CN117611352A

CN117611352A - Vehicle insurance claim processing method, device, computer equipment and storage medium

Info

Publication number: CN117611352A
Application number: CN202311349621.6A
Authority: CN
Inventors: 朱志华
Original assignee: Ping An Property and Casualty Insurance Company of China Ltd
Current assignee: Ping An Property and Casualty Insurance Company of China Ltd
Priority date: 2023-10-17
Filing date: 2023-10-17
Publication date: 2024-02-27

Abstract

The application discloses a vehicle insurance claim processing method, a vehicle insurance claim processing device, computer equipment and a storage medium, and belongs to the technical field of artificial intelligence and the field of financial science and technology. According to the method, first input data are built based on the case reporting factors and the policy factors, the first input data are imported into a self-help claim settlement prediction model to obtain self-help claim settlement prediction results, whether self-help claim settlement processing can be conducted is judged, if self-help claim settlement can be conducted, vehicle loss information is obtained, the vehicle loss information is imported into a vehicle loss identification model to obtain the vehicle loss prediction results, the claim settlement details of accident vehicles are determined based on the vehicle loss prediction results and the policy information, a vehicle risk claim settlement report of a current vehicle accident is generated, and the vehicle risk claim settlement report is uploaded. The application also relates to the technical field of blockchain, and the report information and the policy information are stored on a blockchain node. The self-help claim settlement method and device can judge whether self-help claim settlement can be carried out or not in advance, and if the self-help claim settlement can be carried out, a self-help claim settlement process is carried out, so that the efficiency and the accuracy of the claim settlement are improved.

Description

Vehicle insurance claim processing method, device, computer equipment and storage medium

Technical Field

The application belongs to the technical field of artificial intelligence and the field of financial science and technology, and particularly relates to a car insurance claim processing method, a device, computer equipment and a storage medium.

Background

The car insurance claim service is after-sale service corresponding to the car insurance policy products of each insurance driver, and after the user purchases the car insurance policy (business insurance or traffic forced insurance) product policy to take effect, the whole process from the case settlement to the case settlement payment after the insured person encounters an accident is long and complex.

The traditional vehicle insurance claim case processing flow is that a customer reports a case and then accepts the case by a insurance department, then dispatches the case to related personnel of the insurance department in a task form for tracking processing, the processing flow has a plurality of and complex links, and after the processing of the previous flow is finished, the next personnel is circulated for processing in a workflow form until the case is paid. If the case processing period does not meet the requirement of the task sending rule, repeated communication with the client and the repair shop is carried out for many times, so that the client experience is affected, the service quality of the client to the insurance company is reduced, and meanwhile, the insurance company needs to spend huge manpower to carry out the case task tracking processing, so that the operation cost of the insurance company is high.

Disclosure of Invention

An object of the embodiments of the present application is to provide a method, an apparatus, a computer device, and a storage medium for processing a car insurance claim, so as to solve the technical problems of complex flow, multiple links, frequent communication, poor customer experience, and increased labor cost and operation cost of an insurance company in the existing car insurance claim case processing flow.

In order to solve the above technical problems, the embodiments of the present application provide a method for processing a vehicle insurance claim, which adopts the following technical scheme:

a vehicle insurance claim processing method, comprising:

receiving a car insurance claim settlement instruction, and acquiring the report information of the current car accident and the policy information of the accident car;

extracting a case report factor from case report information of a current vehicle accident and extracting a policy factor from policy information of the accident vehicle;

constructing first input data based on the case reporting factors and the policy factors, and importing the first input data into a pre-trained self-help prediction model of the claim to obtain a self-help prediction result of the claim;

judging whether the current vehicle accident can carry out self-help claim settlement processing according to the self-help prediction result of claim settlement;

if the current vehicle accident can be subjected to self-help claim settlement, acquiring a scene picture of the current vehicle accident;

Extracting first vehicle loss information from the report information of the current vehicle accident, and extracting second vehicle loss information from the field picture of the current vehicle accident;

constructing second input data based on the first vehicle loss information and the second vehicle loss information, and importing the second input data into a pre-trained vehicle loss identification model to obtain a vehicle loss prediction result;

determining claim details of the accident vehicle based on the vehicle loss prediction result and the policy information of the accident vehicle;

and generating a car insurance claim settlement report of the current car accident based on the report information, the field picture, the insurance policy information, the car damage prediction result and the claim settlement detail, and uploading the car insurance claim settlement report.

Further, constructing first input data based on the case reporting factor and the policy factor, and importing the first input data into a pre-trained self-help prediction model of the claim to obtain a self-help prediction result of the claim, wherein the method specifically comprises the following steps:

extracting characteristics of first input data to obtain first data characteristics, wherein the first data characteristics comprise a case report factor characteristic and a policy factor characteristic;

constructing a data feature matrix based on the first data features;

and inputting the data characteristic matrix into a self-help prediction model of the claim to obtain a self-help prediction result of the claim.

Further, the self-help claim-predicting model is obtained based on training of the logistic regression model, and before the step of obtaining the self-help claim-predicting result, the method further comprises the steps of constructing first input data based on the case reporting factor and the policy factor, importing the first input data into the self-help claim-predicting model trained in advance, and obtaining the self-help claim-predicting result:

acquiring first historical data, wherein the first historical data comprises historical report information and historical policy information;

extracting a history report factor from the history report information and extracting a history policy factor from the history policy information;

constructing first historical data based on the historical report factors and the historical policy factors, extracting features of the first historical data, and obtaining first historical features;

constructing a history feature matrix based on the first history feature;

constructing an initial prediction model based on a logistic regression algorithm, and defining a class label of the initial prediction model;

inputting the historical feature matrix into an initial prediction model, and carrying out self-service prediction of the claim settlement on the first historical data based on the category labels and the historical feature matrix to obtain a prediction result of the historical claim settlement;

and performing parameter tuning on the initial prediction model based on the historical claim prediction result until the model is fitted to obtain the self-help prediction model of the trained claim.

Further, the step of inputting the history feature matrix into the initial prediction model, and performing self-help prediction of the claim settlement on the first history data based on the category label and the history feature matrix to obtain a prediction result of the history claim settlement specifically comprises the following steps:

learning an association relationship between the category labels and the historical feature matrix based on the initial prediction model;

and classifying the first historical data according to the association relation to obtain a historical claim settlement prediction result.

