A financial risk management method, device and storage medium

Abstract

This application discloses a financial risk management method, device, and storage medium. The method involves acquiring target financial data, parsing the target financial data based on a preset rule base to determine risk objects, which includes static rules and dynamic rules. The risk objects are further evaluated based on preset risk indicators to obtain target characteristic values, which are used to control the financial risks of the risk objects. This method achieves an efficient financial risk control process. The use of a composite rule combining static and dynamic rules improves the hit rate of risk objects, and further, a secondary evaluation of risk objects is performed using risk indicators, judging risk objects from multiple dimensions and improving the accuracy of risk object determination during the financial risk management process.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a method, device, and storage medium for managing financial risks. Background Art

[0002] With the rapid development of Internet technology, people use mobile payments in more and more scenarios, which brings with it increasing financial risks. Therefore, it is necessary to identify and screen financial data on the Internet in order to facilitate risk control.

[0003] For example, in the prevention and control of money laundering risks, we can develop and launch prevention and control rules based on fixed regulatory provisions. Simultaneously, as new regulatory requirements, such as risk warnings, are introduced, the number of rules can be manually increased to enhance risk control effectiveness, creating a parallel rule-based prevention and control system.

[0004] However, parallel rule-based prevention and control requires a large amount of manual resources, and the various rules cannot cover all risk items in all scenarios, which affects the accuracy of determining the control objects in the financial risk management process. Summary of the Invention

[0005] In view of this, the present application provides a financial risk management method that can effectively improve the accuracy of determining the control objects in the financial risk management process.

[0006] On one hand, the present application provides a financial risk management method that can be applied to a system or program that includes a financial risk management function in a terminal device, specifically including:

[0007] Obtain target financial data;

[0008] parsing the target financial data based on a preset rule base to determine risk objects, the preset rule base including static rules and dynamic rules, the static rules being determined based on regulatory information corresponding to the target financial data, and the dynamic rules being determined based on scenario information corresponding to the target financial data;

[0009] The risk object is evaluated according to a preset risk indicator to obtain a target characteristic value, and the target characteristic value is used to perform financial risk control on the risk object.

[0010] Optionally, in some possible implementations of the present application, parsing the target financial data based on a preset rule base to determine risk objects includes:

[0011] Determining the domain information and time information corresponding to the target financial data;

[0012] determining the supervision information according to the domain information and the time information;

[0013] Extracting regulatory feature items from the regulatory information;

[0014] The target financial data is parsed based on the regulatory feature items to obtain the risk object.

[0015] Optionally, in some possible implementations of the present application, extracting regulatory feature items from the regulatory information includes:

[0016] Determining transaction information corresponding to the target financial data, the transaction information including at least one of a transaction object, a transaction frequency, a transaction time, or a transaction value;

[0017] The regulatory information is traversed according to the transaction object, the transaction frequency, the transaction time, and the transaction value to obtain the regulatory feature item.

[0018] Optionally, in some possible implementations of the present application, determining the transaction information corresponding to the target financial data includes:

[0019] Determining a target object corresponding to the target financial data;

[0020] Retrieving historical information of the target object;

[0021] The transaction information is extracted from the historical information according to a preset time period.

[0022] Optionally, in some possible implementations of the present application, parsing the target financial data based on a preset rule base to determine risk objects includes:

[0023] Calling a scenario model library, wherein the scenario model library is updated based on an increase in cases;

[0024] Traversing the scenario model library according to the scenario information corresponding to the target financial data to obtain a target model associated with the target financial data;

[0025] The target financial data is input into the target model to obtain the risk object.

[0026] Optionally, in some possible implementations of the present application, inputting the target financial data into the target model to obtain the risk object includes:

[0027] Inputting the target financial data into the target model to obtain risk feature items;

[0028] Determine the weight information corresponding to the risk feature item based on the decision number model;

[0029] performing a weighted calculation based on the weight information and the risk feature item for each object indicated in the target financial data to obtain a scenario feature value;

[0030] The risk object is determined based on the scenario feature value.

[0031] Optionally, in some possible implementations of the present application, determining the weight information corresponding to the risk feature item based on the decision number model includes:

[0032] Call the marked target sample;

[0033] Updating the risk feature item based on the target sample;

[0034] The updated weight information corresponding to the risk feature item is determined based on the decision number model.

[0035] Optionally, in some possible implementations of the present application, evaluating the risk object according to a preset risk indicator to obtain a target characteristic value includes:

[0036] Determine a base value, a comparison value, and an associated value corresponding to the risk object based on the preset risk indicator, wherein the base value is used to indicate the correspondence of the risk object to the risk project, the comparison value is used to indicate the comparison between the risk object and a preset threshold, and the associated value is used to indicate the similarity between the risk object and the associated object;

[0037] Calculation is performed based on the base value, the comparison value, and the associated value to obtain the target feature value.

[0038] Optionally, in some possible implementations of the present application, the calculating according to the base value, the comparison value, and the correlation value to obtain the target feature value includes:

[0039] Determine the corresponding feature level according to the base value, the comparison value and the correlation value;

[0040] Calling the level value corresponding to the feature level;

[0041] Calculation is performed based on the level value to obtain the target feature value.

[0042] Optionally, in some possible implementations of the present application, obtaining target financial data includes:

[0043] acquiring financial operation information within a preset time period in response to a target operation;

[0044] Extracting the operation object corresponding to each item of the financial operation information;

[0045] The operation object is associated with the financial operation information to obtain the target financial data.

[0046] Optionally, in some possible implementations of the present application, the method further includes:

[0047] Determining a risk sequence consisting of a plurality of risk objects according to the target feature value;

[0048] extracting target objects in the risk sequence based on order information corresponding to the risk sequence;

[0049] The target object is pushed to the audit platform for financial risk control.

[0050] Optionally, in some possible implementations of the present application, the financial risk control is money laundering risk control, the static rules are regulatory laws and regulations, the scenarios corresponding to the dynamic rules include gambling scenarios, pyramid scheme scenarios, cross-border remittance scenarios, smuggling scenarios, and telecommunications fraud scenarios, and the preset risk indicators include money laundering risk level, risk deviation, historical audit times, historical review status, group behavior correlation, number of audit rules in this round, reporting rate of hit rules, and importance of hit rules.

[0051] On one hand, the present application provides a financial risk management device, comprising:

[0052] an acquisition unit, used for acquiring target financial data;

[0053] a parsing unit, configured to parse the target financial data based on a preset rule base to determine risk objects, the preset rule base including static rules and dynamic rules, the static rules being determined based on regulatory information corresponding to the target financial data, and the dynamic rules being determined based on scenario information corresponding to the target financial data;

[0054] The management unit is used to evaluate the risk object according to the preset risk index to obtain a target characteristic value, and the target characteristic value is used to perform financial risk control on the risk object.

[0055] Optionally, in some possible implementations of the present application, the parsing unit is specifically configured to determine the domain information and time information corresponding to the target financial data;

[0056] The parsing unit is specifically configured to determine the regulatory information based on the domain information and the time information;

[0057] The parsing unit is specifically configured to extract regulatory feature items from the regulatory information;

[0058] The parsing unit is specifically configured to parse the target financial data based on the regulatory feature items to obtain the risk object.

[0059] Optionally, in some possible implementations of the present application, the parsing unit is specifically configured to determine transaction information corresponding to the target financial data, where the transaction information includes at least one of a transaction object, a transaction frequency, a transaction time, or a transaction value;

[0060] The parsing unit is specifically configured to traverse the regulatory information according to the transaction object, the transaction frequency, the transaction time, and the transaction value to obtain the regulatory feature item.

[0061] Optionally, in some possible implementations of the present application, the parsing unit is specifically configured to determine a target object corresponding to the target financial data;

[0062] The parsing unit is specifically used to call the historical information of the target object;

[0063] The parsing unit is specifically configured to extract the transaction information from the historical information according to a preset time period.

