Risk control method and device, electronic equipment and storage medium

Abstract

The invention discloses a risk control method and device, electronic equipment and a storage medium. According to the specific implementation scheme, the method comprises the steps of obtaining to-be-audited data information uploaded by a user; identifying the to-be-audited data information according to a medical risk rule and a financial risk rule of a preset risk identification rule base to obtain a customer risk level of the to-be-audited data information; and determining service limitation conditions of the user according to the customer risk level. According to the embodiment of the invention, comprehensive intelligent risk identification and effective management are realized, accurate prediction of the risk level is ensured, the risk identification efficiency is improved, the risk leakage is reduced, and the user experience is improved.

Description

Technical Field

[0001] The present invention relates to the field of risk control technology, and in particular to a risk control method, device, electronic equipment and storage medium. Background Art

[0002] With the popularization of Internet technology and the rise of big data, the massive growth of user information and the rapid evolution of business models have made risk control increasingly difficult, especially in the financial and medical fields, where data authenticity and accuracy are extremely high, and any negligence of risk may have very serious consequences. At present, traditional risk control methods mainly rely on manual offline verification, which is not only inefficient, but also difficult to meet the accuracy requirements of modern business. In addition, the formulation and implementation of traditional risk control methods are difficult to adapt to the needs of both the financial and medical fields at the same time, making it impossible for risk control methods to fully exert their due effectiveness. Therefore, realizing comprehensive and intelligent risk identification and effective risk management, and ensuring accurate prediction of risk levels are issues that need to be urgently addressed in the current field of risk control technology. Summary of the invention

[0003] The present invention provides a risk control method, device, electronic device and storage medium. The embodiments of the present invention realize comprehensive intelligent identification and effective management of risks, ensure accurate prediction of risk levels, improve risk identification efficiency, reduce risk leakage, and enhance user experience.

[0004] In one aspect of an embodiment of the present invention, a risk control method is provided, comprising:

[0005] Get the information of the materials uploaded by the user that are pending for review;

[0006] Identify the information to be reviewed based on the medical risk rules and financial risk rules of the preset risk identification rule base, and obtain the customer risk level of the information to be reviewed;

[0007] Determine service restrictions for users based on their risk level.

[0008] Another aspect of an embodiment of the present invention provides a risk control device, including:

[0009] The information acquisition module is used to obtain the information of the materials to be reviewed uploaded by the user;

[0010] The risk level module is used to identify the information to be reviewed based on the medical risk rules and financial risk rules of the preset risk identification rule library, and obtain the customer risk level of the information to be reviewed;

[0011] The risk control module is used to determine the service restrictions for users based on their risk levels.

[0012] Another aspect of an embodiment of the present invention provides an electronic device, including:

[0013] at least one processor;

[0014] and a memory communicatively coupled to the at least one processor;

[0015] The memory stores a computer program that can be executed by at least one processor, and the computer program is executed by at least one processor so that the at least one processor can execute the risk control method of any embodiment of the present invention.

[0016] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the risk control method of any embodiment of the present invention when executed.

[0017] In an embodiment of the present invention, information on pending documents uploaded by a user that contains various information of the user and needs to be verified and evaluated is obtained, a preset risk identification rule library is obtained, and a medical risk rule for identifying and evaluating potential risks of the pending documents in the medical field and a financial risk rule for identifying and evaluating potential risks of the pending documents in the financial field are searched in the preset risk identification rule library, and the pending documents uploaded by the user are identified and evaluated based on the found medical risk rules and financial risk rules, and the pending documents are compared with the medical risk rules and the financial risk rules one by one, and the user is divided into different risk levels based on the comparison results, and the different risk levels are used as customer risk levels of the pending documents, and the service restriction conditions of the user are further analyzed and determined based on the obtained customer risk levels, and services with corresponding restriction requirements are provided to the user based on the service restriction conditions of the user. The embodiment of the present invention utilizes the medical risk rules and financial risk rules in the preset risk identification rule library to identify the information of the materials to be reviewed, thereby realizing comprehensive intelligent identification and effective management of risks, ensuring the accurate prediction of risk levels, improving the efficiency of risk identification, determining the service restriction conditions for users based on the customer risk level, and providing users with services with corresponding restriction requirements based on the obtained service restriction conditions, thereby reducing risk leakage and improving user experience.

[0018] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0020] Figure 1 is a flow chart of a risk control method provided according to Embodiment 1 of the present invention;

[0021] Figure 2 is a flow chart of another risk control method provided according to the second embodiment of the present invention;

[0022] Figure 3 is a flow chart of another risk control method provided according to Embodiment 3 of the present invention;

[0023] Figure 4 This is a financial payment application flow chart provided by Embodiment 4 of the present invention;

[0024] Figure 5 This is a flow chart of an application for hospital admission in installments provided by Embodiment 4 of the present invention;

[0025] Figure 6 This is a full-platform full-process risk control flow chart provided by the fourth embodiment of the present invention;

[0026] Figure 7 This is a fraud identification process flow chart provided by Embodiment 4 of the present invention;

[0027] Figure 8 It is a schematic diagram of the structure of a risk control device implementing an embodiment of the present invention;

[0028] Fig. 9 It is a block diagram of an electronic device for executing the risk control method according to an embodiment of the present invention. DETAILED DESCRIPTION

[0029] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0030] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0031] Embodiment 1

[0032] Figure 1 A flow chart of a risk control method is provided for the first embodiment of the present invention. The embodiment of the present invention is applicable to the situation of controlling the potential risks of the platform. The method can be executed by a risk control device. The risk control device can be implemented in the form of hardware and / or software. The risk control device can be configured in an electronic device. Figure 1 As shown, the method includes:

[0033] S101, obtaining the information of the documents to be reviewed uploaded by the user.

