Anomaly data analysis

Abstract

Disclosed in the embodiments of the description are an anomaly data analysis method and apparatus, and a device, a medium and a product. The method comprises: acquiring target underwriting link data corresponding to a target abnormal underwriting result, wherein the target underwriting link data comprises target underwriting data of each underwriting link during underwriting performed on the basis of a target insurance request and according to a target underwriting strategy; and performing anomaly analysis on the target underwriting link data, so as to obtain a target anomaly analysis result corresponding to the target abnormal underwriting result.

Description

Abnormal data analysis Technical Field

[0001] This specification relates to the field of computer technology, and in particular to an abnormal data analysis method, device, equipment, medium, and program product. Background Art

[0002] Underwriting plays a crucial role in insurance. Comprehensive data is used to verify and review users before they purchase insurance, minimizing the risk of intercepting high-risk users. This includes examining whether the user has specific medical conditions that would violate the insurance agreement, whether the user has a history of insurance issues, or whether they have duplicate insurance policies. This helps reduce underwriting risk for insurance companies. However, issues with the quality of underwriting data can lead to underwriting bias, which can easily lead to false interception. Summary of the Invention

[0003] The embodiments of this specification provide an abnormal data analysis method, apparatus, device, medium, and program product that can accurately verify the accuracy of underwriting data across all underwriting links in the event of abnormal underwriting, quickly and automatically identify and analyze the root cause of the abnormal underwriting errors, namely, the target abnormal analysis results, thereby avoiding the problem of false underwriting interception, improving underwriting accuracy, and enhancing the user's insurance experience. The above technical solution is as follows.

[0004] In the first aspect, an embodiment of the present specification provides an abnormal data analysis method, which includes: obtaining target underwriting link data corresponding to a target abnormal underwriting result; the target underwriting link data includes target underwriting data of each underwriting link when underwriting is performed according to a target underwriting strategy based on a target insurance request; performing an abnormality analysis on the target underwriting link data to obtain a target abnormality analysis result corresponding to the target abnormal underwriting result.

[0005] In one possible implementation, before obtaining the target underwriting link data corresponding to the target abnormal underwriting result, the method further includes: monitoring the underwriting results corresponding to each insurance request, and counting the underwriting abnormality information of the underwriting abnormality results; the underwriting abnormality results are used to characterize the underwriting results for classifying and adjusting the underwriting risk or restricting the underwriting; when the underwriting abnormality information meets the preset abnormality condition, the underwriting abnormality result corresponding to the underwriting abnormality information is determined as the target abnormal underwriting result.

[0006] In one possible implementation, the above-mentioned underwriting abnormality information includes the underwriting abnormality factors corresponding to each underwriting abnormality result, and the number of occurrences and / or incidence rates of the underwriting abnormality results caused by the same above-mentioned underwriting abnormality factors; the above-mentioned preset abnormal conditions include the above-mentioned number of occurrences and / or incidence rates reaching the target value.

[0007] In one possible implementation, the above-mentioned abnormality analysis is performed on the above-mentioned target underwriting link data to obtain a target abnormality analysis result corresponding to the above-mentioned target abnormal underwriting result, including: sending a target abnormality analysis instruction to the business end based on the above-mentioned target underwriting link data, so that the above-mentioned business end responds to the above-mentioned target abnormality analysis instruction and displays the above-mentioned target underwriting link data; receiving the target abnormality analysis result returned by the above-mentioned business end; the above-mentioned target abnormality analysis result is obtained by the business staff of the above-mentioned business end performing abnormality analysis on the above-mentioned target underwriting link data.

[0008] In a possible implementation, before obtaining the target underwriting link data corresponding to the target abnormal underwriting result, the method further includes: obtaining the target insurance request of the target user; in response to the target insurance request, obtaining the corresponding data to be underwritten; the data to be underwritten includes the target user data of the target user, the target source corresponding to the target user data, and the target product data of the product to be insured by the target user; inputting the data to be underwritten into the risk control model, outputting the target underwriting result of the target user based on the target underwriting strategy, and recording the target underwriting data of each underwriting link in the risk control model to obtain the target underwriting link data corresponding to the target underwriting result.

[0009] In one possible implementation, the above-mentioned acquisition of target underwriting link data corresponding to the target abnormal underwriting result includes: when the above-mentioned target underwriting result is an underwriting abnormality, and / or when the target complaint request or target query request of the above-mentioned target user is obtained, the above-mentioned target underwriting result is determined as a target abnormal underwriting result, and the target underwriting link data corresponding to the above-mentioned target abnormal underwriting result is queried.

[0010] In one possible implementation, the target abnormality analysis result includes abnormal underwriting data corresponding to the abnormal underwriting link during underwriting; the abnormal underwriting link is used to characterize the underwriting link whose underwriting accuracy is less than a preset value, or the underwriting link that is analyzed and marked as abnormal; after the above-mentioned abnormality analysis is performed on the target underwriting link data and the target abnormality analysis result corresponding to the target abnormal underwriting result is obtained, the method further includes: updating the target underwriting result of the target user and / or the risk control model based on the abnormal underwriting data.

[0011] In one possible implementation, the above-mentioned acquisition of target underwriting link data corresponding to the target abnormal underwriting result includes: querying the target underwriting link data corresponding to the above-mentioned target abnormal underwriting result from the historical underwriting log based on the target underwriting time of the target abnormal underwriting result and the target identity identifier of the target user corresponding to the above-mentioned target abnormal underwriting result; the above-mentioned historical underwriting log is used to record the underwriting link data involved in underwriting based on the user's insurance request.

[0012] In the second aspect, an embodiment of the present specification provides an abnormal data analysis device, which includes: a first acquisition module, used to obtain target underwriting link data corresponding to the target abnormal underwriting result; the above-mentioned target underwriting link data includes target underwriting data of each underwriting link when underwriting is performed according to the target underwriting policy based on the target insurance request; an abnormality analysis module, used to perform abnormality analysis on the above-mentioned target underwriting link data to obtain a target abnormality analysis result corresponding to the above-mentioned target abnormal underwriting result.

