Online-based vehicle loss assessment method and device, computer equipment and storage medium

Abstract

The invention belongs to the technical field of artificial intelligence and finance, is applied to the field of smart cities, and relates to an online-based vehicle loss assessment method, which comprises the following steps: acquiring report information which comprises vehicle information of a target vehicle, position information and time information of a traffic accident, acquiring video information based on the position information and the time information, and sending the video information to the target vehicle; and analyzing the video information according to the vehicle information to obtain collision key information, and performing risk assessment on the collision key information and the vehicle information in a preset model to obtain a vehicle loss assessment result. The invention further provides a vehicle loss assessment device, computer equipment and a storage medium. In addition, the invention also relates to a block chain technology, and the case report information of the user can be stored in a block chain. According to the invention, automatic claim settlement and responsibility determination are realized, so that the user can finish report and vehicle loss assessment processes more efficiently and conveniently, the vehicle claim settlement efficiency is improved, the waiting time of the user is reduced, and the customer experience is greatly improved.

Description

Technical Field

[0001] The present application relates to the fields of artificial intelligence and financial technology, and in particular to online vehicle damage assessment methods, devices, computer equipment and storage media. Background Art

[0002] In the insurance-related field, claims settlement is a very important part of auto insurance. The efficiency and accuracy of claims settlement directly affect the user's service experience. At the same time, the accuracy of damage assessment in the claims process also directly affects the insurance company's damage assessment cost. At present, for single-party accidents, relevant technologies usually use online damage assessment solutions, which can significantly reduce time costs compared to traditional manual on-site inspections. However, when the damage value exceeds a certain amount, manual on-site inspections are still required, and the traffic police must issue a responsibility determination letter before the subsequent process can be carried out. In addition, some drivers may make incorrect operations due to their unfamiliarity with the online damage assessment process, resulting in the failure of online damage assessment, affecting the efficiency of claims settlement and user experience. Summary of the invention

[0003] The purpose of the embodiments of the present application is to propose an online vehicle damage assessment method, device, computer equipment and storage medium to solve the problems of poor efficiency in auto insurance claims and poor user experience in related technologies.

[0004] In order to solve the above technical problems, the embodiment of the present application provides an online vehicle damage assessment method, which adopts the following technical solutions:

[0005] Obtaining the report information, wherein the report information includes vehicle information of the target vehicle, location information and time information of the traffic accident;

[0006] Acquire video information based on location information and time information;

[0007] Analyze the video information according to the vehicle information to obtain the key information of the collision;

[0008] Perform risk assessment on key collision information and vehicle information in the preset model to obtain vehicle damage assessment results.

[0009] Furthermore, the step of obtaining video information based on the location information and time information specifically includes:

[0010] Determine the shape of the street where the traffic accident occurred based on the location information;

[0011] Acquire at least one target acquisition device based on the street shape;

[0012] Determine the target collection time based on the time information and the preset time interval;

[0013] The video information within the target acquisition time is acquired through the target acquisition device.

[0014] Furthermore, the preset models include risk estimation models, historical data models and vehicle data prediction models.

[0015] The steps of performing risk assessment on key collision information and vehicle information in a preset model to obtain vehicle damage assessment results specifically include:

[0016] Determine the risk level of traffic accidents in the risk estimation model based on vehicle information;

[0017] If the risk level is less than the preset risk level, the collision key information is matched with the historical data model to obtain the first damage assessment result; and

[0018] According to the vehicle information and the key collision information, a prediction is made in the vehicle data prediction model to obtain a second damage assessment result;

[0019] The vehicle damage assessment result is obtained according to the preset weights corresponding to each model, the first damage assessment result and the second damage assessment result.

[0020] Furthermore, after the step of determining the risk level of the traffic accident in the risk prediction model according to the vehicle information, the method further includes:

[0021] If the risk level is greater than or equal to the preset risk level, the online vehicle damage assessment process will be transferred to the manual on-site inspection process.

[0022] Furthermore, the video information includes a plurality of continuous video frames, and the steps of analyzing the video information according to the vehicle information to obtain the key collision information specifically include:

[0023] Extracting target vehicle features in video information based on vehicle information;

[0024] Determine collision key information based on target vehicle features and video frames.

[0025] Furthermore, the key collision information includes the target vehicle's speed information.

[0026] The steps of determining the key collision information based on the target vehicle features and the video frame include:

[0027] According to the characteristics of the target vehicle, the motion trajectory of the target vehicle is extracted in the video frame;

[0028] The driving speed information of the target vehicle is determined based on the motion trajectory.

[0029] Furthermore, the collision key information includes the collision part of the target vehicle,

[0030] The steps of determining the key collision information based on the target vehicle features and the video frame include:

[0031] Based on the target vehicle features, extracting a segmented image corresponding to the target vehicle in the video frame;

[0032] Perform edge detection on the segmented image to obtain the collision location of the target vehicle.