[0034] In the embodiment of the present invention, the information to be reviewed can be understood as a group of information that needs to be verified and evaluated. For example, the information to be reviewed can include: medical information of the user or financial information of the user.

[0035] Specifically, the information of pending review materials uploaded by the user, which contains various information of the user and needs to be verified and evaluated, can be obtained, and the pending review materials can be stored to provide a data basis for subsequent risk assessment. For example, the method of obtaining the user's pending review materials can include: obtaining it by the user dragging the pending review materials to the designated area on the front-end interface or by the user clicking the upload button and selecting the pending review materials from the local file system for uploading.

[0036] S102. Identify the information to be reviewed based on the medical risk rules and financial risk rules of the preset risk identification rule library to obtain the customer risk level of the information to be reviewed.

[0037] In an embodiment of the present invention, the preset risk identification rule base can be understood as a database containing multiple risk identification standards, which is used to automatically identify and evaluate potential risks in the information to be reviewed, wherein the preset risk identification rule base at least includes: medical risk rules and financial risk rules.

[0038] Medical risk rules can be understood as a series of preset standards used to identify and evaluate the potential risks of the information to be reviewed in the medical field. For example, medical risk rules may include: rules for determining whether a prescription is compliant or rules for determining whether a medical record is complete.

[0039] Financial risk rules can be understood as a series of preset conditions used to identify and evaluate the potential risks of the information to be reviewed in the financial field. For example, financial risk rules may include: evaluation rules for determining user credit scores or evaluation rules for determining whether user transaction behaviors are compliant.

[0040] Customer risk level can be understood as an assessment result of the user's risk status, where the customer risk level is usually divided into different risk levels. For example, the customer risk level can be divided into four risk levels: major risk, greater risk, general risk and low risk, or divided into three risk levels: high risk, medium risk and low risk.

[0041] Specifically, a pre-set preset risk identification rule library is obtained, and medical risk rules for identifying and evaluating potential risks of information to be reviewed in the medical field and financial risk rules for identifying and evaluating potential risks of information to be reviewed in the financial field are searched in the preset risk identification rule library; based on the found medical risk rules and financial risk rules, the information to be reviewed uploaded by the user is identified and evaluated, and the information to be reviewed is compared with the medical risk rules and the financial risk rules one by one; based on the comparison results, the users are divided into different risk levels, and the different risk levels are used as the customer risk levels of the information to be reviewed.

[0042] S103. Determine a service restriction condition for the user according to the customer risk level, wherein the service restriction condition includes at least one of the following: usage scenario, usage limit, and risk restriction strategy.

[0043] In the embodiment of the present invention, the service restriction condition can be understood as a specific service restriction requirement set for different customer risk levels. For example, the service restriction condition at least includes: usage scenario, usage quota and risk restriction strategy.

[0044] The usage scenario can be understood as the specific environment in which the user uses the service. For example, the usage scenario may include: hospitalization payment scenario or medication payment scenario.

[0045] The usage limit can be understood as the maximum amount that can be used within a certain period of time. For example, the usage limit may include: 10,000 yuan per week or 3,000 yuan per day.

[0046] The risk limit strategy can be understood as a specific rule that aims to establish a clear relationship between the usage scenario and the usage limit of the service according to the customer's risk level. For example, in the hospitalization payment scenario, the maximum amount allowed per week is 20,000 yuan or in the drug payment scenario, the maximum amount allowed per day is 1,000 yuan.

[0047] Specifically, based on the preset risk identification rule base, the information on the audited materials is identified to obtain the customer risk level, and based on the obtained customer risk level, the user's service restriction conditions are further analyzed and determined, and based on the user's service restriction conditions, services with corresponding restriction requirements are provided to the user, wherein the service restriction conditions include at least usage scenarios, usage limits and risk limitation strategies.

[0048] In an embodiment of the present invention, information on pending documents uploaded by a user that contains various information of the user and needs to be verified and evaluated is obtained, a preset risk identification rule library is obtained, and a medical risk rule for identifying and evaluating potential risks of the pending documents in the medical field and a financial risk rule for identifying and evaluating potential risks of the pending documents in the financial field are searched in the preset risk identification rule library, and the pending documents uploaded by the user are identified and evaluated based on the found medical risk rules and financial risk rules, and the pending documents are compared with the medical risk rules and the financial risk rules one by one, and the user is divided into different risk levels based on the comparison results, and the different risk levels are used as customer risk levels of the pending documents, and the service restriction conditions of the user are further analyzed and determined based on the obtained customer risk levels, and services with corresponding restriction requirements are provided to the user based on the service restriction conditions of the user. The embodiment of the present invention utilizes the medical risk rules and financial risk rules in the preset risk identification rule library to identify the information of the materials to be reviewed, thereby realizing the intelligent and comprehensive identification and effective management of risks, ensuring the accurate prediction of the risk level, improving the efficiency of risk identification, determining the service restriction conditions of the user based on the customer's risk level, and providing the user with services with corresponding restriction requirements according to the obtained service restriction conditions, thereby reducing risk leakage and improving the user experience.