[0013] In one possible implementation, the abnormal data analysis device further includes: an underwriting monitoring module for monitoring the underwriting results corresponding to each insurance request, and collecting statistics on the underwriting abnormality information of the abnormal underwriting results; the abnormal underwriting results are used to characterize the underwriting results for classifying and adjusting the underwriting risk or restricting the underwriting; and a first determination module for determining the abnormal underwriting result corresponding to the abnormal underwriting information as the target abnormal underwriting result when the abnormal underwriting information meets a preset abnormal condition.

[0014] In one possible implementation, the above-mentioned underwriting abnormality information includes the underwriting abnormality factors corresponding to each underwriting abnormality result, and the number of occurrences and / or incidence rates of the underwriting abnormality results caused by the same above-mentioned underwriting abnormality factors; the above-mentioned preset abnormal conditions include the above-mentioned number of occurrences and / or incidence rates reaching the target value.

[0015] In one possible implementation, the above-mentioned exception analysis module includes: a sending unit, used to send a target exception analysis instruction to the business end based on the above-mentioned target underwriting link data, so that the above-mentioned business end responds to the above-mentioned target exception analysis instruction and displays the above-mentioned target underwriting link data; a receiving unit, used to receive the target exception analysis result returned by the above-mentioned business end; the above-mentioned target exception analysis result is obtained by the business staff of the above-mentioned business end by performing an exception analysis on the above-mentioned target underwriting link data.

[0016] In one possible implementation, the abnormal data analysis device further includes: a second acquisition module for acquiring the target insurance request of the target user; a third acquisition module for acquiring the corresponding data to be underwritten in response to the target insurance request; the data to be underwritten includes the target user data of the target user, the target source corresponding to the target user data, and the target product data of the product to be insured by the target user; a risk control module for inputting the data to be underwritten into the risk control model, outputting the target underwriting result of the target user based on the target underwriting strategy, and recording the target underwriting data of each underwriting link in the risk control model to obtain the target underwriting link data corresponding to the target underwriting result.

[0017] In one possible implementation, the first acquisition module is specifically used to: when the target underwriting result is an underwriting abnormality, and / or when the target complaint request or target query request of the target user is obtained, determine the target underwriting result as a target abnormal underwriting result, and query the target underwriting link data corresponding to the target abnormal underwriting result.

[0018] In one possible implementation, the above-mentioned target abnormality analysis result includes abnormal underwriting data corresponding to the abnormal underwriting link during underwriting; the above-mentioned abnormal underwriting link is used to characterize the underwriting link whose underwriting accuracy is less than a preset value, or the underwriting link that is analyzed and marked as abnormal; the above-mentioned abnormal data analysis device also includes: an update module, which is used to update the target underwriting result of the above-mentioned target user and / or the above-mentioned risk control model based on the above-mentioned abnormal underwriting data.

[0019] In one possible implementation, the above-mentioned first acquisition module is specifically used to: query the target underwriting link data corresponding to the above-mentioned target abnormal underwriting result from the historical underwriting log based on the target underwriting time of the target abnormal underwriting result and the target identity identifier of the target user corresponding to the above-mentioned target abnormal underwriting result; the above-mentioned historical underwriting log is used to record the underwriting link data involved in underwriting based on the user's insurance request.

[0020] In a third aspect, an embodiment of this specification provides an electronic device, comprising: a processor and a memory; the processor is connected to the memory; the memory is used to store executable program code; the processor runs a program corresponding to the executable program code by reading the executable program code stored in the memory, so as to execute the method provided by the first aspect of the embodiment of this specification or any possible implementation of the first aspect.

[0021] In a fourth aspect, an embodiment of this specification provides a computer storage medium, which stores multiple instructions, and the instructions are suitable for being loaded by a processor and executing the method provided by the first aspect of the embodiment of this specification or any possible implementation of the first aspect.

[0022] In a fifth aspect, an embodiment of this specification provides a computer program product comprising instructions, which, when the above-mentioned computer program product runs on a computer or a processor, enables the above-mentioned computer or the above-mentioned processor to execute the method provided by the first aspect of the embodiment of this specification or any possible implementation of the first aspect.

[0023] In an embodiment of the present specification, target underwriting link data corresponding to a target abnormal underwriting result is obtained; the above-mentioned target underwriting link data includes target underwriting data of each underwriting link when underwriting is performed in accordance with a target underwriting policy based on a target insurance request; an abnormality analysis is performed on the above-mentioned target underwriting link data to obtain a target abnormality analysis result corresponding to the above-mentioned target abnormal underwriting result, thereby accurately checking the accuracy of the underwriting data of each underwriting link under abnormal underwriting, quickly and automatically checking and analyzing the root cause of the error leading to the abnormal underwriting, namely the target abnormality analysis result, avoiding the problem of misinterpretation of underwriting, and improving the underwriting accuracy and user insurance experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the technical solutions in the embodiments of this specification, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of this specification. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0025] FIG1 is a schematic diagram of the architecture of an abnormal data analysis system provided by an exemplary embodiment of this specification.

[0026] FIG2 is a flow chart of an abnormal data analysis method provided by an exemplary embodiment of this specification.

[0027] FIG3 is a flow chart of another abnormal data analysis method provided by an exemplary embodiment of this specification.

[0028] FIG4 is a schematic structural diagram of an abnormal data analysis device provided by an exemplary embodiment of this specification.

[0029] FIG5 is a schematic structural diagram of an electronic device provided by an exemplary embodiment of this specification. DETAILED DESCRIPTION

[0030] The technical solutions in the embodiments of this specification will be described clearly and completely below in conjunction with the drawings in the embodiments of this specification.

[0031] In this specification, claims, and the accompanying drawings, the terms "first," "second," "third," and so on are used to distinguish between different items, not to describe a particular order. Furthermore, the terms "including," "having," and any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or apparatus comprising a series of steps or elements is not limited to the listed steps or elements but may optionally include steps or elements not listed, or may optionally include other steps or elements inherent to the process, method, product, or apparatus.

