CN116977093A

CN116977093A - Method and device for identifying risk of vehicle insurance claim settlement based on clustering and electronic equipment

Info

Publication number: CN116977093A
Application number: CN202310644165.1A
Authority: CN
Inventors: 景慎伟; 李思涛; 秦冬; 蒋成立; 李天驰
Original assignee: Peoples Insurance Company of China
Current assignee: Peoples Insurance Company of China
Priority date: 2023-06-01
Filing date: 2023-06-01
Publication date: 2023-10-31

Abstract

The application provides a cluster-based vehicle insurance claim risk identification method and device, electronic equipment and storage medium, and relates to the technical field of computers. According to the method, a recognition request of vehicle insurance claim risk is conducted on damage assessment single data of a target case, historical damage assessment data is obtained, and effective damage assessment data passing through damage assessment is screened out from the historical damage assessment data; determining a plurality of target loss assessment data associated with the loss assessment single data of the target case in the effective loss assessment data based on the clustering; and identifying the claim risk of the target case according to the claim risk information of the target damage assessment data. The embodiment of the application can determine a plurality of target damage assessment data associated with the damage assessment single data of the target cases based on the clustering thought, further identify the claim risk of the target cases according to the claim risk information of the plurality of target damage assessment data, identify the claim risk in the damage assessment replacement repair list and effectively detect the leakage virtual increased cases in the damage assessment.

Description

Method and device for identifying risk of vehicle insurance claim settlement based on clustering and electronic equipment

Technical Field

The present application relates to the field of computer technologies, and in particular, to a method and apparatus for identifying risk of vehicle insurance claims based on clustering, an electronic device, and a storage medium.

Background

In the management and control of the risk of the vehicle insurance claim, a nuclear damage person needs to manually check whether the replacement and repair items in the damage assessment list are consistent with the positions and the degrees of the vehicle damage presented in the pictures or not, the efficiency is low, the time limit requirements of service processing cannot be guaranteed, the risk of the virtual increase and the damage expansion in the damage assessment can not be well managed and controlled, and the damage is brought to the insurance company claim. Therefore, there is a need to solve this technical problem.

Disclosure of Invention

The present application has been made in view of the above problems, and provides a method and apparatus for identifying cluster-based risk of vehicle insurance claims, an electronic device, and a storage medium that overcome or at least partially solve the above problems. The technical scheme is as follows:

in a first aspect, a method for identifying risk of vehicle insurance claim settlement based on clustering is provided, including:

responding to an identification request of vehicle insurance claim risk aiming at the loss assessment list data of a target case, acquiring historical loss assessment data, and screening effective loss assessment data passing through loss assessment from the historical loss assessment data;

determining a plurality of target loss assessment data associated with the loss assessment single data of the target case in the effective loss assessment data based on clustering;

and identifying the claim risk of the target case according to the claim risk information of the target loss data.

In one possible implementation, determining, based on a cluster, a plurality of target impairment data associated with impairment list data of the target case in the effective impairment data, includes:

inputting the effective loss assessment data into a pre-trained decision tree model, identifying the stressed collision points of the vehicle, and outputting the stressed collision points of the vehicle corresponding to the effective loss assessment data;

inputting the loss-fixed data of the target case into a pre-trained decision tree model, and outputting a stress collision point of the vehicle corresponding to the loss-fixed data of the target case;

and determining a plurality of target loss allocation data associated with the loss allocation single data of the target case in the effective loss allocation data based on clustering based on the stress collision points of the vehicles corresponding to the loss allocation single data of the target case and the stress collision points of the vehicles corresponding to the effective loss allocation data.

In one possible implementation, the decision tree model is trained by:

by carrying out azimuth mapping on single accessories in the historical loss assessment data, a matrix of 8 rows and n columns is formed, n is a positive integer, 8 rows of the matrix represent 8 azimuth, and each element of the matrix represents different accessories;

based on the matrix of 8 rows and n columns, the initial weight and the expert weight, converting the multi-classification output value into probability distribution with the range of 0 and 1 and the sum of 1 through a preset classification algorithm;

and according to the matrix of 8 rows and n columns, coding by using accessory combinations of sample claim cases, and training the preset classification algorithm to obtain a trained decision tree model.

the effective loss assessment data and the loss assessment data of the target case are respectively coded and converted into a matrix of K rows and N columns, wherein the K rows represent damage parts, damage degree, maintenance methods, accident types and risk reasons in the effective loss assessment data and the loss assessment data of the target case, N is the maximum number of fittings concerned, and the column number of each fitting is fixed;

clustering the matrix of K rows and N columns of the effective loss assessment data and the matrix of K rows and N columns of the loss assessment single data of the target case, and determining a plurality of target loss assessment data associated with the loss assessment single data of the target case in the effective loss assessment data.