Further, parameter tuning is performed on the initial prediction model based on the historical claim prediction result until the model is fitted, so as to obtain a trained claim self-help prediction model, which specifically comprises the following steps:

calculating an error between a historical claim settlement prediction result and a preset standard prediction result through a loss function of the initial prediction model to obtain a prediction error;

judging the magnitude of a prediction error and a preset error threshold value;

when the prediction error is greater than a preset error threshold, a model iteration method in a logistic regression algorithm is used for carrying out parameter updating on the initial prediction model until the prediction error is less than or equal to the preset error threshold, and a trained self-help claim-settling prediction model is obtained.

Further, before the step of constructing the second input data based on the first vehicle loss information and the second vehicle loss information and importing the second input data into the pre-trained vehicle loss identification model to obtain the vehicle loss prediction result, the method further comprises:

Acquiring second historical data, and carrying out data division on the second historical data to obtain a training set and a testing set;

carrying out driving loss recognition on a preset initial recognition model through a training set to obtain an initial recognition result;

iterating the initial recognition model based on the initial recognition result to obtain a trained vehicle loss recognition model;

and testing the vehicle loss identification model through the test set, and outputting the vehicle loss identification model passing the test.

Further, the vehicle loss recognition model is obtained based on convolutional neural network training, and the vehicle loss recognition is carried out on the preset initial recognition model through a training set, so that an initial recognition result is obtained, and the method specifically comprises the following steps:

constructing an initial recognition model based on a convolutional neural network, wherein the initial recognition model comprises an input layer, a convolutional layer and an output layer;

acquiring second historical data, wherein the second historical data comprises historical accident information and historical accident pictures;

acquiring first historical vehicle loss information from the historical accident information, and acquiring second historical vehicle loss information from the historical accident picture;

constructing second historical data based on the first historical vehicle loss information and the second historical vehicle loss information, and importing the second historical data into an initial recognition model;

Performing feature extraction and feature vector conversion on the second historical data through the input layer to obtain a historical feature vector;

carrying out convolution operation on the historical feature vector through a convolution layer to obtain a feature convolution vector;

the characteristic convolution vector is linearly transformed through the output layer, and an initial recognition result is obtained through an activation function in the output layer;

iterating the initial recognition model based on the initial recognition result to obtain a trained vehicle loss recognition model, wherein the method specifically comprises the following steps of:

calculating an error between a historical vehicle loss recognition result and a preset standard recognition result based on a loss function of the initial recognition model to obtain a recognition error;

and carrying out iterative updating on the initial recognition model based on the recognition error and a preset back propagation algorithm until the model is fitted, so as to obtain the trained vehicle loss recognition model.

In order to solve the above technical problems, the embodiments of the present application further provide a vehicle insurance claim processing device, which adopts the following technical scheme:

a vehicle insurance claim processing device, comprising:

the accident information acquisition module is used for receiving the vehicle insurance claim settlement instruction and acquiring the report information of the current vehicle accident and the policy information of the accident vehicle;

The accident factor extraction module is used for extracting a case report factor from the case report information of the current vehicle accident and extracting a policy factor from the policy information of the accident vehicle;

the self-help claim-settlement prediction module is used for constructing first input data based on the case report factors and the policy factors, and importing the first input data into a pre-trained self-help claim-settlement prediction model to obtain self-help claim-settlement prediction results;

the self-help claim settlement judging module is used for judging whether the current vehicle accident can carry out self-help claim settlement processing according to the self-help prediction result of claim settlement;

the on-site picture acquisition module is used for acquiring on-site pictures of the current vehicle accidents if the current vehicle accidents can be subjected to self-service claim settlement;

the vehicle loss information extraction module is used for extracting first vehicle loss information from the report information of the current vehicle accident and extracting second vehicle loss information from the field picture of the current vehicle accident;

the accident vehicle loss prediction module is used for constructing second input data based on the first vehicle loss information and the second vehicle loss information, and importing the second input data into a pre-trained vehicle loss recognition model to obtain a vehicle loss prediction result;

the claim detail acquiring module is used for determining the claim detail of the accident vehicle based on the vehicle loss prediction result and the insurance policy information of the accident vehicle;

The accident car insurance claim settlement module is used for generating a car insurance claim settlement report of the current car accident based on the report information, the field picture, the insurance policy information, the car loss prediction result and the claim settlement details, and uploading the car insurance claim settlement report.

In order to solve the above technical problems, the embodiments of the present application further provide a computer device, which adopts the following technical schemes:

a computer device comprising a memory having stored therein computer readable instructions which when executed by the processor implement the steps of the vehicle insurance claim processing method of any of the above claims.

In order to solve the above technical problems, embodiments of the present application further provide a computer readable storage medium, which adopts the following technical solutions:

a computer readable storage medium having stored thereon computer readable instructions which when executed by a processor implement the steps of the vehicle insurance claim processing method of any of the above claims.

Compared with the prior art, the embodiment of the application has the following main beneficial effects:

the application discloses a vehicle insurance claim processing method, a vehicle insurance claim processing device, computer equipment and a storage medium, and belongs to the technical field of artificial intelligence and the field of financial science and technology. According to the method, first input data are built based on the case reporting factors and the policy factors, the first input data are imported into a self-help claim settlement prediction model to obtain self-help claim settlement prediction results, whether self-help claim settlement processing can be conducted is judged, if self-help claim settlement can be conducted, vehicle loss information is obtained, the vehicle loss information is imported into a vehicle loss identification model to obtain the vehicle loss prediction results, the claim settlement details of accident vehicles are determined based on the vehicle loss prediction results and the policy information, a vehicle risk claim settlement report of a current vehicle accident is generated, and the vehicle risk claim settlement report is uploaded. According to the method and the device, the case reporting factor, the policy factor and the pre-trained model are utilized to judge whether self-help claim settlement can be carried out, if self-help claim settlement can be carried out, a self-help claim settlement flow is executed, so that the efficiency and accuracy of claim settlement are improved, then the condition of vehicle damage is identified according to the information of the vehicle damage, the detail of the claim settlement is determined according to the condition of the vehicle damage and the policy information, and a corresponding claim settlement report is generated.