[0032] It should be noted that the information (including but not limited to user device information, user personal information, etc.), data (including but not limited to data used for analysis, stored data, displayed data, etc.), and signals involved in the embodiments of this specification are all authorized by the user or fully authorized by all parties, and the collection, use, and processing of relevant data must comply with the relevant laws, regulations, and standards of the relevant countries and regions. For example, the target underwriting data and pending underwriting data involved in this specification are all obtained with full authorization.

[0033] First, the nouns involved in the embodiments of the present application are introduced.

[0034] Underwriting: refers to the process in which the insurer evaluates and classifies insurable risks based on a comprehensive understanding and verification of the insured information, and then decides whether to provide insurance and under what conditions.

[0035] After introducing the terms involved in the embodiments of the present application, the abnormal data analysis system involved in the embodiments of the present application is described below.

[0036] Next, please refer to Figure 1, which is a schematic diagram of the architecture of an abnormal data analysis system provided in an exemplary embodiment of this specification. As shown in Figure 1, the abnormal data analysis system includes: an underwriting terminal 110, a server 120 and a user terminal 130.

[0037] The underwriting end 110 may include one or more terminals corresponding to underwriting personnel or one or more business terminals corresponding to underwriting business personnel. An underwriting version of the software may be installed in the underwriting end 110 to enable underwriting personnel to list insurance products online and configure the underwriting policy of the insurance product. The underwriting end 110 may also obtain target underwriting link data corresponding to the target abnormal underwriting result. The target underwriting link data includes target underwriting data of each underwriting link when underwriting is performed according to the target underwriting policy based on the target insurance request, and performs abnormal analysis on the target underwriting link data to obtain target abnormal analysis results corresponding to the target abnormal underwriting result. Any underwriting end 110 may be, but is not limited to, a mobile phone, tablet computer, laptop computer or other device installed with the underwriting version of the software.

[0038] Optionally, the underwriting end 110 can establish a data relationship with the network and establish a data connection relationship with the server 120 through the network, such as sending target product data of the target user's product to be insured, target underwriting link data corresponding to the target abnormal underwriting result, or receiving target abnormality analysis instructions sent by the server 120.

[0039] Server 120 can be a server capable of providing various abnormal data analyses and can receive data such as target product information of a target product from the underwriting client 110 corresponding to the underwriter via the network. Server 120 can also receive target underwriting link data corresponding to a target abnormal underwriting result from the underwriting client 110 and perform abnormality analysis on the target underwriting link data to obtain a target abnormality analysis result corresponding to the target abnormal underwriting result. Server 120 can be, but is not limited to, a hardware server, a virtual server, a cloud server, etc.

[0040] It can be understood that the abnormal data analysis method provided in the embodiments of this specification is not limited to being executed by the above-mentioned server 120, but can also be executed by any underwriting terminal 110. The embodiments of this specification do not make specific limitations on this. The following embodiments are all explained using the example of the server 120 executing the above-mentioned abnormal data analysis.

[0041] User terminals 130 may include one or more user terminals of insured users. User-version software may be installed on user terminals 130 to enable users to view or purchase online insurance products, among other functions. User terminals 130 may establish a data relationship with the network and, through this network, establish a data connection with server 120 or underwriting terminal 110. For example, if their underwriting result indicates an underwriting anomaly, they may send a corresponding complaint request or query request and receive target anomaly analysis results returned by server 120 or underwriting terminal 110. Any user terminal 130 may be, but is not limited to, a mobile phone, tablet computer, laptop computer, or other device with the user-version software installed.

[0042] The network can be a medium that provides a communication link between the server 120 and any of the underwriting terminals 110, and between the server 120 and any of the user terminals 130, or can be the Internet including network devices and transmission media, but is not limited thereto. The transmission media can be a wired link, such as, but not limited to, coaxial cable, optical fiber, and digital subscriber line (DSL), or a wireless link, such as, but not limited to, wireless fidelity (WIFI), Bluetooth, and mobile device networks.

[0043] It is understood that the number of underwriting terminals 110, servers 120, and user terminals 130 in the abnormal data analysis system shown in Figure 1 is for example only. In a specific implementation, the abnormal data analysis system may include any number of underwriting terminals, user terminals, and servers, and this specification does not specifically limit this. For example, but not limited to, the underwriting terminal 110 may be an underwriting terminal cluster consisting of multiple underwriting terminals, the server 120 may be a server cluster consisting of multiple servers, and the user terminal 130 may be a user terminal cluster consisting of multiple user terminals.

[0044] Next, with reference to Figure 1 , we will describe the abnormal data analysis method provided by an embodiment of this specification, using server 120 as an example. Specifically, please refer to Figure 2 , which is a flow chart of an abnormal data analysis method provided by an exemplary embodiment of this specification. As shown in Figure 2 , the abnormal data analysis method includes the following steps.

[0045] S202, obtaining target underwriting link data corresponding to the target abnormal underwriting result, the target underwriting link data including target underwriting data of each underwriting link when underwriting is performed according to the target underwriting policy based on the target insurance request.

[0046] Specifically, when an abnormal underwriting result, i.e., a target abnormal underwriting result, is monitored, the target underwriting link data recorded in the underwriting process corresponding to the target abnormal underwriting result can be retrieved from the database or the underwriting end. The target underwriting link data can include, but is not limited to, the target underwriting data involved in each underwriting link in the underwriting process corresponding to the target abnormal underwriting result.

[0047] Optionally, the above-mentioned underwriting link may include, but is not limited to, a data acquisition link, a data standardization processing link, a data matching link, etc. The above-mentioned data acquisition link is used to represent the acquisition link of the data to be underwritten. The target underwriting data of the data acquisition link may include, but is not limited to, the target user data of the target user (policyholder) corresponding to the target abnormal underwriting result (for example, but not limited to the target health data, target occupation data, and target financial data of the target user), the target source corresponding to the target user data, and the target product data of the target user's product to be insured, which are waiting for underwriting data. The above-mentioned data standardization processing link is used to represent the link for standardizing the data to be underwritten. In the data standardization processing link, the target user data, the target source corresponding to the target user data, and the target product data waiting for underwriting data will be standardized to facilitate the statistics of abnormal underwriting situations in subsequent abnormality analysis, improve the statistical efficiency of abnormal underwriting and the standardization of statistical data results; the target underwriting data of the above-mentioned data standardization processing link may include, but is not limited to, the standardized underwriting data after the target user data, the target source corresponding to the target user data, and the target product data waiting for underwriting data are each standardized, and the standardized accuracy rate corresponding to each standardized underwriting data. The above-mentioned data matching link is used to represent the link of matching standardized target user data with standardized target product data or identifying risks in accordance with the corresponding target underwriting strategy to obtain the target underwriting result (for example, the target abnormal underwriting result). The target underwriting data of the above-mentioned data matching link may include but is not limited to the version data of the target underwriting policy, the accuracy of the target underwriting result, the accuracy of the corresponding matching or risk identification of each underwriting rule under the target underwriting strategy, etc.