[0049] Embodiment 2

[0050] Figure 2 This is a flow chart of another risk control method provided by Embodiment 2 of the present invention. Based on the above embodiments, this embodiment of the present invention provides another risk control method. Figure 2 As shown, the method includes:

[0051] S201, receiving authorization verification information and user information uploaded by the user.

[0052] In the embodiment of the present invention, the authorization verification information can be understood as information used to confirm the authority to access user information. For example, the authorization verification information can include: fingerprint information or facial recognition information and other information.

[0053] User information can be understood as a comprehensive document that includes various data of the user. For example, user information may include: user medical data or user financial data.

[0054] Specifically, the authorization verification information uploaded by the user for confirming the authority to access the user information and the user information containing various user data are received to provide user information support for subsequent operations.

[0055] S202: Collect the user's historical transaction data and historical behavior data from a preset data source according to the authorization verification information.

[0056] In the embodiment of the present invention, the preset data source can be understood as a database for storing historical data of the user, wherein the preset data source at least includes: historical transaction data and historical behavior data.

[0057] Historical transaction data can be understood as transaction records of previous transactions conducted by the user. For example, historical transaction data may include data such as transaction amount or transaction time.

[0058] Historical behavior data can be understood as the user's previous activity records. For example, historical behavior data may include: browsing service records or the frequency of applying for and using services.

[0059] Specifically, obtain the user's authorization verification information, obtain the authority to collect historical transaction data and historical behavior data based on the authorization verification information provided by the user, and extract the user's historical transaction data and the user's historical behavior data from a preset data source that stores the user's historical data.

[0060] S203: Use user information, historical transaction data, and historical behavior data as information to be reviewed.

[0061] Specifically, the user's user information, historical transaction data, and historical behavior data are obtained, the user information, historical transaction data, and historical behavior data are integrated, and the integrated data set is used as the information to be reviewed.

[0062] S204. Searching for a target risk rule that matches the user information in the information to be reviewed in a preset risk identification rule library, wherein the target risk rule includes at least a medical risk rule and a financial risk rule.

[0063] In an embodiment of the present invention, the target risk rules can be understood as a set of predefined standards for identifying and evaluating potential risks existing in user information in the data to be reviewed, wherein the target risk rules include at least: medical risk rules and financial risk rules.

[0064] Specifically, different risk rules are created for different user information in the preset risk identification rule library, and the user information is extracted from the user's pending information. The extracted user information is compared one by one with all the risk rules contained in the preset risk identification rule library to find the target risk rules that match the user information, and the user information is assessed for risk based on the target risk rules, wherein the target risk rules include at least two categories: medical risk rules and financial risk rules.

[0065] For example, a method of searching for a target risk rule that matches a user profile in a preset risk identification rule library may include: automatically identifying key fields in the user profile based on the user profile uploaded by the user, automatically searching for a risk rule that is the same as the key field of the user profile in the preset risk identification rule library, and using the risk rule as the target risk rule for the user profile, or, the user directly selects a corresponding risk rule from the preset risk identification rule library as the target risk rule when uploading the user profile.

[0066] S205. Split the information to be reviewed into medical information to be reviewed and financial information to be reviewed.

[0067] In the embodiment of the present invention, the medical information to be reviewed can be understood as all medical-related information separated from the data information to be reviewed. For example, the medical information to be reviewed can include: drug usage or diagnosis records.

[0068] The financial information to be reviewed can be understood as all financial-related information separated from the data information to be reviewed. For example, the financial information to be reviewed may include: credit card usage records or bank account balances.

[0069] Specifically, the user's pending information is obtained, and the user's pending information is classified and identified according to certain splitting criteria, and two types of information are identified from the pending information: medical information related to medical treatment and financial information related to finance.

[0070] For example, the splitting criteria may include: classifying information containing keywords such as "disease", "diagnosis", and "treatment" in the information to be reviewed as medical information to be reviewed, and classifying information containing keywords such as "account", "transaction", and "loan" in the information to be reviewed as financial information to be reviewed.

[0071] S206. Determine the medical knowledge graph that matches the medical risk rules, and determine the medical risk factors of the medical information to be reviewed based on the medical knowledge graph.

[0072] In an embodiment of the present invention, the medical knowledge graph can be understood as a rule library for storing the specific content included in each risk rule. For example, the specific content included in various risk rules may include: weight parameters of each risk rule or rule details of each risk rule.

[0073] The medical risk factor can be understood as a quantitative indicator used to measure the user's medical risk level.

[0074] Specifically, a completed medical knowledge graph is obtained, wherein the medical knowledge graph can be constructed based on the specific content contained in each risk rule, the medical risk rules are found in the preset risk identification rule library, the medical risk rules are mapped to the preset medical knowledge graph, the rules are matched, the medical risk rules are matched with the medical knowledge graph, the specific content corresponding to the medical risk rules is found, and the medical risk factors are determined from the specific content corresponding to the medical risk rules.

[0075] S207: Determine a risk feature library and a risk behavior identification model that match financial risk rules, and determine the financial risk factors of the financial information to be reviewed based on the risk feature library and the risk behavior identification model.

[0076] In the embodiment of the present invention, the risk feature library can be understood as a database that includes all features related to financial risks. For example, the risk feature library can include: transaction features or loan features.

[0077] The risk behavior identification model can be understood as a risk identification algorithm that is used to identify whether a user's financial behavior has potential risks.

[0078] The financial risk factor can be understood as a quantitative indicator used to measure a user's financial risk level.

