Business risk control method and device, equipment, storage medium and product

By deploying multiple decision engines in the risk control system, and dynamically selecting the appropriate decision engine to make risk control decisions based on business scenarios, the problems of poor flexibility and inefficient resource utilization in the existing technology are solved, and the processing capabilities of the risk control system are improved and decision accuracy.

CN119006133APending Publication Date: 2024-11-22CHINA MERCHANTS BANK
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410959089.8
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-17
Publication Date
2024-11-22

AI Technical Summary

Technical Problem

The existing risk control system uses the same decision engine for business risk control, resulting in poor flexibility and cannot effectively respond to different business scenarios and risk needs. It may lead to overload or waste of resources when trading volume fluctuates, affecting the risk control effect.

Method used

Deploy at least two different decision engines in the risk control system. By identifying the business identifier and scenario categories in the service processing request, dynamically call the corresponding decision engine to make risk control decisions, ensuring the flexibility and sequential execution of risk control decisions.

Benefits of technology

It realizes flexible response to different business scenarios, avoids resource overload or waste, ensures the accuracy and reliability of risk control decisions, and improves the system's processing capabilities and efficiency.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119006133A_ABST
    Figure CN119006133A_ABST
Patent Text Reader

Abstract

The invention discloses a business risk control method and device, equipment, a storage medium and a product, relates to the technical field of financial data processing, and discloses a business risk control method which comprises the following steps: in response to a business processing request for a target business, identifying a business identifier contained in the business processing request, and determining a service scene category corresponding to the service processing request based on the service identifier, and calling a decision engine corresponding to the service scene category to perform risk control decision on the target service. According to the method and the device, the service processing request is mapped to the specific service scene category, and the corresponding decision engine is selected according to the service scene category, so that different service scene requirements can be flexibly met.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of financial data processing technology, and in particular to a business risk control method, device, equipment, storage medium and product. Background Art

[0002] The risk control system is a system used to monitor and analyze user behavior, transaction data and other information in real time to evaluate and take quick measures to reduce risks. It is widely used in finance, telecommunications, Internet, games and other industries to prevent the occurrence of risk events such as fraud, money laundering, malicious behavior, etc., to help companies reduce losses and improve business security.

[0003] However, current risk control systems all use the same decision-making engine to make business risk control decisions, which has poor flexibility. Summary of the invention

[0004] The main purpose of this application is to provide a business risk control method, device, equipment, storage medium and product, aiming to solve the technical problem of poor flexibility caused by the related risk control systems using the same decision engine for business risk control.

[0005] To achieve the above objectives, the present application proposes a business risk control method, which is applied to a risk control system, wherein the risk control system is deployed with at least two different decision engines; the business risk control method comprises:

[0006] In response to a service processing request for a target service, identifying a service identifier included in the service processing request;

[0007] Determining a business scenario category corresponding to the business processing request based on the business identifier;

[0008] Calling a decision engine corresponding to the business scenario category to make a risk control decision on the target business.

[0009] In one embodiment, the at least two different decision engines include a main decision engine and a sub-decision engine; the processing performance of the main decision engine is better than the processing performance of the sub-decision engine; the step of calling the decision engine corresponding to the business scenario category to make a risk control decision on the target business includes:

[0010] In the case where the business scenario category belongs to a multi-transaction volume scenario category, calling the main decision engine to make a risk control decision on the target business;

[0011] When the business scenario category belongs to a low transaction volume scenario category, the sub-decision engine is called to make a risk control decision on the target business.

[0012] In one embodiment, the at least two different decision engines include a main decision engine and a secondary decision engine; the step of calling the decision engine corresponding to the business scenario category to make a risk control decision on the target business includes:

[0013] In the case where the business scenario category belongs to the important business scenario category, the main decision engine and the deputy decision engine are respectively called to perform risk control decision on the target business to obtain a risk control decision result.