Drawings

For a clearer description of the solution in the present application, a brief description will be given below of the drawings that are needed in the description of the embodiments of the present application, it being obvious that the drawings in the following description are some embodiments of the present application, and that other drawings may be obtained from these drawings without inventive effort for a person of ordinary skill in the art.

FIG. 1 illustrates an exemplary system architecture diagram in which the present application may be applied;

FIG. 2 illustrates a flow chart of one embodiment of a vehicle insurance claim processing method according to the present application;

FIG. 3 illustrates a schematic diagram of one embodiment of a vehicle insurance claim processing device according to the present application;

fig. 4 shows a schematic structural diagram of one embodiment of a computer device according to the present application.

Detailed Description

Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs; the terminology used in the description of the applications herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application; the terms "comprising" and "having" and any variations thereof in the description and claims of the present application and in the description of the figures above are intended to cover non-exclusive inclusions. The terms first, second and the like in the description and in the claims or in the above-described figures, are used for distinguishing between different objects and not necessarily for describing a sequential or chronological order.

Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the present application. The appearances of such phrases in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. Those of skill in the art will explicitly and implicitly appreciate that the embodiments described herein may be combined with other embodiments.

In order to better understand the technical solutions of the present application, the following description will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the accompanying drawings.

As shown in fig. 1, a system architecture 100 may include terminal devices 101, 102, 103, a network 104, and a server 105. The network 104 is used as a medium to provide communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, among others.

The user may interact with the server 105 via the network 104 using the terminal devices 101, 102, 103 to receive or send messages or the like. Various communication client applications, such as a web browser application, a shopping class application, a search class application, an instant messaging tool, a mailbox client, social platform software, etc., may be installed on the terminal devices 101, 102, 103.

The terminal devices 101, 102, 103 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smartphones, tablet computers, electronic book readers, MP3 players (Moving Picture Experts Group Audio Layer III, dynamic video expert compression standard audio plane 3), MP4 (Moving Picture Experts Group Audio Layer IV, dynamic video expert compression standard audio plane 4) players, laptop and desktop computers, and the like.

The server 105 may be a server that provides various services, such as a background server that provides support for pages displayed on the terminal devices 101, 102, 103, and may be a stand-alone server, or may be a cloud server that provides cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (Content Delivery Network, CDN), and basic cloud computing services such as big data and artificial intelligence platforms.

It should be noted that, the method for processing the vehicle insurance claims provided in the embodiments of the present application is generally executed by a server, and accordingly, the device for processing the vehicle insurance claims is generally disposed in the server.

It should be understood that the number of terminal devices, networks and servers in fig. 1 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.

With continued reference to FIG. 2, a flow chart of one embodiment of a method of claim processing is shown in accordance with the present application. The embodiment of the application can acquire and process the related data based on the artificial intelligence technology. Among these, artificial intelligence (Artificial Intelligence, AI) is the theory, method, technique and application system that uses a digital computer or a digital computer-controlled machine to simulate, extend and extend human intelligence, sense the environment, acquire knowledge and use knowledge to obtain optimal results.

Artificial intelligence infrastructure technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technologies, operation/interaction systems, mechatronics, and the like. The artificial intelligence software technology mainly comprises a computer vision technology, a robot technology, a biological recognition technology, a voice processing technology, a natural language processing technology, machine learning/deep learning and other directions. The vehicle insurance claim processing method comprises the following steps:

S201, receiving a car insurance claim settlement instruction, and acquiring the report information of the current car accident and the policy information of the accident car.

In this embodiment, the system receives the adventure claim instruction submitted by the user, and may be implemented through various channels, such as a mobile App, a website, a customer service phone, and the like. And then obtaining report information of the current vehicle accident and insurance policy information of the accident vehicle, wherein the report information may include accident time, place, vehicle information, accident passing and the like, and the insurance policy information may include vehicle owners, insurance types, insurance amounts and the like. The information can be obtained by filling in a form, calling a third party data interface or performing data interaction with an insurance company system by a user.

S202, extracting a report factor from report information of a current vehicle accident and extracting a policy factor from policy information of the accident vehicle.

In this embodiment, relevant factors, such as a case report factor and a policy factor, are extracted from the case report information and the policy information, and these factors can be used for subsequent prediction and judgment. For example, the report factor may be extracted as the time, place, vehicle brand, vehicle age, etc. of the accident, and the method of extracting the factor may use natural language processing, text matching, data cleaning, etc.

In a specific embodiment of the present application, the policy factor refers to a factor related to a policy, including:

policy risk: specific dangerous types contained in the policy, such as vehicle loss risk in vehicle risk, third party liability risk and the like.

Policy type: refers to the type or form of policy, such as personal policy, group policy, business policy, etc.

Policy amount: the insurance amount or the insurance amount of the insurance policy is indicated to represent the highest responsibility amount born by the insurance company when an insurance accident occurs.

The case reporting factor refers to factors involved in the case reporting process, including:

type of report: specific types of the report, such as vehicle accident, article loss, property loss, etc.

Accident responsibility: the responsibility party and the responsibility proportion related during the accident, such as unilateral accident, multi-party accident, full responsibility accident, etc.

Description of accidents: accident related information provided during reporting such as loss condition, witness and witness, etc.

The consideration of the policy factors and the case reporting factors has important significance on whether self-help claim settlement can be carried out, and reasonable classification and decision can be carried out according to the policy attributes and the accident situation so as to improve the claim settlement efficiency and accuracy.

S203, constructing first input data based on the case reporting factors and the policy factors, and importing the first input data into a pre-trained self-help prediction model of the claim to obtain a self-help prediction result of the claim.

In this embodiment, the case reporting factor and the policy factor are combined into first input data, and the first input data is input into a pre-trained self-help claim settlement prediction model to obtain self-help claim settlement prediction results, where the self-help claim settlement prediction results include "self-help claim settlement" and "non-self-help claim settlement". The first input data may be constructed by encoding, normalizing, etc. the factors and then combining them into a vector or matrix, and the claim self-help prediction model may be trained using a machine learning model, such as decision trees, logistic regression, neural networks, etc.

