collision analysis result by performing a collision simulation analysis on the vehicles in the vehicle trajectory model; obtaining a compliance analysis result by performing a mobile compliance analysis on the vehicles in the vehicle trajectory model; and determining the damage assessment result according to the vehicle speed analysis result, the collision analysis result and the compliance analysis result. In this way, the damage assessment result can be automatically determined through simulation analysis of dimensions such as vehicle speed, collision and mobile compliance, without the need for manual damage assessment, and the objectivity and accuracy of damage assessment are improved.

[0101] S50, based on the damage assessment result and all the user information, generate and review the documents for each of the data to be processed, and obtain the review results corresponding to each of the data to be processed.

[0102] Understandably, according to the damage assessment result, the marked vehicle is matched with the user information, and then the marked vehicle can be associated with the data to be processed one by one, and finally the responsibility type and damage type of each of the data to be processed are determined. The process of generating the document is to generate a declaration document corresponding to each of the data to be processed based on the responsibility type and damage type of each of the data to be processed, that is, to automatically fill in the corresponding responsibility type and damage type into the corresponding position in the document template, and then synthesize a new document, and initiate the process of document review with the generated document. The process of document review processing is to send the generated document to the cloud server. And according to the user information corresponding to each document, the corresponding cross-server address is sent, and the vehicle damage assessment process is completed by receiving the audit result from the cloud server. The audit result is the result returned to the cloud server after cross-server audit. The audit result reflects the result of cross-server approval of the corresponding documents at all links. The corresponding audit result is received by the terminal of the accident vehicle owner corresponding to each of the data to be processed, realizing the rapid assessment of the entire process of vehicle damage assessment. The damage assessment can be completed by just "shaking", without the need for manual arrival at the scene, and the accident scene can be quickly left, achieving the effect of quickly clearing the road and avoiding road congestion.

[0103] Wherein, one piece of the to-be-processed data is associated with one piece of the owner information, and one piece of the owner information is associated with one piece of the user information.

[0104] The present invention realizes receiving at least one data to be processed, locating and analyzing each of the data to be processed, obtaining the accident location address and at least one monitoring interface matching the accident location address; calling the first monitoring video associated with each of the monitoring interfaces, and performing user authentication on each of the data to be processed based on each of the called first monitoring videos to obtain an authentication result; determining the user information corresponding to each of the data to be processed based on the authentication result; performing trajectory damage assessment on the first monitoring video to identify the damage assessment result; and performing document generation and document review processing on each of the data to be processed based on the damage assessment result and all the user information to obtain an audit result corresponding to each of the data to be processed. Therefore, it is realized that the terminal held by each accident vehicle owner is determined by locating and parsing. The accident location address of the reported data sent out automatically retrieves the surveillance video corresponding to the accident location address, and determines the user information of the accident owner through user authentication, and identifies the damage assessment result through trajectory damage assessment, so as to automatically generate documents and review documents based on the damage assessment result and user information, and finally determine the review result. In this way, the accident owner only needs to "shake" on the damage assessment application on the terminal to report the accident data (pending data), without the need for relevant staff (such as traffic police, claims personnel, etc.) to arrive at the scene and manually assess the damage. It can directly and automatically assess the damage and start the claims process, and quickly determine the review result of the claims, which improves the efficiency of damage assessment and claims settlement, greatly saves the waiting time of car owners, and improves the traffic rate of roads, ensures smooth roads, and improves the driving experience satisfaction of car owners.

[0105] It should be understood that the order of execution of the steps in the above embodiment does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.

[0106] In one embodiment, a vehicle damage assessment processing device is provided, and the vehicle damage assessment processing device corresponds one-to-one to the vehicle damage assessment processing method in the above embodiment. Figure 7 As shown, the vehicle damage assessment processing device includes a receiving module 11, an authentication module 12, a determination module 13, a damage assessment module 14 and an audit module 15.