[0014] In one embodiment, when the business scenario category belongs to the important business scenario category, the steps of respectively calling the main decision engine and the sub-decision engine to make a risk control decision on the target business and obtaining the risk control decision result include:

[0015] If the decision result output by the main decision engine is not received within the preset time period and the decision result output by the secondary decision engine is received within the preset time period, the decision result output by the secondary decision engine is obtained as the risk control decision result;

[0016] If the decision result output by the main decision engine is received within a preset time, the decision result output by the main decision engine is obtained as the risk control decision result.

[0017] In one embodiment, the step of calling a decision engine corresponding to the business scenario category to make a risk control decision on the target business includes:

[0018] Calling a target decision engine, so that the target decision engine reads data related to the business processing request from a preset database configured corresponding to the target decision engine, wherein the target decision engine is a decision engine corresponding to the business scenario category;

[0019] The relevant data is evaluated through the risk control rules predefined by the target decision engine to obtain a risk control decision result, wherein the relevant data is the data read out and related to the business processing request.

[0020] In one embodiment, the at least two different decision engines include a main decision engine and a deputy decision engine. The data storage component of the main decision engine adopts a preset first database, and the data storage component of the deputy decision engine adopts a preset second database. The storage capacity of the preset first database is greater than the storage capacity of the preset second database. The preset first database is deployed on a physical machine; and the preset second database is deployed on a virtual machine.

[0021] In addition, to achieve the above purpose, the present application also proposes a business risk control device, which is arranged in a risk control system, and the risk control system is deployed with at least two different decision engines; the business risk control device includes:

[0022] An identification module, configured to respond to a service processing request for a target service and identify a service identifier included in the service processing request;

[0023] A determination module, configured to determine a business scenario category corresponding to the business processing request based on the business identifier;

[0024] The risk control module is used to call the decision engine corresponding to the business scenario category to make a risk control decision on the target business.

[0025] In addition, to achieve the above-mentioned purpose, the present application also proposes a business risk control device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, and the computer program is configured to implement the steps of the business risk control method described above.

[0026] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by the processor, the steps of the business risk control method described above are implemented.

[0027] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, it implements the steps of the business risk control method described above.

[0028] The business risk control method, device, equipment, storage medium and product proposed in the present application are applied to a risk control system. At least two different decision engines are deployed in the risk control system, so as to support more types of business scenarios and risk control requirements. When a decision engine fails or its performance degrades, other decision engines can be used as backup engines to make risk control decisions, thereby ensuring the sequential execution of risk control decisions. By responding to a business processing request for a target business, identifying the business identifier contained in the business processing request, and determining the business scenario category corresponding to the business processing request based on the business identifier, and calling the decision engine corresponding to the business scenario category to make a risk control decision for the target business, since different businesses may correspond to different risk scenarios and risk control requirements, by mapping the business processing request to a specific business scenario category and selecting the corresponding decision engine according to the business scenario category, different business scenario requirements can be flexibly responded to. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0030] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0031] Figure 1 This is a schematic diagram of the structure of a risk control system involved in an exemplary application scenario of the business risk control method of this application;

[0032] Figure 2 A flowchart of an embodiment of the business risk control method of this application is provided;

[0033] Figure 3 This is a schematic diagram of the device structure of the hardware operating environment involved in the business risk control method in the embodiment of the present application.

[0034] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0035] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0036] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0037] The main solution of the embodiment of the present application is: in response to a business processing request for a target business, identify the business identifier contained in the business processing request; determine the business scenario category corresponding to the business processing request based on the business identifier; and call the decision engine corresponding to the business scenario category to make a risk control decision for the target business.

[0038] In the related art, the risk control system is a single decision engine, and all transactions are processed by the same risk control engine, which is bound to cause excessive pressure on the system. At the same time, different business scenarios are processed by the same risk control engine. Since all transactions go through the same processing flow, there may be relatively unimportant businesses competing with relatively important businesses for the same processing resources, which reduces the system's response speed to important businesses. In addition, the system cannot dynamically adjust resource allocation according to fluctuations in transaction volume. When the transaction volume surges, the system may suffer from performance degradation or processing delays due to insufficient resources, thereby affecting the risk control effect. On the other hand, when the transaction volume is low, system resources may not be fully utilized, resulting in resource waste. Therefore, this single decision engine solution will have the problem of ineffective resource utilization.