In one possible implementation manner, clustering the matrix of K rows and N columns of the effective loss assessment data and the matrix of K rows and N columns of the loss assessment single data of the target case, and determining a plurality of target loss assessment data associated with the loss assessment single data of the target case in the effective loss assessment data includes:

and performing Euclidean distance calculation on the matrix of the K rows and N columns of the effective loss assessment data and the matrix of the K rows and N columns of the loss assessment single data of the target case, and determining a plurality of target loss assessment data associated with the loss assessment single data of the target case in the effective loss assessment data according to a calculation result.

In one possible implementation, the claim risk of the target case includes loss logic, repair logic, virtual augmentation risk, and leakage risk of replacement repair criteria.

In one possible implementation, identifying the claim risk of the target case according to the claim risk information of the plurality of target damage data includes:

determining virtual increase risks exceeding a preset value as the claim risk of the target case according to the claim risk information of the target loss data; and/or

And determining target maintenance accessories which exist in the target cases but do not exist in the target loss data according to the claim risk information of the target loss data, and taking the target maintenance accessories as the claim risk of the target cases.

In a second aspect, there is provided a cluster-based vehicle insurance claim risk identification device, including:

the acquisition module is used for responding to an identification request of vehicle insurance claim settlement risk aiming at the loss assessment single data of the target case, acquiring historical loss assessment data and screening effective loss assessment data passing through loss assessment from the historical loss assessment data;

a determining module, configured to determine, from the valid impairment data, a plurality of target impairment data associated with impairment list data of the target case based on a cluster;

and the identification module is used for identifying the claim risk of the target case according to the claim risk information of the target damage assessment data.

In one possible implementation, the determining module is further configured to:

In one possible implementation manner, the apparatus further includes a training module configured to:

In one possible implementation, the identification module is further configured to:

In a third aspect, an electronic device is provided, the electronic device comprising a processor and a memory, wherein the memory has stored therein a computer program, the processor being configured to run the computer program to perform the cluster-based method of identifying a risk of a car insurance claim as set forth in any of the above.

In a fourth aspect, a storage medium is provided, where the storage medium stores a computer program, where the computer program is configured to perform, when run, the cluster-based method of identifying risk of a vehicle insurance claim according to any of the above.

By means of the technical scheme, the identification method and device for the vehicle risk claim risk based on the clustering, the electronic equipment and the storage medium can respond to the identification request of the vehicle risk claim risk aiming at the loss assessment single data of the target case, acquire historical loss assessment data and screen out effective loss assessment data passing through loss assessment from the historical loss assessment data; determining a plurality of target loss assessment data associated with the loss assessment single data of the target case in the effective loss assessment data based on the clustering; and identifying the claim risk of the target case according to the claim risk information of the target damage assessment data. It can be seen that the embodiment of the application can determine a plurality of target damage assessment data associated with the damage assessment single data of the target cases in the effective damage assessment data based on the clustering thought, further identify the claim risk of the target cases according to the claim risk information of the plurality of target damage assessment data, and can identify the claim risk in the damage assessment replacement repair list, thereby effectively detecting the leakage virtual increase cases in damage assessment.

Drawings

In order to more clearly illustrate the technical solution of the embodiments of the present application, the drawings that are required to be used in the description of the embodiments of the present application will be briefly described below.

FIG. 1 shows a flowchart of a method for identifying a cluster-based risk of a vehicle insurance claim provided by an embodiment of the present application;

FIG. 2 shows a block diagram of a cluster-based identification device for risk of vehicle insurance claims according to an embodiment of the present application;

FIG. 3 is a block diagram of an identification device for managing risk of claim based on cluster in accordance with another embodiment of the present application;

fig. 4 shows a block diagram of an electronic device according to an embodiment of the present application.

