Risk control method and system, computer equipment and storage medium

The target relationship network is built through graph storage technology and the GBFS path planning algorithm is used to identify key risk paths, which solves the problems of low efficiency and poor accuracy of relationship network processing in the insurance risk control field in the existing technology, and achieves a more efficient risk control effect.

CN119067787APending Publication Date: 2024-12-03CHINA PING AN PROPERTY INSURANCE CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411210647.7
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-30
Publication Date
2024-12-03

AI Technical Summary

Technical Problem

The prior art is inefficient and poorly accurate when dealing with relationship networks in the insurance risk control field, resulting in poor risk control effects.

Method used

Graph storage technology is used to build a target relationship network, and GBFS path planning algorithm is used to identify key risk paths, and corresponding risk control measures are taken based on the risk assessment results.

Benefits of technology

It improves the accuracy and efficiency of risk control, can reveal complex insurance relationship networks more comprehensively, discover potential risk associations, and reduce the risk of insurance fraud.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119067787A_ABST
    Figure CN119067787A_ABST
Patent Text Reader

Abstract

The invention discloses a risk control method and system, computer equipment and a storage medium, and relates to the technical field of data processing, and the method comprises the steps: obtaining business data related to a risk control object, carrying out the data processing of the business data, and generating a corresponding basic data set; based on the basic data set, utilizing a graph storage technology to construct and obtain a target relation network; implementing a GBFS path planning algorithm in the target relation network, and identifying a key risk path of the risk control object; based on the key risk path, evaluating the risk level of the risk control object, and generating a corresponding risk evaluation result; and based on the risk assessment result, performing risk control on the risk control object by adopting corresponding risk control measures. According to the method provided by the invention, the problem that the risk control effect of the existing risk control object is poor due to the defects of low efficiency, poor accuracy and the like when the relational network of the risk control object is processed in the prior art can be solved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a risk control method, system, computer equipment and non-volatile computer-readable storage medium. Background Art

[0002] At present, with the rapid development of the insurance industry, insurance risk control, as a core part of the insurance industry, has become increasingly important. The field of insurance risk control is an important field in the insurance industry. Its purpose is to reduce the potential risks and losses faced by insurance companies by effectively managing and controlling insurance risks. In this field, building and analyzing relationship networks have become key tools for understanding and predicting risk propagation. However, the existing technologies have defects such as low efficiency and poor accuracy when dealing with relationship networks in the field of insurance risk control, resulting in poor results of existing insurance risk control.

[0003] Therefore, the existing technology still needs to be improved and developed. Summary of the invention

[0004] In view of the above-mentioned shortcomings of the prior art, the purpose of the present invention is to provide a risk control method, system, computer equipment and non-volatile computer-readable storage medium that can be used in financial technology or other related fields, aiming to solve the problems of low efficiency and poor accuracy in the prior art when processing the relationship network of risk control objects, resulting in poor risk control effect on existing risk control objects.

[0005] In order to achieve the above object, the present invention adopts the following technical solutions:

[0006] A risk control method, comprising:

[0007] Obtaining business data related to the risk control object, and generating corresponding basic data sets after data processing on the business data;

[0008] Based on the basic data set, a target relationship network is constructed using graph storage technology;

[0009] Implementing the GBFS path planning algorithm in the target relationship network to identify the key risk path of the risk control object;

[0010] Based on the key risk path, the risk level of the risk control object is evaluated to generate a corresponding risk assessment result;

[0011] Based on the risk assessment results, corresponding risk control measures are adopted to perform risk control on the risk control object.

[0012] In a further technical solution, the risk control method, wherein the step of acquiring business data related to the risk control object and processing the business data to generate a corresponding basic data set, includes:

[0013] Obtain business data related to risk control objects from the business database;

[0014] After data cleaning, data integration and data standardization processing are performed on the business data, a corresponding basic data set is generated.

[0015] In a further technical solution, the risk control method, wherein the target relationship network is constructed based on the basic data set using graph storage technology, comprises:

[0016] Design the graph model according to business requirements and define the data structure of its nodes and edges;

[0017] Select a corresponding graph database, and create a pattern of nodes and edges in the graph database according to the designed graph model;

[0018] The basic data set is imported into the graph database, the relationship between nodes and edges is established, and the corresponding target relationship network is obtained.

[0019] In a further technical solution, the risk control method, wherein the GBFS path planning algorithm is implemented in the target relationship network to identify the key risk path of the risk control object, includes:

[0020] Setting a starting point node in the target relationship network;

[0021] Using the GBFS path planning algorithm to search for a path in the target relationship network starting from the starting point node;

[0022] Evaluating the potential risks of different paths in the target relationship network according to a preset path scoring function;

[0023] The path with the highest score is selected for expansion until the key risk path of the risk control object is identified.

[0024] In a further technical solution, the risk control method, wherein the step of obtaining business data related to the risk control object in the business database includes:

[0025] Obtain insurance business data related to risk control objects from the insurance business database;

[0026] Among them, the risk control object is an insurance product, and the insurance business data includes policyholder information, insured person information, insurance product information and claim records.

[0027] In a further technical solution, the risk control method, wherein the corresponding graph database is selected, and a node and edge pattern is created in the graph database according to a designed graph model, wherein the graph database includes Neo4j, JanusGraph and TigerGraph.

[0028] In a further technical solution, the risk control method, wherein, based on the risk assessment results, adopts corresponding risk control measures to perform risk control on the risk control object, wherein the risk control measures include rejecting high-risk insurance applications, adjusting premium pricing and initiating investigation procedures.

