Risk identification method and device, equipment and storage medium
Through clustering and risk factor mining of the loss assessment data of the auto insurance loss assessment plan, the dimensions of leakage risk are identified, which solves the problem of misjudgment of leakage risk identification in the existing technology and improves the accuracy of risk identification.
Patent Information
- Application Number
- CN202411182857.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-26
- Publication Date
- 2025-01-24
AI Technical Summary
The existing technology has the problem of misjudgment of leakage risks in the process of determining auto insurance losses. The rule engine is based on experience and has the risk of overfitting.
By obtaining the loss assessment data and dimensional information of the auto insurance loss assessment plan, the loss assessment data is clustered based on the dimensional information to obtain the same type of loss assessment data, and then the risk factors are mined for the same type of loss assessment data to identify the dimensions with leakage risks. .
It improves the accuracy of risk recognition of the car insurance loss scheme. Through the characteristics of the cluster algorithm, the characteristics of the leakage risk in the multi -dimensional angle are determined, and the misjudgment is reduced.
Smart Images
Figure CN119359449A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of intelligent decision-making technology, and in particular to a risk identification method, device, equipment and storage medium. Background Art
[0002] The risk of leakage in motor insurance damage assessment refers to the situation where, during the damage assessment process, due to personnel, technical, management and other reasons, the insurance company is unable to fully and accurately grasp and verify some of the loss situations in the motor insurance claims, thereby causing deviations in the insurance company's compensation.
[0003] In the prior art, the leakage risk identification method is mainly based on the rule engine of compound events. Through business experience and logical judgment, support rules are established for basic events, compound events are established, and risk leakage nodes are established. For the real-time loss assessment operation link, when the compound event reaches the risk leakage node, it can play an automatic early warning effect. However, the establishment of the rule engine is based on experience, and there is a risk of overfitting, which brings certain misjudgments. Summary of the invention
[0004] The main purpose of this application is to provide a risk identification method, device, equipment and storage medium to solve the problem of certain misjudgment in leakage risk identification in the prior art.
[0005] In a first aspect, the present application provides a risk identification method, comprising:
[0006] Acquire damage assessment data and dimension information corresponding to the motor vehicle insurance damage assessment scheme to be identified, wherein the dimension information includes at least one dimension;
[0007] Clustering the damage assessment data based on the dimensions in the dimensional information to obtain damage assessment data of the same type corresponding to each dimension;
[0008] Risk factor mining is performed on similar damage assessment data corresponding to each dimension to obtain a risk identification result of the motor vehicle insurance damage assessment scheme, wherein the risk identification result includes dimensions where similar damage assessment data have leakage risks.
[0009] In a second aspect, the present application further provides a risk identification device, the risk identification device comprising:
[0010] An acquisition module, used to acquire damage assessment data and dimension information corresponding to the motor vehicle insurance damage assessment scheme to be identified, wherein the dimension information includes at least one dimension;
[0011] A clustering module, used for clustering the damage assessment data based on the dimensions in the dimensional information to obtain similar damage assessment data corresponding to each dimension;
[0012] The identification module is used to perform risk factor mining on similar damage assessment data corresponding to each dimension to obtain the risk identification result of the motor vehicle insurance damage assessment scheme, wherein the risk identification result includes the dimensions where similar damage assessment data has leakage risks.
[0013] In a third aspect, the present application also provides a computer device, comprising a processor, a memory, and a computer program stored in the memory and executable by the processor, wherein when the computer program is executed by the processor, the steps of the risk identification method as described above are implemented.
[0014] In a fourth aspect, the present application further provides a computer-readable storage medium, on which a computer program is stored, wherein when the computer program is executed by a processor, the steps of the risk identification method as described above are implemented.