[0039] The present application provides a solution which, by configuring at least two different decision engines, can avoid all businesses being processed by the same risk control engine, which would put too much pressure on the system. At the same time, by mapping business processing requests to specific business scenario categories and selecting appropriate decision engines for risk control decisions based on specific business scenario categories, it can flexibly respond to different business scenario requirements.

[0040] See also Figure 1 , Figure 1 : is a flow chart of the first embodiment of the business risk control method of the present application. In this embodiment, the business risk control method is applied to a risk control system, and the risk control system is deployed with at least two different decision engines. The business risk control method includes steps S10 to S30:

[0041] Step S10: In response to a service processing request for a target service, a service identifier included in the service processing request is identified.

[0042] In this embodiment, the business risk control method is applied to the risk control system. Figure 2 , Figure 2 This is a schematic diagram of an application scenario of an embodiment of the business risk control method of the present application. In this application scenario, the risk control system includes a risk management channel docking module, a front-end service, a decision engine module and a support platform, which are explained below respectively.

[0043] The risk control channel docking module is connected to each business client and can be used to receive business processing requests sent by users on the client, such as business processing requests from bank clients, bank sales terminals (Point of Sale, POS) systems, etc. The front-end service can limit the flow and fuse the business processing request, and forward the business processing request to the decision engine module after detecting that the business processing request has passed the flow limit verification. The front-end service can also return the risk control decision result to the risk control channel docking module after receiving the risk control decision result output by the decision engine module, so that the risk control channel docking module returns the risk control decision result to the business client. The support platform mainly provides support for the risk system, including the decision configuration platform, model platform, offline analysis platform, flow platform and graph platform. Among them, the decision configuration platform provides the decision engine with configuration functions such as variables, rules and decision units. The model platform provides the decision engine with model capabilities to realize the "rule + model" risk control mode. The offline analysis platform is mainly used to mine valuable data such as trusted devices, trusted environments, blacklists and whitelists. The flow platform uses flow technology to realize quasi-real-time feature analysis. The graph platform is based on graph theory and topological structure mining technology to achieve self-perception and identification capabilities of abnormal transactions. For example, in a transfer scenario, fraudulent associated accounts can be discovered by deeply mining multi-layer associated risk features.

[0044] The decision engine module can be configured with at least two different decision engines. The decision engine can include a data preprocessing unit, a variable calculation unit, a rule calculation unit and a decision unit. The data preprocessing unit is used to preprocess the business data contained in the received business processing request to facilitate subsequent processing. The variable calculation unit and the rule calculation unit are implemented based on the preset database and stored procedure configured corresponding to the decision engine. The decision unit is used to match and calculate the input data according to the business rules and policies, so as to output the decision result.

[0045] Furthermore, each decision engine in at least two different decision engines can adopt a heterogeneous architecture. The so-called heterogeneity means that the physical configurations adopted by the components in the decision engine are different, so that the processing performance between different decision engines is different. In this way, appropriate decision engines can be adopted to execute risk control decisions for different business scenarios, so that resources can be fully utilized.

[0046] It should be noted that the rule sets set by each decision engine contained in the decision engine module are consistent. The difference lies in the different physical configurations adopted by the components in different decision engines. For example, the processing performance of the physical machine configured by one decision engine is better than the processing performance of the physical machine configured by another decision engine.

[0047] The risk control system may receive a business processing request for a target business initiated by a user through a business client, wherein the target business refers to the business to be processed by the user, such as a transfer business or a user login business. After receiving the business processing request for the target business, the risk control system parses the business processing request to identify the business identifier contained in the business processing request. The business identifier may include business interface information, such as a transfer business interface.