[0029] A risk control system, comprising:

[0030] The data processing module is used to obtain business data related to the risk control object, and generate a corresponding basic data set after processing the business data;

[0031] A network construction module, used to construct a target relationship network based on the basic data set using graph storage technology;

[0032] A path identification module, used to implement the GBFS path planning algorithm in the target relationship network to identify the key risk path of the risk control object;

[0033] A risk assessment module, used to assess the risk level of the risk control object based on the key risk path and generate a corresponding risk assessment result;

[0034] The risk control module is used to perform risk control on the risk control object by adopting corresponding risk control measures based on the risk assessment result.

[0035] A computer device, wherein the computer device comprises at least one processor; and

[0036] a memory communicatively connected to the at least one processor; wherein,

[0037] The memory stores a computer program that can be executed by the at least one processor. When the computer program is executed by the at least one processor, the risk control method as described in any one of the above items can be implemented.

[0038] A non-volatile computer-readable storage medium, wherein the non-volatile computer-readable storage medium stores a computer program, and when the computer program is executed by at least one processor, it can implement the risk control method as described in any one of the above items.

[0039] Compared with the prior art, the present invention provides a risk control method, system, computer device and non-volatile computer-readable storage medium, wherein the method includes: obtaining business data related to the risk control object, and generating a corresponding basic data set after data processing of the business data; constructing a target relationship network based on the basic data set using graph storage technology; implementing the GBFS path planning algorithm in the target relationship network to identify the key risk path of the risk control object; based on the key risk path, evaluating the risk level of the risk control object and generating a corresponding risk assessment result; based on the risk assessment result, adopting corresponding risk control measures to control the risk of the risk control object. In this way, the method of the present invention can solve the problem that the prior art has the defects of low efficiency and poor accuracy in processing the relationship network of the risk control object, resulting in poor risk control effect on the existing risk control objects. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0041] Figure 1 A schematic diagram of a risk control method provided by an embodiment of the present invention.

[0042] Figure 2 A schematic diagram of functional modules of a risk control system provided by an embodiment of the present invention.

[0043] Figure 3 A schematic diagram of the hardware structure of a computer device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0044] In order to make the purpose, technical solution and effect of the present invention clearer and more specific, the present invention is further described in detail with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0045] In the description of the present invention, the terms "include", "including", "have", "contain", etc. are all open terms, which mean including but not limited to. The descriptions with reference to the terms "one embodiment", "a specific embodiment", "some embodiments", "for example", etc. mean that the specific features, structures or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures or characteristics described may be combined in a suitable manner in any one or more embodiments or examples. The order of steps involved in each embodiment is used to schematically illustrate the implementation of the present application, and the order of steps therein is not limited and can be appropriately adjusted as needed.

[0046] Various non-limiting embodiments of the present invention are described in detail below in conjunction with the accompanying drawings.

[0047] See also Figure 1 , an embodiment of the present invention provides a risk control method, wherein the method comprises the steps of:

[0048] S100, obtaining business data related to the risk control object, and generating a corresponding basic data set after processing the business data;

[0049] S200, constructing a target relationship network based on the basic data set using graph storage technology;

[0050] S300, implementing the GBFS path planning algorithm in the target relationship network to identify the key risk path of the risk control object;

[0051] S400: Based on the key risk path, the risk level of the risk control object is evaluated to generate a corresponding risk evaluation result;

[0052] S500: Based on the risk assessment result, adopt corresponding risk control measures to perform risk control on the risk control object.

[0053] Furthermore, the risk control method, wherein the step S100, obtaining business data related to the risk control object, and generating a corresponding basic data set after data processing on the business data, includes:

[0054] Obtain business data related to risk control objects from the business database;

[0055] After data cleaning, data integration and data standardization processing are performed on the business data, a corresponding basic data set is generated.

[0056] Furthermore, in the risk control method, the step of obtaining business data related to the risk control object in the business database includes:

[0057] Obtain insurance business data related to risk control objects from the insurance business database;

[0058] Among them, the risk control object is the insurance product, and the insurance business data includes policyholder information, insured person information, insurance product information and claim records, etc.

[0059] In the specific implementation, in this embodiment, insurance business data related to the risk control object is obtained in the insurance business database; wherein the risk control object is an insurance product, and the insurance business data includes information of the policyholder, information of the insured, information of the insurance product, and claim settlement records, etc.; after data cleaning, data integration, and data standardization processing are performed on the business data, a corresponding basic data set is generated; wherein the specific implementation process is roughly as follows:

[0060] 1. Data extraction

[0061] Extract relevant insurance business data from the insurance business database according to the risk control object (i.e., insurance product), including information of the policyholder (such as name, age, occupation, etc.), information of the insured (such as health status, historical risk record, etc.), insurance product information (such as insurance terms, premiums, insurance liability, etc.), and claims records (such as claim amount, claim time, claim reason, etc.);

[0062] 2. Data cleaning

[0063] Clean the extracted data to improve data quality, including removing duplicate records, correcting erroneous data items, handling missing values ​​(for example, by interpolating or deleting records with missing values), and identifying and deleting abnormal values ​​or outliers; the cleaning process ensures the accuracy and consistency of the data set, laying a solid foundation for subsequent analysis;

[0064] 3. Data Integration

[0065] Integrate the cleaned data as needed; this may involve merging data sets from different data sources or databases to ensure the consistency of the data in logic and format; for example, associating the policyholder information with the corresponding insurance product information to form a complete customer profile;

[0066] 4. Data Standardization

[0067] Standardize the integrated data, including unifying data formats, encodings, and metrics; for example, standardize the date format to YYYY-MM-DD, convert all text data to a unified case format, and ensure that all numerical data uses consistent units of measurement;

[0068] 5. Data Verification and Quality Assessment

[0069] After data cleaning, integration and standardization, data validation and quality assessment are performed to ensure that the data set meets the requirements of subsequent processes; this may include data integrity checks, logical consistency verification and data quality scoring;

[0070] 6. Generate basic data set

[0071] After completing steps 1-5 above, the processed data is organized into a structured form to generate a basic data set; this basic data set will serve as the starting point for risk assessment and analysis, providing the necessary data support for building an insurance relationship network and implementing risk control algorithms;

[0072] Through the above process, it can be ensured that the data extracted from the insurance business database is clean, consistent, accurate and reliable, providing a high-quality data foundation for insurance risk control analysis.