For example, if the first input data includes a small incident or an undisputed incident or a complete and accurate policy information, etc., the self-help prediction model of the claim will determine the incident as a "self-help claimable" incident, and the subsequent steps may continue. If the first input data includes a large number of accidents, disputed accidents, incomplete or incorrect warranty information, etc., the self-help prediction model of the claims will determine the accident as an accident which can not be self-help resolved, and the method needs to be switched to manual processing or other proper processing modes.

S204, judging whether the self-help claim settlement processing can be carried out on the current vehicle accident according to the self-help prediction result of the claim settlement.

In this embodiment, according to the self-help prediction result of claim settlement, it is determined whether the current vehicle accident is suitable for self-help claim settlement, if it is determined that the current vehicle accident is suitable for self-help claim settlement, the subsequent steps may be continuously executed. Otherwise, it is necessary to go to manual processing or other suitable processing.

S205, if the current vehicle accident can be subjected to self-help claim settlement, acquiring a scene picture of the current vehicle accident.

In this embodiment, if the self-help claim settlement is suitable, the system may acquire a field picture of the current vehicle accident, and extract first vehicle damage information from the report information, where the field picture may be acquired by uploading by a user, invoking a camera to shoot, and the first vehicle damage information may include a damaged degree, a damaged portion, and the like of the vehicle.

S206, extracting first vehicle loss information from the report information of the current vehicle accident and extracting second vehicle loss information from the field picture of the current vehicle accident.

In this embodiment, second vehicle loss information is extracted from the field picture, the first vehicle loss information and the second vehicle loss information are combined into second input data, and then a pre-trained vehicle loss identification model is input to obtain a vehicle loss prediction result. The report information belongs to text information, key information can be extracted by using a natural language processing technology, information related to vehicle damage such as damage degree, damage position and the like can be identified by using a keyword extraction method, a named entity identification method and the like, information related to vehicle damage such as image segmentation, target detection and the like can be extracted by using a computer vision technology, and a vehicle damage identification model can be a deep learning model such as a convolutional neural network and the like.

S207, constructing second input data based on the first vehicle loss information and the second vehicle loss information, and importing the second input data into a pre-trained vehicle loss identification model to obtain a vehicle loss prediction result.

In this embodiment, the first vehicle loss information and the second vehicle loss information are combined into the second input data, and then a pre-trained vehicle loss identification model is input to obtain a vehicle loss prediction result, and the vehicle loss identification model is obtained based on machine learning model training.

S208, determining claim details of the accident vehicle based on the vehicle loss prediction result and the insurance policy information of the accident vehicle.

In this embodiment, based on the result of predicting the loss of the accident vehicle and the policy information of the accident vehicle, the system determines the details of the claims of the accident vehicle, including the repair cost, the compensation amount, and the like, and the method of determining the details of the claims may be calculation and judgment based on the result of predicting and the policy provision.

S209, generating a car insurance claim settlement report of the current car accident based on the report information, the field picture, the insurance policy information, the car damage prediction result and the claim settlement details, and uploading the car insurance claim settlement report.

In this embodiment, a vehicle insurance claim report of the current vehicle accident is generated according to the report information, the field picture, the policy information, the vehicle loss prediction result and the claim settlement details, and the vehicle insurance claim report is uploaded to the system for storage. The report can be generated by using template filling, text generation and other technologies, and uploading can be realized by means of file transmission, API call and the like, and when the report is uploaded, the security and the integrity of data need to be ensured.

In the embodiment, the self-help claim settlement process can be judged by using the case reporting factor, the policy factor and the pre-trained model, if the self-help claim settlement process can be carried out, the self-help claim settlement process is executed so as to improve the efficiency and accuracy of the claim settlement process, then the vehicle damage condition is identified according to the vehicle damage information, the claim settlement details are determined according to the vehicle damage condition and the policy information, and corresponding claim settlement reports are generated.

constructing a data feature matrix based on the first data features;

In this embodiment, the self-help claim settlement model may be trained through a logistic regression model, when the self-help claim settlement model is used, the features of the first input data are extracted to obtain the first data features, a data feature matrix is constructed based on the first data features, the data feature matrix includes a case report factor feature and a policy factor feature, each row represents a case report factor feature, each column represents a policy factor feature, and whether the self-help claim settlement can be performed on the current vehicle accident is judged through the relationship between the features and the target variables in the training data learned by the self-help claim settlement model and the input first data features.

constructing a history feature matrix based on the first history feature;

The logistic regression model is a classification model based on a logistic function (Sigmoid function) for solving the classification problem. It is assumed that there is a linear relationship between the input features and the output and that the result of the linear combination is mapped by a logical function to a probability value between 0 and 1 for representing the probability that the sample belongs to a certain class.

In this embodiment, history report information and history policy information are obtained, and these data are basic data for training a self-help prediction model of claim settlement, and relevant factors including accident type, insurance amount, etc. are extracted from the history report information and the history policy information to construct first history data, and corresponding features are extracted to obtain first history features, and the first history features are formed into a feature matrix for subsequent model training. And constructing an initial prediction model based on a logistic regression algorithm, defining a category label of the initial prediction model, inputting a historical feature matrix into the initial prediction model, performing self-help prediction of the claim settlement on the first historical data based on the category label and the historical feature matrix to obtain a result of the self-help prediction of the historical claim settlement, performing parameter tuning on the initial prediction model until the model is fitted, and obtaining the self-help prediction model of the claim settlement after training.

In a specific embodiment of the present application, data sets including policy factors and case reporting factors are collected and sorted, cleaned, missing values, outliers, etc., the preprocessed data sets are divided into training sets and test sets, the data sets are encoded, e.g., using single-heat encoding or tag encoding, and converted into numerical features, feature engineering, such as feature selection, feature scaling, etc., is performed to extract more useful features. Defining a feature matrix X and a target variable y, wherein X comprises feature matrices of policy factors and case reporting factors, y is a corresponding classification label, a training set data fitting logistic regression model is used, namely a fit () method is called, and X and y are transmitted as parameters. And evaluating the trained logistic regression model by using test set data, and calculating indexes such as accuracy, precision, recall rate, F1 value and the like to evaluate the performance of the model.

In a logistic regression model, "fitting" refers to using training data to estimate parameters of the model so that it can predict unknown data. In this step, a logistic regression model is fitted using the training set data so that the model learns the relationship between the features and the target variables.