[0015] The present application provides a risk identification method, device, equipment and storage medium, the risk identification method comprising: obtaining damage assessment data and dimension information corresponding to a motor vehicle insurance damage assessment scheme to be identified, the dimension information comprising at least one dimension; clustering the damage assessment data based on the dimensions in the dimension information to obtain similar damage assessment data corresponding to each dimension; performing risk factor mining on similar damage assessment data corresponding to each dimension to obtain a risk identification result of the motor vehicle insurance damage assessment scheme, the risk identification result comprising the dimension in which similar damage assessment data has leakage risk. The method can learn the data features in the damage assessment data corresponding to each dimension through a clustering algorithm, cluster the damage assessment data corresponding to each dimension, obtain similar damage assessment data corresponding to each dimension, determine the leakage risk of each dimension according to the similar damage assessment data corresponding to each dimension, and thereby determine the leakage risk of the motor vehicle insurance damage assessment scheme. The similar damage assessment data corresponding to multiple dimensions are determined by clustering, and the leakage risk is determined from a multi-dimensional perspective based on the similar damage assessment data corresponding to multiple dimensions, thereby improving the accuracy of identifying the motor vehicle insurance damage assessment scheme. BRIEF DESCRIPTION OF THE DRAWINGS
[0016] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.
[0017] Figure 1 A schematic diagram of the steps of a risk identification method provided in an embodiment of the present application;
[0018] Figure 2 A schematic diagram of the steps of a method for obtaining similar damage assessment data provided in an embodiment of the present application;
[0019] Figure 3 A schematic diagram of a step flow of a method for obtaining a clustering feature vector provided in an embodiment of the present application;
[0020] Figure 4 A schematic diagram of a method for identifying leakage risk provided in an embodiment of the present application;
[0021] Figure 5 A schematic block diagram of a risk identification device provided in an embodiment of the present application;
[0022] Figure 6 A schematic block diagram of the structure of a computer device provided in an embodiment of the present application.
[0023] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION
[0024] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.
[0025] The flowcharts shown in the accompanying drawings are only examples and do not necessarily include all the contents and operations / steps, nor do they have to be executed in the order described. For example, some operations / steps can also be decomposed, combined or partially merged, so the actual execution order may change according to actual conditions. In addition, although the functional modules are divided in the device schematic, in some cases, the module division can be different from that in the device schematic.
[0026] The embodiments of the present application provide a risk identification method, apparatus, device and storage medium. The risk identification method can be applied to a terminal device or a server. The terminal device can be an electronic device such as a mobile phone, a tablet computer, a laptop computer, a desktop computer, a personal digital assistant and a wearable device; the server can be a single server or a server cluster composed of multiple servers. The following explanation is given by taking the application of the risk identification method to a server as an example.
[0027] In conjunction with the accompanying drawings, some embodiments of the present application are described in detail below. In the absence of conflict, the following embodiments and features in the embodiments can be combined with each other.
[0028] Please refer to Figure 1 , Figure 1 A schematic diagram of the steps of a risk identification method provided in an embodiment of the present application. Figure 1As shown, the risk identification method includes steps S101 to S103.
[0029] Step S101: Acquire damage assessment data and dimensional information corresponding to the motor vehicle insurance damage assessment scheme to be identified, where the dimensional information includes at least one dimension.
[0030] Among them, the dimensional information includes at least one of the following: city information, secondary institution information, tertiary institution information, repair shop type, and surveyor information. City information indicates the city information where the car insurance loss assessment plan is located. Different cities have different environmental conditions, so different cities have different car insurance loss assessment plans; secondary institution information indicates the regional department of the company to which the car insurance loss assessment plan belongs. The departments responsible for car insurance loss assessment in different regions of the same company have different car insurance loss assessment plans; tertiary institution information indicates the loss assessment point of the company to which the car insurance loss assessment plan belongs; repair shop type indicates the repair shop that performs repairs in the car insurance loss assessment plan. Different repair shops have different repair plans formulated in the car insurance loss assessment plan; surveyor information indicates the staff who conducts car insurance loss assessment in the car insurance loss assessment plan.
[0031] Among them, damage assessment data is sample data related to the car insurance damage assessment plan. For example, the damage assessment data in a car insurance damage assessment plan is: how much does it cost to repair a certain item of a certain car in a certain city at a certain repair shop, as determined by a certain surveyor. A car insurance damage assessment plan can correspond to multiple dimensions of information, for example, a car insurance damage assessment plan can correspond to city information, repair shop type, and surveyor information.
[0032] Step S102: cluster the damage assessment data based on the dimensions in the dimensional information to obtain similar damage assessment data corresponding to each dimension.
