CN117496149A

CN117496149A - Method and device for generating vehicle insurance claim scheme, computer equipment and storage medium

Info

Publication number: CN117496149A
Application number: CN202311491835.7A
Authority: CN
Inventors: 余宪
Original assignee: Ping An Technology Shanghai Co ltd
Current assignee: Ping An Technology Shanghai Co ltd
Priority date: 2023-11-09
Filing date: 2023-11-09
Publication date: 2024-02-02

Abstract

The application relates to the field of vehicle insurance claim payment, and discloses a vehicle insurance claim payment scheme generation method, a device, computer equipment and a storage medium, wherein the method comprises the following steps: acquiring a vehicle loss image set, and screening vehicle loss images meeting preset confidence conditions from the vehicle loss image set to serve as effective images; analyzing and acquiring a first target area where vehicle damage occurs in an effective image and first component information; performing image segmentation processing on the effective image to determine second target areas corresponding to the plurality of vehicle components in the effective image, and identifying damage information in the second target areas; generating target pay areas according to the fusion of the first target areas and the second target areas, and matching corresponding pay strategies for each target pay area according to the damage information and the first component information; and generating a target pay plan according to the target pay area and the pay strategy, so that the efficiency and accuracy of the dangerous goods allocation to the vehicle are improved, and an accurate dangerous goods allocation plan is generated based on the actual damage condition of the vehicle.

Description

Method and device for generating vehicle insurance claim scheme, computer equipment and storage medium

Technical Field

The present invention relates to the field of vehicle insurance claim payment, and in particular, to a method, an apparatus, a computer device, and a storage medium for generating a vehicle insurance claim payment scheme.

Background

The traffic insurance has high service occupation ratio and wide application range in the insurance industry. In the traditional wind control system, when a traffic accident occurs, a vehicle owner often needs to directly report a car insurance by telephone and then wait for the personnel of an insurance company to perform on-site investigation, and the generation method of the car insurance claim scheme has long period and is easy to cause road congestion, and is too inefficient depending on personal experience of an investigation person.

Although the prior art also has a method for directly carrying out the car insurance report by taking a live photo or recording a live video, if the live photo and the video are subjected to on-line damage assessment in a manual mode, the processing efficiency of the insurance report is still lower, and particularly when the on-line personnel are busy, long-time waiting is caused. If the vehicle is subjected to case reporting processing through the existing algorithm model, the damaged part and the damaged degree of the vehicle are required to be detected in sequence by the existing algorithm model to determine the pay plan, the damaged part and the damaged degree are in a mutually strong dependency relationship, and once the damaged part is missed to be detected or is detected incorrectly, the accuracy of insurance processing is insufficient, and the risk of generating an abnormal vehicle insurance pay plan is high.

Disclosure of Invention

The embodiment of the application mainly aims to provide a method, a device, computer equipment and a storage medium for generating a vehicle insurance claim scheme, aiming at improving the efficiency and accuracy of insurance determination of vehicles and generating an accurate vehicle insurance claim scheme based on the actual damage condition of the vehicles.

In a first aspect, an embodiment of the present application provides a method for generating a vehicle risk claim, including:

acquiring a vehicle damage image set, wherein the vehicle damage image set comprises a plurality of vehicle damage images used for recording the damage state of the vehicle;

screening out vehicle damage images meeting preset confidence conditions from the vehicle damage image set to serve as effective images;

analyzing and acquiring a first target area in the effective image and first component information of a vehicle component in the first target area, wherein the first target area is an area where vehicle damage occurs in the effective image;

performing image segmentation processing on the effective image to determine second target areas corresponding to the plurality of vehicle components in the effective image, and identifying and determining damage information in the second target areas;

generating a plurality of target pay areas according to the fusion of the first target area and the second target area, and matching corresponding pay strategies for each target pay area according to the damage information and the first component information;

And generating a target pay scheme according to the pay strategy corresponding to the target pay area.

In some embodiments, generating a plurality of target pay areas from a fusion of a first target area and a second target area includes:

determining the region type of the second target region, wherein the region type of the second target region is a damaged type or an undamaged type;

the first target area and the second target area belonging to the damage type are merged to generate a target pay area.

In some embodiments, matching corresponding payout policies for respective target payout areas according to the damage information and the first component information includes:

determining the generation type of each target pay area according to the generation process of the target pay area;

determining maintenance cost of the target pay area according to the generation type, the damage information and the first component information;

and matching corresponding pay strategies for the target pay areas according to the maintenance cost of each target pay area.