[0033] In order to solve the above technical problems, the embodiment of the present application also provides an online vehicle damage assessment device, which adopts the following technical solutions:

[0034] A report acquisition module is used to acquire report information, wherein the report information includes vehicle information of the target vehicle, location information and time information of the traffic accident;

[0035] A video acquisition module, used to acquire video information based on location information and time information;

[0036] A collision analysis module is used to analyze the video information according to the vehicle information to obtain the key collision information;

[0037] The vehicle damage assessment module is used to conduct risk assessment on key collision information and vehicle information in a preset model to obtain vehicle damage assessment results.

[0038] In order to solve the above technical problems, an embodiment of the present application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of the above online vehicle damage assessment method are implemented.

[0039] In order to solve the above technical problems, an embodiment of the present application also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above-mentioned online vehicle damage assessment method are implemented.

[0040] Compared with the related art, the embodiments of the present application have the following beneficial effects:

[0041] By obtaining the report information, which includes the vehicle information of the target vehicle, the location information and time information of the traffic accident, obtaining the video information based on the location information and time information, analyzing the video information according to the vehicle information, obtaining the key collision information, and performing risk assessment on the key collision information and the vehicle information in the preset model to obtain the vehicle damage assessment result. That is, the optimized vehicle damage assessment process can automatically retrieve the relevant video based on the reported report information only, and analyze the video in combination with the relevant model to obtain the vehicle damage assessment result, thereby realizing automated claims and liability determination, allowing users to complete the reporting and vehicle damage assessment process more efficiently and conveniently, improving the vehicle claims efficiency, reducing the user's waiting time, and greatly improving the customer experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the scheme in the present application, a brief introduction is given below to the drawings required for use in the description of the embodiments of the present application. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0043] Figure 1 is an exemplary system architecture diagram to which the present application may be applied;

[0044] Figure 2 is a flow chart of an embodiment of an online vehicle damage assessment method of the present application;

[0045] Figure 3 yes Figure 2 A flowchart of a specific implementation of step S202;

[0046] Figure 4 is a structural schematic diagram of an embodiment of an online vehicle damage assessment device according to the present application;

[0047] Figure 5 It is a structural diagram of an embodiment of a computer device according to the present application. DETAILED DESCRIPTION

[0048] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by technicians in the technical field of the present application; the terms used in the specification of the application herein are only for the purpose of describing specific embodiments and are not intended to limit the present application; the terms "including" and "having" and any variations thereof in the specification and claims of the present application and the above-mentioned drawings are intended to cover non-exclusive inclusions. The terms "first", "second", etc. in the specification and claims of the present application or the above-mentioned drawings are used to distinguish different objects, not to describe a specific order.

[0049] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0050] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.

[0051] like Figure 1As shown, the system architecture 100 may include a terminal device 101, a network 102 and a server 103. The terminal device 101 may be a laptop 1011, a tablet computer 1012 or a mobile phone 1013. The network 102 is used to provide a medium for a communication link between the terminal device 101 and the server 103. The network 102 may include various connection types, such as wired, wireless communication links or optical fiber cables.

[0052] The user can use the terminal device 101 to interact with the server 103 through the network 102 to receive or send messages, etc. Various communication client applications can be installed on the terminal device 101, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc.

[0053] The terminal device 101 can be any electronic device with a display screen and supporting web browsing. In addition to a laptop computer 1011, a tablet computer 1012 or a mobile phone 1013, the terminal device 101 can also be an e-book reader, an MP3 player (Moving Picture Experts Group Audio Layer III), an MP4 (Moving Picture Experts Group Audio Layer IV), a laptop computer, a desktop computer, etc.

[0054] The server 103 may be a server that provides various services, such as a background server that provides support for web pages displayed on the terminal device 101 .

[0055] It should be noted that the online vehicle damage assessment method provided in the embodiment of the present application is generally executed by a server / terminal device, and accordingly, the online vehicle damage assessment device is generally set in the server / terminal device.

[0056] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0057] In the related technology, the original claims process includes: after the user reports the accident, he needs to fill in the basic information of the vehicle online and provide on-site materials such as photos or videos of the accident from multiple angles; the claims adjuster determines the vehicle damage based on the on-site materials uploaded by the user. If it is a complex traffic accident or a traffic accident with large vehicle damage, the claims adjuster needs to go to the scene to determine the damage, and the user needs to spend time waiting for the on-site damage determination to be completed. It can be seen that the original claims process is relatively lengthy and the claims efficiency is low, especially when the user cannot take photos / videos in time, which may lead to difficulties in claims.

[0058] To solve the above problems, continue to refer to Figure 2 , shows a flow chart of an embodiment of an online vehicle damage assessment method according to the present application. The online vehicle damage assessment method comprises the following steps:

[0059] Step S201, obtaining report information, wherein the report information includes vehicle information of the target vehicle, location information and time information of the traffic accident.