In this embodiment, the fit () method of the logistic regression model object is called, and the feature matrix X and the target variable y are input as parameters, that is, logreg. In the fitting process, the logistic regression model estimates the parameters of the model by minimizing the loss function according to the relation between the characteristics in the training data and the target variable, and the model adjusts the parameters in an iterative mode to continuously optimize the fitting effect of the model. After the fit () method is completed, the logistic regression model has learned the relationship between the features in the training data and the target variable.

judging the magnitude of a prediction error and a preset error threshold value;

In this embodiment, an error between a historical claim settlement prediction result and a preset standard prediction result is calculated through a loss function of an initial prediction model to obtain a prediction error, the preset standard prediction result is a labeling result for first historical data, the magnitude of the prediction error and a preset error threshold is judged, and when the prediction error is greater than the preset error threshold, a model iteration method in a logistic regression algorithm is used for carrying out parameter updating on the initial prediction model until the prediction error is less than or equal to the preset error threshold, so that a trained claim settlement self-help prediction model is obtained.

In the fitting process, the logistic regression model uses optimization algorithms such as maximum likelihood estimation (Maximum Likelihood Estimation) or gradient descent to gradually adjust model parameters to find the best parameter combination, so that the model can best fit training data, and the fitting result is a trained logistic regression model which can be used for predicting new data.

In this embodiment, the historical data for training and testing the vehicle loss recognition model, that is, the second historical data, is obtained, and the training set is used to perform vehicle loss recognition training on the preset initial recognition model, so as to obtain an initial recognition result. Based on the initial recognition result, carrying out iterative training on the initial recognition model, and gradually optimizing the model by adjusting model parameters or using more complex model structures and other modes to obtain a trained vehicle loss recognition model. And testing the trained vehicle loss recognition model by using a test set, evaluating the performance and accuracy of the model on new data, and selecting the vehicle loss recognition model passing the test as a final model to be output according to a test result, wherein the model can be used for an actual vehicle loss recognition task after being trained and tested.

CNN (Convolutional Neural Network ) is a deep learning model commonly used for image processing and computer vision tasks, which is excellent in many computer vision tasks such as image classification, object detection, image segmentation, etc.

In this embodiment, in the process of constructing and training the vehicle loss recognition model based on the convolutional neural network, the initial recognition result is obtained by extracting features of the historical data and performing feature extraction and vehicle loss recognition through an input layer, a convolutional layer and an output layer of the convolutional neural network. And then carrying out iterative training on the model through a calculation recognition error and a back propagation algorithm until the model fits historical data to obtain a trained vehicle damage recognition model, wherein the model can be used for recognizing vehicle damage and provides support for vehicle damage evaluation and claim settlement processing.

In the above embodiments, the application discloses a method for processing a car insurance claim, which belongs to the technical field of artificial intelligence and the technical field of finance. According to the method, first input data are built based on the case reporting factors and the policy factors, the first input data are imported into a self-help claim settlement prediction model to obtain self-help claim settlement prediction results, whether self-help claim settlement processing can be conducted is judged, if self-help claim settlement can be conducted, vehicle loss information is obtained, the vehicle loss information is imported into a vehicle loss identification model to obtain the vehicle loss prediction results, the claim settlement details of accident vehicles are determined based on the vehicle loss prediction results and the policy information, a vehicle risk claim settlement report of a current vehicle accident is generated, and the vehicle risk claim settlement report is uploaded. According to the method and the device, the case reporting factor, the policy factor and the pre-trained model are utilized to judge whether self-help claim settlement can be carried out, if self-help claim settlement can be carried out, a self-help claim settlement flow is executed, so that the efficiency and accuracy of claim settlement are improved, then the condition of vehicle damage is identified according to the information of the vehicle damage, the detail of the claim settlement is determined according to the condition of the vehicle damage and the policy information, and a corresponding claim settlement report is generated.

In this embodiment, the electronic device (for example, the server shown in fig. 1) on which the vehicle insurance claim processing method operates may receive the instruction or acquire the data through a wired connection manner or a wireless connection manner. It should be noted that the wireless connection may include, but is not limited to, 3G/4G connections, wiFi connections, bluetooth connections, wiMAX connections, zigbee connections, UWB (ultra wideband) connections, and other now known or later developed wireless connection means.

It should be emphasized that, to further ensure the privacy and security of the report information and policy information, the report information and policy information may also be stored in a node of a blockchain.

The blockchain referred to in the application is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, consensus mechanism, encryption algorithm and the like. The Blockchain (Blockchain), which is essentially a decentralised database, is a string of data blocks that are generated by cryptographic means in association, each data block containing a batch of information of network transactions for verifying the validity of the information (anti-counterfeiting) and generating the next block. The blockchain may include a blockchain underlying platform, a platform product services layer, an application services layer, and the like.

Those skilled in the art will appreciate that implementing all or part of the processes of the methods of the embodiments described above may be accomplished by way of computer readable instructions, stored on a computer readable storage medium, which when executed may comprise processes of embodiments of the methods described above. The storage medium may be a nonvolatile storage medium such as a magnetic disk, an optical disk, a Read-Only Memory (ROM), or a random access Memory (Random Access Memory, RAM).

It should be understood that, although the steps in the flowcharts of the figures are shown in order as indicated by the arrows, these steps are not necessarily performed in order as indicated by the arrows. The steps are not strictly limited in order and may be performed in other orders, unless explicitly stated herein. Moreover, at least some of the steps in the flowcharts of the figures may include a plurality of sub-steps or stages that are not necessarily performed at the same time, but may be performed at different times, the order of their execution not necessarily being sequential, but may be performed in turn or alternately with other steps or at least a portion of the other steps or stages.

With further reference to fig. 3, as an implementation of the method shown in fig. 2, the present application provides an embodiment of a vehicle insurance claim processing apparatus, where an embodiment of the apparatus corresponds to the embodiment of the method shown in fig. 2, and the apparatus may be specifically applied to various electronic devices.