Detailed Description

Exemplary embodiments of the present application will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present application are shown in the drawings, it should be understood that the present application may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the application to those skilled in the art.

It should be noted that the terms "first," "second," and the like in the description and the claims of the present application and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that such use is interchangeable under appropriate circumstances such that the embodiments of the application described herein are capable of operation in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "include" and variations thereof are to be interpreted as open-ended terms that mean "include, but are not limited to.

In order to solve the above technical problems, an embodiment of the present application provides a method for identifying a risk of a vehicle insurance claim based on clustering, as shown in fig. 1, the method for identifying a risk of a vehicle insurance claim based on clustering may include steps S101 to S103 as follows:

step S101, responding to an identification request of vehicle insurance claim risk aiming at the loss assessment list data of the target case, acquiring historical loss assessment data, and screening effective loss assessment data passing through loss assessment from the historical loss assessment data.

In this step, the historical damage assessment data may include damage components, damage degree, maintenance method, accident type, risk reasons, maintenance factories, damage assessors, nuclear damage personnel, and the like, which is not limited in this embodiment. The screening of the effective loss assessment data passing through the loss assessment from the historical loss assessment data may refer to screening the loss assessment data passing through the claim risk manual audit from the historical loss assessment data as the effective loss assessment data.

Step S102, determining a plurality of target damage data associated with the damage list data of the target case in the effective damage data based on the clustering.

Step S103, identifying the claim risk of the target case according to the claim risk information of the target damage data.

The embodiment of the application can determine a plurality of target damage assessment data associated with the damage assessment single data of the target cases based on the clustering thought, further identify the claim risk of the target cases according to the claim risk information of the plurality of target damage assessment data, identify the claim risk in the damage assessment replacement repair list and effectively detect the leakage virtual increased cases in the damage assessment.

In the embodiment of the present application, a possible implementation manner is provided, where in the step S102, a plurality of target damage data associated with damage list data of a target case is determined in the effective damage data based on clustering, and the method specifically may include the following steps A1 to A3:

a1, inputting effective loss assessment data into a pre-trained decision tree model, identifying stress collision points of a vehicle, and outputting the stress collision points of the vehicle corresponding to the effective loss assessment data;

step A2, inputting the loss-fixed data of the target case into a pre-trained decision tree model, and outputting a stress collision point of the vehicle corresponding to the loss-fixed data of the target case;

and A3, determining a plurality of target damage assessment data associated with the damage assessment single data of the target case in the effective damage assessment data based on the stress collision points of the vehicles corresponding to the damage assessment single data of the target case and the stress collision points of the vehicles corresponding to the effective damage assessment data.

The embodiment can determine, based on the stress collision points of the vehicle corresponding to the loss allocation single data of the target case and the stress collision points of the vehicle corresponding to the effective loss allocation data, a plurality of target loss allocation data associated with the loss allocation single data of the target case in the effective loss allocation data based on clustering, for example, the stress collision points are the same as one type, and determine, in the effective loss allocation data, a plurality of target loss allocation data associated with the loss allocation single data of the target case, and can accurately and effectively determine a plurality of target loss allocation data associated with the loss allocation single data of the target case so as to identify the claim risk of the target case.

The embodiment of the application provides a possible implementation manner, and the decision tree model can be trained through the following steps B1 to B3:

and B1, performing azimuth mapping on single accessories in the historical impairment data to form a matrix of 8 rows and n columns, wherein n is a positive integer, 8 rows of the matrix represent 8 azimuths, and each element of the matrix represents different accessories.

In this step, a plurality of accessories are involved in the historical impairment data, and an azimuth mapping can be performed on a single accessory in the historical impairment data, wherein there are 8 azimuths, and the accessories can be mapped to corresponding azimuths, so that an 8-row n-column matrix is formed.

And B2, converting the multi-classification output value into probability distribution which ranges from 0 to 1 and is 1 by a preset classification algorithm based on the matrix of 8 rows and n columns, the initial weight and the expert weight.

In this step, the initial weights may be preset, and the expert weights may be determined based on expert experience, so that the matrix of 8 rows and n columns, the initial weights and the expert weights are combined, and the multi-class output values are converted into probability distributions ranging from 0 to 1 and sum to 1 through a preset classification algorithm. The preset classification algorithm here may specifically be a Softmax function in GBDT (iterative decision tree algorithm) method, which is a normalized exponential function.