[0079] Specifically, a preset risk feature library and a preset risk behavior identification model are obtained, financial risk rules are searched for in the preset risk identification rule library, the financial risk rules are matched with the preset risk feature library financial and the preset risk behavior identification model, the successfully matched preset risk feature library financial and the preset risk behavior identification model are respectively determined as the risk feature library and the risk behavior identification model, the financial information to be reviewed is input into the risk behavior identification model, and the financial risk factors for measuring the user's financial risk level are determined based on the output results of the risk feature library and the risk behavior identification model.

[0080] S208. Generate customer risk levels corresponding to financial risk factors and medical risk factors.

[0081] Specifically, financial risk factors and medical risk factors are determined, and based on the determined financial risk factors and medical risk factors, users with potential risks are divided according to preset risk levels to obtain corresponding customer risk levels.

[0082] S209. Determine the user's service restriction conditions according to the customer risk level, wherein the service restriction conditions include at least one of the following: usage scenario, usage limit, and risk restriction strategy.

[0083] In an embodiment of the present invention, authorization verification information uploaded by a user for confirming the authority to access user information and user information containing various data of the user are received, and authority to collect historical transaction data and historical behavior data is obtained based on the authorization verification information provided by the user, and the historical transaction data of the user and the historical behavior data of the user are extracted from a preset data source storing the historical data of the user, and the user information, the historical transaction data and the historical behavior data are integrated, and the integrated data set is used as the information of the information to be reviewed, and the user information is extracted from the information of the information to be reviewed, and the user information is compared one by one with the rules contained in the preset risk identification rule library to find the target risk rules matching the user information, and the risk assessment of the user information is performed based on the target risk rules, wherein the target risk rules include at least two categories: medical risk rules and financial risk rules, and the information of the information of the information to be reviewed is classified and identified according to the specified splitting criteria, and the information of the information to be reviewed is identified from the information of the information to be reviewed. Output the medical information to be reviewed and the financial information to be reviewed, obtain the constructed medical knowledge graph, map the medical risk rules to the preset medical knowledge graph, match the rules, match the medical risk rules with the medical knowledge graph, find out the specific content contained in the medical risk rules, determine the medical risk factors from the specific content contained in the medical risk rules, obtain the preset risk feature library and the preset risk behavior identification model, match the financial risk rules with the preset risk feature library and the preset risk behavior identification model, determine the preset risk feature library and the preset risk behavior identification model that successfully match the financial risk rules as the risk feature library and the risk behavior identification model respectively, input the financial information to be reviewed into the risk behavior identification model, determine the financial risk factors for measuring the user's financial risk level based on the output results of the risk feature library and the risk behavior identification model, and determine the user's service restriction conditions according to the customer's risk level. The embodiment of the present invention collects historical transaction data and historical behavior data in a preset data source based on the authorization verification information uploaded by the user, thereby ensuring the user's data security. By aggregating user information, historical transaction data and historical behavior data to form the user's pending review information, a comprehensive data basis is provided for risk assessment. The target risk rules are determined based on the extracted user information, so that the assessment of the customer's risk level is more targeted and accurate. The pending review information is split into pending medical information and pending financial information, which is helpful for targeted risk assessment. The medical risk factors of the pending medical information are determined based on the medical knowledge graph, and the financial risk factors of the pending financial information are determined according to the risk feature library and the risk behavior identification model, thereby ensuring the accurate generation of risk factors, thereby ensuring the accuracy of risk assessment and improving risk management efficiency.

[0084] Based on the above embodiment, the embodiment of the present invention also includes: determining that the information to be reviewed does not include historical transaction data and historical behavior data, and pushing the information to be reviewed to a preset risk review queue for manual review.

[0085] In the embodiment of the present invention, the preset risk review queue can be understood as a component for storing and managing the information of documents to be reviewed that require additional manual review.

[0086] Specifically, the pending information uploaded by the user is obtained, and the pending information is identified according to the medical risk rules and financial risk rules of the preset risk identification rule library. If it is identified that the pending information does not contain historical transaction data and historical behavior data, the pending information will be pushed to the preset risk review queue, and the user's pending information will be manually reviewed.

[0087] Embodiment 3

[0088] Figure 3 This is a flow chart of another risk control method provided by Embodiment 3 of the present invention. Based on the above embodiments, this embodiment of the present invention provides another risk control method. Figure 3 As shown, the method includes:

[0089] S301, receiving authorization verification information and user information uploaded by the user.

[0090] S302: Collect the user's historical transaction data and historical behavior data from a preset data source according to the authorization verification information.

[0091] S303: Use user information, historical transaction data, and historical behavior data as information to be reviewed.

[0092] S304. Searching for a target risk rule that matches the user information in the information to be reviewed in a preset risk identification rule library, wherein the target risk rule includes at least the medical risk rule and the financial risk rule.

[0093] S305, splitting the information to be reviewed into medical information to be reviewed and financial information to be reviewed.

[0094] S306. Determine the medical knowledge graph that matches the medical risk rules, and perform data cleaning and normalization on the medical information to be reviewed according to the data format of the medical knowledge graph.

[0095] In the embodiment of the present invention, the data format refers to the structure and representation method used when storing and transmitting data. In the medical knowledge graph, the data format generally includes entities, attributes and relationships. For example, entities may include patients, diseases or drugs, attributes may include the patient's age, gender or medical history, and relationships may include the association between patients and diseases, and the therapeutic effects of drugs on diseases.