In some embodiments, if the target pay area is an intersection of the second target area and the first target area belonging to the damaged type, the corresponding generated type is the first type, and determining the maintenance cost of the target pay area according to the generated type, the damage information and the first component information includes:

If the generated type is the first type, determining second component information corresponding to a second target area where the target pay area is located;

if the matching degree of the first component information and the second component information exceeds a preset threshold, determining fusion component information according to the first component information and the second component information;

and determining the maintenance cost of the target pay area according to the fusion component information and the damage information.

In some embodiments, after determining the second component information corresponding to the second target area where the target pay area is located, the method further includes:

if the matching degree of the first component information and the second component information does not exceed the preset threshold value, analyzing the damage information to determine a weighting factor;

determining a first maintenance cost according to the first component information, and determining a second maintenance cost according to the second component information;

and calculating a weighted average value of the first maintenance cost and the second maintenance cost according to the weighting factors, and taking the weighted average value as the maintenance cost of the target pay area.

In some embodiments, determining a repair cost for the target pay area based on the fused component information and the damage information includes:

calling a part three-dimensional model corresponding to the information of the fusion part;

Inputting the damage information into a part three-dimensional model to obtain concave depth information and fascia deformation information;

and determining a maintenance scheme according to the concave depth information and the fascia deformation information, and determining maintenance cost according to the maintenance scheme.

In some embodiments, screening the vehicle loss image meeting the preset confidence condition from the vehicle loss image set as the effective image includes:

identifying a vehicle detection area in the obtained vehicle damage image and a confidence coefficient corresponding to the vehicle detection area, wherein the confidence coefficient is used for representing the probability of having a vehicle in the vehicle detection area;

extracting a target pixel with a vehicle element from a vehicle detection area, and determining a target pixel duty ratio of the target pixel in a vehicle damage image;

and taking the vehicle loss image with the confidence coefficient and the target pixel duty ratio meeting the preset numerical conditions as an effective image.

In a second aspect, an embodiment of the present application further provides a device for generating a vehicle risk claim, including:

the vehicle damage image acquisition module is used for acquiring a vehicle damage image set, wherein the vehicle damage image set comprises a plurality of vehicle damage images used for recording the damage state of the vehicle;

the effective image screening module is used for screening out the vehicle damage images meeting the preset confidence condition from the vehicle damage image set to serve as effective images;

The device comprises a component damage detection module, a first image acquisition module and a second image acquisition module, wherein the component damage detection module is used for analyzing and acquiring a first target area in an effective image and first component information of a vehicle component in the first target area, and the first target area is an area where vehicle damage occurs in the effective image;

the component segmentation and identification module is used for carrying out image segmentation processing on the effective image to determine second target areas corresponding to the plurality of vehicle components in the effective image respectively, and identifying and determining damage information in the second target areas;

the partition strategy matching module is used for generating a plurality of target pay areas according to fusion of the first target area and the second target area, and matching corresponding pay strategies for each target pay area according to the damage information and the first component information;

and the claim scheme generation module is used for generating a target claim scheme according to the claim strategy corresponding to the target claim area.

In a third aspect, embodiments of the present application also provide an electronic device comprising a processor, a memory, a computer program stored on the memory and executable by the processor, and a data bus for enabling a connection communication between the processor and the memory, wherein the computer program, when executed by the processor, implements the steps of any of the vehicle insurance claim scheme generating methods as provided in the present application.

In a fourth aspect, embodiments of the present application further provide a storage medium for computer readable storage, wherein the storage medium stores one or more programs executable by one or more processors to implement steps of any of the vehicle risk claim generation methods as provided herein.

In summary, an embodiment of the present application provides a method, an apparatus, a computer device, and a storage medium for generating a vehicle risk claim scheme, where the method includes: acquiring a vehicle damage image set, wherein the vehicle damage image set comprises a plurality of vehicle damage images used for recording the damage state of the vehicle; screening out vehicle damage images meeting preset confidence conditions from the vehicle damage image set to serve as effective images; analyzing and acquiring a first target area in the effective image and first component information of a vehicle component in the first target area, wherein the first target area is an area where vehicle damage occurs in the effective image; performing image segmentation processing on the effective image to determine second target areas corresponding to the plurality of vehicle components in the effective image, and identifying and determining damage information in the second target areas; generating a plurality of target pay areas according to the fusion of the first target area and the second target area, and matching corresponding pay strategies for each target pay area according to the damage information and the first component information; and generating a target pay scheme according to the pay strategy corresponding to the target pay area, so that the efficiency and accuracy of the danger setting of the vehicle are improved, and an accurate vehicle danger pay scheme is generated based on the actual damage condition of the vehicle.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present application, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

Fig. 1 is a schematic flow chart of a method for generating a vehicle risk claim plan according to an embodiment of the present application;

fig. 2 is a schematic flow chart of determining and generating a plurality of target pay areas based on an effective image in a method for generating a vehicle risk claim plan according to an embodiment of the present application;

fig. 3 is a schematic flow chart of a fusion generation target pay area in a method for generating a vehicle risk pay plan according to an embodiment of the present application;

fig. 4 is a schematic flow diagram of a matching claim policy in a method for generating a vehicle risk claim scheme according to an embodiment of the present application;

FIG. 5 is a logic judgment diagram of a matching claim policy in a method for generating a vehicle risk claim scheme according to an embodiment of the present application;

FIG. 6 is a schematic block diagram of a device for generating a vehicle insurance claim plan according to an embodiment of the present application;

Fig. 7 is a schematic block diagram of an electronic device according to an embodiment of the present application.