[0060] In this embodiment, the electronic device (eg, Figure 1 The server / terminal device shown in the figure) can receive the report information input by the user through a wired connection or a wireless connection. It should be noted that the above wireless connection method may include but is not limited to 3G / 4G / 5G connection, WiFi connection, Bluetooth connection, WiMA vehicle damage assessment connection, Zigbee connection, UWB (ultra wideband) connection, and other wireless connection methods currently known or to be developed in the future.

[0061] Specifically, the user can log in to the APP on the mobile terminal or the claim system on the web page, and fill in the report information of the vehicle in which the user was involved in a traffic accident (i.e., the target vehicle), where the vehicle information can be imported based on the user's historical records in the claim system, and the vehicle information includes but is not limited to the license plate, model, historical traffic accident information, etc. of the target vehicle.

[0062] It should be noted that the report information does not require users to upload videos or images of the traffic accident. They only need to fill in the location information of the traffic accident (i.e. position information) and the time of the accident in the claims system. The operation is simple, thereby reducing the user's operations in submitting online claims procedures, improving claims efficiency and user experience.

[0063] For example, when a user is involved in a single-vehicle traffic accident on the road, he or she uses the APP to report the accident, and the claims system records the vehicle information filled in by the user, the current location, and the time when the traffic accident occurred.

[0064] Step S202: acquiring video information based on the location information and time information.

[0065] In this embodiment, the relevant geographic information system can be called according to the location information of the traffic accident to search for the collection device whose location information is within the preset spatial range, so as to retrieve the video information whose time information is within the preset time interval through the collection device. In this way, the user does not need to upload the relevant video operation in the claim system after the traffic accident occurs, thereby improving the claim efficiency.

[0066] Step S203: Analyze the video information according to the vehicle information to obtain key collision information.

[0067] In this embodiment, the video clips belonging to the accident vehicle (ie, the target vehicle) are analyzed based on the video information collected by all acquisition devices and the vehicle information such as license plate, model, color, etc. provided by the user.

[0068] Among them, the key collision information includes but is not limited to relevant data such as driving speed, speed when the collision occurs, collision object and collision location.

[0069] Step S204, performing risk assessment on the collision key information and vehicle information in a preset model to obtain a vehicle damage assessment result.

[0070] In this embodiment, the preset models include but are not limited to risk estimation models, historical data models, and vehicle data prediction models.

[0071] Specifically, the risk estimation model records the vehicle's past claims, vehicle damage, driver's past driving conditions, etc. The risk estimation model can estimate the risk of this traffic accident. If the risk is too high, the online claims process will be converted to a manual on-site inspection process. The historical data model records various types of relevant data such as past case types, vehicle damage, damage assessment, and responsibility division, and can make the same type of estimate for the vehicle damage in this traffic accident. The vehicle data prediction model is a model established through relevant data such as vehicle type, vehicle physical material characteristics, speed collision prediction, and corresponding characteristics of the inside and outside of the collision part. It can estimate the objective collision situation of the vehicle in this traffic accident.

[0072] The vehicle damage assessment results may include but are not limited to the vehicle damage assessment compensation amount, vehicle damage conditions, basic information of the traffic accident and other report information.

[0073] By obtaining the report information, which includes the vehicle information of the target vehicle, the location information and time information of the traffic accident, obtaining the video information based on the location information and time information, analyzing the video information according to the vehicle information, obtaining the key collision information, and performing risk assessment on the key collision information and the vehicle information in the preset model to obtain the vehicle damage assessment result. That is, the optimized vehicle damage assessment process can automatically retrieve the relevant video based on the reported report information only, and analyze the video in combination with the relevant model to obtain the vehicle damage assessment result, thereby realizing automated claims and liability determination, allowing users to complete the reporting and vehicle damage assessment process more efficiently and conveniently, improving the vehicle claims efficiency, reducing the user's waiting time, and greatly improving the customer experience.

[0074] In some optional implementations, such as Figure 3 As shown, Figure 3 yes Figure 2 A flowchart of a specific implementation of step S202 in the embodiment of the present invention, wherein step S202 acquires video information based on the location information and the time information and includes the following steps:

[0075] Step S2021, determining the shape of the street where the traffic accident occurred based on the location information;

[0076] Among them, street shapes include but are not limited to straight roads, curves, intersections, roundabouts, diagonal intersections, forked roads, circular roads, dead ends, pedestrian streets and ramps.

[0077] In this embodiment, the target street corresponding to the location information can be found through the geographic information system, and the street shape of the area to which the target street belongs can be determined.

[0078] Step S2022, acquiring at least one target collection device based on the street shape;

[0079] The shape of the street directly affects the distribution and viewing angle of the collection device (such as the camera). For example, on a straight street (i.e. a straight road), the camera usually covers the straight section, while on a circular or curved street, the camera's field of view will be more complicated. Based on the street shape, it is possible to more effectively filter out cameras covering the traffic accident area, reduce irrelevant cameras or cameras with poor viewing angles, and optimize the extraction of video information.