[0096] Data cleaning is a data processing method. For example, the data cleaning steps may include: removing data redundancy or removing erroneous data, etc., aiming to improve the reliability of data.

[0097] Normalization refers to converting data of different scales or ranges to the same standard to facilitate comparison and analysis.

[0098] Specifically, determine the medical knowledge graph that matches the medical risk rules, and perform data cleaning and normalization operations on the medical information to be reviewed in accordance with the data format defined by the medical knowledge graph.

[0099] S307. Fill the processed medical information to be reviewed into the medical knowledge graph to determine the medical fraud relationship of the medical knowledge graph that the medical information to be reviewed satisfies.

[0100] In the embodiment of the present invention, the medical fraud relationship can be understood as a relationship between entities related to medical fraud behavior in the medical knowledge graph, and potential medical fraud behavior can be revealed through the medical fraud relationship.

[0101] Specifically, data cleaning and normalization operations are performed on the medical information to be reviewed in accordance with the data format of the medical knowledge graph to obtain the processed medical information to be reviewed, and the medical information to be reviewed is filled into the medical knowledge graph, and associations are established with entities in the medical knowledge graph. In the medical knowledge graph, entity relationships are identified based on the medical information to be reviewed, and the relationships between entities that match the medical risk rules are used as medical fraud relationships of the medical information to be reviewed.

[0102] S308. Find the medical risk weight corresponding to the medical fraud relationship, and take the sum of the medical risk weights corresponding to all medical fraud relationships as the medical risk factor.

[0103] In the embodiment of the present invention, the medical risk weight can be understood as a quantitative indicator used to measure the size of the potential risk brought about by medical fraud relationships.

[0104] Specifically, based on the determined medical fraud relationship, the medical risk weight corresponding to the medical fraud relationship is found in the medical knowledge graph to measure the potential risk brought by the medical fraud relationship, and all the found medical risk weights are added together to obtain the medical risk factor. It can be understood that the higher the medical risk factor, the greater the risk of medical fraud in the medical information to be reviewed.

[0105] S309: Determine a risk feature library and a risk behavior identification model that matches financial risk rules, extract feature extraction rules from the risk feature library, extract financial features of the financial information to be reviewed according to the feature extraction rules, and determine the number of feature matches between the financial features and the risk features in the risk feature library.

[0106] In the embodiment of the present invention, the feature extraction rule can be understood as an extraction criterion, which aims to extract features that are of great value to risk prediction from complex financial information.

[0107] Financial characteristics can be understood as a kind of key data, which is extracted from the financial information to be reviewed and has important value for risk prediction. For example, financial characteristics may include: transaction type or transaction frequency.

[0108] The number of feature matches refers to the number of successful matches between the financial features of the financial information to be reviewed and the risk features in the risk feature library, and is used to measure the similarity between the financial information to be reviewed and the risk feature library.

[0109] Specifically, determine the risk feature library and risk behavior identification model that match the financial risk rules, extract feature extraction rules from the risk feature library, and based on the feature extraction rules, extract financial features that are of great value to risk prediction from the financial information to be reviewed, match the extracted financial features with the risk features in the risk feature library one by one, calculate the number of successful matches, and use the number of successful matches as the number of feature matches.

[0110] S310: Calling a risk behavior identification model to identify risk behaviors of the financial information to be reviewed, and counting the number of risk behaviors of the financial information to be reviewed.

[0111] In the embodiment of the present invention, risky behavior refers to behavior that leads to financial risk. For example, risky behavior may include: bad credit behavior or fraudulent behavior.

[0112] The number of behaviors refers to the total number of risky behaviors identified in the financial information to be reviewed, and is used to measure the distribution and frequency of risky behaviors in the entire financial information to be reviewed.

[0113] Specifically, the financial information to be reviewed is input into the risk behavior identification model, and the risk behavior identification model is used to identify the financial information to be reviewed, and the risk behavior that causes the financial risk is output by the risk behavior identification model. The total number of risk behaviors in the financial information to be reviewed is counted, and the total number of identified risk behaviors is used as the number of risk behavior behaviors.

[0114] S311. Determine the financial risk factors corresponding to the number of behaviors and the number of feature matches.

[0115] Specifically, the number of risky behaviors is obtained, the number of feature matches that successfully match financial features with risk features is obtained, a comprehensive analysis is conducted on the potential financial risks that may exist in the financial information to be reviewed based on the number of behaviors and the number of feature matches, and the corresponding financial risk factors are determined based on the analysis results.

[0116] S312. Generate customer risk levels corresponding to financial risk factors and medical risk factors.

[0117] S313. Determine the user's service restriction conditions according to the customer risk level, wherein the service restriction conditions include at least one of the following: usage scenario, usage limit, and risk restriction strategy.