[0033] Exemplarily, the damage assessment data corresponding to the same dimension are clustered. For example, if the dimension is city A, the damage assessment data corresponding to city A are clustered. Clustering will learn and identify the features in the damage assessment data, and classify the damage assessment data that are similar to the damage assessment data corresponding to city A into the same category, thereby obtaining the same type of damage assessment data corresponding to city A.
[0034] Step S103: Perform risk factor mining on similar damage assessment data corresponding to each dimension to obtain a risk identification result of the motor vehicle insurance damage assessment solution, wherein the risk identification result includes dimensions where similar damage assessment data have leakage risks.
[0035] For example, by setting corresponding risk screening conditions, the same type of damage assessment data corresponding to each dimension is screened to determine whether there is risk leakage in the same type of damage assessment data corresponding to each dimension. By determining the risk leakage of the same type of damage assessment data, it can be determined whether there is risk leakage in the dimension corresponding to the same type of damage assessment data. For example, if there are multiple risk leakages in the same type of damage assessment data of city A, then there is risk leakage in city A. By determining whether there is risk leakage in different dimensions, a more accurate risk identification result of the motor vehicle insurance damage assessment scheme can be obtained.
[0036] In the above embodiment, the damage assessment data corresponding to each dimension is obtained, and then the damage assessment data of each dimension is clustered to obtain the same type of damage assessment data corresponding to each dimension. The same type of damage assessment data corresponding to each dimension is mined for risk factors, so as to determine the risk leakage of the corresponding auto insurance damage assessment scheme. In this way, the features in the damage assessment data can be clustered through cluster learning, and further judgment can be made on whether there is risk leakage in the damage assessment data, and risk factors can be mined from multiple aspects from a multi-dimensional perspective to improve the accuracy of risk leakage identification.
[0037] Please refer to Figure 2 , Figure 2 A schematic diagram of the steps of a method for obtaining similar damage assessment data provided by an embodiment of the present application. Figure 2 As shown, the method for obtaining similar damage assessment data includes steps S201 to S204.
[0038] Step S201: extract features from damage assessment data to obtain feature data corresponding to the damage assessment data.
[0039] Exemplarily, the damage assessment data is disassembled and cleaned and filtered to extract key features and obtain feature data corresponding to the damage assessment data. For example, the damage assessment data is "how much does it cost to repair a certain item of a certain car in a certain repair shop", and after feature extraction, the feature data obtained is "a certain car", "a certain repair shop", "a certain item", "how much amount". Among them, the feature data may include but is not limited to the implementation plan, the damage assessment amount, the number of spare parts items, the number of working hours items, the amount of loss reduction, internal repair items, external repair items, etc.
[0040] Step S202: construct multiple feature vectors corresponding to each dimension in the dimensional information based on the feature data.
[0041] Exemplarily, feature data belonging to the same dimension are combined into feature vectors to construct multiple feature vectors corresponding to the dimension. For example, the dimension includes: city information, secondary organization, tertiary organization, "repair shop information, surveyor information, feature data includes: damage assessment plan, damage assessment amount, number of spare parts items, number of working hours items, loss reduction amount, number of internal repair items, number of external repair items, then the feature vector corresponding to the dimension can be expressed as:
[0042]
[0043] i∈{'city','secondary institution','tertiary institution','repair shop','damage assessor'},
[0044] in is the feature vector corresponding to the dimension, i represents the specific dimension, I case For the damage assessment scheme, I amount is the estimated loss amount, N peijian is the number of accessory items, N gongshi is the number of working-hour items, I jiansun is the impairment amount, N inner_fix is the number of internal repair items, N out_fix The number of external repair projects.
[0045] Step S203: performing clustering operation on multiple feature vectors corresponding to each dimension to obtain a cluster feature vector corresponding to each dimension.
[0046] Exemplarily, multiple feature vectors corresponding to each dimension are input into a clustering algorithm for clustering operation, and the input feature vectors are divided into similar feature vectors according to the similarity of the feature vectors through the clustering algorithm, and the cluster feature vector corresponding to each dimension is calculated and obtained according to the similar feature vectors. The cluster feature vector corresponding to each dimension is the cluster center of the similar feature vector corresponding to each dimension. The clustering algorithm may include multiple ones, such as K-means algorithm, bi-kmeans algorithm, etc.
[0047] Step S204: Determine the same type of damage assessment data corresponding to each dimension based on the cluster feature vector corresponding to each dimension.