[0064] Optionally, in some possible implementations of the present application, the parsing unit is specifically configured to call a scenario model library, and the scenario model library is updated based on an increase in cases;

[0065] The parsing unit is specifically configured to traverse the scenario model library according to the scenario information corresponding to the target financial data to obtain a target model associated with the target financial data;

[0066] The parsing unit is specifically configured to input the target financial data into the target model to obtain the risk object.

[0067] Optionally, in some possible implementations of the present application, the parsing unit is specifically configured to input the target financial data into the target model to obtain risk feature items;

[0068] The parsing unit is specifically configured to determine weight information corresponding to the risk feature item based on a decision number model;

[0069] The parsing unit is specifically configured to perform weighted calculation on each object indicated in the target financial data based on the weight information and the risk feature item to obtain a scenario feature value;

[0070] The parsing unit is specifically configured to determine the risk object based on the scenario feature value.

[0071] Optionally, in some possible implementations of the present application, the parsing unit is specifically configured to call a marked target sample;

[0072] The parsing unit is specifically configured to update the risk feature item based on the target sample;

[0073] The parsing unit is specifically used to determine the updated weight information corresponding to the risk feature item based on the decision number model.

[0074] Optionally, in some possible implementations of the present application, the management unit is specifically configured to determine a base value, a comparison value, and an associated value corresponding to the risk object based on the preset risk indicator, wherein the base value is used to indicate the corresponding situation of the risk object in the risk project, the comparison value is used to indicate the comparison situation of the risk object with a preset threshold, and the associated value is used to indicate the similarity between the risk object and the associated object;

[0075] The management unit is specifically configured to perform calculations based on the base value, the comparison value, and the associated value to obtain the target feature value.

[0076] Optionally, in some possible implementations of the present application, the management unit is specifically configured to determine the corresponding feature levels according to the base value, the comparison value, and the correlation value;

[0077] The management unit is specifically configured to call the level value corresponding to the feature level;

[0078] The management unit is specifically configured to perform calculations based on the level value to obtain the target feature value.

[0079] Optionally, in some possible implementations of the present application, the acquiring unit is specifically configured to acquire financial operation information within a preset time period in response to a target operation;

[0080] The acquisition unit is specifically configured to extract the operation object corresponding to each item of the financial operation information;

[0081] The acquisition unit is specifically configured to associate the operation object with the financial operation information to obtain the target financial data.

[0082] Optionally, in some possible implementations of the present application, the management unit is specifically configured to determine a risk sequence consisting of a plurality of risk objects according to the target feature value;

[0083] The management unit is specifically configured to extract the target object in the risk sequence based on the sequence information corresponding to the risk sequence;

[0084] The management unit is specifically used to push the target object to the audit platform for financial risk control.

[0085] On the one hand, the present application provides a computer device, including: a memory, a processor and a bus system; the memory is used to store program code; the processor is used to execute the financial risk management method described in the first aspect or any one of the first aspects according to the instructions in the program code.

[0086] On one hand, the present application provides a computer-readable storage medium, in which instructions are stored. When the computer-readable storage medium is run on a computer, the computer is enabled to execute the financial risk management method described in the above-mentioned one aspect or any one of the aspects.

[0087] According to one aspect of the present application, a computer program product or computer program is provided, comprising computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the financial risk management method provided in the first aspect or various optional implementations of the first aspect.

[0088] It can be seen from the above technical solutions that the embodiments of the present application have the following advantages:

[0089] The system obtains target financial data and then analyzes it based on a preset rule base to identify risk targets. The preset rule base includes static and dynamic rules. Static rules are determined based on regulatory information corresponding to the target financial data, while dynamic rules are determined based on scenario information corresponding to the target financial data. Furthermore, the risk targets are evaluated based on preset risk indicators to obtain target characteristic values, which are used to control the financial risks of the risk targets. This achieves efficient financial risk control. The use of a composite rule of static and dynamic rules improves the hit rate of risk targets. Furthermore, risk targets are secondary evaluated using risk indicators, judging risk targets from multiple dimensions and improving the accuracy of risk target identification during the financial risk management process. BRIEF DESCRIPTION OF THE DRAWINGS

[0090] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are merely embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without any creative work.

[0091] Figure 1A diagram of the network architecture that operates the financial risk management system;

[0092] Figure 2 A process architecture diagram for financial risk management provided in an embodiment of the present application;

[0093] Figure 3 A flowchart of a financial risk management method provided in an embodiment of the present application;

[0094] Figure 4 A schematic diagram of a scenario of a financial risk management method provided in an embodiment of the present application;

[0095] Figure 5 A schematic diagram of another scenario of a financial risk management method provided in an embodiment of the present application;

[0096] Figure 6 A schematic diagram of another scenario of a financial risk management method provided in an embodiment of the present application;

[0097] Figure 7 A flowchart of another financial risk management method provided in an embodiment of the present application;

[0098] Figure 8 A schematic diagram of another scenario of a financial risk management method provided in an embodiment of the present application;

[0099] Figure 9 A schematic diagram of another scenario of a financial risk management method provided in an embodiment of the present application;

[0100] Figure 10 A schematic diagram of the structure of a financial risk management device provided in an embodiment of the present application;

[0101] Figure 11 A schematic diagram of the structure of a terminal device provided in an embodiment of the present application;

[0102] Figure 12 A schematic diagram of the structure of a server provided in an embodiment of the present application. DETAILED DESCRIPTION

[0103] The embodiment of the present application provides a financial risk management method, device and storage medium, which can be applied to a system or program in a terminal device that includes a financial risk management function, by acquiring target financial data; then parsing the target financial data based on a preset rule base to determine the risk object, the preset rule base includes static rules and dynamic rules, the static rules are determined based on the regulatory information corresponding to the target financial data, and the dynamic rules are determined based on the scenario information corresponding to the target financial data; further, the risk object is evaluated according to the preset risk index to obtain a target characteristic value, which is used to control the financial risk of the risk object. Thereby, an efficient control process of financial risk is achieved. Due to the use of a composite rule of static rules and dynamic rules, the hit rate of the risk object is improved, and further the risk object is secondary evaluated through the risk index, and the risk object is judged from multiple dimensions, which improves the accuracy of risk object determination in the financial risk management process.

[0104] The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequential order. It should be understood that the numbers used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can, for example, be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "corresponding to" 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 clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0105] First, some terms that may appear in the embodiments of this application are explained.

[0106] Anti-money laundering: refers to financial institutions controlling money laundering risks within the system through processes, rules, etc.

[0107] Effectiveness: refers to the ability to audit risk users as accurately as possible when preventing and controlling money laundering risks.

[0108] Explainability: refers to the ability to provide a reasonable and transparent explanation of the effectiveness, effects, and measures of the prevention and control system.

[0109] Risk prevention and control: refers to monitoring, auditing and handling money laundering risks within the system through rules and model systems to reduce money laundering risks within the system.

[0110] It should be understood that the financial risk management method provided in this application can be applied to a system or program containing a financial risk management function in a terminal device, such as a security manager. Specifically, the financial risk management system can be run on Figure 1 In the network architecture shown in Figure 1 As shown in FIG, it is a network architecture diagram of the operation of the financial risk management system. As can be seen from the figure, the financial risk management system can provide a financial risk management process with multiple information sources, that is, through the transaction operation on the terminal side, the corresponding financial information is generated on the server, and the server performs financial operations between different terminals based on the financial information; it can be understood that Figure 1 A variety of terminal devices are shown in FIG. 4 . The terminal devices may be computer devices. In actual scenarios, more or fewer types of terminal devices may be involved in the management of financial risks. The specific number and type depend on the actual scenario and are not limited here. In addition, Figure 1 One server is shown in the figure, but in actual scenarios, multiple servers may also be involved, especially in scenarios of multi-model training interaction. The specific number of servers depends on the actual scenario.