And B3, coding by using accessory combinations of sample claim cases according to a matrix of 8 rows and n columns, and training a preset classification algorithm to obtain a trained decision tree model.

In the step, the sample claim case is marked with the stress collision points of the vehicle, so that the accessory combination of the sample claim case is used for coding according to a matrix of 8 rows and n columns, a preset classification algorithm is trained to obtain a trained decision tree model, and further the trained decision tree model can be used for predicting and identifying the stress collision points of the subsequent vehicle, for example, the stress collision points of the vehicle corresponding to effective damage assessment data, or the stress collision points of the vehicle corresponding to the damage assessment single data of the target case, and the like.

The embodiment can be combined with the fittings in the historical damage assessment data and the stressed collision points of the sample claim cases marked with the vehicles to train the decision tree model so as to predict and identify the stressed collision points of the subsequent vehicles by using the trained decision tree model.

The embodiment of the present application provides a possible implementation manner, where in step S102 above, a plurality of target impairment data associated with impairment list data of a target case is determined in the effective impairment data based on clustering, and specifically may include the following steps C1 and C2:

step C1, the loss-defining data of the effective loss-defining data and the loss-defining data of the target case are respectively coded and converted into a matrix of K rows and N columns, wherein the K rows represent damage parts, damage degree, maintenance methods, accident types and risk reasons in the loss-defining data of the effective loss-defining data and the loss-defining data of the target case, N is the maximum number of fittings concerned, and the column number of each fitting is fixed;

and C2, clustering the matrix of K rows and N columns of the effective loss assessment data and the matrix of K rows and N columns of the loss assessment single data of the target case, and determining a plurality of target loss assessment data associated with the loss assessment single data of the target case in the effective loss assessment data.

According to the embodiment, the effective loss assessment data and the loss assessment single data of the target case are respectively encoded and converted into the matrix of K rows and N columns, the matrix of K rows and N columns of the effective loss assessment data and the matrix of K rows and N columns of the loss assessment single data of the target case are clustered, a plurality of target loss assessment data associated with the loss assessment single data of the target case are determined in the effective loss assessment data, and a plurality of target loss assessment data associated with the loss assessment single data of the target case can be accurately and effectively determined so as to conveniently identify the claim settlement risk of the target case.

The embodiment of the present application provides a possible implementation manner, where step C2 above clusters a matrix of K rows and N columns of effective loss assessment data and a matrix of K rows and N columns of loss assessment single data of a target case, and determines, in the effective loss assessment data, a plurality of target loss assessment data associated with the loss assessment single data of the target case, and may specifically include step C21 below:

and step C21, performing Euclidean distance calculation on the matrix of the K rows and N columns of the effective loss assessment data and the matrix of the K rows and N columns of the loss assessment single data of the target case, and determining a plurality of target loss assessment data associated with the loss assessment single data of the target case in the effective loss assessment data according to a calculation result.

Here, the loss data having the euclidean distance smaller than the preset distance in the calculation result may be determined as a plurality of target loss data associated with the loss order data of the target case.

According to the embodiment, the Euclidean distance calculation is adopted, a plurality of target damage assessment data associated with the damage assessment single data of the target case are determined in the effective damage assessment data according to the calculation result, and the plurality of target damage assessment data associated with the damage assessment single data of the target case can be accurately and effectively determined so as to conveniently identify the claim risk of the target case.

In the embodiment of the application, a possible implementation manner is provided, and the claim risk of the target case may include loss logic, maintenance logic, virtual increase risk, leakage risk of replacement and repair standards and the like. For example, the loss logic may be that the x-fitting does not conform to collision logic; the repair logic may be that the xx fitting does not require painting; the risk of virtual increase may be that the xxx fitting photographs are not damaged; the replacement criteria may be that the xxxx fitting fails the replacement criteria, and so on. The examples are illustrative only and are not intended to limit the present embodiments.

In the embodiment of the present application, a possible implementation manner is provided, where step S103 identifies the claim risk of the target case according to the claim risk information of the multiple target loss assessment data, and may specifically include the following steps D1 and/or D2:

and D1, determining the virtual increase risk exceeding a preset value as the claim settlement risk of the target case according to the claim settlement risk information of the target damage data.