[0118] In an embodiment of the present invention, authorization verification information and user information uploaded by a user are received, historical transaction data and historical behavior data of the user are collected from a preset data source according to the authorization verification information, the user information, historical transaction data and historical behavior data are used as information of the information to be reviewed, and a target risk rule matching the user information in the information of the information to be reviewed is searched in a preset risk identification rule library, wherein the target risk rule at least includes the medical risk rule and the financial risk rule, the information of the information to be reviewed is split into medical information to be reviewed and financial information to be reviewed, a medical knowledge graph matching the medical risk rule is determined, the medical information to be reviewed is subjected to data cleaning and normalization processing according to the data format defined by the medical knowledge graph to obtain processed medical information to be reviewed, the processed medical information to be reviewed is filled into the medical knowledge graph, an association with an entity in the medical knowledge graph is established, entity relationships are identified based on the medical information to be reviewed, and the relationships between entities matching the medical risk rules are used as medical fraud information of the medical information to be reviewed. Fraud relationship, find out the medical risk weight corresponding to the medical fraud relationship in the medical knowledge graph, add up all the found medical risk weights to get the medical risk factor, determine the risk feature library and risk behavior identification model that match the financial risk rules, extract feature extraction rules in the risk feature library, extract financial features that are of great value to risk prediction from the financial information to be reviewed based on the feature extraction rules, match the extracted financial features with the risk features in the risk feature library one by one, calculate the number of feature matches, input the financial information to be reviewed into the risk behavior identification model, use the risk behavior identification model to identify the financial information to be reviewed, obtain the risk behavior output by the risk behavior identification model, count the number of risk behaviors in the financial information to be reviewed, conduct a comprehensive analysis of the potential financial risks that may exist in the financial information to be reviewed based on the number of behaviors and the number of feature matches, determine the corresponding financial risk factors based on the analysis results, generate the corresponding customer risk level based on the financial risk factors and medical risk factors, and determine the user's service restriction conditions according to the customer risk level. The embodiments of the present invention process the medical information to be reviewed in accordance with the data format defined by the medical knowledge graph, thereby ensuring the accuracy and reliability of the data; by filling the medical information to be reviewed into the medical knowledge graph and using the medical knowledge graph to search and match medical fraud relationships, the medical risk weight is accurately determined, reducing misjudgments and missed judgments; medical risk factors are determined based on medical risk weights, financial risk factors are determined based on the number of behaviors and the number of feature matches, customer risk levels are determined based on medical risk factors and financial risk factors, and the customer risk level is determined by comprehensively considering the two risk factors in the information to be reviewed, making risk assessment more comprehensive and accurate.

[0119] Embodiment 4

[0120] Based on the above embodiments, embodiments of the present invention provide a financial payment application flow chart; a hospital admission installment application flow chart; a full-platform and full-process risk control flow chart; and a fraud identification and processing flow chart.

[0121] like Figure 4 As shown in the figure, a financial payment application process is described in detail, which is divided into four parts: applicants, risk control platforms, financial institutions and pharmacies (hospitals). The applicant first starts the process by uploading the information to the project-specific official account of the risk control platform. The risk control platform reviews the information. If it fails the review, the process ends. If it passes the review, the information is handed over to the financial institution. The financial institution conducts a financial risk control review on the information again. If it fails the financial risk control review, the process ends. If it passes the review, the financial institution system places an order and signs a loan agreement, and then lends money to the applicant. After receiving the payment, the pharmacy or hospital distributes the medicine to the patient. The patient takes the medicine regularly, and the applicant needs to repay on time every month until the loan is settled.

[0122] like Figure 5 As shown, a process of applying for hospitalization installment is described in detail. The risk control platform reviews the hospitalization order uploaded by the applicant and determines whether the applicant has successfully activated the enterprise code. If the enterprise code is not successfully activated, the application will not be approved, and the applicant will be notified to supplement the information and continue to activate the enterprise code. If the enterprise code is successfully activated and the hospitalization order is approved, the cost control system is created through the enterprise code, and the cost control system information is obtained. The applicant is notified that the enterprise code can be used to pay the hospitalization fee. After the payment is successfully made using the enterprise code, the risk control platform obtains the bill information. Among them, the process of activating the enterprise code includes: the applicant initiates an application for hospitalization fee installment to the risk control platform and provides an order for purchasing medicines in the hospital. The applicant confirms the financial installment order for hospitalization, and the content of the financial installment order can include: the installment amount and the installment time. The risk control platform calls the enterprise code personnel interface based on the hospitalization application and the medicine purchase order, and adds the corresponding applicant or patient to the enterprise code personnel interface. The risk control platform obtains a link to activate the enterprise code, and the applicant clicks the link to activate the enterprise code to complete the activation of the enterprise code.

[0123] like Figure 6As shown in the figure, a full-process risk control process of a risk control platform is described in detail. The flowchart shows the various stages of the full-process risk control, which include three links: before, during and after. The before-the-time link includes the step of collecting benefits. Among them, the risk control measures taken in the step of collecting benefits are mainly data acquisition. Among them, the acquired data include: policy validity verification data, financial bad data, pre-existing condition judgment data, operation data and limit display data. The characteristic of the before-the-time link is no blocking; the during-the-process link includes four steps: application, risk control model, limit strategy and payment. Among them, the application step mainly makes the initial risk decision through external blacklists, internal blacklists, out-of-coverage conditions, cases in transit and the use of pre-existing condition labels. If necessary, it will be transferred to manual claim review. The characteristics of the application step are that it can quickly identify risks and immediately reject applications. Please; the steps in the risk control model include cost estimation, assessment of reasonable amount and customer risk level, and transfer to manual claim review when necessary. The characteristic of the risk control model steps is actual control of the amount; the steps in the credit limit strategy are to judge the applicant's single increase in credit limit based on financial logic and medical logic to obtain the recommended credit limit. The characteristic of the credit limit strategy step is to determine the upper limit of the credit limit; in the payment stage, the code display risk control strategy is carried out to monitor the account in real time. When paying fees, the user limits the credit limit (fixed amount), the destination (directional) and the time (timing), verifies the applicant's payment method, and monitors the applicant's payment behavior. The purpose of the payment stage is to control payment. The post-event link includes two steps: claim settlement and default handling. Among them, in the claim settlement stage, warning tracking is carried out through abnormal warning, timeout tracking, special person supervision, advance guidance, and manual receipt. The characteristic of the claim settlement stage is the timeliness of claim settlement; in the default handling stage, a full closed loop is achieved through the recovery of illegal debts, intelligent reminders, classification strategies, manual negotiations and judicial termination.