[0111] In this embodiment, the server can be a standalone physical server, a server cluster or distributed system consisting of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms. The terminal can be a smartphone, tablet computer, laptop computer, desktop computer, smart speaker, smartwatch, etc., but is not limited to these. The terminal and server can be connected directly or indirectly via wired or wireless communication, and the terminal and server can be connected to form a blockchain network, which is not limited in this application.

[0112] It can be understood that the above-mentioned financial risk management system can run on personal mobile terminals, for example: as an application such as a security manager, it can also run on a server, and it can also run on a third-party device to provide financial risk management to obtain the management and processing results of the financial risks of the information source; the specific financial risk management system can be run in the above-mentioned device in the form of a program, or it can be run as a system component in the above-mentioned device, or it can be used as a cloud service program. The specific operation mode depends on the actual scenario and is not limited here.

[0113] With the rapid development of Internet technology, people use mobile payments in more and more scenarios, which brings with it increasing financial risks. Therefore, it is necessary to identify and screen financial data on the Internet in order to facilitate risk control.

[0114] For example, in the prevention and control of money laundering risks, we can develop and launch prevention and control rules based on fixed regulatory provisions. Simultaneously, as new regulatory requirements, such as risk warnings, are introduced, the number of rules can be manually increased to enhance risk control effectiveness, creating a parallel rule-based prevention and control system.

[0115] However, parallel rule-based prevention and control requires a large amount of manual resources, and the various rules cannot cover all risk items in all scenarios, which affects the accuracy of determining the control objects in the financial risk management process.

[0116] In order to solve the above problems, this application proposes a financial risk management method, which is applied to Figure 2 The process framework of financial risk management is shown as follows: Figure 2 As shown, it is a process architecture diagram of financial risk management provided by an embodiment of the present application. The user performs transaction operations through the terminal, thereby generating corresponding financial information on the server side, and then comparing the financial information with a preset rule library, and the preset rule library is updateable; the risk object is determined by the comparison result, and then the risk object is subjected to risk assessment based on risk indicators, thereby carrying out the risk management process.

[0117] It is understandable that the method provided by the present application can be written as a program to serve as a processing logic in a hardware system, or as a financial risk management device, which implements the above processing logic in an integrated or external manner. As an implementation method, the financial risk management device obtains target financial data; then parses the target financial data based on a preset rule library to determine the risk object. The preset rule library includes static rules and dynamic rules. The static rules are determined based on the regulatory information corresponding to the target financial data, and the dynamic rules are determined based on the scenario information corresponding to the target financial data. Furthermore, the risk object is evaluated according to the preset risk indicators to obtain the target characteristic value, which is used to control the financial risk of the risk object. In this way, an efficient control process of financial risk is achieved. Due to the use of a composite rule of static rules and dynamic rules, the hit rate of the risk object is improved, and further the risk object is evaluated twice by the risk indicator, and the risk object is judged from multiple dimensions, which improves the accuracy of risk object determination in the financial risk management process.

[0118] In combination with the above process structure, the following will introduce the management method of financial risks in this application. Please refer to Figure 3 , Figure 3A flowchart of a financial risk management method provided in an embodiment of the present application is provided. The management method can be executed by a terminal device, by a service, or by both a terminal device and a server. The following description takes server execution as an example. The embodiment of the present application includes at least the following steps:

[0119] 301. Obtain target financial data.

[0120] In this embodiment, the target financial data can be the financial data corresponding to a single user object or multiple user objects. Specifically, the user object can be a natural person or a company. It can also be other identifiable transaction objects, and the specific form depends on the actual scenario.

[0121] In one possible scenario, the target financial data may be data collected over a period of time, that is, financial operation information within a preset time period is obtained in response to a target operation, wherein the target operation may be an audit operation clicked by the auditor; then the operation object corresponding to each item in the financial operation information is extracted, in order to determine the object corresponding to the financial information and facilitate the organization of the information of the object; and then the operation object is associated with the financial operation information to obtain the target financial data, so as to facilitate the rapid determination of the object during the analysis of the target financial data, thereby improving the efficiency of the audit.

[0122] 302. Analyze the target financial data based on the preset rule base to determine the risk objects.

[0123] In this embodiment, the preset rule base includes static rules and dynamic rules. The static rules are determined based on the regulatory information corresponding to the target financial data, and the dynamic rules are determined based on the scenario information corresponding to the target financial data. Specifically, the basic rules for risk control can be determined through static rules. These are basic rules that can provide explainability in the risk control process. The precise rules for risk control can be determined through dynamic rules, that is, characteristic rules corresponding to different control scenarios, which can provide accuracy in the risk control process.

[0124] Specifically, the static rule parsing process first determines the domain and time information corresponding to the target financial data; then, based on this domain and time information, determines the regulatory information; further, extracts regulatory signatures from this regulatory information; and finally, parses the target financial data based on these signatures to identify risk objects. This takes into account the applicable domains and timeliness of regulations, ensuring that static rules are set based on the latest regulations, thus ensuring accurate risk management.

[0125] Optionally, regulatory feature items can be determined by parsing transaction information from different dimensions. Specifically, the transaction information corresponding to the target financial data is first determined, including at least one of the following: transaction object, transaction frequency, transaction time, or transaction value. The regulatory information is then traversed based on the transaction object, transaction frequency, transaction time, and transaction value to obtain regulatory feature items, thereby ensuring comprehensiveness of the regulatory feature items.

[0126] Optionally, since the user object is time-sensitive during the transaction process, that is, there is historical information, the most recent information can be used for judgment, that is, first determine the target object corresponding to the target financial data; then call the historical information of the target object; and then extract the transaction information from the historical information according to a preset time period, wherein the preset time period can be set immediately, such as 1 month, or the preset time period can be obtained based on historical statistics, such as November to December being a high-risk period; thereby improving the pertinence of the transaction information and better reflecting the transaction situation of the user object.

[0127] In one possible scenario, static rules serve as the foundational rules, i.e., conventional risk control rules established in accordance with regulatory requirements. These rules are highly interpretable. Specifically, the regulatory information uses some of the 18 items on suspicious transactions in the Measures for the Administration of Reporting Large and Suspicious Transactions of Financial Institutions issued by the People's Bank of China in 2006 as an example. The specific prevention and control rules are as follows:

[0128] (1) Dispersed transfer-in and centralized transfer-out patterns: By counting the number of users’ funds transferred into counterparties (USE-IN), the number of users’ funds transferred out (USER-OUT), and the amount of funds transferred in (AMT), basic rules can be established to prevent and control this type of risk pattern. X, Y, and Z are the risk control thresholds for these characteristics.

[0129] Specifically, the static rule is to judge: USE-IN>X; USER-OUT<Y;AMT> Z, any object that meets the above size relationship can be regarded as a risk object.

[0130] (2) High-frequency transactions: Frequent payments and receipts between the same payer and payee within a short period of time, with the transaction amount approaching the high-value transaction standard. Count the frequency N and amount AMT of transactions between users.

[0131] Specifically, the static rule may be to calculate users who meet the following rules: N>frequency threshold; AMT>amount threshold, that is, objects that meet the above size relationship can be regarded as risk objects.

[0132] (3) Transaction surge: A long-idle account is suddenly activated for unknown reasons, or an account with low capital flow experiences an abnormal inflow of funds, with a large amount of funds received and paid in a short period of time. Calculate the user's transaction amount X in the past six months and the transaction amount Y in the past seven days. Specifically, the static rule can be that if the following rules are met, then this type of risk is met: Y / X > a certain ratio; Y is greater than the amount threshold. In other words, objects that meet the above size relationship can be considered risk objects.

[0133] (4) Large-value transactions: refers to the total amount of AMT transactions in and out of a user during the statistical period exceeding a certain threshold.

[0134] Specifically, the static rule is to judge: AMT> amount threshold, that is, objects that meet the above size relationship can be regarded as risk objects.