Detailed Description

The following description of the embodiments of the present application will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are some, but not all, of the embodiments of the present application. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the present disclosure, are within the scope of the present disclosure.

The flow diagrams depicted in the figures are merely illustrative and not necessarily all of the elements and operations/steps are included or performed in the order described. For example, some operations/steps may be further divided, combined, or partially combined, so that the order of actual execution may be changed according to actual situations.

It is to be understood that the terminology used in the description of the present application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used in this specification and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.

In order to solve the above problems, embodiments of the present application provide a method, an apparatus, a computer device, and a storage medium for generating a vehicle risk claim. Some embodiments of the present application are described in detail below with reference to the accompanying drawings. The following embodiments and features of the embodiments may be combined with each other without conflict.

It should be noted that the method for generating the vehicle insurance claim settlement scheme can be applied to electronic equipment, and the electronic equipment can be a service terminal such as a mobile phone, a tablet computer, a notebook computer, a desktop computer, a personal digital assistant, a wearable device and the like, and can also be a server terminal, wherein the server terminal can be an independent server or a server cluster. The following embodiments take an electronic device applied by the vehicle insurance claim scheme generating method as an example of a server terminal, and describe a specific implementation procedure of the vehicle insurance claim scheme generating method. But is not limited to, the vehicle risk claim generation method may be applied only to the server terminal. The server terminal executing the method is specifically used for distributing and distributing the total task set to a plurality of different service terminals.

Referring to fig. 1, fig. 1 is a flow chart of a method for generating a vehicle insurance claim plan according to an embodiment of the present application.

As shown in fig. 1, the vehicle risk claim plan generation method includes steps S1 to S6.

Step S1: a vehicle damage image set is obtained, wherein the vehicle damage image set comprises a plurality of vehicle damage images used for recording the damage state of the vehicle.

Specifically, the vehicle damage image set includes a plurality of vehicle damage images, and the vehicle damage images are used for recording the damage state of the vehicle. In the scene where the user declares the danger of the damaged vehicle, the user or the surveyor needs to shoot or record the damaged vehicle, and the vehicle damage image set is obtained by extracting the image or the video shot by the user on the damaged vehicle.

In some embodiments, the obtaining the vehicle damage image set may specifically be selecting an image captured by a user or a surveyor for a damaged vehicle according to a preset selection condition, for example, a condition of sharpness, brightness or resolution of the image, so as to obtain a plurality of vehicle damage images.

In some embodiments, acquiring the set of loss images may specifically be acquiring a video captured by a user or surveyor for the damaged vehicle, and capturing several images from the video as loss images.

Step S2: and screening out the vehicle loss images meeting the preset confidence condition from the vehicle loss image set to serve as effective images.

It should be noted that after the loss image set is acquired, elements related to the vehicle in part of the loss images may exist in the loss image set, and even no vehicle exists in the images, so that processing the loss images wastes computational resources, affects the generation rate of the subsequent risk claim scheme, and may cause incorrect recognition in the subsequent processing process to reduce the accuracy of the risk claim scheme.

Based on the method, the vehicle damage images meeting the preset confidence condition are screened out from the vehicle damage image set to serve as effective images, so that the generation accuracy of a vehicle insurance claim scheme is improved, and the processing period of single vehicle insurance claim is shortened.

It should be noted that, the identification of the acquired vehicle detection area from the single Zhang Che damage image does not characterize that valid vehicle elements must exist in the vehicle detection area, and each vehicle detection area also has a confidence level for characterizing the probability of having a vehicle element in the vehicle detection area. It will be appreciated that the higher the confidence of the vehicle detection region, the higher the probability of characterizing a vehicle detection region having a vehicle element, and the lower the confidence of the vehicle detection region, the lower the probability of characterizing a vehicle detection region having a vehicle element.

In some embodiments, identifying a vehicle detection region in the acquired single frame image and a confidence corresponding to the vehicle detection region includes: the single Zhang Che loss image is input into a preset vehicle detection algorithm, so that the vehicle detection algorithm outputs a vehicle detection area in the single Zhang Che loss image and corresponding confidence level according to the single Zhang Che loss image.