[0048] Optionally, in an embodiment of the present specification, the underwriting end or server can monitor the underwriting results corresponding to the insurance requests sent by each user end in real time, and collect underwriting abnormality information of the underwriting abnormal results. The above-mentioned underwriting abnormal results are used to characterize the underwriting results of classifying and adjusting the underwriting risk or restricting underwriting (i.e., intercepting insurance); when it is monitored that a certain underwriting abnormality information meets the preset abnormality condition, it means that the underwriting abnormality result corresponding to the underwriting abnormality information may be caused by abnormal underwriting, i.e., erroneous underwriting (such as erroneous interception), and the underwriting abnormality result corresponding to the underwriting abnormality information can be determined as the target abnormal underwriting result, so as to automatically and actively capture and warn of abnormal underwriting cases through statistical learning of the underwriting abnormal results. For example, when the interception rate of a rare disease is very high, an alarm is actively issued, and the above-mentioned S202 is executed to obtain the target underwriting link data corresponding to the target abnormal underwriting result, and timely perform abnormal analysis on the erroneous underwriting (abnormal underwriting) situation, and quickly and automatically analyze the root cause of the abnormality, so as to adjust the target abnormal underwriting result in time and optimize the underwriting accuracy and the accuracy of the underwriting data.

[0049] Furthermore, the above-mentioned underwriting abnormality information includes the underwriting abnormality factors corresponding to each underwriting abnormality result, and the number of occurrences and / or incidence rate of underwriting abnormality results caused by the same underwriting abnormality factor. The above-mentioned preset abnormal conditions may include, but are not limited to, the number of occurrences and / or incidence rate of underwriting abnormality results caused by the same underwriting abnormality factor reaching the target value. The above-mentioned underwriting abnormality factors may include, but are not limited to, health factors, financial factors, position factors and other types, which are used to characterize the factors that cause the user's insurance to have an abnormal underwriting result. For example, when the user's (policyholder's) insurance is blocked (abnormal underwriting result) because he suffers from rare disease A and does not meet the risk control requirements of the insured product, the underwriting abnormality factor corresponding to his underwriting abnormal result is rare disease A under the health factor type.

[0050] For example, when it is monitored that there have been 1,000 times (target value) in the day or month that the user (policyholder)'s insurance request has been intercepted, i.e., the insurance has been restricted, due to the user (policyholder) suffering from rare disease A (underwriting abnormality factor), it is very likely that a false interception has occurred. The underwriting abnormality result caused by the underwriting abnormality factor (suffering from rare disease A) on the day or month may not be accurate enough and is an abnormal underwriting result, that is, an underwriting result caused by an abnormality in the underwriting process (such as low accuracy of data or data processing, etc.).

[0051] Optionally, the above S202, obtaining the target underwriting link data corresponding to the target abnormal underwriting result may include: querying the target underwriting link data corresponding to the target abnormal underwriting result from the historical underwriting log based on the target underwriting time of the target abnormal underwriting result and the target identity identifier of the target user corresponding to the target abnormal underwriting result, and the above historical underwriting log is used to record the underwriting link data involved in the underwriting based on the user's insurance request. The above target user is the target insured person corresponding to the target abnormal underwriting result. In the embodiment of this specification, the link related to the underwriting business will be found in the underwriting technical link and buried, and the underwriting link data involved in the underwriting based on the insurance request of each user, that is, the historical underwriting log, will be recorded, so that the underwriting system on the underwriting end or server can perceive the operation status of the underwriting business, and query the corresponding target underwriting link data from the recorded historical underwriting log through the target underwriting time and target identity identifier of the target abnormal underwriting result so as to conduct more accurate abnormality analysis in line with the actual underwriting situation later.

[0052] S204, performing an abnormality analysis on the target underwriting link data to obtain a target abnormality analysis result corresponding to the target abnormal underwriting result.

[0053] Specifically, after obtaining the target underwriting link data corresponding to the target abnormal underwriting result, the target underwriting data of each underwriting link in the target underwriting link data can be analyzed for abnormalities to obtain the abnormal analysis results of each underwriting link. Then, the target abnormal analysis result corresponding to the target abnormal underwriting result is determined based on the abnormal analysis results of each underwriting link. For example, when the accuracy of the target underwriting data of the underwriting link is lower than the threshold (i.e., there is abnormal underwriting data) or the accuracy of the data processing (such as standardization processing or matching processing, etc.) of the underwriting link is lower than the threshold, etc., it can be confirmed that the abnormal analysis result of the underwriting link is abnormal, that is, the underwriting link is an abnormal underwriting link. When the abnormal analysis result of the underwriting link is normal, the underwriting link can be considered to be a normal underwriting link. The target abnormal analysis result corresponding to the target abnormal underwriting result may include, but is not limited to, abnormal underwriting data of the abnormal underwriting link in the target underwriting link data.

[0054] Optionally, after obtaining the target underwriting link data corresponding to the target abnormal underwriting result, the target underwriting link data can be input into a pre-trained anomaly analysis model to output the target abnormal underwriting result. The anomaly analysis model is trained based on the underwriting link data corresponding to the abnormal underwriting results of multiple known abnormal analysis results.