[0135] It is understandable that the specific static rule setting can be to satisfy one or more of the above examples as a risk object. The specific form depends on the actual scenario and is not limited here.

[0136] The following describes dynamic rules. These rules can be set based on target models corresponding to different scenarios. Specifically, a scenario model library is first invoked, which is updated based on the addition of new cases (i.e., transaction parameters associated with users identified as risk targets). The scenario model library is then traversed based on the scenario information corresponding to the target financial data to obtain a target model associated with the target financial data. The target financial data is then input into the target model to obtain the risk target, ensuring targeted targeting across different scenarios and improving the accuracy of risk identification.

[0137] Optionally, the process of identifying risk objects can be calculated based on the characteristic values ​​input into the target model. Specifically, the target financial data is first input into the target model to obtain risk characteristic items. Then, based on the decision number model, weight information corresponding to the risk characteristic items is determined. Furthermore, a weighted calculation is performed for each object indicated in the target financial data based on the weight information and the risk characteristic items to obtain a scenario characteristic value. Risk objects are then determined based on the scenario characteristic values. For example, the risk values ​​corresponding to multiple risk characteristic items are calculated, and the user's scenario characteristic value Sn = ∑ characteristic m * weight m. The risk object is then determined based on the relationship between the scenario characteristic value and the threshold. This ensures that different risk characteristic items have different degrees of influence on the risk object, thereby improving the accuracy of risk object determination.

[0138] Optionally, the determination of risk characteristic items may also include black samples marked by relevant personnel, that is, characteristic data with risks; that is, first call the marked target sample (black sample); then update the risk characteristic item based on the target sample; and then determine the weight information corresponding to the updated risk characteristic item based on the decision number model. Among them, the decision number model is a decision analysis method that evaluates project risks and judges its feasibility by constructing a decision tree based on the known probabilities of occurrence of various situations. It is a graphical method that intuitively uses probability analysis, thereby ensuring the comprehensiveness of the risk characteristic item setting and the rationality of the weights.

[0139] Optionally, the target model can utilize multi-dimensional features and multiple model algorithms, and use samples for supervised training or unsupervised attempts, not limited to the features and algorithms in the above examples.

[0140] In one possible scenario, dynamic rules are scenario rules determined based on actual case circumstances. These are precise rules developed through multi-dimensional features and complex models. These precise rules offer high accuracy but are relatively weak in interpretability, thus complementing static rules. Common model rules (scenario information) include gambling, pyramid schemes, cross-border remittances, smuggling, and telecommunications fraud. The following uses a gambling model (scenario) as an example:

[0141] First, risk characteristics can include:

[0142] (1) Transaction characteristics: number of counterparties, average transaction amount, average number of transactions per counterparty, proportion of weekday transaction amount, proportion of daytime transaction amount, number of counterparties with transaction inflows, ratio of daily inflows to daily balance, etc.

[0143] (2) Store characteristics: percentage of virtual transactions, store transaction rate, number of store products, store credibility, etc.

[0144] (3) Transaction note features: the number of transactions and counterparties containing sensitive words, the number of transactions and counterparties containing numbers.

[0145] (4) Characteristics of the buyer-seller relationship: the strength of the non-financial relationship between the two parties to the transaction, and the proportion of overlap between the counterparty of the funds flowing into the transaction and the counterparty of other users.

[0146] Then, for the above risk feature items and the black samples marked by historical manual confirmation, the decision number model is used to determine the weight value of each feature.

[0147] Furthermore, for each user, the risk corresponding to the above features is calculated, and the user's gambling risk value Sn = ∑ feature m * weight m is summarized.

[0148] Finally, the N users whose risk values ​​Sn are higher than the threshold or whose risk values ​​are the highest are audited and input into the next indicator calculation.

[0149] It is understandable that after the classification of the above rules, basic rules are used to ensure the explainability of the prevention and control system, and refined model rules are used to improve the hit rate of the entire system and focus on combating core risks, which better balances explainability and effectiveness.

[0150] In one possible scenario, the target financial data is processed as follows: Figure 4 As shown, Figure 4 A scenario diagram of a financial risk management method provided by an embodiment of the present application. Static rules (basic rules) and dynamic rules (precise rules) are written into the rule engine, and then the rule hits are determined. For users whose financial data hits any rule or multiple rules, further risk indicator assessment is performed. If the assessment result meets the threshold, it is input into the audit platform for manual review, thereby realizing a hierarchical risk determination process and ensuring the accuracy of risk objects.

[0151] It is understandable that other major types of rules can be added to the basic rules and special rules, but the overall prevention and control rules are classified, and different categories are responsible for achieving overall prevention and control goals such as explainability and effectiveness.

[0152] 303. Evaluate the risk object according to the preset risk indicators to obtain the target characteristic value, which is used to control the financial risk of the risk object.

[0153] In this embodiment, the preset risk indicators are used to further evaluate the relevant parameters of the risk object and to judge the risk object from the perspective of overall data.

[0154] Specifically, the process of determining the target feature value may include first determining a base value, a comparison value, and an associated value corresponding to the risk object based on a preset risk indicator, wherein the base value is used to indicate the risk object's corresponding situation in the risk project, the comparison value is used to indicate the comparison between the risk object and a preset threshold, and the associated value is used to indicate the similarity between the risk object and the associated object; then, calculations are performed based on the base value, the comparison value, and the associated value to obtain the target feature value. For example, the base value may be a transaction amount, transaction volume, etc.; the comparison value may be a comparison (deviation) between the transaction amount and a preset limit; and the associated value may be the numerical similarity of the transaction values ​​of users within a group associated with the user, thereby improving the accuracy of the target feature value.

[0155] Optionally, since numerical values ​​have range characteristics, they can be divided into levels according to data relationships, that is, first determine the corresponding feature levels based on the basic value, comparison value and associated value; then call the level value corresponding to the feature level; and then calculate based on the level value to obtain the target feature value, thereby improving the generalization degree of the target feature value and avoiding interference from special values.

[0156] In addition, items can be added, deleted, or modified for the preset risk indicators in the process of comprehensive user risk assessment, so that the final high-scoring population is more in line with the organization's definition of high-risk population. The specific indicator type depends on the actual scenario.

[0157] In one possible scenario, the pre-set risk indicators for a comprehensive risk assessment may include:

[0158] (1) The user's money laundering risk level. This is the base value; the higher the risk level, the higher the risk, which is recorded as R1. Risk levels 1-5 are scored 1-5 points respectively.

[0159] (2) Risk deviation from the rule hit. This is a comparative value; that is, the proportion of users exceeding the rule hit threshold. Users who are just above the rule threshold have a lower risk, while users who exceed the threshold further have a higher risk, denoted as R2. R2 = (user feature value - threshold) / threshold.

[0160] (3) Historical audit times. This is the base value; the number of times the user system has been audited by anti-money laundering rules. The greater the number, the higher the risk. R3 = audit times.

[0161] (4) Historical audit status. This is the base value. Users who have been audited in the past can refer to the results of historical manual audits. If the result is a true hit, the risk is higher. If the result is a false hit, the risk is lower, recorded as R4. If the result is a true hit, R4 = 1; if the result is a false hit, R4 = 0.

[0162] (5) Group behavior correlation. This is the correlation value; that is, the behavioral similarity between the user and the group similar to him or her. For example, white-collar workers who are divided into the same group may spend more at the beginning of the month, while others spend more at other times of the month, or their funds fluctuate at other frequencies. The greater the difference, the lower the group behavior similarity and the greater the risk. This is recorded as R5. R5 = (actual funds of the user - mean funds of the group) / standard deviation of funds of the group.

[0163] (6) Number of audit rules in this round. This is the base value. In the same audit cycle, the more rules are hit simultaneously, the higher the risk of the user, which is recorded as R6 = the number of audit rules in this round.