[0073] Furthermore, in the risk control method, the step S200, based on the basic data set, constructing a target relationship network using graph storage technology, comprises:

[0074] Design the graph model according to business requirements and define the data structure of its nodes and edges;

[0075] Select a corresponding graph database, and create a pattern of nodes and edges in the graph database according to the designed graph model;

[0076] The basic data set is imported into the graph database, the relationship between nodes and edges is established, and the corresponding target relationship network is obtained.

[0077] Furthermore, in the risk control method, a corresponding graph database is selected, and a node and edge pattern is created in the graph database according to a designed graph model, wherein the graph database includes Neo4j, JanusGraph and TigerGraph.

[0078] In the specific implementation, in this embodiment, a graph model is designed according to business requirements, and the data structure of its nodes and edges is defined; a corresponding graph database is selected, and a node and edge pattern is created in the graph database according to the designed graph model; the basic data set is imported into the graph database, the relationship between nodes and edges is established, and the corresponding target relationship network is obtained; wherein the specific implementation process is roughly as follows:

[0079] 1. Requirements analysis and graph model design

[0080] Work with the business team to clarify business needs and goals, identify key entities (such as policyholders, insured persons, insurance products) and the relationships between them (such as insurance relationships, claims records);

[0081] Design a graph model to define the data structure of nodes (including node type and attributes) and edge data structure (including edge type, direction, and attributes); for example, a policyholder node may contain attributes such as age and occupation; an insurance product node may contain attributes such as premium and insurance coverage; an edge may represent an insurance relationship and have attributes such as start time and insurance period;

[0082] 2. Select a graph database and create a schema

[0083] Choose a suitable graph database (such as Neo4j, JanusGraph, or TigerGraph) based on business needs and performance considerations;

[0084] In the chosen graph database, create a schema for nodes and edges based on the designed graph model; this may include creating node labels and attributes, defining the type and direction of relationships, and setting up indexes to optimize query performance;

[0085] 3. Data import and graph construction

[0086] Develop a data import process to import the underlying dataset into the graph database; this may involve using the import tools provided by the graph database or writing custom scripts to convert the data into a format supported by the graph database;

[0087] Create nodes and edges in the database and establish relationships between them; for example, create a node for each policyholder and a node for each insurance product, and create an edge connecting the two nodes based on the insurance record;

[0088] 4. Data verification and optimization

[0089] Verify that the imported data accurately reflects business entities and relationships; check the completeness and consistency of the data to ensure that there are no missing or incorrect connections;

[0090] Optimize the graph database based on query requirements and performance test results; this may include adjusting indexes, redesigning queries, or adjusting database configuration;

[0091] 5. Build a target relationship network

[0092] Leverage graph database query languages ​​(such as Cypher, Gremlin, etc.) to perform complex graph queries to identify and construct key risk paths and community structures;

[0093] Analyze graph data, identify high-risk patterns and trends, and build target relationship networks (i.e., insurance relationship networks) to provide support for risk assessment and decision-making;

[0094] Through the above process, it can be ensured that the graph model accurately reflects the complex relationships of the insurance business, and the data in the graph database can effectively support the needs of risk control and analysis.

[0095] Furthermore, the risk control method, wherein the step S300, implementing the GBFS path planning algorithm in the target relationship network to identify the key risk path of the risk control object, includes:

[0096] Setting a starting point node in the target relationship network;

[0097] Using the GBFS path planning algorithm to search for a path in the target relationship network starting from the starting point node;

[0098] Evaluating the potential risks of different paths in the target relationship network according to a preset path scoring function;

[0099] The path with the highest score is selected for expansion until the key risk path of the risk control object is identified.

[0100] In the specific implementation, in this embodiment, a starting point node is set in the target relationship network; a path is searched from the starting point node in the target relationship network using the GBFS path planning algorithm; the potential risks of different paths in the target relationship network are evaluated according to a preset path scoring function; the path with the highest score is selected for expansion until the key risk path of the risk control object is identified; wherein the specific implementation process is roughly as follows:

[0101] 1. Determine the starting point

[0102] According to the needs of risk control analysis, a node in the target relationship network is selected as the starting point of the search; this node may be a specific policyholder, insurance product or risk event, depending on the analysis objectives and context;

[0103] 2. Configure GBFS path planning algorithm parameters

[0104] Set the parameters of the GBFS (Generalized Best-First Search) path planning algorithm, including the path scoring function and search termination conditions; the path scoring function is used to evaluate the potential risk of each path, which may be based on risk probability, impact level, or other business-specific indicators; the search termination condition may be reaching a certain risk threshold, searching a specific node, or reaching the maximum search depth;

[0105] 3. Perform a GBFS search

[0106] Starting from the starting node, the GBFS path planning algorithm is used to search for a path in the target relationship network. The algorithm will evaluate each node according to the path scoring function and select the node with the highest current score for expansion. This process will be repeated until the preset search termination condition is met.

[0107] 4. Risk scoring and path selection

[0108] During the search, for each node, the algorithm considers all possible outgoing edges and calculates the path scores through these edges to reach the new node; the path with the highest score is selected for expansion and added to the candidate risk path set;

[0109] 5. Identify critical risk paths

[0110] After the search is completed, the path with the highest score is selected from the set of candidate risk paths as the key risk path; this may involve post-processing analysis of the highest-scoring paths to determine the most representative and influential risk path;

[0111] 6. Results Analysis and Application

[0112] Conduct in-depth analysis of identified key risk paths to understand the risk transmission mechanism and key influencing factors; formulate risk control measures and strategies based on the analysis results to reduce the impact of potential risks;

[0113] Through the above process, the GBFS path planning algorithm can efficiently identify key risk paths in complex insurance relationship networks and provide decision support for risk management and control.