[0080] In addition, different street shapes may have different traffic flows and driving patterns, affecting the angles and scenes of traffic accidents. For example, on roundabouts or curves, accidents often occur when turning, while straight streets may involve collisions at high speeds. By analyzing the street shape, the possible location of the accident can be determined, thereby locking in the camera that is most likely to capture the accident.

[0081] Furthermore, street shape can affect the speed and direction of vehicles, as well as the type of accidents. For example, on curved or cornered streets, vehicles usually need to slow down, while on straight streets, speeds are higher and the force and damage of accidents can vary greatly. Selecting cameras based on street shape can not only capture accidents more clearly, but also better analyze details such as speed, collision angle, and damaged parts at the time of the accident.

[0082] In this embodiment, at least one target acquisition device may be acquired based on the area range of the street shape, that is, the range of the street may be expanded or reduced to filter out effective target acquisition devices.

[0083] For example, based on the street shape, the cameras of the street within the range of ±0.001 of longitude and latitude can be obtained.

[0084] Step S2023, determining the target collection time based on the time information and the preset time interval;

[0085] In this embodiment, the time information plus the preset time interval is used as the target acquisition time of the video information, and the preset time interval may be -30 minutes to +15 minutes.

[0086] Since the exact time of the accident is often roughly estimated by the user and not necessarily accurate. The acquisition device may not start recording at the exact moment of the accident. If only the video clips at the exact time of the accident are obtained, important accident details may be missed. Therefore, the use of superimposed time intervals can ensure that the complete accident scene is captured and avoid missing important information due to time estimation deviation. At the same time, obtaining the time period before the traffic accident can help analyze the vehicle's driving status, the driver's reaction, and other potential influencing factors. The time period after the traffic accident helps to record the vehicle dynamics, damage, and reactions of other related vehicles and personnel after the collision.

[0087] Step S2024, obtaining video information within the target acquisition time through the target acquisition device.

[0088] For example, when the longitude and latitude of the accident site are (31.224, 121.477), the geographic information system or traffic management system can be called to obtain the street shape around the location information. For example, the system recognizes that the street is a road connected to a curve and an intersection, and there is a camera nearby. Assume that a camera within the range of ±0.001 of longitude and latitude is selected, that is, the longitude and latitude range is (31.223-31.225) and (121.476-121.478).

[0089] Three cameras were found within the above range:

[0090] Camera A: latitude and longitude (31.2241, 121.4770) (located at the intersection);

[0091] Camera B: longitude and latitude (31.2239, 121.4772) (located at the entrance of the curve);

[0092] Camera C: latitude and longitude (31.2245, 121.4775) (located on the right side of the intersection).

[0093] When the traffic accident occurs at 10:30 on September 28, 2024, according to the requirements, the time interval is: 30 minutes before the traffic accident (ie 10:00), 15 minutes after the traffic accident (ie 10:45), that is, the time period that can be retrieved is from 10:00 to 10:45. The camera video clips in this time period may include the situation before and after the accident, which is convenient for accident restoration and analysis. Furthermore, the video clips within the above time period may include: Camera A (intersection) recorded the dynamics of the vehicle at the intersection from 10:00 to 10:45 on September 28, 2024, clearly showing the collision of the two vehicles and the reactions of the surrounding pedestrians when the accident occurred; Camera B (curve entrance) recorded the driving process of the accident vehicle on the curve from 10:00 to 10:45 on September 28, 2024, showing how the vehicle entered the curve, which may have been speeding or skidding; Camera C (right side of the intersection) filmed the driving conditions of vehicles on the far side of the intersection from 10:00 to 10:45 on September 28, 2024, which may indirectly show the reaction of the traffic after the accident, but it was not in the main perspective when the accident occurred.

[0094] By determining the street shape through location information and then acquiring the target acquisition device, and retrieving video information within the relevant time period, the scenes from all angles before and after the traffic accident can be clearly obtained, so as to facilitate the analysis of the division of accident responsibility.

[0095] In some optional implementations, the video information includes a plurality of continuous video frames. For example, the step of analyzing the video information according to the vehicle information to obtain the critical collision information in step S203 specifically includes:

[0096] S2031: extracting target vehicle features in the video information based on the vehicle information;

[0097] S2032: Determine key collision information based on target vehicle features and video frames.

[0098] Specifically, the target vehicle in the video information is identified and tracked through video analysis algorithms (such as computer vision technology). For example, a deep learning model (such as YOLO, Faster R-CNN) is used to identify the outline and position of the target vehicle, and image processing libraries such as OpenCV are further used to extract the target vehicle features, such as the target vehicle color, model, license plate, etc.

[0099] Since the video is composed of a series of continuous static images (i.e. video frames), the specific process of the accident can be analyzed based on the information in each frame of the image, i.e. the video frame. For example, by analyzing the time sequence of the video frames, the state changes of the target vehicle when the traffic accident occurs, such as the vehicle's driving speed, braking conditions, etc., can be determined; by performing motion detection on the video frames, the moving trajectory and collision moment of the target vehicle can be identified; some frames may contain the key moment of the collision, and through image analysis, the deformation and breakage of the vehicle body can be seen, which helps to determine the exact time and location of the collision.