It should be further noted that the vehicle detection algorithm used in the embodiments of the present application may be a deep neural network-based algorithm or a non-neural network algorithm. For example, the deep neural network-based algorithm includes but is not limited to Yolov1/2/3/4/5/6/7, ssd (Single Shot MultiBox Detector) algorithm, central rnet, fast RCNN (Region Convolutional Neural Networks) and other neural networks, and if the non-neural network algorithm is adopted for processing, HOG (Histogram of Oriented Gradient, direction gradient histogram) algorithm and SVM (support vector machines, support vector machine) model may be adopted for acquiring the vehicle detection area and the corresponding confidence.

After that, a target pixel having a vehicle element is extracted from the vehicle detection area, and a target pixel duty ratio of the target pixel in the vehicle damage image is determined, and then the vehicle damage image, in which both the confidence and the target pixel duty ratio meet preset numerical conditions, is taken as an effective image.

Exemplary, taking the vehicle damage image with the confidence and the target pixel duty ratio both meeting the preset numerical conditions as the effective image specifically includes: and selecting an image with the confidence value of the vehicle detection area exceeding a preset confidence threshold value and the target pixel duty ratio exceeding a preset duty ratio threshold value from the multiple vehicle damage images as an effective image.

Through the screening operation of the step S2, the confidence coefficient and the pixel ratio of the vehicle in the effective image meet the actual requirements, so that the analyzability of the effective image is improved, and the vehicle is contained in the effective image with high probability. ,

step S3: and analyzing and acquiring a first target area in the effective image and first component information of the vehicle component in the first target area, wherein the first target area is an area where the vehicle damage occurs in the effective image.

It is known that, through the screening operation in step S2, the confidence coefficient and the pixel duty ratio of the vehicle in the effective image meet the actual requirements, and the first target area is the area where the vehicle damage occurs in the effective image.

Referring to fig. 2, fig. 2 is a flow chart illustrating a method for generating a vehicle risk claim plan according to an embodiment of the present application, wherein the method is based on effective image determination to generate a plurality of target claim areas.

As shown in fig. 2, the apparatus performing the present method analyzes the effective image to acquire a first target area therein and first component information of the vehicle component in the first target area.

In some embodiments, analyzing first component information of the first target area in the captured valid image and the vehicle component in the first target area includes: and retrieving a preset damage identification model, inputting an effective image into the damage identification model, so that the damage identification model identifies and acquires positions with damage characteristics in the effective image, identifying vehicle parts corresponding to the positions with the damage characteristics to generate first part information, and establishing a first target area according to the positions with the damage characteristics, wherein the positions with the damage characteristics are distributed in the first target area, and each first target area corresponds to one vehicle part.

Illustratively, the damage features described above include, but are not limited to: scratches, depressions, cracks, wrinkles, deletions, deep depressions, and the like. Exemplary, the vehicle components described above include, but are not limited to: automobile bumpers, fender panels, engine hoods, and the like.

Step S4: and performing image segmentation processing on the effective image to determine second target areas corresponding to the plurality of vehicle components in the effective image, and identifying and determining damage information in the second target areas.

As shown in fig. 2, the effective image is subjected to image division processing to determine a plurality of second target areas, each of which corresponds to a respective one of the vehicle components. The damage information includes at least: whether a vehicle damage has occurred in the corresponding second target area or whether a damage has occurred to the corresponding vehicle component can be determined based on the second target area. Further, if it is determined that the second target area is damaged, the damage information further includes a damage form and a damage depth.

In some embodiments, performing an image segmentation process on the effective image to determine second target areas corresponding to the plurality of vehicle components in the effective image, and identifying damage information in the determined second target areas, includes: and calling a preset part segmentation model, and inputting the effective image into the part segmentation model so that the part segmentation model performs segmentation processing on the effective image.

The component segmentation model is illustratively a neural network such as Faster RCNN. The component segmentation model is used for segmenting a plurality of second target areas corresponding to the vehicle components from the effective image. After the second target region is segmented, damage information of the second target region is determined based on the image recognition, in particular, whether a vehicle damage occurs in the second target region is determined.

Step S5: and generating a plurality of target pay areas according to the fusion of the first target area and the second target area, and matching corresponding pay strategies for each target pay area according to the damage information and the first component information.

As shown in fig. 2, a plurality of target pay areas are generated according to the fusion of the first target area and the second target area, wherein the target pay areas are areas where damage exists in the vehicle, which are determined by combining the analysis of the first target area and the second target area.

Referring to fig. 3, fig. 3 is a flow chart illustrating a process of generating a target payment area by fusion in the method for generating a vehicle risk payment scheme according to an embodiment of the present application.