[0048] Exemplarily, based on the clustering feature vector corresponding to each dimension, the similar feature vector corresponding to each dimension is determined, and the similar feature vectors correspond to the similar damage assessment data, so as to determine the similar damage assessment data corresponding to each dimension.
[0049] In the above embodiment, feature data is obtained by extracting features from damage assessment data, constructing features into feature vectors, clustering the feature vectors, obtaining cluster feature vectors corresponding to each dimension, and determining similar damage assessment data corresponding to each dimension based on the cluster feature vectors corresponding to each dimension. Clustering feature vectors using a clustering algorithm helps identify potential features in feature vectors, more accurately cluster feature vectors, and thus more accurately determine similar damage assessment data corresponding to each dimension.
[0050] Please refer to Figure 3 , Figure 3 A schematic diagram of the steps of obtaining a cluster feature vector provided in an embodiment of the present application. Figure 3 As shown, the method for obtaining cluster feature vectors includes steps S301 to S303.
[0051] Step S301, determine each dimension as the first dimension in turn.
[0052] Step S302: Select a feature vector from the multiple feature vectors corresponding to the first dimension as a cluster center.
[0053] The cluster center is used to determine whether the feature vector belongs to the same type of feature vector. The cluster center represents the center point of all feature vectors in the same type of feature vector. The selection of the cluster center can be determined according to the specific situation. It should be noted that the selection of the initial cluster center does not affect the final clustering result, and it can be randomly selected.
[0054] Step S303: assign each feature vector in the multiple feature vectors corresponding to the first dimension to a cluster center in turn and update the cluster center until the obtained cluster center no longer changes, thereby obtaining a cluster feature vector corresponding to the first dimension.
[0055] Exemplarily, the distance between each feature vector and the cluster center in the multiple feature vectors corresponding to the first dimension is calculated in turn, and the distance is assigned to the cluster center closest to it. Assigning to the cluster center closest to it means assigning the feature vector to the same type of feature vector corresponding to the cluster center.
[0056] Among them, each feature vector is assigned to the cluster center and can be expressed as follows:
[0057]
[0058] Among them, I K represents the cluster center, K represents the Kth cluster center, I n Represents each eigenvector in the multiple eigenvectors corresponding to the first dimension, n represents the nth eigenvector, i represents the dimension, Represents the set of similar feature vectors corresponding to the i-th dimension. The formula indicates that the distance between the feature vector and the cluster center is calculated, the nearest cluster center is found, and the feature vector is classified into the set of similar feature vectors, that is, the feature vector is assigned to the cluster center.
[0059] Among them, the formula for updating the cluster center can be expressed as:
[0060]
[0061] in, represents the cluster center corresponding to the updated dimension i, represents the same type of feature vector corresponding to dimension i, Represents the nth eigenvector corresponding to dimension i.
[0062] In the above embodiment, by selecting a feature vector as a cluster center, and assigning multiple feature vectors corresponding to each dimension to the cluster center, the cluster center is updated and the cluster feature vector is obtained. Obtaining the cluster feature vector by calculating multiple feature vectors of each dimension can enable the clustering algorithm to learn the feature values of multiple feature vectors of each dimension to obtain a more accurate cluster feature vector.
[0063] Please refer to Figure 4 , Figure 4 A schematic flow chart of the steps of a method for identifying leakage risk provided in an embodiment of the present application. Figure 4 As shown, the method for identifying leakage risk includes steps S401 to S403.
[0064] Step S401: determine each dimension as the second dimension in sequence.
[0065] Step S402: Calculate the standard damage value of the damage value in the same type of damage assessment data corresponding to the second dimension.
[0066] It should be noted that the damage value in the damage assessment data can be used as a standard to determine whether there is a risk of leakage in the damage assessment data. The standard damage value of the damage value in the same type of damage assessment represents the normal level of the same type of damage assessment. By comparing the damage value in the damage assessment data with the same type of damage assessment data, it can be determined whether the damage value in the damage assessment data is normal.
[0067] Exemplarily, the average value of the damage assessment value in the same type of damage assessment data corresponding to the second dimension is calculated as the standard damage assessment value.