As shown in fig. 3, the vehicle insurance claim processing device 300 according to the present embodiment includes:

the accident information acquisition module 301 is configured to receive a vehicle insurance claim instruction, and acquire report information of a current vehicle accident and policy information of an accident vehicle;

an accident factor extraction module 302, configured to extract a case factor from case report information of a current vehicle accident, and extract a policy factor from policy information of an accident vehicle;

the self-help claim-predicting module 303 is configured to construct first input data based on the case report factor and the policy factor, and import the first input data into a self-help claim-predicting model trained in advance to obtain a self-help claim-predicting result;

the self-help claim settlement judging module 304 is used for judging whether the current vehicle accident can perform self-help claim settlement processing according to the self-help prediction result of claim settlement;

the on-site picture acquisition module 305 is configured to acquire an on-site picture of the current vehicle accident if the current vehicle accident can be subjected to self-service claim settlement;

The vehicle loss information extraction module 306 is configured to extract first vehicle loss information from the report information of the current vehicle accident, and extract second vehicle loss information from the field picture of the current vehicle accident;

the accident vehicle loss prediction module 307 is configured to construct second input data based on the first vehicle loss information and the second vehicle loss information, and import the second input data into a pre-trained vehicle loss recognition model to obtain a vehicle loss prediction result;

a claim detail obtaining module 308, configured to determine a claim detail of the accident vehicle based on the vehicle loss prediction result and the policy information of the accident vehicle;

the accident car insurance claim settlement module 309 is configured to generate a car insurance claim settlement report of the current car accident based on the report information, the field picture, the policy information, the car loss prediction result and the claim settlement details, and upload the car insurance claim settlement report.

Further, the self-help prediction module 303 specifically includes:

the first feature extraction unit is used for extracting features of first input data to obtain first data features, wherein the first data features comprise case report factor features and policy factor features;

the feature matrix construction unit is used for constructing a data feature matrix based on the first data features;

and the self-help prediction unit for the claim is used for inputting the data characteristic matrix into the self-help prediction model for the claim to obtain a self-help prediction result for the claim.

Further, the self-help prediction model for claim settlement is obtained based on training of the logistic regression model, and the vehicle insurance claim settlement processing device 300 further includes:

the first historical data module is used for acquiring first historical data, wherein the first historical data comprises historical report information and historical policy information;

the history factor extraction module is used for extracting the history report factors from the history report information and extracting the history policy factors from the history policy information;

the first history feature module is used for constructing first history data based on the history report factors and the history policy factors, extracting features of the first history data and obtaining first history features;

the historical feature matrix module is used for constructing a historical feature matrix based on the first historical features;

the initial prediction model construction module is used for constructing an initial prediction model based on a logistic regression algorithm and defining a class label of the initial prediction model;

the historical claim settlement self-help prediction module is used for inputting the historical feature matrix into the initial prediction model, and performing claim settlement self-help prediction on the first historical data based on the category labels and the historical feature matrix to obtain a historical claim settlement prediction result;

and the model parameter tuning module is used for performing parameter tuning on the initial prediction model based on the historical claim prediction result until the model is fitted to obtain the self-help prediction model of the claim after training is completed.

Further, the self-help prediction module for the historical claim settlement specifically comprises:

the association relation learning unit is used for learning association relation between the category labels and the historical feature matrix based on the initial prediction model;

and the historical data classification unit is used for classifying the first historical data according to the association relation to obtain a historical claim settlement prediction result.

Further, the model parameter tuning module specifically includes:

the prediction error calculation unit is used for calculating the error between the historical claim prediction result and the preset standard prediction result through the loss function of the initial prediction model to obtain a prediction error;

the prediction error comparison unit is used for judging the magnitude of the prediction error and a preset error threshold value;

and the model parameter updating unit is used for carrying out parameter updating on the initial prediction model by using a model iteration method in a logistic regression algorithm when the prediction error is greater than a preset error threshold value until the prediction error is less than or equal to the preset error threshold value, so as to obtain the trained self-help prediction model for the claim settlement.

Further, the vehicle insurance claim processing device 300 further includes:

the historical data dividing module is used for acquiring second historical data and dividing the second historical data to obtain a training set and a testing set;

The historical vehicle loss recognition module is used for carrying out vehicle loss recognition on a preset initial recognition model through a training set to obtain an initial recognition result;

the model iteration updating module is used for iterating the initial recognition model based on the initial recognition result to obtain a trained vehicle loss recognition model;

and the model performance test module is used for testing the vehicle loss identification model through the test set and outputting the vehicle loss identification model which passes the test.

Further, the historical vehicle loss identification module specifically includes:

the initial recognition model construction unit is used for constructing an initial recognition model based on the convolutional neural network, wherein the initial recognition model comprises an input layer, a convolutional layer and an output layer;

the second historical data unit is used for acquiring second historical data, wherein the second historical data comprises historical accident information and historical accident pictures;

the historical vehicle loss information unit is used for acquiring first historical vehicle loss information from the historical accident information and acquiring second historical vehicle loss information from the historical accident picture;

the second historical data unit is used for constructing second historical data based on the first historical vehicle loss information and the second historical vehicle loss information and importing the second historical data into the initial recognition model;

The history feature processing unit is used for carrying out feature extraction and feature vector conversion on the second history data through the input layer to obtain a history feature vector;

the characteristic convolution operation unit is used for carrying out convolution operation on the historical characteristic vector through the convolution layer to obtain a characteristic convolution vector;

the characteristic linear transformation unit is used for carrying out linear transformation on the characteristic convolution vector through the output layer and obtaining an initial recognition result through an activation function in the output layer;

the model iteration updating module specifically comprises:

the recognition error calculation unit is used for calculating errors between the historical vehicle loss recognition result and the preset standard recognition result based on the loss function of the initial recognition model to obtain recognition errors;

and the model iteration updating unit is used for carrying out iteration updating on the initial recognition model based on the recognition error and a preset back propagation algorithm until the model is fitted, so as to obtain a trained vehicle loss recognition model.