[0048] Step S20: determining the business scenario category corresponding to the business processing request based on the business identifier.

[0049] In some implementations, the business identifier may include a business interface, and the risk control system may identify the business scenario category through the business interface. Specifically, the risk control system may read the pre-established correspondence between the business identifier and the business scenario category from a cloud storage or local storage module to obtain the business scenario category.

[0050] Step S30, calling the decision engine corresponding to the business scenario category to make a risk control decision for the target business.

[0051] Specifically, after identifying the business scenario category, the risk control system can call the decision engine that matches the current business scenario category to make a risk control decision for the target business based on the pre-configured correspondence between the business scenario category and the decision engine.

[0052] In the above implementation scheme, by deploying at least two different decision engines in the risk control system, it is possible to support more types of business scenarios and risk control requirements, and when a decision engine fails or its performance degrades, the redundant decision engine can be used as a backup engine to perform risk control, thereby ensuring the sequential execution of risk control decisions; by responding to a business processing request for a target business, identifying the business identifier contained in the business processing request, and determining the business scenario category corresponding to the business processing request based on the business identifier, and calling the decision engine corresponding to the business scenario category to make a risk control decision for the target business. Since different businesses may correspond to different risk scenarios and risk control requirements, by mapping the business processing request to a specific business scenario category and selecting the corresponding decision engine according to the business scenario category, different business scenario requirements can be flexibly responded to.

[0053] In a feasible implementation manner, the above step S30 may include steps S301 to S302:

[0054] S301, calling a target decision engine, so that the target decision engine reads data related to the business processing request from a preset database configured corresponding to the target decision engine, where the target decision engine is a decision engine corresponding to the business scenario category. Different decision engines have different preset databases configured corresponding to them, so that different decision engines have different data storage capabilities and processing performances.

[0055] Specifically, the system calls the target decision engine, which reads data related to the business processing request from the preset database based on key information in the business processing request (such as user ID, transaction amount, etc.). For example, the relevant data may be the transaction amount of the corresponding user in the past week.

[0056] S302, evaluating relevant data through risk control rules predefined by the target decision engine to obtain a risk control decision result, where the relevant data is the data read out and related to the business processing request.

[0057] Specifically, after receiving the business processing request, the target decision engine will load the predefined risk control rules. The target decision engine inputs the read data related to the business processing request into the risk control rules, evaluates the relevant data, and obtains the risk control decision result. Among them, the risk control rules predefined by the decision engine may include multiple. When there are multiple risk control rules predefined by the decision engine, the target decision engine calls each risk control rule in turn to make a decision on the relevant data, and obtains the execution results of each risk control rule respectively, and determines the risk control decision result based on the execution results of each risk control rule.

[0058] Furthermore, when making risk control decisions for a certain business, some of the risk control rules included in the decision engine may be unnecessary. For example, in some scenarios, it may not be necessary to call third-party data sources, such as third-party credit information such as industrial and commercial information and tax information. If unnecessary risk control rules are executed for the target business, paid third-party systems may be redundantly called, which will increase the cost of risk control decisions.

[0059] To this end, in the present embodiment, each risk control rule may correspond to each monitoring dimension, that is, the decision engine pre-configures risk control rules corresponding to different monitoring dimensions, and each risk control rule may include at least one risk control sub-rule. Then the above step S302 may include: the target decision engine determines at least one monitoring dimension corresponding to the relevant data, and determines each risk control rule corresponding to the relevant data based on each corresponding monitoring dimension, and makes a decision on the relevant data through each corresponding risk control rule to obtain a risk control decision result.

[0060] Specifically, when there are multiple corresponding risk control rules, a decision flow can be generated based on the pre-defined priorities of each risk control rule, and the decision flow defines each risk control rule and the execution order of each risk control rule; then, the decision flow is executed, and when any risk control rule in the decision flow fails to execute, the execution of the decision flow is terminated, and a risk control decision result including risk control failure information is output; when each risk control rule in the decision flow is executed and passed, a risk control decision result including risk control pass information is output.