[0068] In one embodiment, the standard damage value of the damage value in the same type of damage assessment data corresponding to the second dimension is calculated, including: calculating the average value and standard deviation of the damage value in the same type of damage assessment data corresponding to the second dimension; and performing weighted summation of the average value and the standard deviation to obtain the standard damage value.
[0069] For example, the average value of the damage assessment value in the same type of damage assessment data is μ amount and the standard deviation is σ amount The standard loss value s amount =μ amount +3*σ amount It should be noted that the standard damage value calculated by weighted summation can better reflect the degree of dispersion of damage values in similar damage data and improve the accuracy of subsequent judgments.
[0070] Step S403: If the damage assessment value in the same type of damage assessment data corresponding to the second dimension is greater than the standard damage assessment value, it is determined that the same type of damage assessment data corresponding to the second dimension has a leakage risk.
[0071] For example, when the damage assessment value in the same type of damage assessment data corresponding to the second dimension is greater than the standard damage assessment value, it indicates that the damage assessment value in the same type of damage assessment data does not meet the standard level and there is a risk of leakage. The formula for determining whether the damage assessment value in the same type of damage assessment data is greater than the standard damage assessment value can be expressed as:
[0072]
[0073] Where I represents the damage value, i represents the dimension information, and n represents the nth damage data in the same type of damage data. When the damage value I in the nth damage data of dimension i is greater than the standard damage value s amount If , it is determined that there is a risk, otherwise there is no risk.
[0074] In one embodiment, if the number of similar damage assessment data corresponding to the second dimension that have leakage risks exceeds a preset number, it is determined that the second dimension has leakage risks.
[0075] For example, if the number of similar damage assessment data corresponding to the second dimension with leakage risk exceeds a preset number, it indicates that the impact of the leakage risk of the same type of damage assessment data corresponding to the second dimension exceeds a preset range, and therefore it can be determined that there is a leakage risk in the second dimension.
[0076] In the above embodiment, by obtaining the standard damage assessment value, the standard damage assessment value is compared with the damage assessment value of similar damage assessment data corresponding to each dimension to determine whether there is risk leakage in the same damage assessment data. The standard damage assessment value can well measure the general level of damage assessment value in the same damage assessment data, thereby determining whether the damage assessment value in the damage assessment data fluctuates abnormally by comparing the standard damage assessment value, thereby accurately determining whether there is risk leakage in the same damage assessment data.
[0077] Please refer to Figure 5 , Figure 5 A schematic block diagram of a risk identification device provided in an embodiment of the present application.
[0078] like Figure 5 As shown, the risk identification device 1000 includes: an acquisition module 1001 , a clustering module 1002 , and an identification module 1003 .
[0079] The acquisition module 1001 is used to acquire damage assessment data and dimension information corresponding to the motor vehicle insurance damage assessment scheme to be identified, wherein the dimension information includes at least one dimension;
[0080] A clustering module 1002 is used to cluster the damage assessment data based on the dimensions in the dimensional information to obtain damage assessment data of the same type corresponding to each dimension;
[0081] The identification module 1003 is used to perform risk factor mining on the same type of damage assessment data corresponding to each dimension to obtain the risk identification result of the motor vehicle insurance damage assessment scheme, and the risk identification result includes the dimension where the same type of damage assessment data has leakage risk.
[0082] It should be noted that technical personnel in the relevant field can clearly understand that for the convenience and conciseness of description, the specific working process of the above-described device and each module and unit can refer to the corresponding process in the aforementioned risk identification method embodiment, and will not be repeated here.
[0083] The apparatus provided in the above embodiment may be implemented in the form of a computer program. The computer program may be Figure 6 Runs on the computer device shown.
[0084] See also Figure 6 , Figure 6 A schematic block diagram of the structure of a computer device provided in an embodiment of the present application. The computer device may be a server or a terminal device.
[0085] like Figure 6 As shown, the computer device includes a processor, a memory and a network interface connected via a system bus, wherein the memory may include a storage medium and an internal memory, and the storage medium may be non-volatile or volatile.
[0086] The storage medium can store an operating system and a computer program. The computer program includes program instructions, and when the program instructions are executed, the processor can execute any risk identification method.
[0087] The processor is used to provide computing and control capabilities and support the operation of the entire computer equipment.
[0088] The internal memory provides an environment for the operation of the computer program in the storage medium. When the computer program is executed by the processor, the processor can execute any risk identification method.