[0164] (7) Reporting rate of hit rules. This is the base value; if a rule with a high hit rate is hit, the user's risk is higher. Conversely, if the hit rate of the rules is low, the risk is lower, recorded as R7 = historical reporting rate.

[0165] (8) Importance of the hit rule. This is the base value. For example, rules like social phobia and gangsterism are more important than ordinary rules, which is recorded as R8. The value is assigned from 1 to 5 based on manual definition, with 1 being low risk, 3 being medium risk, and 5 being high risk.

[0166] Furthermore, using decision tree algorithms or manual experience, based on historical manually confirmed black samples, the importance of the above risks is weighted, with weights S1 to S8 respectively; and the summary score of each audited user in the eight dimensions of comprehensive risk is calculated, and the formula can be: target eigenvalue = ∑Rm*Sm.

[0167] Specifically, after the target feature value is determined, users corresponding to financial data with a target feature value greater than a threshold value can be manually reviewed or directly prohibited from trading.

[0168] Optionally, since there may be multiple users to be audited at the same time, a risk sequence consisting of multiple risk objects can be determined based on the target characteristic value; then the target object in the risk sequence is extracted based on the order information corresponding to the risk sequence; and then the target object is pushed to the audit platform for financial risk control; for example, the total comprehensive risk of all audited users is sorted, and the N users with risk values ​​greater than a threshold or the highest risk values ​​are audited, and then the audited users are pushed to the review platform for manual review, thereby improving the efficiency of the audit push.

[0169] It is understandable that in addition to pushing and manually processing users with a final comprehensive score higher than N points, you can also choose to directly cut off the M users with the highest risk. If you do not cut off, you can also push all users to the review platform for manual review.

[0170] In conjunction with the above embodiments, it can be seen that by acquiring target financial data and then parsing the target financial data based on a preset rule base to determine risk objects, the preset rule base includes static rules and dynamic rules. The static rules are determined based on the regulatory information corresponding to the target financial data, and the dynamic rules are determined based on the scenario information corresponding to the target financial data. Furthermore, the risk objects are evaluated according to preset risk indicators to obtain target characteristic values, which are used to control the financial risks of the risk objects. This achieves an efficient control process for financial risks. Due to the use of a composite rule of static and dynamic rules, the hit rate of risk objects is improved. Furthermore, the risk objects are secondary evaluated through risk indicators, and the risk objects are judged from multiple dimensions, which improves the accuracy of risk object determination in the financial risk management process.

[0171] In a possible scenario, the financial risk management process in this application can also be performed on the real-time operation of a single user, that is, real-time monitoring of a single user. Figure 5 As shown, Figure 5 A schematic diagram of another scenario of a financial risk management method provided by an embodiment of the present application. When a user performs a financial operation, such as a payment operation, after clicking OK A1 on the terminal, the server side will be triggered to perform financial risk management. Specifically, first determine whether the financial data corresponding to the user (including current transaction operations and historical transaction operations) hits the preset rule library 501. For the description of the preset rule library, refer to Figure 3 Step 302 of the illustrated embodiment will not be described in detail here.

[0172] If it is determined to be a risk object, then risk indicator evaluation 502 is performed. For the description of the preset rule base, refer to Figure 3 Step 303 of the illustrated embodiment will not be described in detail here.

[0173] Then, the target characteristic value of the user can be obtained. If the target characteristic value is less than the threshold, it means that the transaction operation of the user does not have any risk and can be carried out, so the interface A2 indicating successful payment can be displayed.

[0174] In addition, if the target feature value is greater than or equal to the threshold, it means that the user's transaction operation is risky and cannot be carried out, so it can be displayed as follows Figure 6 The interface shown, Figure 6 A scenario diagram of another financial risk management method provided in an embodiment of the present application, that is, when a risk object is determined, an operation abnormality B1 is prompted on the terminal, that is, the user's transaction operation is blocked, and it is necessary to contact customer service to carry out the relevant financial authentication process. For the money laundering scenario, the user's money laundering operation is blocked.

[0175] Specifically, the above-mentioned financial risk control can be money laundering risk control, the static rules are regulatory laws and regulations, and the scenarios corresponding to the dynamic rules include gambling scenarios, pyramid scheme scenarios, cross-border remittance scenarios, smuggling scenarios, and telecommunications fraud scenarios. The preset risk indicators include money laundering risk level, risk deviation, historical audit times, historical review status, group behavior correlation, number of audit rules in this round, reporting rate of hit rules, and importance of hit rules. The specific scenario parameters depend on actual conditions and are not limited here.

[0176] As can be seen from the above examples, the systematic construction of prevention and control rules, divided into basic rules and precise rules, balances explainability and accuracy. Furthermore, a comprehensive risk assessment is added before formal audits, comprehensively adjusting the quality of all rule audits, reducing the withdrawal of low-risk users and appropriately reducing the demand for manpower.

[0177] The above embodiment describes the process of triggering financial risk management by the terminal. The following describes the process of triggering financial risk management by the server. Figure 7 , Figure 7 This is a flowchart of another financial risk management method provided in an embodiment of the present application. The embodiment of the present application includes at least the following steps:

[0178] 701. Responding to a target operation, obtain financial operation information within a preset time period.

[0179] In this embodiment, the target operation may be a click operation performed by a relevant person during the inspection process on the server side, such as Figure 8 As shown, Figure 8 A schematic diagram of another scenario for managing financial risk provided by an embodiment of the present application. The diagram shows the total volume of transactions, the total transaction amount, and the transaction speed (frequency) in the trading system. Financial operation information can be monitored based on this real-time data, i.e., by clicking the button shown in the diagram, or automatically executing when any parameter in the trading system is abnormal.

[0180] Specifically, the preset time period can be fixed, such as one year; or it can be determined based on different abnormal information. For example, when the total transaction volume is abnormal, the preset time period is set to half a year, thereby improving the pertinence of relevant financial operation information.

[0181] 702. Integrate the financial operation information to obtain target financial data.

[0182] In this embodiment, the financial operation information is integrated, that is, the user objects corresponding to the financial operation information are determined and associated, thereby obtaining target financial data.

[0183] Optionally, after determining the user, the transaction information associated with the user in the system may also be traversed to supplement the financial operation information, thereby improving the comprehensiveness of the target financial data.

[0184] 703. Determine the monitoring scenario corresponding to the target operation.

[0185] In this embodiment, the monitoring scenario is the scenario targeted by the current risk control, such as gambling, pyramid schemes, cross-border remittances, smuggling, telecommunications fraud, etc.

[0186] 704. Call the corresponding target model based on the monitoring scenario.

[0187] In this embodiment, the calling of the target model is the setting of the user dynamic rules. The specific setting process is as follows: Figure 3 The steps described in step 302 of the illustrated embodiment are not described in detail here.

[0188] 705. Analyze the target financial data to obtain risk objects.

[0189] 706. Evaluate the risk object based on the risk indicator to obtain the target characteristic value.

[0190] In this embodiment, steps 705 and 706 can be found in Figure 3 The description of the illustrated embodiment is omitted here.

[0191] 707. Conduct risk review based on target characteristic values.

[0192] In this embodiment, risk review based on target feature values ​​can classify users into high-risk users and low-risk users, and then mark them with different identifiers to facilitate review after being pushed to the manual review platform.

[0193] In one possible scenario, Figure 9 As shown, Figure 9 This is a scenario diagram of another financial risk management method provided by an embodiment of the present application. Specifically, data pushed to the audit platform can be categorized and displayed using different objects, indicating the corresponding risk level and the target characteristic value determined during the risk assessment process. Users can also click on details to learn about the financial scenario corresponding to the user object, the number of hits against the preset rule, and related indicator parameters. The specific parameters displayed can be any of the parameters mentioned in the above embodiments and are not limited here.