In the above-mentioned embodiment, the application discloses a car insurance claim processing apparatus, belongs to artificial intelligence technical field and finance science and technology field. According to the method, first input data are built based on the case reporting factors and the policy factors, the first input data are imported into a self-help claim settlement prediction model to obtain self-help claim settlement prediction results, whether self-help claim settlement processing can be conducted is judged, if self-help claim settlement can be conducted, vehicle loss information is obtained, the vehicle loss information is imported into a vehicle loss identification model to obtain the vehicle loss prediction results, the claim settlement details of accident vehicles are determined based on the vehicle loss prediction results and the policy information, a vehicle risk claim settlement report of a current vehicle accident is generated, and the vehicle risk claim settlement report is uploaded. According to the method and the device, the case reporting factor, the policy factor and the pre-trained model are utilized to judge whether self-help claim settlement can be carried out, if self-help claim settlement can be carried out, a self-help claim settlement flow is executed, so that the efficiency and accuracy of claim settlement are improved, then the condition of vehicle damage is identified according to the information of the vehicle damage, the detail of the claim settlement is determined according to the condition of the vehicle damage and the policy information, and a corresponding claim settlement report is generated.

In order to solve the technical problems, the embodiment of the application also provides computer equipment. Referring specifically to fig. 4, fig. 4 is a basic structural block diagram of a computer device according to the present embodiment.

The computer device 4 comprises a memory 41, a processor 42, a network interface 43 communicatively connected to each other via a system bus. It should be noted that only computer device 4 having components 41-43 is shown in the figures, but it should be understood that not all of the illustrated components are required to be implemented and that more or fewer components may be implemented instead. It will be appreciated by those skilled in the art that the computer device herein is a device capable of automatically performing numerical calculations and/or information processing in accordance with predetermined or stored instructions, the hardware of which includes, but is not limited to, microprocessors, application specific integrated circuits (Application Specific Integrated Circuit, ASICs), programmable gate arrays (fields-Programmable Gate Array, FPGAs), digital processors (Digital Signal Processor, DSPs), embedded devices, etc.

The computer equipment can be a desktop computer, a notebook computer, a palm computer, a cloud server and other computing equipment. The computer equipment can perform man-machine interaction with a user through a keyboard, a mouse, a remote controller, a touch pad or voice control equipment and the like.

The memory 41 includes at least one type of readable storage medium including flash memory, hard disk, multimedia card, card memory (e.g., SD or DX 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, magnetic disk, optical disk, etc. In some embodiments, the storage 41 may be an internal storage unit of the computer device 4, such as a hard disk or a memory of the computer device 4. In other embodiments, the memory 41 may also be an external storage device of the computer device 4, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash Card (Flash Card) or the like, which are provided on the computer device 4. Of course, the memory 41 may also comprise both an internal memory unit of the computer device 4 and an external memory device. In this embodiment, the memory 41 is typically used to store an operating system and various application software installed on the computer device 4, such as computer readable instructions of a vehicle insurance claim processing method. Further, the memory 41 may be used to temporarily store various types of data that have been output or are to be output.

The processor 42 may be a central processing unit (Central Processing Unit, CPU), controller, microcontroller, microprocessor, or other data processing chip in some embodiments. The processor 42 is typically used to control the overall operation of the computer device 4. In this embodiment, the processor 42 is configured to execute computer readable instructions stored in the memory 41 or process data, such as computer readable instructions for executing the vehicle insurance claim processing method.

The network interface 43 may comprise a wireless network interface or a wired network interface, which network interface 43 is typically used for establishing a communication connection between the computer device 4 and other electronic devices.

In the above embodiment, the application discloses a computer device, which belongs to the technical field of artificial intelligence and the technical field of finance. According to the method, first input data are built based on the case reporting factors and the policy factors, the first input data are imported into a self-help claim settlement prediction model to obtain self-help claim settlement prediction results, whether self-help claim settlement processing can be conducted is judged, if self-help claim settlement can be conducted, vehicle loss information is obtained, the vehicle loss information is imported into a vehicle loss identification model to obtain the vehicle loss prediction results, the claim settlement details of accident vehicles are determined based on the vehicle loss prediction results and the policy information, a vehicle risk claim settlement report of a current vehicle accident is generated, and the vehicle risk claim settlement report is uploaded. According to the method and the device, the case reporting factor, the policy factor and the pre-trained model are utilized to judge whether self-help claim settlement can be carried out, if self-help claim settlement can be carried out, a self-help claim settlement flow is executed, so that the efficiency and accuracy of claim settlement are improved, then the condition of vehicle damage is identified according to the information of the vehicle damage, the detail of the claim settlement is determined according to the condition of the vehicle damage and the policy information, and a corresponding claim settlement report is generated.

The present application also provides another embodiment, namely, a computer-readable storage medium storing computer-readable instructions executable by at least one processor to cause the at least one processor to perform the steps of the vehicle insurance claim processing method as described above.

In the above embodiments, the application discloses a computer readable storage medium, which belongs to the technical field of artificial intelligence and the technical field of finance. According to the method, first input data are built based on the case reporting factors and the policy factors, the first input data are imported into a self-help claim settlement prediction model to obtain self-help claim settlement prediction results, whether self-help claim settlement processing can be conducted is judged, if self-help claim settlement can be conducted, vehicle loss information is obtained, the vehicle loss information is imported into a vehicle loss identification model to obtain the vehicle loss prediction results, the claim settlement details of accident vehicles are determined based on the vehicle loss prediction results and the policy information, a vehicle risk claim settlement report of a current vehicle accident is generated, and the vehicle risk claim settlement report is uploaded. According to the method and the device, the case reporting factor, the policy factor and the pre-trained model are utilized to judge whether self-help claim settlement can be carried out, if self-help claim settlement can be carried out, a self-help claim settlement flow is executed, so that the efficiency and accuracy of claim settlement are improved, then the condition of vehicle damage is identified according to the information of the vehicle damage, the detail of the claim settlement is determined according to the condition of the vehicle damage and the policy information, and a corresponding claim settlement report is generated.

From the above description of the embodiments, it will be clear to those skilled in the art that the above-described embodiment method may be implemented by means of software plus a necessary general hardware platform, but of course may also be implemented by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a storage medium (such as ROM/RAM, magnetic disk, optical disk), comprising several instructions for causing a terminal device (which may be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to perform the method described in the embodiments of the present application.

The subject application is operational with numerous general purpose or special purpose computer system environments or configurations. For example: personal computers, server computers, hand-held or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments that include any of the above systems or devices, and the like. The application may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The application may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.