[0089] The network interface is used for network communication, such as sending assigned tasks, etc. Those skilled in the art will understand that Figure 6 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.
[0090] It should be understood that the processor may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.
[0091] In one embodiment, the processor is used to run a computer program stored in the memory to implement the following steps:
[0092] Acquire damage assessment data and dimensional information corresponding to the motor vehicle insurance damage assessment scheme to be identified, wherein the dimensional information includes at least one dimension; cluster the damage assessment data based on the dimensions in the dimensional information to obtain similar damage assessment data corresponding to each dimension; perform risk factor mining on similar damage assessment data corresponding to each dimension to obtain a risk identification result of the motor vehicle insurance damage assessment scheme, wherein the risk identification result includes dimensions where similar damage assessment data have leakage risks.
[0093] In one embodiment, when the processor implements clustering the damage assessment data based on the dimensions in the dimensional information to obtain similar damage assessment data corresponding to each dimension, the processor includes:
[0094] Perform feature extraction on the damage assessment data to obtain feature data corresponding to the damage assessment data; construct multiple feature vectors corresponding to each dimension in the dimensional information based on the feature data; perform clustering operation on the multiple feature vectors corresponding to each dimension to obtain a cluster feature vector corresponding to each dimension; determine the same type of damage assessment data corresponding to each dimension based on the cluster feature vector corresponding to each dimension.
[0095] In one embodiment, when the processor implements the clustering operation on the plurality of feature vectors corresponding to each dimension to obtain the cluster feature vector corresponding to each dimension, the processor includes:
[0096] Determine each of the dimensions as the first dimension in turn; select a feature vector from the multiple feature vectors corresponding to the first dimension as the cluster center; assign each of the multiple feature vectors corresponding to the first dimension to the cluster center in turn and update the cluster center until the obtained cluster center no longer changes, thereby obtaining a cluster feature vector corresponding to the first dimension.
[0097] In one embodiment, when the processor implements the same type of damage assessment data, including the damage assessment value, the risk factor mining of the same type of damage assessment data corresponding to each dimension to obtain the risk identification result of the motor vehicle insurance damage assessment scheme includes:
[0098] Determine each of the dimensions as the second dimension in turn; calculate the standard damage value of the damage value in the same type of damage assessment data corresponding to the second dimension; if the damage value in the same type of damage assessment data corresponding to the second dimension is greater than the standard damage value, determine that the same type of damage assessment data corresponding to the second dimension has a leakage risk.
[0099] In one embodiment, when the processor implements the method, the processor further includes:
[0100] If the number of similar damage assessment data corresponding to the second dimension that have leakage risks exceeds a preset number, it is determined that the second dimension has leakage risks.
[0101] In one embodiment, when the processor calculates the standard damage assessment value of the damage assessment value in the same type of damage assessment data corresponding to the second dimension, the processor includes:
[0102] Calculate the average value and standard deviation of the damage assessment value in the same type of damage assessment data corresponding to the second dimension; perform weighted summation on the average value and the standard deviation to obtain the standard damage assessment value.
[0103] It should be noted that those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the computer device described above can refer to the corresponding process in the aforementioned risk identification method embodiment, and will not be repeated here.
[0104] The present application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, etc. The present application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application can also be practiced in distributed computing environments, in which tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.
[0105] An embodiment of the present application also provides a computer-readable storage medium, on which a computer program is stored. The computer program includes program instructions. The method implemented when the program instructions are executed can refer to the various embodiments of the risk identification method of the present application.
[0106] The computer-readable storage medium may be an internal storage unit of the computer device described in the foregoing embodiment, such as a hard disk or memory of the computer device. The computer-readable storage medium may also be an external storage device of the computer device, such as a plug-in hard disk, a smart memory card (SmartMedia Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc., equipped on the computer device.
[0107] It should be understood that the terms used in this application specification are only for the purpose of describing specific embodiments and are not intended to limit the application. As used in this application specification and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.
[0108] It should also be understood that the term "and / or" used in the specification of this application and the appended claims refers to any combination of one or more of the associated listed items and all possible combinations, including these combinations. It should be noted that, in this article, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or system. In the absence of further restrictions, an element defined by the sentence "including a..." does not exclude the presence of other identical elements in the process, method, article or system including the element.