[0124] like Figure 7 As shown in the figure, a fraud identification and processing flow is described in detail, and the flow is divided into three main stages: the first is fraud avoidance, through product design, underwriting conditions, underwriting rules and claims settlement rules, combined with artificial intelligence (AI) technology to intelligently disassemble insurance terms and health notices, and then build medical rules in combination with the medical knowledge base, where the medical knowledge base contains labels and knowledge graphs; the fraud factor or risk score is determined through the feature library and data model, where the applicant is judged based on the feature library whether it meets the blacklist, frequent insurance claims and the short time between insurance claim and insurance claim, etc., the data model performs previous disease identification, case risk stratification, group risk control, and medical rules are applied to medical risk control, and fraud factors / risk scores are applied to insurance behavior model risk control. Medical risk control and insurance behavior model risk control jointly identify fraud; finally, in the fraud handling stage, suspected cases are investigated and fraudulent behaviors are prompted, and the case is closed based on the investigation results.

[0125] Embodiment 5

[0126] Figure 8 A risk control device is provided in Embodiment 5 of the present invention, such as Figure 8 As shown, the device comprises:

[0127] The information acquisition module 401 is used to acquire the information of the materials to be reviewed uploaded by the user;

[0128] The risk level module 402 is used to identify the information to be reviewed according to the medical risk rules and financial risk rules of the preset risk identification rule library, and obtain the customer risk level of the information to be reviewed;

[0129] The risk control module 403 is used to determine the service restriction conditions of the user according to the customer risk level.

[0130] In an embodiment of the present invention, information on pending documents uploaded by a user that contains various information of the user and needs to be verified and evaluated is obtained, a preset risk identification rule library is obtained, and a medical risk rule for identifying and evaluating potential risks of the pending documents in the medical field and a financial risk rule for identifying and evaluating potential risks of the pending documents in the financial field are searched in the preset risk identification rule library, and the pending documents uploaded by the user are identified and evaluated based on the found medical risk rules and financial risk rules, and the pending documents are compared with the medical risk rules and the financial risk rules one by one, and the user is divided into different risk levels based on the comparison results, and the different risk levels are used as customer risk levels of the pending documents, and the service restriction conditions of the user are further analyzed and determined based on the obtained customer risk levels, and services with corresponding restriction requirements are provided to the user based on the service restriction conditions of the user. The embodiment of the present invention utilizes the medical risk rules and financial risk rules in the preset risk identification rule library to identify the information of the materials to be reviewed, thereby realizing the intelligent and comprehensive identification and effective management of risks, ensuring the accurate prediction of the risk level, improving the efficiency of risk identification, determining the service restriction conditions of the user based on the customer's risk level, and providing the user with services with corresponding restriction requirements according to the obtained service restriction conditions, thereby reducing risk leakage and improving the user experience.

[0131] Based on the above embodiments, the embodiments of the present invention further include:

[0132] Determine that the information to be reviewed does not include historical transaction data and historical behavior data, and push the information to be reviewed to the preset risk review queue for manual review.

[0133] Based on the above embodiment, the information acquisition module 401 is specifically used to receive the authorization verification information and user information uploaded by the user; collect the user's historical transaction data and historical behavior data in the preset data source according to the authorization verification information; and use the user information, historical transaction data and historical behavior data as information to be reviewed.

[0134] On the basis of the above embodiment, the risk level module 402 also includes: a target risk rule search submodule, which is used to search for a target risk rule that matches the user information in the information to be reviewed in a preset risk identification rule library, wherein the target risk rule includes at least a medical risk rule and a financial risk rule; an audit information splitting submodule, which is used to split the information to be reviewed into medical information to be reviewed and financial information to be reviewed; a medical risk factor determination submodule, which is used to determine the medical knowledge graph that matches the medical risk rule, and determine the medical risk factor of the medical information to be reviewed based on the medical knowledge graph; a financial risk factor determination submodule, which is used to determine the risk feature library and risk behavior identification model that match the financial risk rule, and determine the financial risk factor of the financial information to be reviewed based on the risk feature library and the risk behavior identification model; a customer risk level generation submodule, which is used to generate customer risk levels corresponding to financial risk factors and medical risk factors.

[0135] On the basis of the above-mentioned embodiment, the medical risk factor determination submodule is specifically used to clean and normalize the medical information to be reviewed according to the data format of the medical knowledge graph;

[0136] Fill the processed medical information to be reviewed into the medical knowledge graph to determine the medical fraud relationship of the medical knowledge graph satisfied by the medical information to be reviewed;

[0137] Find the medical risk weight corresponding to the medical fraud relationship, and take the sum of the medical risk weights corresponding to all medical fraud relationships as the medical risk factor.

[0138] On the basis of the above embodiment, the financial risk factor determination submodule is specifically used to extract feature extraction rules from the risk feature library, extract financial features of the financial information to be reviewed according to the feature extraction rules, and determine the number of feature matches between the financial features and the risk features in the risk feature library;

[0139] Calling the risk behavior identification model to identify the risk behavior of the financial information to be reviewed, and counting the number of risk behaviors of the financial information to be reviewed;

[0140] Determine the financial risk factors corresponding to the number of behaviors and the number of feature matches.