[0061] As an example, the multiple risk control rules pre-configured by the decision engine may include risk control rules A, B and C corresponding to the three monitoring dimensions of user, product and financial model respectively. Risk control rule A corresponding to the user monitoring dimension may include but is not limited to: risk control rules corresponding to users, for example, blacklist rules and credit rules based on user subjects; risk control rule B corresponding to the product monitoring dimension may be purchase rules corresponding to financial products; risk control rule C corresponding to the financial model may include but is not limited to: risk control rules and transfer rules corresponding to loan models. Therefore, assuming that the target business is a transfer business, and the relevant data obtained includes user credit information and transfer amount, it can be determined that the monitoring dimensions corresponding to the relevant data include users and financial models, and then the risk control rules corresponding to the user monitoring dimension and the risk control rules corresponding to the financial model are called to make decisions on the relevant data to obtain risk control decision results, without calling redundant risk control rules corresponding to the product monitoring dimension.

[0062] In the above implementation scheme, by determining the monitoring dimensions corresponding to the relevant data for the risk control decision to be made, and the risk control rules corresponding to the relevant data, it is possible to avoid the decision engine from executing unnecessary risk control decisions for the target business, thereby improving the performance of the decision engine; on the other hand, by avoiding the execution of unnecessary risk control strategies for the target, it is possible to avoid the decision engine from redundantly calling other paid third-party systems, thereby reducing the cost of risk control decisions.

[0063] In some implementation schemes, business scenario categories can be divided into: multi-transaction scenario categories, low-transaction scenario categories, and important business scenario categories. Among them, the multi-transaction scenario category refers to a business scenario involving a large number of high-frequency transactions during the business processing process. These scenarios usually have high requirements for the system's processing capabilities and response speed, because a large amount of transaction data needs to be processed quickly and accurately. For example, in the stock trading business scenario, during the opening and closing periods of the stock market, a large number of buy and sell orders flow into the system in a short period of time, requiring the decision engine to quickly conduct risk assessment and transaction confirmation. The low-transaction scenario category refers to a business scenario with relatively small transaction volume and low transaction frequency during the business transaction process. These scenarios have relatively low requirements for the system's real-time processing capabilities, such as user login business scenarios; important business scenario categories refer to those involving important and secure businesses, such as transfer business scenarios. The risk control system can pre-classify different business scenario categories for different business scenarios and save them to cloud storage or local storage modules.

[0064] In some implementations, the at least two different decision engines include a main decision engine and a sub-decision engine; the processing performance of the main decision engine is better than the processing performance of the sub-decision engine.

[0065] Furthermore, the data storage component of the main decision engine adopts a preset first database, and the data storage component of the sub-decision engine adopts a preset second database. The storage capacity of the preset first database is greater than the storage capacity of the preset second database; the preset first database is deployed on a physical machine; and the preset second database is deployed on a virtual machine.

[0066] As an example, the data storage component of the main decision engine uses the VoltDB in-memory database, and the decision unit uses the Drools rule engine. VoltDB is a high-performance in-memory database that can provide extremely fast query speed and data processing capabilities, and supports SQL queries and complex data analysis. Drools is an open source business rule management system (BRMS) that supports various forms of rule definitions such as business rules, decision tables, decision trees, and provides rich APIs for external system calls. The VoltDB in-memory database can be deployed on the first physical machine, which has the following characteristics: (1) High-performance CPU: used to handle a large number of data processing and computing tasks to ensure the fast execution of VoltDB and stored procedures; (2) Large-capacity memory: VoltDB is an in-memory database, and all data is stored in memory, so a large amount of memory space is required to store data.