As shown in fig. 3, in some embodiments, step S5 generates a plurality of target pay areas according to the fusion of the first target area and the second target area, and specifically includes steps S51-S52:

step S51: determining the region type of the second target region, wherein the region type of the second target region is a damaged type or an undamaged type;

step S52: and merging the first target area and the second target area belonging to the damage type to generate the target pay area.

As can be readily seen, the damage information includes at least: whether a vehicle damage has occurred in the corresponding second target area or whether a damage has occurred to the corresponding vehicle component can be determined based on the second target area. In this case, the region type of the second target region may be determined based on the damage information, but the region type of the second target region is not limited to the determination based on the damage information, and it may be detected whether the second target region is damaged or not.

Specifically, after the second target area is determined to be of a damaged type or an undamaged type, the first target area and the second target area belonging to the damaged type are combined to generate the target pay area, or a union of the second target area with the damaged type and the first target area is used as the target pay area. Specifically, if a pixel in the effective image satisfies at least one condition of "belonging to the second target area with the area type as the damaged type" and "belonging to the first target area", the determined pixel is in the target pay area.

Referring to fig. 4 and fig. 5, fig. 4 is a schematic flow chart of a matching claim policy in a method for generating a vehicle risk claim scheme according to an embodiment of the present application, and fig. 5 is a logic judgment chart of a matching claim policy in a method for generating a vehicle risk claim scheme according to an embodiment of the present application.

As shown in fig. 4 to 5, in some embodiments, in step S5, a corresponding payout policy is matched for each target payout area according to the damage information and the first component information, and specifically includes steps S51 to S53:

step S53: determining the generation type of each target pay area according to the generation process of the target pay area;

Step S54: determining maintenance cost of the target pay area according to the generation type, the damage information and the first component information;

step S55: and matching corresponding pay strategies for the target pay areas according to the maintenance cost of each target pay area.

The generation process based on the target pay area is as follows: the first target area and the second target area belonging to the damage type are combined to generate the target pay area, and thus the generation type of each target pay area can be determined by the generation process of the target pay area.

By way of example, the target pay area may be divided into three generation types according to the generation process of the target pay area: the first type is a union of a second target area belonging to the damaged type and the first target area, the second type is at the second target area belonging to the damaged type but not at the first target area, and the third type is at the first target area but not at the second target area belonging to the damaged type.

In some embodiments, if the target pay area is an intersection of the second target area belonging to the damaged type and the first target area, the corresponding generation type is the first type, and in step S54, determining the maintenance cost of the target pay area according to the generation type, the damage information and the first component information includes:

Specifically, if the target pay area is of the first type, the target pay area is located in both the second target area belonging to the damaged type and the second target area. In this embodiment, first, second component information corresponding to a second target area where a target pay area is located is determined, then, a matching degree between the first component information and the second component information is obtained, and the matching degree is compared with a preset threshold.

The matching degree is used to indicate whether the first component information and the second component information correspond to the same vehicle component: the first component information and the second component information correspond to the same vehicle component if the degree of matching between the first component information and the second component information exceeds a preset threshold, and the first component information and the second component information correspond to the same vehicle component if the degree of matching between the first component information and the second component information exceeds a preset threshold.

The matching degree between the first component information and the second component information is determined according to the component similarity between the first component information and the second component information and/or the position distance between the first component information and the second component information, wherein the component similarity refers to the type similarity between the component corresponding to the first component information and the component corresponding to the second information, and the higher the component similarity is, the higher the matching degree between the first component information and the second component information is. The position distance refers to the physical distance between the parts corresponding to the first part information and the parts corresponding to the second information, and the lower the position distance is, the higher the matching degree between the first part information and the second part information is.

Specifically, when the matching degree of the first component information and the second component information exceeds the preset threshold, determining that the first component information and the second component information correspond to the same vehicle component, and determining the fusion component information according to the first component information and the second component information, for example:

after that, corresponding maintenance schemes are determined according to the information of the fusion component and the corresponding damage information, and further the maintenance cost of the target pay area is obtained according to the maintenance schemes. By way of example, repair schemes determinable from the fused component information and its corresponding damage information are, for example, painting, repair, replacement, and the sheet metal part dimensions employed, etc.