[0141] Embodiment 6

[0142] Embodiments of the present invention provide an electronic device for executing a risk control method, a computer-readable storage medium, and a computer program product.

[0143] Fig. 9 A schematic diagram of an electronic device that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown in the embodiments of the present invention, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the embodiments of the present invention described and / or required herein.

[0144] like Fig. 9 As shown, the electronic device includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the ROM 12 or the computer program loaded from the storage unit 18 to the RAM 13. In the RAM 13, various programs and data required for the operation of the electronic device can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. The input / output (I / O) interface 15 is also connected to the bus 14.

[0145] A number of components in the electronic device are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0146] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit, a graphics processing unit, various special artificial intelligence computing chips, various processors running machine learning model algorithms, digital signal processors, and any appropriate processors, controllers, microcontrollers, etc. The processor 11 performs the various methods and processes described above, for example, the risk control method.

[0147] In some embodiments, the risk control method may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the risk control method may be performed. Alternatively, in other embodiments, the processor 11 may be configured as the risk control method in any other appropriate manner (e.g., by means of firmware).

[0148] Various implementations of the systems and techniques described above in the embodiments of the present invention may be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays, application specific integrated circuits, application specific standard products, systems on a chip, load programmable logic devices, computer hardware, firmware, software, and / or combinations thereof. These various implementations may include: being implemented in one or more computer programs, which may be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general programmable processor, which may receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0149] The computer programs for implementing the methods of the embodiments of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer programs are executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer programs may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0150] In the context of an embodiment of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, device, or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a RAM, a ROM, an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0151] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a cathode ray tube or a liquid crystal display monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or a trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including: acoustic input, voice input, or tactile input).

[0152] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local area networks, wide area networks, blockchain networks, and the Internet.

[0153] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the respective computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and virtual private server services.

[0154] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0155] The above specific implementations do not constitute a limitation on the protection scope of the embodiments of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A risk control method, characterized in that: The method comprises: Get the information of the materials uploaded by the user that are pending for review; Identify the information to be reviewed according to the medical risk rules and financial risk rules of the preset risk identification rule library, and obtain the customer risk level of the information to be reviewed; Determine the service restriction condition for the user according to the customer risk level.

2. The method according to claim 1, characterized in that: The obtaining of the pending review information uploaded by the user includes: Receiving authorization verification information and user information uploaded by the user; Collect the user's historical transaction data and historical behavior data from a preset data source according to the authorization verification information; The user information, the historical transaction data and the historical behavior data are used as the information to be reviewed.

3. The method according to claim 1, characterized in that: The step of identifying the information to be reviewed based on the medical risk rules and financial risk rules of the preset risk identification rule base to obtain the customer risk level of the information to be reviewed includes: Searching the preset risk identification rule library for a target risk rule that matches the user information in the to-be-reviewed information, wherein the target risk rule at least includes the medical risk rule and the financial risk rule; Split the information to be reviewed into medical information to be reviewed and financial information to be reviewed; Determine a medical knowledge graph that matches the medical risk rule, and determine the medical risk factor of the medical information to be reviewed based on the medical knowledge graph; Determine a risk feature library and a risk behavior identification model that match the financial risk rule, and determine the financial risk factor of the financial information to be reviewed based on the risk feature library and the risk behavior identification model; Generate the customer risk level corresponding to the financial risk factor and the medical risk factor.

4. The method according to claim 3, characterized in that: The determining of the medical risk factors of the to-be-reviewed medical information according to the medical knowledge graph includes: Cleaning and normalizing the medical information to be reviewed according to the data format of the medical knowledge graph; Filling the processed medical information to be reviewed into the medical knowledge graph to determine the medical fraud relationship of the medical knowledge graph satisfied by the medical information to be reviewed; The medical risk weight corresponding to the medical fraud relationship is found, and the sum of the medical risk weights corresponding to all the medical fraud relationships is used as the medical risk factor.

5. The method according to claim 3, characterized in that: The determining of the financial risk factors of the to-be-audited financial information according to the risk feature library and the risk behavior identification model includes: Extracting feature extraction rules from the risk feature library, extracting financial features of the to-be-reviewed financial information according to the feature extraction rules, and determining the number of feature matches between the financial features and the risk features in the risk feature library; Calling the risk behavior identification model to identify the risk behavior of the financial information to be reviewed, and counting the number of risk behaviors of the financial information to be reviewed; Determine the financial risk factor corresponding to the number of behaviors and the number of feature matches.

6. The method according to claim 1, characterized in that: The service restriction condition includes at least one of the following: usage scenario, usage quota, and risk limitation strategy.

7. The method according to claim 1, characterized in that: Also includes: It is determined that the information to be reviewed does not include historical transaction data and historical behavior data, and the information to be reviewed is pushed to a preset risk review queue for manual review.

8. A risk control device, characterized in that: The device comprises: The information acquisition module is used to obtain the information of the materials to be reviewed uploaded by the user; A risk level module, used to identify the information to be reviewed according to the medical risk rules and financial risk rules of the preset risk identification rule library, and obtain the customer risk level of the information to be reviewed; The risk control module is used to determine the service restriction conditions of the user according to the customer risk level.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively coupled to the at least one processor; The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the risk control method described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the risk control method according to any one of claims 1 to 7 when executed.

Images