[0114] Further, the risk control method, wherein the step S400, based on the key risk path, evaluates the risk level of the risk control object and generates a corresponding risk evaluation result;

[0115] In the specific implementation, in this embodiment, based on the key risk path, the risk level of the risk control object is evaluated to generate a corresponding risk assessment result; wherein the specific implementation process is roughly as follows:

[0116] 1. Key risk path analysis

[0117] Identify critical risk paths from the highest scoring paths obtained by the GBFS path planning algorithm; these paths represent potential risk propagation pathways or concentrated manifestations of risk factors;

[0118] 2. Risk Quantification

[0119] Quantify the risk factors on the key risk path; this may include assessing the probability of risk occurrence, the size of the possible loss, the duration of the risk, etc.; use statistical methods, historical data or expert opinions to estimate these quantitative indicators;

[0120] 3. Risk level assessment

[0121] Assign a risk level to each risk factor based on the quantified risk indicators; this usually involves a risk matrix that classifies risks into levels (e.g., low, medium, high) based on the probability of occurrence and impact of the risk;

[0122] 4. Comprehensive evaluation

[0123] Comprehensively consider all risk factors on the key risk paths and conduct an overall risk assessment of the risk control object; this may require weighting the importance of different risk factors or using a multi-criteria decision-making approach to determine the final risk level;

[0124] 5. Generate risk assessment report

[0125] Organize the risk assessment results into a risk assessment report; the report should include the risk assessment method, description of key risk paths, quantitative risk indicators, risk level assessment, and risk management recommendations;

[0126] 6. Formulation of risk control measures

[0127] Formulate corresponding risk control measures based on risk assessment results;

[0128] Through the above process, the accuracy and practicality of risk assessment can be ensured, while providing insurance companies with targeted risk management strategies and decision-making support.

[0129] Furthermore, in the risk control method, in step S500, based on the risk assessment result, corresponding risk control measures are adopted to perform risk control on the risk control object;

[0130] Furthermore, the risk control method, wherein, based on the risk assessment result, adopts corresponding risk control measures to control the risk of the risk control object, wherein the risk control measures include rejecting high-risk insurance applications, adjusting premium pricing and initiating investigation procedures.

[0131] In specific implementation, in this embodiment, based on the risk assessment results, corresponding risk control measures are adopted to control the risk of the risk control object; wherein, the risk control measures include rejecting high-risk insurance applications, adjusting premium pricing, and initiating investigation procedures; wherein, the specific implementation process is roughly as follows:

[0132] 1. Detailed analysis of risk assessment results

[0133] Based on the risk assessment reports generated previously, identify high-risk insurance applications, insurance products or specific risk factors; conduct in-depth analysis of these high-risk objects to determine the specific sources of risk and possible impacts;

[0134] 2. Determine risk control measures

[0135] Based on the risk assessment results, select appropriate risk control measures; this may include rejecting high-risk insurance applications to avoid potential large losses, adjusting premium pricing to reflect the actual risk level, or initiating investigation procedures to further understand the risk situation;

[0136] 3. Execute risk control decisions

[0137] For insurance applications that are assessed as high risk, clearly state the reasons and basis for rejection and send a formal rejection notice to the applicant; for situations where premium adjustment is required, recalculate the premium and communicate the reasons for adjustment and the new premium standard to the customer; for risk objects that require further investigation, formulate an investigation plan and allocate resources for in-depth analysis;

[0138] 4. Monitoring and feedback

[0139] After implementing risk control measures, establish a monitoring mechanism to track the effectiveness of the measures; collect relevant data, evaluate whether the risk control measures have effectively reduced risks, and make necessary adjustments based on feedback;

[0140] 5. Communication and Records

[0141] Communicate risk control measures and their results with internal teams and relevant parties to ensure transparency and consistency; at the same time, record the implementation details and effects of all risk control measures to provide reference for future risk control decisions;

[0142] Through the above process, insurance companies can effectively manage risks and protect companies from unnecessary losses while ensuring compliance and sustainable development of the business.

[0143] It can be seen from the above method embodiments that the risk control method provided by the present invention at least includes: obtaining business data related to the risk control object, and generating a corresponding basic data set after data processing of the business data; constructing a target relationship network based on the basic data set using graph storage technology; implementing the GBFS path planning algorithm in the target relationship network to identify the key risk path of the risk control object; based on the key risk path, evaluating the risk level of the risk control object and generating a corresponding risk assessment result; based on the risk assessment result, using corresponding risk control measures to control the risk of the risk control object; etc. In this way, the method of the present invention can solve the problem that the existing technology has the defects of low efficiency and poor accuracy when processing the relationship network of the risk control object, resulting in poor risk control effect for the existing risk control objects.

[0144] Specifically, the risk control method provided by the embodiment of the present invention can be used to identify and predict insurance risks to reduce the risk of insurance fraud; the method of the present invention uses a graph storage structure to represent a complex insurance relationship network, finds key risk paths through a GBFS path planning algorithm, and evaluates risk levels; compared with traditional methods, the method of the present invention can more comprehensively reveal complex insurance relationship networks, discover potential risk associations, and improve the accuracy and efficiency of risk control.

[0145] It should be understood that, although the present application provides method operation steps as described in the embodiments or flowcharts, more or less operation steps may be included based on conventional or non-creative labor, and these operation steps are not necessarily performed in sequence according to the embodiment or flowchart. The order of steps listed in the embodiment or flowchart is only one way of executing the order of many steps, and does not represent the only execution order. It should be noted that there is not necessarily a certain order between the above steps. A person of ordinary skill in the art can understand from the description of the embodiment of the present invention that in different embodiments, the above steps may have different execution orders, that is, they may be executed in parallel, or they may be executed in exchange, etc. Moreover, at least a part of the steps in the embodiment or flowchart may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but may be executed at different times, and the execution order of these sub-steps or stages is not necessarily performed in sequence, but may be executed in turn, alternately or synchronously with other steps or at least a part of the sub-steps or stages of other steps.