[0194] In one possible scenario, based on calculations of existing rules, after the above-mentioned transformation, while ensuring the interpretability of the entire prevention and control system remains unchanged, the hit rate can be increased by more than 50%, and at the same time, the output can be controlled to about 20% of low-risk users, which means a 20% reduction in manpower consumption.

[0195] Through the optimization of this embodiment, the original purely parallel rule-based control system has been split into two parts: basic rules and specialized rules. Basic rules ensure the interpretability of the entire control system, while specialized rules enhance the effectiveness of the entire control system and focus on risk control. Furthermore, through a secondary comprehensive risk assessment of targeted users, the overall control quality of the control system and the stability of the number of risky users promoted have been improved.

[0196] In order to better implement the above solution of the embodiment of the present application, the following also provides related devices for implementing the above solution. Figure 10 , Figure 10 This is a schematic diagram of the structure of a financial risk management device provided in an embodiment of the present application. The management device 1000 includes:

[0197] An acquisition unit 1001 is used to acquire target financial data;

[0198] A parsing unit 1002 is configured to parse the target financial data based on a preset rule base to determine risk objects, wherein the preset rule base includes static rules and dynamic rules, wherein the static rules are determined based on regulatory information corresponding to the target financial data, and the dynamic rules are determined based on scenario information corresponding to the target financial data;

[0199] The management unit 1003 is configured to evaluate the risk object according to a preset risk indicator to obtain a target characteristic value, and the target characteristic value is used to perform financial risk control on the risk object.

[0200] Optionally, in some possible implementations of the present application, the parsing unit 1002 is specifically configured to determine the domain information and time information corresponding to the target financial data;

[0201] The parsing unit 1002 is specifically configured to determine the regulatory information based on the domain information and the time information;

[0202] The parsing unit 1002 is specifically configured to extract regulatory feature items from the regulatory information;

[0203] The parsing unit 1002 is specifically configured to parse the target financial data based on the regulatory feature items to obtain the risk object.

[0204] Optionally, in some possible implementations of the present application, the parsing unit 1002 is specifically configured to determine transaction information corresponding to the target financial data, where the transaction information includes at least one of a transaction object, a transaction frequency, a transaction time, or a transaction value;

[0205] The parsing unit 1002 is specifically configured to traverse the regulatory information according to the transaction object, the transaction frequency, the transaction time, and the transaction value to obtain the regulatory feature item.

[0206] Optionally, in some possible implementations of the present application, the parsing unit 1002 is specifically configured to determine a target object corresponding to the target financial data;

[0207] The parsing unit 1002 is specifically configured to call the historical information of the target object;

[0208] The parsing unit 1002 is specifically configured to extract the transaction information from the historical information according to a preset time period.

[0209] Optionally, in some possible implementations of the present application, the parsing unit 1002 is specifically configured to call a scenario model library, and the scenario model library is updated based on an increase in cases;

[0210] The parsing unit 1002 is specifically configured to traverse the scenario model library according to the scenario information corresponding to the target financial data to obtain a target model associated with the target financial data;

[0211] The parsing unit 1002 is specifically configured to input the target financial data into the target model to obtain the risk object.

[0212] Optionally, in some possible implementations of the present application, the parsing unit 1002 is specifically configured to input the target financial data into the target model to obtain risk feature items;

[0213] The parsing unit 1002 is specifically configured to determine weight information corresponding to the risk feature item based on a decision number model;

[0214] The parsing unit 1002 is specifically configured to perform weighted calculation on each object indicated in the target financial data based on the weight information and the risk feature item to obtain a scenario feature value;

[0215] The parsing unit 1002 is specifically configured to determine the risk object based on the scenario feature value.

[0216] Optionally, in some possible implementations of the present application, the parsing unit 1002 is specifically configured to call a marked target sample;

[0217] The parsing unit 1002 is specifically configured to update the risk feature item based on the target sample;

[0218] The analyzing unit 1002 is specifically configured to determine the updated weight information corresponding to the risk feature item based on the decision number model.

[0219] Optionally, in some possible implementations of the present application, the management unit 1003 is specifically configured to determine a base value, a comparison value, and an associated value corresponding to the risk object based on the preset risk indicator, wherein the base value is used to indicate the corresponding situation of the risk object in the risk project, the comparison value is used to indicate the comparison situation of the risk object with a preset threshold, and the associated value is used to indicate the similarity between the risk object and the associated object;

[0220] The management unit 1003 is specifically configured to perform calculations based on the base value, the comparison value, and the associated value to obtain the target feature value.

[0221] Optionally, in some possible implementations of the present application, the management unit 1003 is specifically configured to determine, according to the base value, the comparison value, and the correlation value, the corresponding feature levels;

[0222] The management unit 1003 is specifically configured to call the level value corresponding to the feature level;

[0223] The management unit 1003 is specifically configured to perform calculations based on the level value to obtain the target feature value.

[0224] Optionally, in some possible implementations of the present application, the acquiring unit 1001 is specifically configured to acquire financial operation information within a preset time period in response to a target operation;

[0225] The acquisition unit 1001 is specifically configured to extract the operation object corresponding to each item in the financial operation information;

[0226] The acquisition unit 1001 is specifically configured to associate the operation object with the financial operation information to obtain the target financial data.

[0227] Optionally, in some possible implementations of the present application, the management unit 1003 is specifically configured to determine a risk sequence consisting of a plurality of risk objects according to the target feature value;

[0228] The management unit 1003 is specifically configured to extract target objects in the risk sequence based on sequence information corresponding to the risk sequence;

[0229] The management unit 1003 is specifically used to push the target object to the review platform for financial risk control.

[0230] The system obtains target financial data and then analyzes it based on a preset rule base to identify risk targets. The preset rule base includes static and dynamic rules. Static rules are determined based on regulatory information corresponding to the target financial data, while dynamic rules are determined based on scenario information corresponding to the target financial data. Furthermore, the risk targets are evaluated based on preset risk indicators to obtain target characteristic values, which are used to control the financial risks of the risk targets. This achieves efficient financial risk control. The use of a composite rule of static and dynamic rules improves the hit rate of risk targets. Furthermore, risk targets are secondary evaluated using risk indicators, judging risk targets from multiple dimensions and improving the accuracy of risk target identification during the financial risk management process.

[0231] The present application also provides a terminal device, such as Figure 11The figure is a schematic diagram of the structure of another terminal device provided by an embodiment of the present application. For ease of explanation, only the parts related to the embodiment of the present application are shown. For specific technical details not disclosed, please refer to the method section of the embodiment of the present application. The terminal can be any terminal device including a mobile phone, tablet computer, personal digital assistant (PDA), point of sales (POS), car computer, etc. Taking the mobile phone as an example:

[0232] Figure 11 The block diagram shows a partial structure of a mobile phone related to the terminal provided in the embodiment of the present application. Figure 11 The mobile phone includes components such as a radio frequency (RF) circuit 1110, a memory 1120, an input unit 1130, a display unit 1140, a sensor 1150, an audio circuit 1160, a wireless fidelity (WiFi) module 1170, a processor 1180, and a power supply 1190. Those skilled in the art will appreciate that Figure 11 The mobile phone structure shown in the figure does not constitute a limitation to the mobile phone, and may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently.

[0233] The following combination Figure 11 A detailed introduction to the various components of a mobile phone:

[0234] The RF circuit 1110 can be used to receive and send signals during information transmission or calls. In particular, after receiving the downlink information from the base station, it is sent to the processor 1180 for processing; in addition, the designed uplink data is sent to the base station. Generally, the RF circuit 1110 includes but is not limited to an antenna, at least one amplifier, a transceiver, a coupler, a low noise amplifier (LNA), a duplexer, etc. In addition, the RF circuit 1110 can also communicate with the network and other devices through wireless communication. The above-mentioned wireless communication can use any communication standard or protocol, including but not limited to the global system of mobile communications (GSM), general packet radio service (GPRS), code division multiple access (CDMA), wideband code division multiple access (WCDMA), long term evolution (LTE), email, short messaging service (SMS), etc.