In this step, the preset value may be 2 or 3, etc., and may be set according to actual requirements. For example, 5 target damage data, 3 of which are at risk of virtual increase, i.e. xxx fitting virtual increase, would consider xxx fitting virtual increase as the claim risk of the target case. The examples are illustrative only and are not intended to limit the present embodiments.

And D2, determining target maintenance accessories which exist in the target cases but not exist in the plurality of target loss data according to the claim risk information of the plurality of target loss data, and taking the target maintenance accessories as the claim risk of the target cases.

In this step, if, for example, the xxxx repair parts exist in the target case but do not exist in the plurality of target damage assessment data, the xxxx repair parts are regarded as the claim risk of the target case, specifically, the virtual increase risk.

Having introduced various implementations of each link of the embodiment shown in fig. 1, a method for identifying a risk of claim for vehicle insurance based on clustering according to an embodiment of the present application will be further described below through a specific embodiment.

First, GBDT training is performed.

1) By azimuth mapping of single accessories in the historical impairment data, a matrix of 8 rows and n columns is formed, n is a positive integer, 8 rows of the matrix represent 8 azimuths, and each element of the matrix represents a different accessory.

In this step, a plurality of accessories are involved in the historical impairment data, and azimuth mapping can be performed on single accessories in the historical impairment data, where there are 8 azimuths, such as right front, right back, front left, front right, right front upper and right lower, respectively, and the accessories can be mapped to corresponding azimuths, so that an 8-row n-column matrix is formed.

For example, the straight ahead orientation may include a front bumper, a front bumper under grille, a mid-net logo, and the like; the front left aspect may include a front headlight left, a front lappet left, a front tire left, etc.; the front-rear orientation may include a rear bumper, lift gate molding, trunk lid, etc.

2) Based on the matrix of 8 rows and n columns, the initial weight and the expert weight, the multi-classification output value is converted into probability distribution in the range of 0 and 1 and the sum is 1 through a preset classification algorithm.

In this step, the initial weights may be preset, and the expert weights may be determined based on expert experience, so that the matrix of 8 rows and n columns, the initial weights and the expert weights are combined, and the multi-class output values are converted into probability distributions ranging from 0 to 1 and sum to 1 through a preset classification algorithm. The preset classification algorithm here may be specifically a Softmax function, which is a normalized exponential function.

3) And according to the matrix of 8 rows and n columns, coding by using accessory combinations of sample claim cases, and training a preset classification algorithm to obtain a trained decision tree model.

Then, on the basis of historical damage assessment data (comprising damaged parts, damage degree, maintenance method, accident type, danger occurrence reason and the like), vehicle stress collision points and vehicle basic data (comprising vehicle type structure, part basic data and the like), the historical data are learned through a machine learning clustering idea to generate a rule model corresponding to frequent leakage and virtual increase risk of each part.

1) Inputting the effective loss assessment data into a pre-trained decision tree model, identifying the stressed collision points of the vehicle, and outputting the stressed collision points of the vehicle corresponding to the effective loss assessment data; and inputting the loss-fixed data of the target case into a pre-trained decision tree model, and outputting a stress collision point of the vehicle corresponding to the loss-fixed data of the target case.

2) The method comprises the steps of respectively encoding and converting the effective loss-defining data and the loss-defining data of a target case into a matrix of K rows and N columns, wherein the K rows represent damage parts, damage degree, maintenance methods, accident types and risk reasons in the effective loss-defining data and the loss-defining data of the target case, N is the maximum number of fittings concerned, and the column number of each fitting is fixed.

In this step, all data can be values between 0 and 100, and the scores are demapped according to the mapping rule, for example, the damage degree is nondestructive, scratch, dent, mild damage, moderate damage, severe damage, etc., and 0, 10, 20, 40, 70, 100 are respectively given; the class of data such as the amount is 100 times the history duty, for example, the highest accessory amount that the history appears in is 2000, this time 200, then the score is 10.

3) Clustering the matrix of K rows and N columns of the effective loss assessment data and the matrix of K rows and N columns of the loss assessment single data of the target case, and determining a plurality of target loss assessment data associated with the loss assessment single data of the target case in the effective loss assessment data.