[0146] Based on the above method embodiment, please refer to Figure 2 Another embodiment of the present invention further provides a risk control system, wherein the system comprises:

[0147] The data processing module 11 is used to obtain business data related to the risk control object, and generate a corresponding basic data set after processing the business data;

[0148] A network construction module 12 is used to construct a target relationship network based on the basic data set using graph storage technology;

[0149] A path identification module 13 is used to implement the GBFS path planning algorithm in the target relationship network to identify the key risk path of the risk control object;

[0150] The risk assessment module 14 is used to assess the risk level of the risk control object based on the key risk path and generate a corresponding risk assessment result;

[0151] The risk control module 15 is used to perform risk control on the risk control object by adopting corresponding risk control measures based on the risk assessment result.

[0152] Furthermore, the risk control system, wherein the business data related to the risk control object is obtained and the corresponding basic data set is generated after data processing of the business data, includes:

[0153] Obtain business data related to risk control objects from the business database;

[0154] After data cleaning, data integration and data standardization processing are performed on the business data, a corresponding basic data set is generated.

[0155] Furthermore, in the risk control system, the step of obtaining business data related to the risk control object in the business database includes:

[0156] Obtain insurance business data related to risk control objects from the insurance business database;

[0157] Among them, the risk control object is the insurance product, and the insurance business data includes policyholder information, insured person information, insurance product information and claim records, etc.

[0158] In the specific implementation, in this embodiment, insurance business data related to the risk control object is obtained in the insurance business database; wherein the risk control object is an insurance product, and the insurance business data includes information of the policyholder, information of the insured, information of the insurance product, and claim settlement records, etc.; after data cleaning, data integration, and data standardization processing are performed on the business data, a corresponding basic data set is generated; wherein the specific implementation process is roughly as follows:

[0159] 1. Data extraction

[0160] Extract relevant insurance business data from the insurance business database according to the risk control object (i.e., insurance product), including information of the policyholder (such as name, age, occupation, etc.), information of the insured (such as health status, historical risk record, etc.), insurance product information (such as insurance terms, premiums, insurance liability, etc.), and claims records (such as claim amount, claim time, claim reason, etc.);

[0161] 2. Data cleaning

[0162] Clean the extracted data to improve data quality, including removing duplicate records, correcting erroneous data items, handling missing values ​​(for example, by interpolating or deleting records with missing values), and identifying and deleting abnormal values ​​or outliers; the cleaning process ensures the accuracy and consistency of the data set, laying a solid foundation for subsequent analysis;

[0163] 3. Data Integration

[0164] Integrate the cleaned data as needed; this may involve merging data sets from different data sources or databases to ensure the consistency of the data in logic and format; for example, associating the policyholder information with the corresponding insurance product information to form a complete customer profile;

[0165] 4. Data Standardization

[0166] Standardize the integrated data, including unifying data formats, encodings, and metrics; for example, standardize the date format to YYYY-MM-DD, convert all text data to a unified case format, and ensure that all numerical data uses consistent units of measurement;

[0167] 5. Data Verification and Quality Assessment

[0168] After data cleaning, integration and standardization, data validation and quality assessment are performed to ensure that the data set meets the requirements of subsequent processes; this may include data integrity checks, logical consistency verification and data quality scoring;

[0169] 6. Generate basic data set

[0170] After completing steps 1-5 above, the processed data is organized into a structured form to generate a basic data set; this basic data set will serve as the starting point for risk assessment and analysis, providing the necessary data support for building an insurance relationship network and implementing risk control algorithms;

[0171] Through the above process, it can be ensured that the data extracted from the insurance business database is clean, consistent, accurate and reliable, providing a high-quality data foundation for insurance risk control analysis.

[0172] Furthermore, the risk control system, wherein the target relationship network is constructed based on the basic data set using graph storage technology, includes:

[0173] Design the graph model according to business requirements and define the data structure of its nodes and edges;

[0174] Select a corresponding graph database, and create a pattern of nodes and edges in the graph database according to the designed graph model;

[0175] The basic data set is imported into the graph database, the relationship between nodes and edges is established, and the corresponding target relationship network is obtained.

[0176] Furthermore, in the risk control system, a corresponding graph database is selected, and a node and edge pattern is created in the graph database according to a designed graph model, wherein the graph database includes Neo4j, JanusGraph and TigerGraph.

[0177] In the specific implementation, in this embodiment, a graph model is designed according to business requirements, and the data structure of its nodes and edges is defined; a corresponding graph database is selected, and a node and edge pattern is created in the graph database according to the designed graph model; the basic data set is imported into the graph database, the relationship between nodes and edges is established, and the corresponding target relationship network is obtained; wherein the specific implementation process is roughly as follows:

[0178] 1. Requirements analysis and graph model design

[0179] Work with the business team to clarify business needs and goals, identify key entities (such as policyholders, insured persons, insurance products) and the relationships between them (such as insurance relationships, claims records);

[0180] Design a graph model to define the data structure of nodes (including node type and attributes) and edge data structure (including edge type, direction, and attributes); for example, a policyholder node may contain attributes such as age and occupation; an insurance product node may contain attributes such as premium and insurance coverage; an edge may represent an insurance relationship and have attributes such as start time and insurance period;

[0181] 2. Select a graph database and create a schema

[0182] Choose a suitable graph database (such as Neo4j, JanusGraph, or TigerGraph) based on business needs and performance considerations;