[0235] The memory 1120 can be used to store software programs and modules. The processor 1180 executes the various functional applications and data processing of the mobile phone by running the software programs and modules stored in the memory 1120. The memory 1120 may mainly include a program storage area and a data storage area. The program storage area may store an operating system and at least one application required for a function (such as a sound playback function, an image playback function, etc.); the data storage area may store data created based on the use of the mobile phone (such as audio data, a phone book, etc.). In addition, the memory 1120 may include high-speed random access memory and may also include non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage device.

[0236] The input unit 1130 can be used to receive input digital or character information, and to generate key signal input related to the user settings and function control of the mobile phone. Specifically, the input unit 1130 may include a touch panel 1131 and other input devices 1132. The touch panel 1131, also known as a touch screen, can collect user touch operations on or near it (such as operations performed by the user using any suitable object or accessory such as a finger, stylus, etc. on or near the touch panel 1131, as well as air touch operations within a certain range on the touch panel 1131) and drive the corresponding connection device according to a pre-set program. Optionally, the touch panel 1131 may include two parts: a touch detection device and a touch controller. Among them, the touch detection device detects the user's touch direction, detects the signal caused by the touch operation, and transmits the signal to the touch controller; the touch controller receives the touch information from the touch detection device, converts it into touch point coordinates, and then sends it to the processor 1180, and can receive commands sent by the processor 1180 and execute them. In addition, the touch panel 1131 can be implemented using various types such as resistive, capacitive, infrared, and surface acoustic wave. In addition to the touch panel 1131, the input unit 1130 can also include other input devices 1132. Specifically, the other input devices 1132 can include, but are not limited to, one or more of a physical keyboard, function keys (such as volume control keys, power keys, etc.), a trackball, a mouse, a joystick, and the like.

[0237] The display unit 1140 can be used to display information input by the user or information provided to the user and various menus of the mobile phone. The display unit 1140 may include a display panel 1141. Optionally, the display panel 1141 may be configured in the form of a liquid crystal display (LCD), an organic light-emitting diode (OLED), etc. Further, the touch panel 1131 may cover the display panel 1141. When the touch panel 1131 detects a touch operation on or near it, it is transmitted to the processor 1180 to determine the type of touch event. Subsequently, the processor 1180 provides corresponding visual output on the display panel 1141 according to the type of touch event. Although in Figure 11 In the embodiment, the touch panel 1131 and the display panel 1141 are used as two independent components to realize the input and output functions of the mobile phone, but in some embodiments, the touch panel 1131 and the display panel 1141 can be integrated to realize the input and output functions of the mobile phone.

[0238] The mobile phone may also include at least one sensor 1150, such as a light sensor, a motion sensor, and other sensors. Specifically, the light sensor may include an ambient light sensor and a proximity sensor, wherein the ambient light sensor may adjust the brightness of the display panel 1141 according to the brightness of the ambient light, and the proximity sensor may turn off the display panel 1141 and / or the backlight when the mobile phone is moved to the ear. As a type of motion sensor, the accelerometer sensor can detect the magnitude of acceleration in all directions (generally three axes), and can detect the magnitude and direction of gravity when stationary. It can be used for applications that identify the posture of the mobile phone (such as horizontal and vertical screen switching, related games, magnetometer posture calibration), vibration recognition related functions (such as pedometer, tapping), etc.; as for other sensors that the mobile phone can also be configured with, such as gyroscopes, barometers, hygrometers, thermometers, infrared sensors, etc., they will not be described here.

[0239] Audio circuit 1160, speaker 1161, and microphone 1162 provide an audio interface between the user and the phone. Audio circuit 1160 converts received audio data into electrical signals and transmits them to speaker 1161, which then converts them into sound signals for output. Microphone 1162, on the other hand, converts collected sound signals into electrical signals, which are then received by audio circuit 1160 and converted into audio data. The audio data is then processed by processor 1180 and transmitted to, for example, another phone via RF circuit 1110, or stored in memory 1120 for further processing.

[0240] WiFi is a short-range wireless transmission technology. The mobile phone can help users send and receive emails, browse the web and access streaming media through the WiFi module 1170. It provides users with wireless broadband Internet access. Figure 11 A WiFi module 1170 is shown, but it is understandable that it is not an essential component of the mobile phone and can be omitted as needed without changing the essence of the invention.

[0241] Processor 1180 is the control center of the phone, connecting all parts of the phone using various interfaces and circuits. It executes software programs and / or modules stored in memory 1120 and accesses data stored in memory 1120 to perform various phone functions and process data. Optionally, processor 1180 may include one or more processing units. Alternatively, processor 1180 may integrate an application processor and a modem processor. The application processor primarily handles the operating system, user interface, and application programs, while the modem processor primarily handles wireless communications. It is understood that the modem processor may not be integrated into processor 1180.

[0242] The mobile phone also includes a power supply 1190 (such as a battery) for supplying power to various components. Optionally, the power supply can be logically connected to the processor 1180 through a power management system, thereby managing charging, discharging, and power consumption through the power management system.

[0243] Although not shown, the mobile phone may also include a camera, a Bluetooth module, etc., which will not be described in detail here.

[0244] In the embodiment of the present application, the processor 1180 included in the terminal also has the function of executing each step of the above-mentioned page processing method.

[0245] The present application also provides a server. Figure 12 , Figure 12 This is a structural diagram of a server provided in an embodiment of the present application. The server 1200 may have relatively large differences due to different configurations or performances, and may include one or more central processing units (CPU) 1222 (for example, one or more processors) and memory 1232, and one or more storage media 1230 (for example, one or more mass storage devices) for storing application programs 1242 or data 1244. Among them, the memory 1232 and the storage medium 1230 can be short-term storage or persistent storage. The program stored in the storage medium 1230 may include one or more modules (not shown in the figure), and each module may include a series of instruction operations on the server. Furthermore, the central processing unit 1222 can be configured to communicate with the storage medium 1230 to execute a series of instruction operations in the storage medium 1230 on the server 1200.

[0246] The server 1200 may also include one or more power supplies 1226, one or more wired or wireless network interfaces 1250, one or more input and output interfaces 1258, and / or one or more operating systems 1241, such as Windows Server™, Mac OS X™, Unix™, Linux™, FreeBSD™, etc.

[0247] The steps performed by the management device in the above embodiment can be based on the Figure 12 The server structure shown.

[0248] The present application also provides a computer-readable storage medium in which financial risk management instructions are stored. When the computer-readable storage medium is run on a computer, the computer executes the above-mentioned Figures 3 to 9 The illustrated embodiment describes the steps performed by the financial risk management device in the method.

[0249] The present application also provides a computer program product including financial risk management instructions, which, when executed on a computer, enables the computer to execute the aforementioned Figures 3 to 9 The illustrated embodiment describes the steps performed by the financial risk management device in the method.

[0250] The embodiment of the present application also provides a financial risk management system, which may include Figure 10 The financial risk management device of the described embodiment, or Figure 11 The terminal device in the described embodiment, or Figure 12 The server being described.

[0251] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0252] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0253] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0254] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0255] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for enabling a computer device (which can be a personal computer, a financial risk management device, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0256] As described above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the above embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the above embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for managing financial risk, characterized in that: include: Obtain target financial data; Parsing the target financial data based on a preset rule library to determine risk objects, the preset rule library including static rules and dynamic rules, the static rules being determined based on regulatory information corresponding to the target financial data, and the dynamic rules being determined based on scenario information corresponding to a target model in a scenario model library, the scenario information corresponding to the target financial data, and the scenario model library being updated based on the addition of cases; Determine a base value, a comparison value, and an associated value corresponding to the risk object based on a preset risk indicator, wherein the base value is used to indicate the correspondence of the risk object to the risk project, the comparison value is used to indicate the comparison between the risk object and a preset threshold, and the associated value is used to indicate the similarity between the risk object and the associated object; Calculation is performed based on the basic value, the comparison value, and the associated value to obtain a target characteristic value, which is used to perform financial risk control on the risk object.