[0100] By analyzing each frame of the traffic accident video and combining it with the target vehicle's specific appearance and behavior characteristics (such as license plate, model, color, damage, etc.) and other target vehicle characteristics, key information related to the target vehicle collision can be extracted, such as the speed at the time of collision, collision location, collision object, etc., so as to accurately identify and analyze the details of the traffic accident for subsequent processing such as liability determination and insurance claims.

[0101] In some optional implementations, the critical collision information includes the driving speed information of the target vehicle. For example, the step of determining the critical collision information based on the target vehicle characteristics and the video frame in step S2032 includes:

[0102] According to the characteristics of the target vehicle, the motion trajectory of the target vehicle is extracted in the video frame;

[0103] The driving speed information of the target vehicle is determined based on the motion trajectory.

[0104] Among them, the target vehicle features are used to identify specific vehicle features of the target vehicle, for example, it may include: using license plate recognition technology to lock the target vehicle; using appearance features such as vehicle color, model and brand to filter out the target vehicle from the video frame. If the target vehicle is identified, the target vehicle is tracked in each frame of the video information. Here, computer vision technology, such as target detection and tracking algorithms (such as YOLO, SSD or DeepSort algorithms), can be used to mark the target vehicle in continuous video frames.

[0105] Furthermore, by analyzing the position change of the target vehicle in each video frame, the motion trajectory of the vehicle can be generated, which represents the driving route of the target vehicle in the video. For example, in each video frame, the center point (or other defined reference point) of the target vehicle will be identified and its position in the frame will be recorded. When these points are connected, a curve or line segment can be formed, which represents the actual driving trajectory of the target vehicle. This process can use algorithms such as optical flow method, Kalman filter and convolutional neural network (CNN).

[0106] In this embodiment, the motion trajectory of the target vehicle in the video frame is extracted, and the motion trajectory displays the displacement information of the target vehicle in the video frame. Based on the displacement information in the motion trajectory and the time interval of the video frame, the speed formula (displacement divided by the time interval) is used to calculate the driving speed of the target vehicle. Thus, the driving status and dynamic information of the target vehicle can be extracted from the video information, providing support for accident analysis, speed identification, responsibility division, etc.

[0107] Further, in some optional implementations, the critical collision information includes the collision location of the target vehicle, and step S2032 determines the critical collision information based on the target vehicle features and the video frame, including:

[0108] Based on the target vehicle features, extracting a segmented image corresponding to the target vehicle in the video frame;

[0109] Perform edge detection on the segmented image to obtain the collision location of the target vehicle.

[0110] In this embodiment, on the premise of identifying the target vehicle in the video frame, the area to which the target vehicle belongs is separated from the background area through an image segmentation algorithm. The image segmentation algorithm may include but is not limited to a semantic segmentation algorithm, an instance segmentation algorithm, and a Mask R-CNN algorithm. The segmented image is a pixel-level area of ​​the target vehicle, which means that the outline of the target vehicle is marked in each video frame, and the part not related to the background is removed.

[0111] The collision part refers to the deformation part of the target vehicle caused by the collision.

[0112] Furthermore, for the segmented target vehicle image (i.e., the segmented image), the edge detection algorithm can determine the external shape and contour of the target vehicle. Common edge detection algorithms include the Canny edge detection algorithm, the Sobel operator, the Laplace operator, etc. Through edge detection, the external boundary of the target vehicle and the deformed part can be identified. In the video frame, the collision will cause the vehicle to deform, such as dents, damage, or bending of the body. By performing edge detection on the segmented image, abnormal edge changes in the video frame can be identified, such as dents in the front of the vehicle, damage to the door, etc., and the abnormal edges are different from the normal vehicle contour. If the edge shape marked in the segmented image is inconsistent with the normal boundary of the target vehicle, it can be determined as the collision part. For example, the collision part is the bending of the front and rear bumpers, the dents on the side, etc. The detected vehicle contour is matched with the standard vehicle contour to find the deviated parts, and these deviated areas are the deformed parts caused by the collision.

[0113] In this embodiment, the pixel-level area of ​​the target vehicle in each frame is accurately extracted through target detection and image segmentation technology, which helps to separate the target vehicle from the complex background, so as to facilitate subsequent detailed image processing. The segmented image is analyzed through the edge detection algorithm to obtain the contour information of the target vehicle and compare the edge changes of the vehicle. Then, the deformation caused by the collision can be clearly found. Through these two steps, the damaged parts of the target vehicle can be automatically analyzed from the video, eliminating the steps of manual investigation, and providing a basis for subsequent damage assessment and claims.