[0183] In the chosen graph database, create a schema for nodes and edges based on the designed graph model; this may include creating node labels and attributes, defining the type and direction of relationships, and setting up indexes to optimize query performance;

[0184] 3. Data import and graph construction

[0185] Develop a data import process to import the underlying dataset into the graph database; this may involve using the import tools provided by the graph database or writing custom scripts to convert the data into a format supported by the graph database;

[0186] Create nodes and edges in the database and establish relationships between them; for example, create a node for each policyholder and a node for each insurance product, and create an edge connecting the two nodes based on the insurance record;

[0187] 4. Data verification and optimization

[0188] Verify that the imported data accurately reflects business entities and relationships; check the completeness and consistency of the data to ensure that there are no missing or incorrect connections;

[0189] Optimize the graph database based on query requirements and performance test results; this may include adjusting indexes, redesigning queries, or adjusting database configuration;

[0190] 5. Build a target relationship network

[0191] Leverage graph database query languages ​​(such as Cypher, Gremlin, etc.) to perform complex graph queries to identify and construct key risk paths and community structures;

[0192] Analyze graph data, identify high-risk patterns and trends, and build target relationship networks (i.e., insurance relationship networks) to provide support for risk assessment and decision-making;

[0193] Through the above process, it can be ensured that the graph model accurately reflects the complex relationships of the insurance business, and the data in the graph database can effectively support the needs of risk control and analysis.

[0194] Furthermore, the risk control system, wherein the GBFS path planning algorithm is implemented in the target relationship network to identify the key risk path of the risk control object, includes:

[0195] Setting a starting point node in the target relationship network;

[0196] Using the GBFS path planning algorithm to search for a path in the target relationship network starting from the starting point node;

[0197] Evaluating the potential risks of different paths in the target relationship network according to a preset path scoring function;

[0198] The path with the highest score is selected for expansion until the key risk path of the risk control object is identified.

[0199] In the specific implementation, in this embodiment, a starting point node is set in the target relationship network; a path is searched from the starting point node in the target relationship network using the GBFS path planning algorithm; the potential risks of different paths in the target relationship network are evaluated according to a preset path scoring function; the path with the highest score is selected for expansion until the key risk path of the risk control object is identified; wherein the specific implementation process is roughly as follows:

[0200] 1. Determine the starting point

[0201] According to the needs of risk control analysis, a node in the target relationship network is selected as the starting point of the search; this node may be a specific policyholder, insurance product or risk event, depending on the analysis objectives and context;

[0202] 2. Configure GBFS path planning algorithm parameters

[0203] Set the parameters of the GBFS (Generalized Best-First Search) path planning algorithm, including the path scoring function and search termination conditions; the path scoring function is used to evaluate the potential risk of each path, which may be based on risk probability, impact level, or other business-specific indicators; the search termination condition may be reaching a certain risk threshold, searching a specific node, or reaching the maximum search depth;

[0204] 3. Perform a GBFS search

[0205] Starting from the starting node, the GBFS path planning algorithm is used to search for a path in the target relationship network. The algorithm will evaluate each node according to the path scoring function and select the node with the highest current score for expansion. This process will be repeated until the preset search termination condition is met.

[0206] 4. Risk scoring and path selection

[0207] During the search, for each node, the algorithm considers all possible outgoing edges and calculates the path scores through these edges to reach the new node; the path with the highest score is selected for expansion and added to the candidate risk path set;

[0208] 5. Identify critical risk paths

[0209] After the search is completed, the path with the highest score is selected from the set of candidate risk paths as the key risk path; this may involve post-processing analysis of the highest-scoring paths to determine the most representative and influential risk path;

[0210] 6. Results Analysis and Application

[0211] Conduct in-depth analysis of identified key risk paths to understand the risk transmission mechanism and key influencing factors; formulate risk control measures and strategies based on the analysis results to reduce the impact of potential risks;

[0212] Through the above process, the GBFS path planning algorithm can efficiently identify key risk paths in complex insurance relationship networks and provide decision support for risk management and control.

[0213] Furthermore, the risk control system, wherein the risk level of the risk control object is evaluated based on the key risk path to generate a corresponding risk evaluation result;

[0214] In the specific implementation, in this embodiment, based on the key risk path, the risk level of the risk control object is evaluated to generate a corresponding risk assessment result; wherein the specific implementation process is roughly as follows:

[0215] 1. Key risk path analysis

[0216] Identify critical risk paths from the highest scoring paths obtained by the GBFS path planning algorithm; these paths represent potential risk propagation pathways or concentrated manifestations of risk factors;

[0217] 2. Risk Quantification

[0218] Quantify the risk factors on the key risk path; this may include assessing the probability of risk occurrence, the size of the possible loss, the duration of the risk, etc.; use statistical methods, historical data or expert opinions to estimate these quantitative indicators;

[0219] 3. Risk level assessment

[0220] Assign a risk level to each risk factor based on the quantified risk indicators; this usually involves a risk matrix that classifies risks into levels (e.g., low, medium, high) based on the probability of occurrence and impact of the risk;

[0221] 4. Comprehensive evaluation

[0222] Comprehensively consider all risk factors on the key risk paths and conduct an overall risk assessment of the risk control object; this may require weighting the importance of different risk factors or using a multi-criteria decision-making approach to determine the final risk level;

[0223] 5. Generate risk assessment report

[0224] Organize the risk assessment results into a risk assessment report; the report should include the risk assessment method, description of key risk paths, quantitative risk indicators, risk level assessment, and risk management recommendations;

[0225] 6. Formulation of risk control measures

[0226] Formulate corresponding risk control measures based on risk assessment results;

[0227] Through the above process, the accuracy and practicality of risk assessment can be ensured, while providing insurance companies with targeted risk management strategies and decision-making support.