2. The method according to claim 1, characterized in that The analyzing the target financial data based on a preset rule base to determine risk objects includes: Determining the domain information and time information corresponding to the target financial data; determining the supervision information according to the domain information and the time information; Extracting regulatory feature items from the regulatory information; The target financial data is parsed based on the regulatory feature items to obtain the risk object.

3. The method according to claim 2, characterized in that The extracting of regulatory feature items from the regulatory information includes: Determining transaction information corresponding to the target financial data, the transaction information including at least one of a transaction object, a transaction frequency, a transaction time, or a transaction value; The regulatory information is traversed according to the transaction object, the transaction frequency, the transaction time, and the transaction value to obtain the regulatory feature item.

4. The method according to claim 3, characterized in that The determining of transaction information corresponding to the target financial data includes: Determining a target object corresponding to the target financial data; Retrieving historical information of the target object; The transaction information is extracted from the historical information according to a preset time period.

5. The method according to claim 1, wherein The analyzing the target financial data based on a preset rule base to determine risk objects includes: Call the scene model library; Traversing the scenario model library according to the scenario information corresponding to the target financial data to obtain a target model associated with the target financial data; The target financial data is input into the target model to obtain the risk object.

6. The method according to claim 5, characterized in that Inputting the target financial data into the target model to obtain the risk object includes: Inputting the target financial data into the target model to obtain risk feature items; Determine the weight information corresponding to the risk feature item based on the decision number model; performing a weighted calculation based on the weight information and the risk feature item for each object indicated in the target financial data to obtain a scenario feature value; The risk object is determined based on the scenario feature value.

7. The method according to claim 6, characterized in that The determining of the weight information corresponding to the risk feature item based on the decision number model includes: Call the marked target sample; Updating the risk feature item based on the target sample; The updated weight information corresponding to the risk feature item is determined based on the decision number model.

8. The method according to claim 1, characterized in that The calculating according to the base value, the comparison value and the correlation value to obtain the target feature value includes: Determine the corresponding feature level according to the base value, the comparison value and the correlation value; Calling the level value corresponding to the feature level; Calculation is performed based on the level value to obtain the target feature value.

9. The method according to claim 1, characterized in that The obtaining of target financial data includes: acquiring financial operation information within a preset time period in response to a target operation; Extracting the operation object corresponding to each item of the financial operation information; The operation object is associated with the financial operation information to obtain the target financial data.

10. The method according to any one of claims 1 to 9, characterized in that The method further comprises: Determining a risk sequence consisting of a plurality of risk objects according to the target feature value; extracting target objects in the risk sequence based on order information corresponding to the risk sequence; The target object is pushed to the audit platform for financial risk control.

11. The method according to claim 1, characterized in that The financial risk control is money laundering risk control, the static rules are regulatory laws and regulations, the scenarios corresponding to the dynamic rules include gambling scenarios, pyramid scheme scenarios, cross-border remittance scenarios, smuggling scenarios, and telecommunications fraud scenarios, and the preset risk indicators include money laundering risk level, risk deviation, historical audit times, historical review status, group behavior correlation, number of audit rules in this round, reporting rate of hit rules, and importance of hit rules.

12. A financial risk management device, characterized in that: include: an acquisition unit, used for acquiring target financial data; a parsing unit, configured to parse the target financial data based on a preset rule library to determine risk objects, the preset rule library including static rules and dynamic rules, the static rules being determined based on regulatory information corresponding to the target financial data, and the dynamic rules being determined based on scenario information corresponding to a target model in a scenario model library, the scenario information corresponding to the target financial data, and the scenario model library being updated based on the addition of cases; A management unit, configured to evaluate the risk object according to a preset risk indicator to obtain a target characteristic value, wherein the target characteristic value is used to perform financial risk control on the risk object; The management unit is specifically configured to determine a basic value, a comparison value, and an associated value corresponding to the risk object based on the preset risk indicator, wherein the basic value is used to indicate the corresponding status of the risk object in the risk project, the comparison value is used to indicate the comparison status of the risk object with a preset threshold, and the associated value is used to indicate the similarity between the risk object and the associated object; The management unit is specifically configured to perform calculations based on the base value, the comparison value, and the associated value to obtain the target feature value.

13. The device according to claim 12, characterized in that The parsing unit is specifically used to determine the domain information and time information corresponding to the target financial data; The parsing unit is specifically configured to determine the regulatory information based on the domain information and the time information; The parsing unit is specifically configured to extract regulatory feature items from the regulatory information; The parsing unit is specifically configured to parse the target financial data based on the regulatory feature items to obtain the risk object.

14. The device according to claim 13, characterized in that The parsing unit is specifically configured to determine transaction information corresponding to the target financial data, wherein the transaction information includes at least one of a transaction object, a transaction frequency, a transaction time, or a transaction value; The parsing unit is specifically configured to traverse the regulatory information according to the transaction object, the transaction frequency, the transaction time, and the transaction value to obtain the regulatory feature item.

15. The device according to claim 14, characterized in that The parsing unit is specifically configured to determine a target object corresponding to the target financial data; The parsing unit is specifically used to call the historical information of the target object; The parsing unit is specifically configured to extract the transaction information from the historical information according to a preset time period.

16. The device according to claim 12, characterized in that The parsing unit is specifically used to call the scene model library; The parsing unit is specifically configured to traverse the scenario model library according to the scenario information corresponding to the target financial data to obtain a target model associated with the target financial data; The parsing unit is specifically configured to input the target financial data into the target model to obtain the risk object.

17. The device according to claim 16, characterized in that The parsing unit is specifically configured to input the target financial data into the target model to obtain risk feature items; The parsing unit is specifically configured to determine weight information corresponding to the risk feature item based on a decision number model; The parsing unit is specifically configured to perform weighted calculation on each object indicated in the target financial data based on the weight information and the risk feature item to obtain a scenario feature value; The parsing unit is specifically configured to determine the risk object based on the scenario feature value.

18. The device according to claim 17, characterized in that The parsing unit is specifically used to call the marked target sample; The parsing unit is specifically configured to update the risk feature item based on the target sample; The parsing unit is specifically configured to determine weight information corresponding to the updated risk feature item based on the decision number model.

19. The device according to claim 12, characterized in that The management unit is specifically configured to determine the corresponding feature levels according to the basic value, the comparison value, and the correlation value; The management unit is specifically configured to call the level value corresponding to the feature level; The management unit is specifically configured to perform calculations based on the level value to obtain the target feature value.

20. The device according to claim 12, characterized in that The acquisition unit is specifically configured to acquire financial operation information within a preset time period in response to a target operation; The acquisition unit is specifically configured to extract the operation object corresponding to each item of the financial operation information; The acquisition unit is specifically configured to associate the operation object with the financial operation information to obtain the target financial data.

21. The device according to any one of claims 12 to 20, characterized in that The management unit is specifically configured to determine a risk sequence consisting of a plurality of risk objects according to the target feature value; The management unit is specifically configured to extract the target object in the risk sequence based on the sequence information corresponding to the risk sequence; The management unit is specifically used to push the target object to the audit platform for financial risk control.

22. A computer device, characterized in that: The computer device includes a processor and a memory: The memory is used to store program code; the processor is used to execute the financial risk management method according to any one of claims 1 to 11 according to instructions in the program code.

23. A computer-readable storage medium, wherein instructions are stored in the computer-readable storage medium, which, when executed on a computer, enables the computer to execute the financial risk management method according to any one of claims 1 to 11.

24. A computer program product, characterized in that The computer program product includes instructions, and when the instructions are executed on a computer device, the computer is caused to execute the financial risk management method according to any one of claims 1 to 11.

Images