In the step, euclidean distance calculation is carried out on a matrix of K rows and N columns of the effective loss assessment data and a matrix of K rows and N columns of the loss assessment single data of the target case, and a plurality of target loss assessment data associated with the loss assessment single data of the target case are determined in the effective loss assessment data according to a calculation result.

4) The claim risk of the target case may include loss logic, maintenance logic, virtual increase risk, leakage risk of replacement repair criteria, and the like. For example, the loss logic may be that the x-fitting does not conform to collision logic; the repair logic may be that the xx fitting does not require painting; the risk of virtual increase may be that the xxx fitting photographs are not damaged; the replacement criteria may be that the xxxx fitting fails the replacement criteria, and so on. The examples are illustrative only and are not intended to limit the present embodiments.

And determining the virtual increase risk exceeding a preset value as the claim settlement risk of the target case according to the claim settlement risk information of the target damage data.

And determining target maintenance accessories which exist in the target cases but are not in the target loss data according to the claim risk information of the target loss data, and taking the target maintenance accessories as the claim risk of the target cases.

According to the embodiment, the multiple target damage assessment data related to the damage assessment single data of the target cases can be determined in the effective damage assessment data based on the clustering thought, and then the claim settlement risk of the target cases can be identified according to the claim settlement risk information of the multiple target damage assessment data, the claim settlement risk in the damage assessment replacement repair list can be identified, and the leakage virtual increase cases in damage assessment can be effectively detected.

It should be noted that, the sequence number of each step in the above embodiment does not mean the sequence of execution sequence, and the execution sequence of each process should be determined by its function and internal logic, and should not limit the implementation process of the embodiment of the present application in any way. In practical applications, all the possible embodiments may be combined in any combination manner to form possible embodiments of the present application, which are not described in detail herein.

Based on the recognition method of the vehicle insurance claim risk based on the clustering provided by the embodiments, based on the same inventive concept, the embodiment of the application also provides a recognition device of the vehicle insurance claim risk based on the clustering.

Fig. 2 is a block diagram of a device for identifying risk of claim of vehicle insurance based on clustering according to an embodiment of the present application. As shown in fig. 2, the cluster-based identifying device for risk of claim settlement of car insurance may specifically include an obtaining module 210, a determining module 220, and an identifying module 230.

An obtaining module 210, configured to obtain historical damage assessment data in response to an identification request for performing vehicle risk settlement on damage assessment single data of a target case, and screen effective damage assessment data passing damage assessment from the historical damage assessment data;

a determining module 220, configured to determine, from the valid impairment data, a plurality of target impairment data associated with impairment list data of the target case based on a cluster;

the identifying module 230 is configured to identify a claim risk of the target case according to claim risk information of the target damage data.

In one possible implementation manner provided in the embodiment of the present application, the determining module 220 is further configured to:

In one possible implementation manner provided in the embodiment of the present application, as shown in fig. 3, the apparatus shown in fig. 2 above may further include a training module 310, configured to:

In the embodiment of the application, a possible implementation manner is provided, and the claim settlement risk of the target case comprises loss logic, maintenance logic, virtual increase risk and leakage risk of replacement and repair standards.

In one possible implementation manner provided in the embodiment of the present application, the identification module 230 is further configured to:

Based on the same inventive concept, the embodiment of the present application further provides an electronic device, including a processor and a memory, where the memory stores a computer program, and the processor is configured to run the computer program to execute the cluster-based identification method for risk of claim settlement of vehicle insurance according to any one of the above embodiments.

In an exemplary embodiment, there is provided an electronic device, as shown in fig. 4, the electronic device 400 shown in fig. 4 includes: a processor 401 and a memory 403. Processor 401 is connected to memory 403, such as via bus 402. Optionally, the electronic device 400 may also include a transceiver 404. It should be noted that, in practical applications, the transceiver 404 is not limited to one, and the structure of the electronic device 400 is not limited to the embodiment of the present application.

The processor 401 may be a CPU (Central Processing Unit, central processor), general purpose processor, DSP (Digital Signal Processor, data signal processor), ASIC (Application Specific Integrated Circuit ), FPGA (Field Programmable Gate Array, field programmable gate array) or other programmable logic device, transistor logic device, hardware components, or any combination thereof. Which may implement or perform the various exemplary logic blocks, modules and circuits described in connection with this disclosure. Processor 401 may also be a combination that implements computing functionality, such as a combination comprising one or more microprocessors, a combination of a DSP and a microprocessor, or the like.