[0055] Optionally, the above S204, performing an abnormality analysis on the target underwriting link data, and obtaining a target abnormality analysis result corresponding to the target abnormal underwriting result may include: first sending a target abnormality analysis instruction to the business end (underwriting end) based on the target underwriting link data, so that the business end (underwriting end) responds to the target abnormality analysis instruction and displays the corresponding target underwriting link data; then, receiving the target abnormality analysis result returned by the business end, and the above target abnormality analysis result is obtained by the business staff (underwriting personnel) of the business end (underwriting end) performing an abnormality analysis on the target underwriting link data. That is, in the embodiment of this specification, the target underwriting link data corresponding to the monitored target abnormal underwriting result can be directly displayed on the business end (underwriting end), so that the business staff (underwriting personnel) of the business end (underwriting end) can quickly view and analyze the abnormality and input the corresponding target abnormality analysis result, so that the business staff (underwriting personnel) can promptly eliminate the root cause of the underwriting problem.

[0056] In an embodiment of the present specification, target underwriting link data corresponding to a target abnormal underwriting result is obtained; the above-mentioned target underwriting link data includes target underwriting data of each underwriting link when underwriting is performed in accordance with a target underwriting policy based on a target insurance request; an abnormality analysis is performed on the above-mentioned target underwriting link data to obtain a target abnormality analysis result corresponding to the above-mentioned target abnormal underwriting result, thereby accurately checking the accuracy of the underwriting data of each underwriting link under abnormal underwriting, and quickly and automatically checking and analyzing the root cause of the error that led to the abnormal underwriting (for example, which underwriting data in which underwriting link has a problem), that is, the target abnormality analysis result, to avoid the problem of misinterpretation of underwriting, and improve the underwriting accuracy and user insurance experience.

[0057] Next, please refer to Figure 3, which is a flowchart of another abnormal data analysis method provided by an exemplary embodiment of this specification. As shown in Figure 3, the abnormal data analysis method includes the following steps.

[0058] S302: Obtain the target insurance request of the target user.

[0059] Specifically, when the target user wants to purchase an insurance product (product to be insured) from an insurance institution, it can trigger the corresponding user terminal to send a corresponding target insurance request to the underwriting terminal or server corresponding to the insurance institution. The target insurance request carries the target identity identifier of the target user and the target product identifier of the product to be insured.

[0060] S304: In response to the target insurance application request, obtain the corresponding underwriting data.

[0061] Specifically, the above-mentioned data to be underwritten include the target user data of the target user, the target source corresponding to the target user data, and the target product data of the target user's product to be insured. After obtaining the target insurance request of the target user, the target user data corresponding to the target identity identifier can be queried from an external institution (such as but not limited to the hospital side, enterprise side, bank side, etc.) based on the target identity identifier and with the authorization of the target user in response to the target insurance request, and the corresponding target product data can be queried from the database of the underwriting side based on the target product identifier of the product to be insured. The above-mentioned target user data may include but is not limited to target health data, target occupation data, target financial data, etc. The above-mentioned target health data may include but is not limited to the target user's medical details (for example, but not limited to the target user being diagnosed with a certain disease at a certain time and place), whether the parents have genetic diseases, etc. The above-mentioned target product data may include but is not limited to insurance product terms, health report conclusions corresponding to each disease, etc. The above-mentioned target sources may include, but are not limited to, multiple data source categories and data source subcategories under each source category. For example, but not limited to, the data source category is an external organization, and its data source subcategory is an external data supplier (for example, but not limited to, hospital, enterprise, bank, etc.).

[0062] Optionally, in order to improve underwriting efficiency and accuracy, the above-mentioned data to be underwritten will be standardized during underwriting, for example, but not limited to standardizing the disease name, hospital name, etc. in the target user data, to obtain the standardized data and standardized confidence corresponding to each data in the data to be underwritten, thereby facilitating subsequent underwriting anomaly analysis and further improving the accuracy and efficiency of abnormal data analysis.

[0063] S306: Input the data to be underwritten into the risk control model, output the target underwriting result of the target user based on the target underwriting strategy, and record the target underwriting data of each underwriting link in the risk control model to obtain the target underwriting link data corresponding to the target underwriting result.

[0064] Specifically, the above-mentioned risk control model is trained based on the data to be underwritten with multiple known underwriting results. After obtaining the corresponding data to be underwritten, the data to be underwritten can be directly input into the risk control model, and risk identification can be performed according to the corresponding target underwriting strategy. The target underwriting result of the target user is output, and the target underwriting data of each underwriting link in the risk control model is recorded to obtain the target underwriting link data corresponding to the target underwriting result, thereby realizing the recording of the data processing status of each underwriting link while underwriting, so that when abnormal underwriting is discovered later (that is, the target underwriting result is inaccurate), the target underwriting link data recorded in the corresponding underwriting process can be retrieved in time for corresponding abnormal analysis.

[0065] S308, when the target underwriting result is an underwriting abnormality, and / or when a target complaint request or a target query request is obtained from a target user, the target underwriting result is determined to be a target abnormal underwriting result, and the target underwriting link data corresponding to the target abnormal underwriting result is queried.

[0066] Specifically, when the target underwriting result is an underwriting abnormality, that is, the insurer needs to classify and adjust the underwriting risk or restrict underwriting (that is, intercept insurance), and / or when the target user obtains a target complaint request or a target query request (used to query the reasons why the target underwriting result is an underwriting abnormality) for the target underwriting result, it can be considered that there is a problem with the target underwriting result, and the target underwriting result can be determined as a target abnormal underwriting result, and the query of the target underwriting link data corresponding to the target abnormal underwriting result can be triggered.

[0067] S310, performing an abnormality analysis on the target underwriting link data to obtain a target abnormality analysis result corresponding to the target abnormal underwriting result.

[0068] Specifically, the above-mentioned target abnormality analysis results include abnormal underwriting data corresponding to abnormal underwriting links during underwriting. The above-mentioned abnormal underwriting links are used to characterize underwriting links whose underwriting accuracy is less than a preset value, or underwriting links that are analyzed and marked as abnormal by underwriting personnel.

[0069] S312: Update the target underwriting results and / or risk control model of the target user based on the abnormal underwriting data.