[0109] The serial numbers of the embodiments of the present application are for description only and do not represent the advantages and disadvantages of the embodiments. The above description is only a specific implementation mode of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in the present application, and these modifications or replacements should be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.
Claims
1. A risk identification method, characterized in that: include: Acquire damage assessment data and dimension information corresponding to the motor vehicle insurance damage assessment scheme to be identified, wherein the dimension information includes at least one dimension; Clustering the damage assessment data based on the dimensions in the dimensional information to obtain damage assessment data of the same type corresponding to each dimension; Risk factor mining is performed on similar damage assessment data corresponding to each dimension to obtain a risk identification result of the motor vehicle insurance damage assessment scheme, wherein the risk identification result includes dimensions where similar damage assessment data have leakage risks.
2. The risk identification method according to claim 1, characterized in that: The clustering of the damage assessment data based on the dimensions in the dimensional information to obtain similar damage assessment data corresponding to each dimension includes: Extracting features from the damage assessment data to obtain feature data corresponding to the damage assessment data; Based on the feature data, construct multiple feature vectors corresponding to each dimension in the dimensional information; Performing a clustering operation on the plurality of feature vectors corresponding to each dimension to obtain a cluster feature vector corresponding to each dimension; According to the clustering feature vector corresponding to each dimension, the same type of damage assessment data corresponding to each dimension is determined.
3. The risk identification method according to claim 2, characterized in that: The performing clustering operation on the plurality of feature vectors corresponding to each dimension to obtain a cluster feature vector corresponding to each dimension includes: sequentially determining each of the dimensions as a first dimension; Selecting a feature vector from the plurality of feature vectors corresponding to the first dimension as a cluster center; Each of the plurality of feature vectors corresponding to the first dimension is sequentially assigned to the cluster center and the cluster center is updated until the obtained cluster center no longer changes, thereby obtaining the cluster feature vector corresponding to the first dimension.
4. The risk identification method according to claim 1, characterized in that: The same type of damage assessment data includes the damage assessment value, and the risk factor mining is performed on the same type of damage assessment data corresponding to each dimension to obtain the risk identification result of the motor vehicle insurance damage assessment scheme, including: sequentially determining each of the dimensions as a second dimension; Calculate the standard damage value of the damage value in the same type of damage assessment data corresponding to the second dimension; If the damage assessment value in the same type of damage assessment data corresponding to the second dimension is greater than the standard damage assessment value, it is determined that the same type of damage assessment data corresponding to the second dimension has a leakage risk.
5. The risk identification method according to claim 4, characterized in that: The method further comprises: If the number of similar damage assessment data corresponding to the second dimension that have leakage risks exceeds a preset number, it is determined that the second dimension has leakage risks.
6. The risk identification method according to claim 4, characterized in that: The calculation of the standard damage value of the damage value of the same type of damage assessment data corresponding to the second dimension includes: Calculate the average value and standard deviation of the damage assessment value in the same type of damage assessment data corresponding to the second dimension; The average value and the standard deviation are weightedly summed to obtain the standard damage assessment value.
7. The risk identification method according to any one of claims 1 to 6, characterized in that: The dimensional information includes at least one of the following: city information, secondary institution information, tertiary institution information, repair shop type, and surveyor information.
8. A risk identification device, characterized in that: The risk identification device comprises: An acquisition module, used to acquire damage assessment data and dimension information corresponding to the motor vehicle insurance damage assessment scheme to be identified, wherein the dimension information includes at least one dimension; A clustering module, used for clustering the damage assessment data based on the dimensions in the dimensional information to obtain similar damage assessment data corresponding to each dimension; The identification module is used to perform risk factor mining on similar damage assessment data corresponding to each dimension to obtain the risk identification result of the motor vehicle insurance damage assessment scheme, wherein the risk identification result includes the dimensions where similar damage assessment data has leakage risks.
9. A computer device, characterized in that: The computer device includes a processor, a memory, and a computer program stored in the memory and executable by the processor, wherein when the computer program is executed by the processor, the steps of the risk identification method according to any one of claims 1 to 7 are implemented.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, wherein when the computer program is executed by a processor, the steps of the risk identification method according to any one of claims 1 to 7 are implemented.