Bus 402 may include a path to transfer information between the components. Bus 402 may be a PCI (Peripheral Component Interconnect, peripheral component interconnect standard) bus or EISA (Extended Industry Standard Architecture ) bus, among others. Bus 402 may be divided into an address bus, a data bus, a control bus, and the like. For ease of illustration, only one thick line is shown in fig. 4, but not only one bus or one type of bus.

The Memory 403 may be, but is not limited to, a ROM (Read Only Memory) or other type of static storage device that can store static information and instructions, a RAM (Random Access Memory ) or other type of dynamic storage device that can store information and instructions, an EEPROM (Electrically Erasable Programmable Read Only Memory ), a CD-ROM (Compact Disc Read Only Memory, compact disc Read Only Memory) or other optical disk storage, optical disk storage (including compact discs, laser discs, optical discs, digital versatile discs, blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer.

The memory 403 is used for storing computer program code for performing the aspects of the application and is controlled by the processor 401 for execution. The processor 401 is arranged to execute computer program code stored in the memory 403 for implementing what is shown in the foregoing method embodiments.

Among them, electronic devices include, but are not limited to: mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and the like, and stationary terminals such as digital TVs, desktop computers, and the like. The electronic device shown in fig. 4 is only an example and should not be construed as limiting the functionality and scope of use of the embodiments of the application.

Based on the same inventive concept, the embodiment of the present application further provides a storage medium, in which a computer program is stored, where the computer program is configured to perform the cluster-based identification method of the risk claim of the vehicle insurance claim of any of the above embodiments when running.

It will be clear to those skilled in the art that the specific working processes of the above-described systems, devices and modules may refer to the corresponding processes in the foregoing method embodiments, and are not described herein for brevity.

Those of ordinary skill in the art will appreciate that: the aspects of the present application may be embodied in essence or in whole or in part in a software product stored on a storage medium, comprising program instructions for causing an electronic device (e.g., personal computer, server, network device, etc.) to perform all or part of the steps of the methods of the embodiments of the present application when the program instructions are executed. And the aforementioned storage medium includes: a usb disk, a removable hard disk, a read-only memory (ROM), a random-access memory (RAM), a magnetic disk, or an optical disk, etc.

Alternatively, all or part of the steps of implementing the foregoing method embodiments may be implemented by hardware (such as a personal computer, a server, or an electronic device such as a network device) associated with program instructions, where the program instructions may be stored in a computer-readable storage medium, and where the program instructions, when executed by a processor of the electronic device, perform all or part of the steps of the method according to the embodiments of the present application.

The above embodiments are only for illustrating the technical solution of the present application, and not for limiting the same; although the application has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some or all technical features thereof can be replaced by others within the spirit and principle of the present application; such modifications and substitutions do not depart from the scope of the application.

Claims

1. A cluster-based method for identifying risk of a vehicle insurance claim, comprising:

2. The method of claim 1, wherein determining a plurality of target impairment data associated with impairment list data for the target case in the effective impairment data based on clustering comprises:

3. The method of claim 2, wherein the decision tree model is trained by:

4. The method of claim 1, wherein determining a plurality of target impairment data associated with impairment list data for the target case in the effective impairment data based on clustering comprises:

5. The method of claim 4, wherein clustering the matrix of K rows and N columns of the effective impairment data with the matrix of K rows and N columns of impairment bill data for the target case, determining a plurality of target impairment data in the effective impairment data associated with the impairment bill data for the target case, comprises:

6. The method of any one of claims 1 to 5, wherein the claim risk of the target case includes loss logic, repair logic, virtual increase risk, and leakage risk of replacement repair criteria.

7. The method of claim 6, wherein identifying the claim risk of the target case based on the claim risk information for the plurality of target damage data comprises:

8. A cluster-based vehicle insurance claim risk identification device, comprising:

9. An electronic device comprising a processor and a memory, wherein the memory has stored therein a computer program configured to run the computer program to perform the cluster-based method of identifying risk of a car insurance claim of any of claims 1 to 7.

10. A storage medium having a computer program stored therein, wherein the computer program is configured to perform the cluster-based method of identifying risk of a car insurance claim of any of claims 1 to 7 at run-time.