[0070] Specifically, after performing an abnormality analysis on the target underwriting link data and obtaining the target abnormal analysis result corresponding to the target abnormal underwriting result, the target underwriting result and / or risk control model of the target user can also be updated based on the abnormal underwriting data. For example, but not limited to, first obtaining the correction data corresponding to the abnormal underwriting data, and then re-underwriting the target user's corresponding underwriting data based on the above correction data to obtain the corresponding updated target underwriting result, or directly modifying the target underwriting result from underwriting abnormality to underwriting normal when it is determined that the correction data corresponding to the abnormal underwriting data meets the corresponding underwriting rules in the target underwriting strategy, that is, changing from blocking the target user from purchasing insurance to allowing the target user to purchase insurance normally, etc. It is also possible, but not limited to, to modify the underwriting parameters and / or underwriting rules of the corresponding abnormal underwriting link in the risk control model according to the correction data corresponding to the abnormal underwriting data to improve the accuracy of the target underwriting result and / or risk control model of the target user.

[0071] Next, please refer to Figure 4, which is a schematic diagram of the structure of an abnormal data analysis device provided in an exemplary embodiment of this specification. As shown in Figure 4, the abnormal data analysis device 400 includes: a first acquisition module 410, configured to obtain target underwriting link data corresponding to a target abnormal underwriting result; the target underwriting link data includes target underwriting data for each underwriting step when underwriting is performed based on a target insurance request and in accordance with a target underwriting policy; and an abnormality analysis module 420, configured to perform abnormality analysis on the target underwriting link data to obtain a target abnormality analysis result corresponding to the target abnormal underwriting result.

[0072] In one possible implementation, the abnormal data analysis device 400 further includes: an underwriting monitoring module for monitoring the underwriting results corresponding to each insurance request, and collecting statistics on the underwriting abnormality information of the abnormal underwriting results; the abnormal underwriting results are used to characterize the underwriting results for classifying and adjusting the underwriting risk or restricting the underwriting; and a first determination module for determining the abnormal underwriting result corresponding to the abnormal underwriting information as the target abnormal underwriting result when the abnormal underwriting information meets a preset abnormal condition.

[0073] In one possible implementation, the above-mentioned underwriting abnormality information includes the underwriting abnormality factors corresponding to each underwriting abnormality result, and the number of occurrences and / or incidence rates of the underwriting abnormality results caused by the same above-mentioned underwriting abnormality factors; the above-mentioned preset abnormal conditions include the above-mentioned number of occurrences and / or incidence rates reaching the target value.

[0074] In one possible implementation, the above-mentioned exception analysis module 420 includes: a sending unit, used to send a target exception analysis instruction to the business end based on the above-mentioned target underwriting link data, so that the above-mentioned business end responds to the above-mentioned target exception analysis instruction and displays the above-mentioned target underwriting link data; a receiving unit, used to receive the target exception analysis result returned by the above-mentioned business end; the above-mentioned target exception analysis result is obtained by the business staff of the above-mentioned business end by performing an exception analysis on the above-mentioned target underwriting link data.

[0075] In one possible implementation, the abnormal data analysis device 400 further includes: a second acquisition module for acquiring the target insurance request of the target user; a third acquisition module for acquiring the corresponding data to be underwritten in response to the target insurance request; the data to be underwritten includes the target user data of the target user, the target source corresponding to the target user data, and the target product data of the product to be insured by the target user; a risk control module for inputting the data to be underwritten into the risk control model, outputting the target underwriting result of the target user based on the target underwriting strategy, and recording the target underwriting data of each underwriting link in the risk control model to obtain the target underwriting link data corresponding to the target underwriting result.

[0076] In one possible implementation, the first acquisition module 410 is specifically used to: when the target underwriting result is an underwriting abnormality, and / or when the target complaint request or target query request of the target user is obtained, determine the target underwriting result as a target abnormal underwriting result, and query the target underwriting link data corresponding to the target abnormal underwriting result.

[0077] In one possible implementation, the above-mentioned target abnormality analysis result includes abnormal underwriting data corresponding to the abnormal underwriting link during underwriting; the above-mentioned abnormal underwriting link is used to characterize the underwriting link whose underwriting accuracy is less than a preset value, or the underwriting link that is analyzed and marked as abnormal; the above-mentioned abnormal data analysis device 400 also includes: an update module, which is used to update the target underwriting result of the above-mentioned target user and / or the above-mentioned risk control model based on the above-mentioned abnormal underwriting data.

[0078] In one possible implementation, the first acquisition module 410 is specifically used to: query the target underwriting link data corresponding to the target abnormal underwriting result from the historical underwriting log based on the target underwriting time of the target abnormal underwriting result and the target identity identifier of the target user corresponding to the target abnormal underwriting result; the historical underwriting log is used to record the underwriting link data involved in underwriting based on the user's insurance request.

[0079] The division of the modules in the above-described abnormal data analysis device is for illustrative purposes only. In other embodiments, the abnormal data analysis device can be divided into different modules as needed to perform all or part of the functions of the above-described abnormal data analysis device. The various modules in the abnormal data analysis device provided in the embodiments of this specification can be implemented in the form of a computer program. The computer program can be executed on a terminal or server. The program modules comprising the computer program can be stored in the memory of the terminal or server. When the computer program is executed by a processor, it implements all or part of the steps of the abnormal data analysis method described in the embodiments of this specification.

[0080] Next, please refer to Figure 5, which is a schematic diagram of the structure of an electronic device provided in an exemplary embodiment of this specification. As shown in Figure 5, the electronic device 500 may include: at least one processor 510, at least one communication bus 520, a user interface 530, at least one network interface 540, and a memory 550.

[0081] The communication bus 520 may be used to implement connection and communication among the above components.

[0082] The user interface 530 may include a display screen (Display) and a camera (Camera), and the optional user interface may also include a standard wired interface and a wireless interface.

[0083] The network interface 540 may optionally include a Bluetooth module, a Near Field Communication (NFC) module, a Wireless Fidelity (Wi-Fi) module, and the like.