Specifically, when the matching degree of the first component information and the second component information does not exceed the preset threshold, it is determined that the first component information and the second component information correspond to two different vehicle components, that is, the output results of the damage identification model and the component segmentation model are not matched. Based on this, the damage information is analyzed to determine a weighting factor, a first repair cost is determined according to the first component information, a second repair cost is determined according to the second component information, and a weighted average of the first repair cost and the second repair cost is calculated according to the weighting factor to serve as the repair cost of the target pay area.

the corresponding part three-dimensional model is called according to the information of the fusion part;

inputting the damage information into a part three-dimensional model to obtain corresponding concave depth information and fascia deformation information;

Specifically, the corresponding component three-dimensional model is called according to the fusion component information, and the component three-dimensional model needs to be known to comprise the three-dimensional form of the fusion component information. And inputting the damage information into the part three-dimensional model to load the damage information onto the three-dimensional form of the fusion part information to obtain the three-dimensional deformation of the fusion part information, obtaining corresponding concave depth information and fascia deformation information according to the three-dimensional deformation of the fusion part information, determining a maintenance scheme according to the concave depth information and fascia deformation information, and determining the maintenance cost according to the maintenance scheme.

Similarly, determining the first repair cost from the first component information includes: calling a corresponding part three-dimensional model according to the first part information; inputting the damage information into a part three-dimensional model to obtain corresponding concave depth information and fascia deformation information; and determining a maintenance scheme according to the concave depth information and the reinforcement line deformation information, and determining the maintenance cost corresponding to the first component information according to the maintenance scheme.

Similarly, determining the second repair cost from the second component information includes: calling a corresponding part three-dimensional model according to the second part information; inputting the damage information into a part three-dimensional model to obtain corresponding concave depth information and fascia deformation information; and determining a maintenance scheme according to the concave depth information and the reinforcement line deformation information, and determining the maintenance cost corresponding to the second component information according to the maintenance scheme.

By taking the corresponding part three-dimensional model and inputting the damage information into the part three-dimensional model, the damage condition of the vehicle part is three-dimensional and imaging, the concave depth information and the fascia deformation information can be more accurately determined, and further an accurate maintenance scheme and maintenance cost are obtained.

As shown in fig. 5, the target pay area may be classified into three generation types according to a generation process of the target pay area, wherein the target pay area of the second type is located at a second target area belonging to the damaged type but not at a first target area, and the target pay area of the third type is located at the first target area but not at the second target area belonging to the damaged type.

If the target pay area is of the second type, the maintenance cost can be determined according to the second component information and the corresponding damage information. If the target pay area is of the third type, the repair cost may be determined based on the first component information and the location with the damage characteristic.

Therefore, the target pay area is divided into different generation types based on the generation process of the target pay area, and a reasonable maintenance cost determination scheme is set for the target area of different generation types according to the different generation processes, so that corresponding pay strategies are matched for the target pay area according to the maintenance cost of each target pay area. The amount of payouts in the payouts policy of the respective target payouts areas is proportional to the maintenance cost.

Step S6: and generating a target pay scheme according to the pay strategy corresponding to the target pay area.

Specifically, at least one target pay area in the effective images can be determined in the previous step, the processing of the plurality of effective images is repeated to obtain target pay areas in the effective images, then vehicle components corresponding to the target pay areas in the effective images are determined, the vehicle components in the plurality of effective images are classified to determine the damaged target components actually appearing in the damaged vehicle, a target strategy is determined according to the pay strategies of the target pay areas corresponding to the target components in the plurality of effective images, and the target strategies corresponding to the plurality of target components are counted to obtain the target pay scheme.

In summary, the method for generating the vehicle insurance claim scheme provided by the application comprises the following steps: acquiring a vehicle damage image set, wherein the vehicle damage image set comprises a plurality of vehicle damage images used for recording the damage state of the vehicle; screening out vehicle damage images meeting preset confidence conditions from the vehicle damage image set to serve as effective images; analyzing and acquiring a first target area in the effective image and first component information of a vehicle component in the first target area, wherein the first target area is an area where vehicle damage occurs in the effective image; performing image segmentation processing on the effective image to determine second target areas corresponding to the plurality of vehicle components in the effective image, and identifying and determining damage information in the second target areas; generating a plurality of target pay areas according to the fusion of the first target area and the second target area, and matching corresponding pay strategies for each target pay area according to the damage information and the first component information; and generating a target pay scheme according to the pay strategy corresponding to the target pay area, so that the efficiency and accuracy of the danger setting of the vehicle are improved, and an accurate vehicle danger pay scheme is generated based on the actual damage condition of the vehicle.

Referring to fig. 6, fig. 6 is a schematic block diagram of a device for generating a vehicle insurance claim plan according to an embodiment of the present application.

As shown in fig. 6, the apparatus 700 for generating a vehicle risk claim plan is applicable to an electronic device, and the apparatus 700 for generating a vehicle risk claim plan includes a vehicle damage image acquisition module 701, an effective image screening module 702, a component damage detection module 703, a component division identification module 704, a division policy matching module 705, and a claim plan generation module 706.