[0114] In some optional implementations, the step of performing risk assessment on the collision key information and vehicle information in a preset model in step S204 to obtain a vehicle damage assessment result specifically includes:

[0115] Determine the risk level of traffic accidents in the risk estimation model based on vehicle information;

[0116] If the risk level is less than the preset risk level, the collision key information is matched with the historical data model to obtain the first damage assessment result; and

[0117] According to the vehicle information and the key collision information, a prediction is made in the vehicle data prediction model to obtain a second damage assessment result;

[0118] The vehicle damage assessment result is obtained according to the preset weights corresponding to each model, the first damage assessment result and the second damage assessment result.

[0119] In this embodiment, the risk estimation model is a model that evaluates the risk level of this traffic accident based on information such as vehicle history information, driver behavior records, and previous claims data. The vehicle information input into the risk estimation model may include but is not limited to vehicle age, brand, model, insurance record, driver's past accidents, driving behavior data (such as whether there are records of violations, speeding, etc.), previous claims records of the vehicle, damage, repair costs, etc. The risk estimation model can estimate the claim risk level of this traffic accident by evaluating vehicle information such as the vehicle and the driver. The evaluation result of the risk estimation model is compared with the preset risk level threshold. If the risk level of the evaluation result is less than the preset risk level, the automated process, that is, the online claims process, is entered, and the vehicle damage assessment result can be quickly generated; if the risk level is high, manual processing is triggered, that is, manual intervention is required for further on-site verification and damage assessment.

[0120] Furthermore, after the step of determining the risk level of the traffic accident in the risk prediction model according to the vehicle information, the method further includes:

[0121] If the risk level is greater than or equal to the preset risk level, the online vehicle damage assessment process will be transferred to the manual on-site inspection process.

[0122] In this embodiment, the historical data model is based on a large amount of past traffic accident data to establish a database model that includes various case types, vehicle damage, damage amounts, and liability divisions. The collision information of the target vehicle is compared with the historical data model to find similar cases that match it, thereby inferring the first damage assessment result. The first damage assessment result is information such as the repair cost and compensation amount output based on the compensation situation of similar cases in the past.

[0123] The vehicle data prediction model is based on the physical characteristics of the vehicle (such as model, material, speed, etc.) and collision information, using physical simulation and data analysis technology to predict the damage to the vehicle in this collision. It can simulate collisions at different speeds and angles, estimate the severity of the damage to the vehicle, and obtain a second damage assessment result based on physical simulation and big data analysis.

[0124] Furthermore, the first damage assessment result and the second damage assessment result are combined, and corresponding weights are assigned according to the importance of each model. For example, if the historical data model is richer and the case is closer, the historical data model may have a higher weight. If the physical structure of the vehicle is relatively special, the vehicle data prediction model may have a higher weight. By combining the results of each model and according to the preset weights, the final vehicle damage assessment result is calculated. Among them, the vehicle damage assessment result includes information such as the vehicle repair cost and compensation amount caused by the traffic accident.

[0125] It should be noted that the preset models in this embodiment are not limited to the above three models, that is, the results can be divided into different weights according to the calculation results of N models to obtain the final vehicle damage assessment.

[0126] In this embodiment, after the claims settlement system obtains the vehicle damage assessment result, it automatically generates a vehicle damage assessment report, exchanges real-time data with the 12123 traffic management system, and submits relevant accident information of the target vehicle to request official liability determination.

[0127] Furthermore, after determining the vehicle damage assessment results, users can choose to have the vehicle repaired with a cooperating repair shop, which will then repair the vehicle based on the APP report results.

[0128] Therefore, the optimized claims settlement process of the embodiment of the present application can be changed to:

[0129] The user reports the incident → fills in basic information → leaves the scene → obtains the damage assessment result → confirms the compensation → performs car repairs. In other words, this application uses a combination of camera and AI model technology to restore the scene through video, so that when users encounter a unilateral accident, they can "report and leave immediately" and handle subsequent procedures without getting off the car, reducing the possibility of users who are not familiar with the process making mistakes. At the same time, if they encounter more complex or relatively large damage assessments, they can also do it online, which greatly reduces the user's waiting time, improves efficiency, and reduces the user's waiting time. This application combines with a third-party system to obtain cameras on both sides of the road to trace the accident, intelligently obtain the responsibility of the traffic police, and conduct damage assessment based on the video and the comprehensive judgment of the repair shop. This solves the problem of difficult damage assessment and slow claims settlement in unilateral accidents.

[0130] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Among them, artificial intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0131] The basic technologies of artificial intelligence generally include sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics and other technologies. Artificial intelligence software technology mainly includes computer vision technology, robotics technology, biometrics technology, speech processing technology, natural language processing technology, and machine learning / deep learning. This application can be applied in the field of smart cities, thereby promoting the construction of smart cities.

[0132] This application belongs to the field of smart vehicle damage assessment, and this solution can promote the construction of smart cities.

[0133] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through computer-readable instructions, and the computer-readable instructions can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, the aforementioned storage medium can be a non-volatile storage medium such as a disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

[0134] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0135] Further references Figure 4 , as a response to the above Figure 2 The present application provides an embodiment of an online vehicle damage assessment device, which is similar to Figure 2 Corresponding to the method embodiment shown, the device can be specifically applied to various electronic devices.