[0084] The processor 510 may include one or more processing cores. The processor 510 utilizes various interfaces and circuits to connect the various components within the electronic device 500. By running or executing instructions, programs, code sets, or instruction sets stored in the memory 550, and accessing data stored in the memory 550, the processor 510 performs various functions and processes data for the routing electronic device 500. Optionally, the processor 510 may be implemented using at least one hardware form factor selected from the group consisting of a digital signal processing (DSP), a field-programmable gate array (FPGA), and a programmable logic array (PLA). The processor 510 may integrate one or a combination of a central processing unit (CPU), a graphics processing unit (GPU), and a modem. The CPU primarily processes the operating system, user interface, and application programs; the GPU is responsible for rendering and drawing the content displayed on the display; and the modem handles wireless communications. It is understood that the modem may not be integrated into the processor 510 and may be implemented as a separate chip.

[0085] The memory 550 may include a random access memory (RAM) or a read-only memory (ROM). Optionally, the memory 550 includes a non-transitory computer-readable medium. The memory 550 can be used to store instructions, programs, codes, code sets, or instruction sets. The memory 550 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as an acquisition function, an anomaly analysis function, an underwriting monitoring function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store data involved in the above-mentioned various method embodiments, etc. The memory 550 may also optionally be at least one storage device located away from the aforementioned processor 510. As shown in Figure 5, the memory 550 as a computer storage medium may include an operating system, a network communication module, a user interface module, and program instructions.

[0086] In some possible embodiments, the electronic device 500 may be the aforementioned abnormal data analysis device, and the processor 510 may be used to call the program instructions stored in the memory 550, and specifically perform the following operations: obtaining target underwriting link data corresponding to the target abnormal underwriting result; the target underwriting link data includes target underwriting data of each underwriting link when underwriting is performed according to the target underwriting policy based on the target insurance request; performing abnormal analysis on the target underwriting link data to obtain a target abnormal analysis result corresponding to the target abnormal underwriting result.

[0087] In some possible embodiments, before executing the above-mentioned acquisition of the target underwriting link data corresponding to the target abnormal underwriting result, the above-mentioned processor 510 is also used to execute: monitoring the underwriting results corresponding to each insurance request, and counting the underwriting abnormality information of the underwriting abnormality results; the above-mentioned underwriting abnormality results are used to characterize the underwriting results for classifying and adjusting the underwriting risk or restricting the underwriting; when the above-mentioned underwriting abnormality information meets the preset abnormality condition, the underwriting abnormality result corresponding to the above-mentioned underwriting abnormality information is determined as the above-mentioned target abnormal underwriting result.

[0088] In some possible embodiments, the above-mentioned underwriting abnormality information includes the underwriting abnormality factors corresponding to each underwriting abnormality result, and the number of occurrences and / or incidence rates of the underwriting abnormality results caused by the same above-mentioned underwriting abnormality factors; the above-mentioned preset abnormal conditions include the above-mentioned number of occurrences and / or incidence rates reaching the target value.

[0089] In some possible embodiments, when the processor 510 performs the above-mentioned abnormality analysis on the target underwriting link data and obtains the target abnormality analysis result corresponding to the target abnormal underwriting result, it is specifically used to execute: sending a target abnormality analysis instruction to the business end based on the target underwriting link data, so that the business end responds to the target abnormality analysis instruction and displays the target underwriting link data; receiving the target abnormality analysis result returned by the business end; the target abnormality analysis result is obtained by the business staff of the business end performing abnormality analysis on the target underwriting link data.

[0090] In some possible embodiments, before executing the above-mentioned acquisition of the target underwriting link data corresponding to the target abnormal underwriting result, the above-mentioned processor 510 is also used to execute: obtaining the target insurance request of the target user; in response to the above-mentioned target insurance request, obtaining the corresponding data to be underwritten; the above-mentioned data to be underwritten includes the target user data of the above-mentioned target user, the target source corresponding to the above-mentioned target user data, and the target product data of the product to be insured by the above-mentioned target user; inputting the above-mentioned data to be underwritten into the risk control model, outputting the target underwriting result of the above-mentioned target user based on the above-mentioned target underwriting strategy, and recording the target underwriting data of each underwriting link in the above-mentioned risk control model to obtain the target underwriting link data corresponding to the above-mentioned target underwriting result.

[0091] In some possible embodiments, when the processor 510 executes the above-mentioned acquisition of the target underwriting link data corresponding to the target abnormal underwriting result, it is specifically used to execute: when the target underwriting result is an underwriting abnormality, and / or when the target complaint request or target query request of the target user is obtained, the target underwriting result is determined as a target abnormal underwriting result, and the target underwriting link data corresponding to the target abnormal underwriting result is queried.

[0092] In some possible embodiments, the above-mentioned target abnormality analysis result includes abnormal underwriting data corresponding to the abnormal underwriting link during underwriting; the above-mentioned abnormal underwriting link is used to characterize the underwriting link whose underwriting accuracy is less than a preset value, or the underwriting link that is analyzed and marked as abnormal; the above-mentioned processor 510 executes the above-mentioned abnormality analysis on the above-mentioned target underwriting link data, and after obtaining the target abnormality analysis result corresponding to the above-mentioned target abnormal underwriting result, it is also used to execute: updating the target underwriting result of the above-mentioned target user and / or the above-mentioned risk control model based on the above-mentioned abnormal underwriting data.

[0093] In some possible embodiments, when the processor 510 executes the above-mentioned acquisition of the target underwriting link data corresponding to the target abnormal underwriting result, it is specifically used to execute: querying the target underwriting link data corresponding to the target abnormal underwriting result from the historical underwriting log based on the target underwriting time of the target abnormal underwriting result and the target identity identifier of the target user corresponding to the target abnormal underwriting result; the historical underwriting log is used to record the underwriting link data involved in underwriting based on the user's insurance request.

[0094] The embodiments of this specification also provide a computer-readable storage medium storing instructions that, when executed on a computer or processor, cause the computer or processor to perform one or more steps of the above-described embodiments. If the various components of the abnormal data analysis device described above are implemented as software functional units and sold or used as independent products, they may be stored in the computer-readable storage medium.