[0107] The detailed description of each functional module is as follows:

[0108] The receiving module 11 is used to receive at least one data to be processed, locate and analyze each of the data to be processed, and obtain an accident location address and at least one monitoring interface matching the accident location address;

[0109] The authentication module 12 is used to retrieve the first monitoring video associated with each of the monitoring interfaces, and perform user authentication on each of the to-be-processed data according to each of the retrieved first monitoring videos to obtain an authentication result;

[0110] A determination module 13, configured to determine user information corresponding to each of the data to be processed according to the authentication result;

[0111] A damage assessment module 14 is used to perform trajectory damage assessment on the first monitoring video and identify a damage assessment result;

[0112] The audit module 15 is used to generate and audit documents for each of the data to be processed based on the damage assessment results and all the user information, and obtain audit results that correspond one-to-one to each of the data to be processed.

[0113] For the specific definition of the vehicle damage assessment processing device, please refer to the definition of the vehicle damage assessment processing method above, which will not be repeated here. The various modules in the above-mentioned vehicle damage assessment processing device can be implemented in whole or in part through software, hardware and their combination. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0114] In one embodiment, a computer device is provided. The computer device may be a client or a server. The internal structure diagram thereof may be as follows: Figure 8 As shown. The computer device includes a processor, a memory, a network interface and a database connected via a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a readable storage medium and an internal memory. The readable storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the readable storage medium. The network interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, a vehicle damage assessment processing method is implemented.

[0115] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, and when the processor executes the computer program, the vehicle damage assessment processing method in the above embodiment is implemented.

[0116] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the vehicle damage assessment processing method in the above embodiment is implemented.

[0117] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided by the present invention can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0118] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0119] The embodiments described above are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A vehicle damage assessment method, It is characterized in that include: receiving at least one data to be processed, performing location analysis on each of the data to be processed, and obtaining an accident location address and at least one monitoring interface matching the accident location address; Retrieving the first monitoring video associated with each of the monitoring interfaces, and performing user authentication on each of the to-be-processed data according to each of the retrieved first monitoring videos to obtain an authentication result; Determining user information corresponding to each of the data to be processed according to the authentication result; Performing trajectory damage assessment on the first surveillance video to identify a damage assessment result; According to the damage assessment result and all the user information, a document is generated and a document audit is performed on each of the data to be processed, and an audit result corresponding to each of the data to be processed is obtained; The performing trajectory damage assessment on the first monitoring video to identify a damage assessment result includes: Based on all the user information, simulate the vehicle trajectory of all the first monitoring videos to construct a vehicle trajectory model; Performing damage assessment analysis on the vehicle trajectory model to obtain the damage assessment result; The performing damage assessment analysis on the vehicle trajectory model to obtain the damage assessment result includes: Performing a vehicle speed simulation analysis on the vehicles in the vehicle trajectory model to obtain a vehicle speed analysis result; A collision simulation analysis is performed on the vehicles in the vehicle trajectory model to obtain a collision analysis result; the collision simulation analysis is to determine whether there is an overlapping volume of each marked vehicle according to the movement trajectory in the vehicle trajectory model when the marked vehicle does not change its size, associate the overlapping volume with the two vehicles, summarize the overlapping volumes at all time points, and record them as the collision analysis result, which reflects the result of the overlapping volume between the vehicles on the time axis; Performing a mobile compliance analysis on the vehicles in the vehicle trajectory model to obtain a compliance analysis result; the mobile compliance analysis is to analyze whether the driving of each marked vehicle is compliant based on the headlight lighting records of each vehicle in a preset time period before the overlap volume appears in the collision analysis result, thereby outputting the compliance identification of each marked vehicle at each trajectory point to determine the compliance analysis result; The damage assessment result is determined based on the vehicle speed analysis result, the collision analysis result and the compliance analysis result.

2. The vehicle damage assessment method according to claim 1, It is characterized in that The performing location analysis on each of the to-be-processed data to obtain an accident location address and at least one monitoring interface matching the accident location address includes: Performing road positioning on each of the positioning coordinate information to obtain a positioning address corresponding to each of the positioning coordinate information; the data to be processed includes the positioning coordinate information; Determine the accident location address and the road accident area according to all the location addresses; Scan the monitoring interfaces in the road accident area to obtain at least one monitoring interface.