[0136] like Figure 4 As shown, the online vehicle damage assessment device 400 described in this embodiment includes: a report acquisition module 401, a video acquisition module 402, a collision analysis module 403, and a vehicle damage assessment module 404. Among them:

[0137] The report acquisition module 401 is used to acquire the report information, wherein the report information includes the vehicle information of the target vehicle, the location information and the time information of the traffic accident;

[0138] The video acquisition module 402 is used to acquire video information based on the location information and the time information;

[0139] A collision analysis module 403 is used to analyze the video information according to the vehicle information to obtain key collision information;

[0140] The vehicle damage assessment module 404 is used to perform risk assessment on the key collision information and vehicle information in a preset model to obtain a vehicle damage assessment result.

[0141] Furthermore, the video acquisition module 402 specifically includes:

[0142] A street shape determination submodule, used to determine the street shape where the traffic accident occurred based on the location information;

[0143] A collection device determination submodule, used to obtain at least one target collection device based on the street shape;

[0144] A collection time determination submodule, used to determine the target collection time based on the time information and the preset time interval;

[0145] The video acquisition submodule is used to acquire video information within a target acquisition time through a target acquisition device.

[0146] Furthermore, the preset model includes a risk estimation model, a historical data model and a vehicle data prediction model, and the vehicle damage assessment module 404 specifically includes:

[0147] A risk determination submodule, used to determine the risk level of a traffic accident in a risk estimation model based on vehicle information;

[0148] A first damage assessment submodule, for matching the collision key information with the historical data model to obtain a first damage assessment result if the risk level is less than a preset risk level; and

[0149] The second damage assessment submodule is used to make a prediction in the vehicle data prediction model based on the vehicle information and the key collision information to obtain a second damage assessment result;

[0150] The vehicle damage assessment submodule is used to obtain the vehicle damage assessment result based on the preset weights corresponding to each model, the first damage assessment result and the second damage assessment result.

[0151] Furthermore, the above-mentioned online vehicle damage assessment device 400 further includes:

[0152] The process switching module is used to transfer the online vehicle damage assessment process to the manual on-site inspection process if the risk level is greater than or equal to the preset risk level.

[0153] Furthermore, the video information includes a plurality of continuous video frames, and the collision analysis module 403 specifically includes:

[0154] A feature acquisition submodule is used to extract target vehicle features in video information based on vehicle information;

[0155] The collision determination submodule is used to determine the key collision information based on the target vehicle characteristics and video frames.

[0156] Furthermore, the key collision information includes the target vehicle's speed information.

[0157] The collision determination submodule specifically includes:

[0158] A trajectory determination unit, used to extract the motion trajectory of the target vehicle in the video frame according to the characteristics of the target vehicle;

[0159] The speed determination unit is used to determine the driving speed information of the target vehicle based on the motion trajectory.

[0160] Furthermore, the collision key information includes the collision part of the target vehicle,

[0161] The collision determination submodule specifically includes:

[0162] An image segmentation unit, used for extracting a segmented image corresponding to the target vehicle in the video frame based on the target vehicle features;

[0163] The edge detection unit is used to perform edge detection on the segmented image to obtain the collision position of the target vehicle.

[0164] To solve the above technical problems, the present application also provides a computer device. Figure 5 , Figure 5 This is a basic structural block diagram of the computer device in this embodiment.

[0165] The computer device 5 includes a memory 51, a processor 52, and a network interface 53 that are interconnected through a system bus. It should be noted that the figure only shows a computer device 5 with a memory 51, a processor 52, and a network interface 53, but it should be understood that it is not required to implement all the components shown, and more or fewer components can be implemented instead. Among them, those skilled in the art can understand that the computer device here is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application specific integrated circuits (Application Specific Integrated Circuit, ASIC), programmable gate arrays (Field-Programmable Gate Array, FPGA), digital processors (Digital Signal Processor, DSP), embedded devices, etc.

[0166] The computer device may be a computing device such as a desktop computer, a notebook, a PDA, a cloud server, etc. The computer device may interact with a user through a keyboard, a mouse, a remote controller, a touch pad, or a voice control device.

[0167] The memory 51 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or D vehicle damage assessment memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, disk, optical disk, etc. In some embodiments, the memory 51 can be an internal storage unit of the computer device 5, such as a hard disk or memory of the computer device 5. In other embodiments, the memory 51 can also be an external storage device of the computer device 5, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card, etc. equipped on the computer device 5. Of course, the memory 51 can also include both the internal storage unit of the computer device 5 and its external storage device. In this embodiment, the memory 51 is generally used to store the operating system and various application software installed on the computer device 5, such as computer-readable instructions based on the online vehicle damage assessment method, etc. In addition, the memory 51 can also be used to temporarily store various types of data that have been output or are to be output.