[0228] Furthermore, the risk control system, wherein, based on the risk assessment result, corresponding risk control measures are adopted to perform risk control on the risk control object;

[0229] Furthermore, the risk control system, wherein, based on the risk assessment results, adopts corresponding risk control measures to perform risk control on the risk control object, wherein the risk control measures include rejecting high-risk insurance applications, adjusting premium pricing, and initiating investigation procedures.

[0230] In specific implementation, in this embodiment, based on the risk assessment results, corresponding risk control measures are adopted to control the risk of the risk control object; wherein, the risk control measures include rejecting high-risk insurance applications, adjusting premium pricing, and initiating investigation procedures; wherein, the specific implementation process is roughly as follows:

[0231] 1. Detailed analysis of risk assessment results

[0232] Based on the risk assessment reports generated previously, identify high-risk insurance applications, insurance products or specific risk factors; conduct in-depth analysis of these high-risk objects to determine the specific sources of risk and possible impacts;

[0233] 2. Determine risk control measures

[0234] Based on the risk assessment results, select appropriate risk control measures; this may include rejecting high-risk insurance applications to avoid potential large losses, adjusting premium pricing to reflect the actual risk level, or initiating investigation procedures to further understand the risk situation;

[0235] 3. Execute risk control decisions

[0236] For insurance applications that are assessed as high risk, clearly state the reasons and basis for rejection and send a formal rejection notice to the applicant; for situations where premium adjustment is required, recalculate the premium and communicate the reasons for adjustment and the new premium standard to the customer; for risk objects that require further investigation, formulate an investigation plan and allocate resources for in-depth analysis;

[0237] 4. Monitoring and feedback

[0238] After implementing risk control measures, establish a monitoring mechanism to track the effectiveness of the measures; collect relevant data, evaluate whether the risk control measures have effectively reduced risks, and make necessary adjustments based on feedback;

[0239] 5. Communication and Records

[0240] Communicate risk control measures and their results with internal teams and relevant parties to ensure transparency and consistency; at the same time, record the implementation details and effects of all risk control measures to provide reference for future risk control decisions;

[0241] Through the above process, insurance companies can effectively manage risks and protect companies from unnecessary losses while ensuring compliance and sustainable development of the business.

[0242] It can be seen from the above system embodiments that the risk control system provided by the present invention at least includes: obtaining business data related to the risk control object, and generating a corresponding basic data set after data processing of the business data; constructing a target relationship network based on the basic data set using graph storage technology; implementing the GBFS path planning algorithm in the target relationship network to identify the key risk path of the risk control object; based on the key risk path, evaluating the risk level of the risk control object and generating a corresponding risk assessment result; based on the risk assessment result, adopting corresponding risk control measures to control the risk of the risk control object; etc. In this way, the system of the present invention can solve the problem that the existing technology has the defects of low efficiency and poor accuracy in processing the relationship network of the risk control object, resulting in poor risk control effect for the existing risk control objects.

[0243] Specifically, the risk control system provided by the embodiment of the present invention can be used to identify and predict insurance risks to reduce the risk of insurance fraud; the system of the present invention uses a graph storage structure to represent a complex insurance relationship network, finds key risk paths through the GBFS path planning algorithm, and evaluates the risk level; compared with traditional systems, the system of the present invention can more comprehensively reveal complex insurance relationship networks, discover potential risk associations, and improve the accuracy and efficiency of risk control.

[0244] Based on the above method embodiment, please refer to Figure 3 Another embodiment of the present invention further provides a computer device, wherein the computer device 10 includes:

[0245] memory 120 and one or more processors 110, Figure 3 A processor 110 is used as an example for description. The processor 110 and the memory 120 may be connected via a communication bus or other means. Figure 3 The example of connection via a communication bus is taken as an example.

[0246] The processor 110 is used to complete various control logics of the computer device 10. It can be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA), a single-chip microcomputer, an ARM (Acorn RISC Machine) or other programmable logic device, a discrete gate or transistor logic, a discrete hardware component, or any combination of these components. In addition, the processor 110 can also be any traditional processor, microprocessor or state machine. The processor 110 can also be implemented as a combination of computing devices, for example, a combination of a DSP and a microprocessor, a plurality of microprocessors, one or more microprocessors combined with a DSP, or any other such configuration.

[0247] The memory 120 is a non-volatile computer-readable storage medium that can be used to store non-volatile software programs, non-volatile computer executable programs and modules, such as the computer program corresponding to the risk control method in the embodiment of the present invention. The processor 110 executes various functional applications and data processing of the computer device 10 by running the non-volatile software programs, instructions and units stored in the memory 120, that is, implements the risk control method in the above method embodiment.

[0248] The memory 120 may include a program storage area and a data storage area, wherein the program storage area may store an application required for operating the device or at least one function; the data storage area may store data created according to the use of the computer device 10, etc. In addition, the memory 120 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some embodiments, the memory 120 may optionally include a memory remotely arranged relative to the processor 110, and these remote memories may be connected to the computer device 10 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0249] One or more units are stored in the memory 120, and when executed by one or more processors 110, a risk control method as in any of the above method embodiments may be implemented, for example, the risk control method described above may be implemented. Figure 1 The method comprises steps S100 to S500.

[0250] Those skilled in the art will understand that Figure 3 The hardware structure diagram shown in the figure is only a schematic diagram of a partial structure related to the solution of the present invention, and does not constitute a limitation on the computer device to which the solution of the present invention is applied. The specific computer device may include more components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0251] Based on the above method embodiments, another embodiment of the present invention further provides a non-volatile computer-readable storage medium, wherein the non-volatile computer-readable storage medium stores a computer program, and when the computer program is executed by at least one processor, the risk control method in any of the above method embodiments can be implemented, for example, the risk control method described above can be implemented. Figure 1 The method comprises steps S100 to S500.