3. The vehicle damage assessment method according to claim 1, It is characterized in that The step of performing user authentication on each of the to-be-processed data according to each of the retrieved first surveillance videos to obtain an authentication result includes: Performing vehicle owner recognition on all the first surveillance videos to identify vehicle owner results in the first surveillance videos; Searching for vehicle information and insurance policy information corresponding to the owner information in the data to be processed; According to the vehicle owner result, user authentication is performed on the vehicle information and the insurance policy information to obtain the authentication result; the authentication result reflects whether the vehicle owner information in each of the data to be processed has passed the authentication.

4. The vehicle damage assessment method according to claim 3, It is characterized in that The step of performing vehicle owner identification on all the first surveillance videos to identify vehicle owners in the first surveillance videos includes: Capturing a face in the first surveillance video, and performing face recognition on the captured face image to obtain a face recognition result; Capturing the license plate of the first surveillance video, and performing license plate number recognition on the captured license plate image to obtain a license plate recognition result; The face recognition result and the license plate recognition result are matched and identified to identify the owner of the vehicle.

5. The vehicle damage assessment method according to claim 1, It is characterized in that Determining the user information corresponding to each of the data to be processed according to the authentication result includes: When it is detected that the authentication result contains information of the owner that has not passed the authentication, searching for a video acquisition device closest to the accident location address; Planning a moving route for the video acquisition device to the accident location address, and starting the video acquisition device to move along the moving route; Acquire a second monitoring video of the video acquisition device; the second monitoring video is obtained by the video acquisition device through all-round collection at the accident location address; Performing unauthenticated owner identification and unauthenticated owner authentication on the second surveillance video, and updating the authentication result; Retrieve the user information associated with the authenticated owner information in the authentication result.

6. A vehicle damage assessment processing device, It is characterized in that include: A receiving module, configured to receive at least one piece of data to be processed, locate and analyze each piece of data to be processed, and obtain an accident location address and at least one monitoring interface matching the accident location address; An authentication module, used to retrieve the first monitoring video associated with each of the monitoring interfaces, and perform user authentication on each of the to-be-processed data according to each of the retrieved first monitoring videos to obtain an authentication result; A determination module, used to determine the user information corresponding to each of the data to be processed according to the authentication result; A damage assessment module, used to perform trajectory damage assessment on the first monitoring video and identify a damage assessment result; An audit module, used to generate and audit each of the data to be processed according to the damage assessment result and all the user information, and obtain an audit result corresponding to each of the data to be processed; The performing trajectory damage assessment on the first monitoring video to identify a damage assessment result includes: Based on all the user information, simulate the vehicle trajectory of all the first monitoring videos to construct a vehicle trajectory model; Performing damage assessment analysis on the vehicle trajectory model to obtain the damage assessment result; The performing damage assessment analysis on the vehicle trajectory model to obtain the damage assessment result includes: Performing a vehicle speed simulation analysis on the vehicles in the vehicle trajectory model to obtain a vehicle speed analysis result; A collision simulation analysis is performed on the vehicles in the vehicle trajectory model to obtain a collision analysis result; the collision simulation analysis is to determine whether there is an overlapping volume of each marked vehicle according to the movement trajectory in the vehicle trajectory model when the marked vehicle does not change its size, associate the overlapping volume with the two vehicles, summarize the overlapping volumes at all time points, and record them as the collision analysis result, which reflects the result of the overlapping volume between the vehicles on the time axis; Performing a mobile compliance analysis on the vehicles in the vehicle trajectory model to obtain a compliance analysis result; the mobile compliance analysis is to analyze whether the driving of each marked vehicle is compliant based on the headlight lighting records of each vehicle in a preset time period before the overlap volume appears in the collision analysis result, thereby outputting the compliance identification of each marked vehicle at each trajectory point to determine the compliance analysis result; The damage assessment result is determined based on the vehicle speed analysis result, the collision analysis result and the compliance analysis result.

7. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, It is characterized in that When the processor executes the computer program, the vehicle damage assessment method as described in any one of claims 1 to 5 is implemented.

8. A computer-readable storage medium storing a computer program. It is characterized in that When the computer program is executed by a processor, it implements the vehicle damage assessment processing method as described in any one of claims 1 to 5.