[0168] The processor 52 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chips in some embodiments. The processor 52 is generally used to control the overall operation of the computer device 5. In this embodiment, the processor 52 is used to run computer-readable instructions stored in the memory 51 or process data, such as computer-readable instructions for running the online vehicle damage assessment method.

[0169] The network interface 53 may include a wireless network interface or a wired network interface. The network interface 53 is generally used to establish a communication connection between the computer device 5 and other electronic devices.

[0170] The present application also provides another embodiment, namely, providing a computer-readable storage medium, which stores computer-readable instructions, and the computer-readable instructions can be executed by at least one processor to enable the at least one processor to perform the steps of the online vehicle damage assessment method as described above.

[0171] The non-Company software tools or components appearing in the embodiments of this application are merely examples and do not represent actual use.

[0172] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0173] Obviously, the embodiments described above are only some embodiments of the present application, rather than all embodiments. The preferred embodiments of the present application are given in the accompanying drawings, but they do not limit the patent scope of the present application. The present application can be implemented in many different forms. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosure of the present application more thorough and comprehensive. Although the present application is described in detail with reference to the aforementioned embodiments, for those skilled in the art, it is still possible to modify the technical solutions recorded in the aforementioned specific implementation methods, or to perform equivalent replacement of some of the technical features therein. Any equivalent structure made using the contents of the specification and drawings of this application, directly or indirectly used in other related technical fields, is similarly within the scope of patent protection of this application.

Claims

1. An online vehicle damage assessment method, characterized in that: The steps include: Acquiring report information, wherein the report information includes vehicle information of the target vehicle, location information and time information of the traffic accident; Acquire video information based on the location information and the time information; Analyze the video information according to the vehicle information to obtain key collision information; A risk assessment is performed on the key collision information and the vehicle information in a preset model to obtain a vehicle damage assessment result.

2. The online vehicle damage assessment method according to claim 1, characterized in that: The step of acquiring the video information based on the position information and the time information specifically includes: Determining the shape of the street where the traffic accident occurred based on the location information; Acquire at least one target acquisition device based on the street shape; Determining a target collection time based on the time information and a preset time interval; The video information within the target acquisition time is acquired through the target acquisition device.

3. The online vehicle damage assessment method according to claim 1, characterized in that: The preset models include risk estimation models, historical data models and vehicle data prediction models. The step of performing risk assessment on the collision key information and the vehicle information in the preset model to obtain a vehicle damage assessment result specifically includes: Determining the risk level of the traffic accident in the risk estimation model according to the vehicle information; If the risk level is less than the preset risk level, matching the collision key information with the historical data model to obtain a first damage assessment result; and Perform prediction in the vehicle data prediction model according to the vehicle information and the collision key information to obtain a second damage assessment result; The vehicle damage assessment result is obtained according to the preset weights corresponding to each model, the first damage assessment result and the second damage assessment result.

4. The online vehicle damage assessment method according to claim 3 is characterized in that: After the step of determining the risk level of the traffic accident in the risk prediction model according to the vehicle information, the method further includes: If the risk level is greater than or equal to the preset risk level, the online vehicle damage assessment process will be transferred to the manual on-site inspection process.

5. The online vehicle damage assessment method according to claim 1, characterized in that: The video information includes a plurality of continuous video frames, and the step of analyzing the video information according to the vehicle information to obtain the key collision information specifically includes: Extracting target vehicle features in the video information based on the vehicle information; The collision critical information is determined based on the target vehicle features and the video frame.

6. The online vehicle damage assessment method according to claim 5, characterized in that: The collision key information includes the driving speed information of the target vehicle, The step of determining the collision key information based on the target vehicle features and the video frame comprises: Extracting the motion trajectory of the target vehicle in the video frame according to the target vehicle features; The driving speed information of the target vehicle is determined based on the motion trajectory.

7. The online vehicle damage assessment method according to claim 5, characterized in that: The key collision information includes the collision position of the target vehicle, The step of determining the collision key information based on the target vehicle features and the video frame comprises: Based on the target vehicle features, extracting a segmented image corresponding to the target vehicle in the video frame; Perform edge detection on the segmented image to obtain the collision location of the target vehicle.

8. An online vehicle damage assessment device, characterized in that: include: A report acquisition module, used to acquire report information, wherein the report information includes vehicle information of the target vehicle, location information and time information of the traffic accident; A video acquisition module, used for acquiring video information based on the position information and the time information; A collision analysis module, used to analyze the video information according to the vehicle information to obtain key collision information; The vehicle damage assessment module is used to perform risk assessment on the collision key information and the vehicle information in a preset model to obtain a vehicle damage assessment result.

9. A computer device, characterized in that: It includes a memory and a processor, wherein the memory stores computer-readable instructions, and when the processor executes the computer-readable instructions, the steps of the online vehicle damage assessment method as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-readable instructions, which, when executed by a processor, implement the steps of the online vehicle damage assessment method as described in any one of claims 1 to 7.

Images