[0252] As an example, the non-volatile storage medium can include a read-only memory (ROM), a programmable ROM (PROM), an electrically programmable ROM (EPROM), an electrically erasable ROM (EEPROM), or a flash memory. Volatile memory can include a random access memory (RAM) as an external cache memory. By way of illustration and not limitation, RAM can be obtained in many forms such as synchronous RAM (SRAM), dynamic RAM, (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), Synch link DRAM (SLDRAM), and direct Rambus RAM (DRRAM). The disclosed memory components or memories of the operating environment described herein are intended to include one or more of these and / or any other suitable types of memory.

[0253] Based on the above method embodiments, another embodiment of the present invention further provides a computer program product, the computer program product includes a computer program stored on a non-volatile computer-readable storage medium, the computer program includes program instructions, when the program instructions are executed by a processor, the risk control method in any of the above method embodiments can be implemented, for example, the risk control method described above can be implemented Figure 1 The method comprises steps S100 to S500.

[0254] The embodiments described above are merely illustrative, in which the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0255] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a general hardware platform, and of course can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the relevant technology can be embodied in the form of a software product, and the computer software product can exist in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods of each embodiment or some parts of the embodiment.

[0256] Conditional language such as "can," "can," "might," or "may," unless specifically stated otherwise or otherwise understood within the context as used, is generally intended to convey, among other things, that a particular embodiment can include (while other embodiments do not) a particular feature, element, and / or operation. Thus, such conditional language is also generally intended to imply that a feature, element, and / or operation is required for one or more embodiments anyway or that one or more embodiments must include logic for determining, with or without input or prompting, whether such features, elements, and / or operations are included or will be performed in any particular embodiment.

[0257] What has been described herein, in this specification and in the accompanying drawings includes examples that can provide a risk control method, system, computer device, and non-volatile computer-readable storage medium. Of course, it is not possible to describe every conceivable combination of elements and / or methods for the purpose of describing the various features of the present disclosure, but it can be recognized that many other combinations and permutations of the disclosed features are possible. Therefore, it is obvious that various modifications can be made to the present disclosure without departing from the scope or spirit of the present disclosure, but all these various modifications should belong to the scope of protection of the claims attached to the present invention. In addition, or in an alternative, other embodiments of the present disclosure may be obvious from consideration of the present specification and the accompanying drawings and from the practice of the present disclosure as presented herein. It is intended that the examples proposed in the present specification and the accompanying drawings are considered to be illustrative and not restrictive in all respects. Although specific terms are used herein, they are used in a general and descriptive sense and are not used for limiting purposes.

Claims

1. A risk control method, It is characterized in that include: Obtaining business data related to the risk control object, and generating corresponding basic data sets after data processing on the business data; Based on the basic data set, a target relationship network is constructed using graph storage technology; Implementing the GBFS path planning algorithm in the target relationship network to identify the key risk path of the risk control object; Based on the key risk path, the risk level of the risk control object is evaluated to generate a corresponding risk assessment result; Based on the risk assessment results, corresponding risk control measures are adopted to perform risk control on the risk control object.

2. According to the risk control method of claim 1, It is characterized in that The obtaining of business data related to the risk control object and processing of the business data to generate a corresponding basic data set includes: Obtain business data related to risk control objects from the business database; After data cleaning, data integration and data standardization processing are performed on the business data, a corresponding basic data set is generated.

3. According to the risk control method of claim 2, It is characterized in that The target relationship network is constructed based on the basic data set using graph storage technology, including: Design the graph model according to business requirements and define the data structure of its nodes and edges; Select a corresponding graph database, and create a pattern of nodes and edges in the graph database according to the designed graph model; The basic data set is imported into the graph database, the relationship between nodes and edges is established, and the corresponding target relationship network is obtained.

4. According to the risk control method of claim 3, It is characterized in that Implementing the GBFS path planning algorithm in the target relationship network to identify the key risk path of the risk control object includes: Setting a starting point node in the target relationship network; Using the GBFS path planning algorithm to search for a path in the target relationship network starting from the starting point node; Evaluating the potential risks of different paths in the target relationship network according to a preset path scoring function; The path with the highest score is selected for expansion until the key risk path of the risk control object is identified.

5. The risk control method according to claim 4, It is characterized in that The business data related to the risk control object is obtained in the business database, including: Obtain insurance business data related to risk control objects from the insurance business database; Among them, the risk control object is an insurance product, and the insurance business data includes policyholder information, insured person information, insurance product information and claim records.

6. The risk control method according to claim 5, It is characterized in that The corresponding graph database is selected, and a node and edge pattern is created in the graph database according to the designed graph model, wherein the graph database includes Neo4j, JanusGraph and TigerGraph.

7. The risk control method according to claim 6, It is characterized in that Based on the risk assessment results, corresponding risk control measures are adopted to control the risk of the risk control object, wherein the risk control measures include rejecting high-risk insurance applications, adjusting premium pricing and initiating investigation procedures.

8. A risk control system, It is characterized in that include: The data processing module is used to obtain business data related to the risk control object, and generate a corresponding basic data set after processing the business data; A network construction module, used to construct a target relationship network based on the basic data set using graph storage technology; A path identification module, used to implement the GBFS path planning algorithm in the target relationship network to identify the key risk path of the risk control object; A risk assessment module, used to assess the risk level of the risk control object based on the key risk path and generate a corresponding risk assessment result; The risk control module is used to perform risk control on the risk control object by adopting corresponding risk control measures based on the risk assessment result.

9. A computer device, It is characterized in that The computer device comprises at least one processor; and, a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor. When the computer program is executed by the at least one processor, the risk control method as described in any one of claims 1 to 7 can be implemented.

10. A non-volatile computer-readable storage medium, It is characterized in that The non-volatile computer-readable storage medium stores a computer program, and when the computer program is executed by at least one processor, the risk control method according to any one of claims 1 to 7 can be implemented.