The vehicle damage image acquisition module 701 is configured to acquire a vehicle damage image set, where the vehicle damage image set includes a plurality of vehicle damage images for recording a damaged state of a vehicle;

the effective image screening module 702 is configured to screen a vehicle damage image meeting a preset confidence condition from the vehicle damage image set as an effective image;

the component damage detection module 703 is configured to analyze and acquire a first target area in the effective image and first component information of the vehicle component in the first target area, where the first target area is an area where the vehicle damage occurs in the effective image;

the component segmentation recognition module 704 is configured to perform image segmentation processing on the effective image to determine second target areas corresponding to the plurality of vehicle components in the effective image, and recognize and determine damage information in the second target areas;

the partition policy matching module 705 is configured to generate a plurality of target pay areas according to fusion of the first target area and the second target area, and match corresponding pay policies for the target pay areas according to the damage information and the first component information;

The pay plan generation module 706 is configured to generate a target pay plan according to the pay policy corresponding to the target pay area.

In some implementations, the partition policy matching module 705, when generating a plurality of target pay areas from a fusion of a first target area and a second target area, includes:

In some implementations, the partition policy matching module 705, when matching corresponding payout policies for respective target payout areas according to the damage information and the first component information, includes:

In some embodiments, if the target pay area is an intersection of a second target area belonging to the damaged type and the first target area, the corresponding generated type is the first type;

The partition policy matching module 705, when determining the maintenance cost of the target pay area from the generation type, the damage information, and the first component information, includes:

In some embodiments, after determining the second component information corresponding to the second target area where the target pay area is located, the partition policy matching module 705 further includes:

In some implementations, the partition policy matching module 705, when determining a repair cost for a target pay area from the fused component information and the damage information, includes:

In some embodiments, the effective image screening module 702 screens the vehicle damage image meeting the preset confidence condition from the vehicle damage image set as an effective image, including:

Referring to fig. 7, fig. 7 is a schematic block diagram of an electronic device according to an embodiment of the present application.

As shown in fig. 7, the electronic device 300 includes a processor 301 and a memory 302, the processor 301 and the memory 302 being connected by a bus 303, such as an I2C (Inter-integrated Circuit) bus.

In particular, the processor 301 is used to provide computing and control capabilities to support the operation of the overall electronic device. The processor 301 may be a central processing unit (Central Processing Unit, CPU), the processor 301 may also be other general purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), field-programmable gate arrays (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. Wherein the general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.

Specifically, the Memory 302 may be a Flash chip, a Read-Only Memory (ROM) disk, an optical disk, a U-disk, a removable hard disk, or the like.

It will be appreciated by those skilled in the art that the structure shown in fig. 5 is merely a block diagram of a portion of the structure related to the embodiment of the present application and does not constitute a limitation of the electronic device to which the embodiment of the present application is applied, and in particular, the electronic device may include more or less components than those shown in the drawings, or may combine some components, or have a different arrangement of components.

The processor 301 is configured to execute a computer program stored in the memory, and implement any one of the methods for generating a vehicle risk claim scheme provided in the embodiments of the present application when the computer program is executed.

In some embodiments, the processor 301 is configured to run a computer program stored in a memory and when executing the computer program implement the steps of:

In some implementations, the processor 301, when generating a plurality of target pay areas from a fusion of a first target area and a second target area, includes:

In some embodiments, the processor 301 includes, when matching corresponding payout policies for respective target payout areas according to the damage information and the first component information:

In some embodiments, if the target pay area is an intersection of the second target area and the first target area belonging to the damaged type, the corresponding generated type is the first type, the processor 301, when determining the maintenance cost of the target pay area according to the generated type, the damage information, and the first component information, includes:

In some embodiments, after determining the second component information corresponding to the second target area where the target pay area is located, the processor 301 further includes:

In some embodiments, the processor 301, when determining the repair cost of the target pay area from the fused component information and the damage information, includes:

In some embodiments, when selecting a loss image from the set of loss images that meets the preset confidence condition as a valid image, the processor 301 includes:

It should be noted that, for convenience and brevity of description, specific working processes of the above-described electronic device may refer to corresponding processes in the foregoing embodiments of the vehicle risk claim scheme generating method, and are not described herein again.

The embodiments of the present application also provide a storage medium for computer readable storage, where the storage medium stores one or more programs, and the one or more programs may be executed by one or more processors to implement the steps of any of the methods for generating a vehicle risk claim plan provided in the embodiments of the present application.

The storage medium may be an internal storage unit of the electronic device of the foregoing embodiment, for example, a hard disk or a memory of the electronic device. The storage medium may also be an external storage device of the electronic device, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card) or the like, which are provided on the electronic device.