[0095] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When software is used for implementation, it can be implemented in whole or in part in the form of a computer program product. The above-mentioned computer program product includes one or more computer instructions. When the above-mentioned computer program instructions are loaded and executed on a computer, the above-mentioned process or function according to the embodiment of this specification is generated in whole or in part. The above-mentioned computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The above-mentioned computer instructions can be stored in a computer-readable storage medium or transmitted by the above-mentioned computer-readable storage medium. The above-mentioned computer instructions can be transmitted from a website, computer, server or data center to another website, computer, server or data center by wired (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (such as infrared, wireless, microwave, etc.). The above-mentioned computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrations. The available media may be magnetic media (eg, floppy disks, hard disks, tapes), optical media (eg, digital versatile discs (DVDs)), or semiconductor media (eg, solid state disks (SSDs)).

[0096] Those skilled in the art will appreciate that all or part of the processes in the above-described method embodiments can be implemented by instructing the relevant hardware through a computer program. The program can be stored in a computer-readable storage medium. When executed, the program can include the processes of the above-described method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks. The technical features of this embodiment and the implementation scheme can be combined in any manner unless they conflict.

[0097] The embodiments described above are merely preferred embodiments of this specification and are not intended to limit the scope of this specification. Without departing from the design spirit of this specification, various modifications and improvements made to the technical solutions of this specification by ordinary technicians in this field should fall within the scope of protection determined by the claims.

[0098] The foregoing description of specific embodiments of this specification is intended to be a description of other embodiments. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps described in the claims and specification can be performed in a different order than that described in the embodiments described in the specification and still achieve the desired results. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order shown or the sequential order to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

Claims

1. An abnormal data analysis method, the method comprising: Obtaining target underwriting link data corresponding to a target abnormal underwriting result; The target underwriting link data includes target underwriting data of each underwriting link when underwriting is performed according to a target underwriting policy based on a target insurance application request; Performing abnormal analysis on the target underwriting link data to obtain a target abnormal analysis result corresponding to the target abnormal underwriting result.

2. The method according to claim 1, before obtaining the target underwriting link data corresponding to the target abnormal underwriting result, the method further comprising: Monitoring underwriting results corresponding to each insurance application request and counting underwriting abnormal information of underwriting abnormal results; The underwriting abnormal result is used to represent an underwriting result for classifying and adjusting underwriting risks or restricting underwriting; When the underwriting abnormal information meets a preset abnormal condition, determining the underwriting abnormal result corresponding to the underwriting abnormal information as the target abnormal underwriting result.

3. The method according to claim 2, the underwriting abnormal information includes underwriting abnormal factors corresponding to each underwriting abnormal result, and the occurrence times and / or occurrence rates of underwriting abnormal results caused by the same underwriting abnormal factor; The preset abnormal condition includes that the occurrence times and / or occurrence rates reach a target value.

4. The method according to claim 2, the performing abnormal analysis on the target underwriting link data to obtain a target abnormal analysis result corresponding to the target abnormal underwriting result includes: Sending a target abnormal analysis instruction to the service end based on the target underwriting link data, so that the service end responds to the target abnormal analysis instruction and displays the target underwriting link data; Receiving the target abnormal analysis result returned by the service end; The target abnormal analysis result is obtained by an underwriter at the service end performing abnormal analysis on the target underwriting link data.

5. The method according to claim 1, before obtaining the target underwriting link data corresponding to the target abnormal underwriting result, the method further comprising: Obtaining a target insurance application request of a target user; Responding to the target insurance application request and obtaining corresponding data to be underwritten; The data to be underwritten includes target user data of the target user, a target source corresponding to the target user data, and target product data of a target product to be insured by the target user; Inputting the data to be underwritten into a risk control model, outputting a target underwriting result of the target user based on the target underwriting policy, and recording target underwriting data of each underwriting link in the risk control model to obtain target underwriting link data corresponding to the target underwriting result.

6. The method according to claim 5, the obtaining target underwriting link data corresponding to the target abnormal underwriting result includes: In the case where the target underwriting result is an underwriting abnormality, and / or, in the case where a target complaint request or a target query request of the target user is obtained, determining the target underwriting result as a target abnormal underwriting result, and querying target underwriting link data corresponding to the target abnormal underwriting result.

7. The method according to claim 6, wherein the target abnormal analysis result includes abnormal underwriting data corresponding to an abnormal underwriting link during underwriting; the abnormal underwriting link is used to represent an underwriting link with an underwriting accuracy rate less than a preset value, or an underwriting link marked as abnormal through analysis. After obtaining the target abnormal analysis result corresponding to the target abnormal underwriting result by performing abnormal analysis on the target underwriting link data, the method further includes: Updating the target underwriting result of the target user and / or the risk control model based on the abnormal underwriting data.

8. The method according to claim 1, wherein obtaining the target underwriting link data corresponding to the target abnormal underwriting result includes: Querying the target underwriting link data corresponding to the target abnormal underwriting result from the historical underwriting log based on the target underwriting time of the target abnormal underwriting result and the target identity identifier of the target user corresponding to the target abnormal underwriting result; the historical underwriting log is used to record the underwriting link data involved during underwriting based on the insurance application request of the user.

9. An abnormal data analysis device, the device includes: A first acquisition module, configured to acquire target underwriting link data corresponding to a target abnormal underwriting result; The target underwriting link data includes target underwriting data of each underwriting link when underwriting is performed according to a target underwriting policy based on a target insurance application request; An abnormal analysis module, configured to perform abnormal analysis on the target underwriting link data to obtain a target abnormal analysis result corresponding to the target abnormal underwriting result.

10. An electronic device, comprising: A processor and a memory; The processor is connected to the memory; The memory is used to store executable program codes; The processor runs a program corresponding to the executable program code by reading the executable program code stored in the memory, so as to execute the method according to any one of claims 1-8.

11. A computer storage medium, the computer storage medium stores multiple instructions, and the instructions are suitable for being loaded and executed by a processor to perform the method steps according to any one of claims 1-8.

12. A computer program product containing instructions, when the computer program product runs on a computer or a processor, the computer or the processor is caused to execute the method according to any one of claims 1-8.

Images