It is apparent that the embodiments described above are only some embodiments of the present application, but not all embodiments, the preferred embodiments of the present application are given in the drawings, but not limiting the patent scope of the present application. This application may be embodied in many different forms, but rather, embodiments are provided in order to provide a more thorough understanding of the present disclosure. Although the present application has been described in detail with reference to the foregoing embodiments, it will be apparent to those skilled in the art that modifications may be made to the embodiments described in the foregoing, or equivalents may be substituted for elements thereof. All equivalent structures made by the specification and the drawings of the application are directly or indirectly applied to other related technical fields, and are also within the protection scope of the application.

Claims

1. A method of processing a vehicle insurance claim, comprising:

extracting a case report factor from the case report information of the current vehicle accident, and extracting a policy factor from the policy information of the accident vehicle;

Constructing first input data based on the case report factor and the policy factor, and importing the first input data into a pre-trained self-help prediction model of the claim to obtain a self-help prediction result of the claim;

judging whether the current vehicle accident can carry out self-help claim settlement processing or not according to the self-help predicting result of claim settlement;

and generating a car insurance claim settlement report of the current car accident based on the report information, the field picture, the insurance policy information, the car loss prediction result and the claim settlement detail, and uploading the car insurance claim settlement report.

2. The method for processing a claim 1, wherein the step of constructing first input data based on the case report factor and the policy factor, and importing the first input data into a pre-trained self-help prediction model for claim settlement, to obtain a self-help prediction result for claim settlement, specifically comprises the steps of:

extracting characteristics of the first input data to obtain first data characteristics, wherein the first data characteristics comprise a case report factor characteristic and a policy factor characteristic;

constructing a data feature matrix based on the first data feature;

and inputting the data characteristic matrix into the self-help prediction model of the claim to obtain the self-help prediction result of the claim.

3. The method for processing a claim 1, wherein the self-help prediction model for claim settlement is obtained based on training a logistic regression model, and before the steps of constructing first input data based on the case report factor and the policy factor and importing the first input data into the self-help prediction model for claim settlement trained in advance, the method further comprises:

constructing first historical data based on the historical report factor and the historical policy factor, and extracting features of the first historical data to obtain first historical features;

constructing a history feature matrix based on the first history feature;

constructing an initial prediction model based on a logistic regression algorithm, and defining a category label of the initial prediction model;

inputting the historical feature matrix into the initial prediction model, and carrying out self-help prediction of claim settlement on the first historical data based on the category labels and the historical feature matrix to obtain a prediction result of the historical claim settlement;

and performing parameter tuning on the initial prediction model based on the historical claim settlement prediction result until the model is fitted to obtain a self-help claim settlement prediction model with completed training.

4. The method for processing a vehicle insurance claim 3, wherein the step of inputting the history feature matrix into the initial prediction model, and performing a claim self-service prediction on the first history data based on the category label and the history feature matrix to obtain a history claim prediction result specifically includes:

and classifying the first historical data according to the association relation to obtain the obtained historical claim prediction result.

5. The method for processing the vehicle insurance claim 3, wherein the step of performing parameter tuning on the initial prediction model based on the historical claim settlement prediction result until model fitting to obtain the self-help prediction model of the claim settlement after training specifically comprises the following steps:

calculating an error between the historical claim prediction result and a preset standard prediction result through a loss function of the initial prediction model to obtain a prediction error;

judging the magnitude of the prediction error and a preset error threshold value;

and when the prediction error is greater than the preset error threshold, performing parameter updating on the initial prediction model by using a model iteration method in the logistic regression algorithm until the prediction error is less than or equal to the preset error threshold, so as to obtain the trained self-help prediction model for claims.

6. The vehicle risk claim 1 to 5, wherein before the step of constructing second input data based on the first vehicle loss information and the second vehicle loss information and importing the second input data into a pre-trained vehicle loss recognition model to obtain a vehicle loss prediction result, the method further comprises:

carrying out driving loss recognition on a preset initial recognition model through the training set to obtain an initial recognition result;

and testing the vehicle loss identification model through the test set, and outputting the vehicle loss identification model which passes the test.

7. The vehicle insurance claim processing method according to claim 6, wherein the vehicle loss recognition model is obtained based on convolutional neural network training, and the step of performing vehicle loss recognition on a preset initial recognition model through the training set to obtain an initial recognition result specifically comprises the following steps:

constructing the initial recognition model based on a convolutional neural network, wherein the initial recognition model comprises an input layer, a convolutional layer and an output layer;

acquiring first historical vehicle loss information from the historical accident information and acquiring second historical vehicle loss information from the historical accident picture;

Constructing second historical data based on the first historical vehicle loss information and the second historical vehicle loss information, and importing the second historical data into the initial recognition model;

performing convolution operation on the historical feature vector through the convolution layer to obtain a feature convolution vector;

the characteristic convolution vector is linearly transformed through the output layer, and the initial recognition result is obtained through an activation function in the output layer;

the step of iterating the initial recognition model based on the initial recognition result to obtain a trained vehicle loss recognition model specifically comprises the following steps:

calculating an error between a historical vehicle loss recognition result and a preset standard recognition result based on the loss function of the initial recognition model to obtain a recognition error;

and carrying out iterative updating on the initial recognition model based on the recognition error and a preset back propagation algorithm until the model is fitted to obtain the trained vehicle loss recognition model.

8. A vehicle insurance claim processing device, comprising:

the self-help claim settlement judging module is used for judging whether the current vehicle accident can carry out self-help claim settlement processing according to the claim settlement self-help prediction result;

the on-site picture acquisition module is used for acquiring on-site pictures of the current vehicle accident if the current vehicle accident can be subjected to self-service claim settlement;

The claim detail obtaining module is used for determining the claim detail of the accident vehicle based on the vehicle loss prediction result and the policy information of the accident vehicle;

and the accident car insurance claim settlement module is used for generating a car insurance claim settlement report of the current car accident based on the report information, the field picture, the insurance policy information, the car damage prediction result and the claim settlement detail and uploading the car insurance claim settlement report.

9. A computer device comprising a memory and a processor, the memory having stored therein computer readable instructions which when executed by the processor implement the steps of the vehicle risk claim processing method of any one of claims 1 to 7.

10. A computer readable storage medium having stored thereon computer readable instructions which when executed by a processor implement the steps of the vehicle insurance claim processing method of any of claims 1 to 7.