Those of ordinary skill in the art will appreciate that all or some of the steps, systems, functional modules/units in the apparatus, and methods disclosed above may be implemented as software, firmware, hardware, and suitable combinations thereof. In a hardware embodiment, the division between the functional modules/units mentioned in the above description does not necessarily correspond to the division of physical components; for example, one physical component may have multiple functions, or one function or step may be performed cooperatively by several physical components. Some or all of the physical components may be implemented as software executed by a processor, such as a central processing unit, digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application specific integrated circuit. Such software may be distributed on computer readable media, which may include computer storage media (or non-transitory media) and communication media (or transitory media). The term computer storage media includes both volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data, as known to those skilled in the art. Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital Versatile Disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium which can be used to store the desired information and which can be accessed by a computer. Furthermore, as is well known to those of ordinary skill in the art, communication media typically embodies computer readable instructions, data structures, program modules or other data in a modulated data signal such as a carrier wave or other transport mechanism and includes any information delivery media.

It should be understood that the term "and/or" as used in this specification and the appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes such combinations. It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or system that comprises the element.

The foregoing embodiment numbers of the present application are merely for describing, and do not represent advantages or disadvantages of the embodiments. The foregoing is merely illustrative of the embodiments of the present application, but the scope of the present application is not limited thereto, and any equivalent modifications or substitutions will be apparent to those skilled in the art within the scope of the present application, and these modifications or substitutions are intended to be included in the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims

1. A method of generating a vehicle insurance claim settlement scheme, the method comprising:

acquiring a vehicle damage image set, wherein the vehicle damage image set comprises a plurality of vehicle damage images used for recording the damage state of a vehicle;

screening out the vehicle loss images meeting preset confidence conditions from the vehicle loss image set to serve as effective images;

performing image segmentation processing on the effective image to determine second target areas corresponding to a plurality of vehicle components in the effective image, and identifying and determining damage information in the second target areas;

generating a plurality of target pay areas according to the fusion of the first target area and the second target area, and matching corresponding pay strategies for the target pay areas according to the damage information and the first component information;

2. The method of claim 1, wherein generating a plurality of target pay areas from the fusion of the first target area and the second target area comprises:

and merging the first target area and the second target area belonging to the damage type to generate the target pay area.

3. The method of claim 1, wherein the matching of the corresponding payoff policies for the respective target payoff areas based on the damage information and the first component information comprises:

4. The method of claim 3, wherein if the target pay area is an intersection of the second target area and the first target area belonging to a damaged type, the corresponding generated type is a first type, and determining a maintenance cost of the target pay area according to the generated type, the damaged information, and the first component information comprises:

If the generation type is the first type, determining second component information corresponding to a second target area where the target pay area is located;

5. The method of claim 4, wherein after determining the second component information corresponding to the second target area in which the target pay area is located, further comprising:

6. The method of claim 4, wherein the determining a repair cost for the target pay area based on the fused component information and the damage information comprises:

Calling a part three-dimensional model corresponding to the fused part information;

inputting the damage information into the part three-dimensional model to obtain concave depth information and fascia deformation information;

and determining a maintenance scheme according to the concave depth information and the fascia deformation information, and determining the maintenance cost according to the maintenance scheme.

7. The method according to any one of claims 1-6, wherein the screening the loss image from the loss image set to meet a preset confidence condition as a valid image includes:

identifying and acquiring a vehicle detection area in the vehicle damage image and a confidence coefficient corresponding to the vehicle detection area, wherein the confidence coefficient is used for representing the probability of having a vehicle in the vehicle detection area;

extracting target pixels with vehicle elements from the vehicle detection area, and determining target pixel duty ratios of the target pixels in the vehicle damage image;

and taking the vehicle loss image with the confidence coefficient and the target pixel duty ratio meeting the preset numerical condition as the effective image.

8. A vehicle risk claim plan generation apparatus, comprising:

the device comprises a component damage detection module, a first image acquisition module and a second image acquisition module, wherein the component damage detection module is used for analyzing and acquiring a first target area in the effective image and first component information of a vehicle component in the first target area, and the first target area is an area where vehicle damage occurs in the effective image;

the component segmentation and identification module is used for carrying out image segmentation processing on the effective image so as to determine second target areas corresponding to a plurality of vehicle components in the effective image respectively, and identifying and determining damage information in the second target areas;

the partition strategy matching module is used for generating a plurality of target pay areas according to fusion of the first target area and the second target area, and matching corresponding pay strategies for the target pay areas according to the damage information and the first component information;

9. A computer device, the computer device comprising a memory and a processor;

The memory is used for storing a computer program;

the processor is configured to execute the computer program and implement the vehicle risk claim 1 to 7.

10. A computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer program which, when executed by a processor, causes the processor to implement the vehicle risk claim settlement scheme generation method as defined in any one of claims 1 to 7.