[0067] The data storage component of the deputy decision engine uses the Redis in-memory database, and the decision unit uses the Drools rule engine. Redis is an open source in-memory data structure storage system that can be used as a database, cache, and message middleware. Since Redis stores data in memory, the read and write speeds are very fast, making it very suitable for scenarios with high real-time requirements. Redis is deployed using virtual machines, and resources can be dynamically adjusted according to actual needs.

[0068] Furthermore, the above step S30 may include steps A1 to A3:

[0069] Step A1, when the business scenario category belongs to the multi-transaction volume scenario category, the main decision engine is called to make a risk control decision for the target business.

[0070] Specifically, in the high-volume scenario category, due to the large volume and high frequency of transactions, powerful processing capabilities and rich data support are required to make risk control decisions quickly and accurately. Since the main decision engine uses the VoltDB in-memory database for data storage and the physical machine deployed by the main decision engine has good processing performance, the main decision engine has high-performance processing capabilities and huge data storage capabilities, and can store more dimensional data and run complex algorithms to support high-concurrency, low-latency risk control decisions. By calling the main decision engine, the real-time and efficiency requirements in multi-volume scenarios can be met while ensuring the accuracy of risk control decisions. This helps reduce transaction risks, improve transaction success rates, and ensure the stable operation of the system under high concurrency.

[0071] Step A2: When the business scenario category belongs to the low transaction volume scenario category, the sub-decision engine is called to make a risk control decision for the target business.

[0072] In the category of low-transaction scenarios, due to the small transaction volume and low frequency, the real-time processing capability requirements of the system are relatively low. Although the processing performance of the secondary decision engine is not as good as that of the main decision engine, it is sufficient to meet the risk control needs in these scenarios. At the same time, the secondary decision engine is usually low-cost and lightweight, suitable for processing simple and fast risk control decisions. By calling the secondary decision engine, the system cost can be reduced and the decision-making efficiency can be improved while ensuring the accuracy of risk control decisions, which helps to optimize resource utilization, reduce unnecessary resource waste, and reduce the operating costs of enterprises.

[0073] Step A3, when the business scenario category belongs to the important business scenario category, the main decision engine and the sub-decision engine are respectively called to make risk control decisions on the target business to obtain risk control decision results.

[0074] Specifically, when the business scenario category belongs to the important business scenario category, the main decision engine and the sub-decision engine are asynchronously called to make risk control decisions on the target business to obtain risk control decision results.

[0075] When the risk control system receives a business processing request and determines that the business scenario category corresponding to the business processing request is an important scenario category, the asynchronous call mechanism is triggered, that is, the business processing request is distributed to the main decision engine and the sub-decision engine for parallel processing, so that after the main decision engine and the sub-decision engine each receive the business processing request, each reads the relevant data corresponding to the business processing request from the corresponding preset database, and makes decisions on the relevant data based on the predefined risk control rules, and outputs the decision results respectively. Among them, the time points at which the main decision engine and the sub-decision engine output the decision results can be different.

[0076] In the category of important business scenarios, due to the importance and complexity of the business, more comprehensive risk control decisions are required. By calling the main decision engine and the secondary decision engine at the same time, the linkage decision of the main and secondary engines can be realized to identify and evaluate business risks from multiple dimensions and angles. The main decision engine provides richer and more comprehensive data and algorithm support, while the secondary decision engine provides fast and simple decision support. The two complement each other and jointly improve the accuracy and reliability of risk control decisions. Through the linkage decision of the main and secondary engines, the risk protection capability can be greatly improved, and the availability of risk control can be greatly improved, which helps to ensure the security and stability of important businesses, reduce potential business risks, and enhance the overall competitiveness of enterprises. At the same time, this decision-making method can also provide enterprises with more comprehensive and in-depth risk insights, helping enterprises to better manage risks and optimize business operations.

[0077] Furthermore, for the scenario where the main decision engine and the sub-decision engine are simultaneously called to make risk control decisions on the target business, the above step A3 may include:

[0078] If the decision result output by the main decision engine is not received within the preset time period and the decision result output by the secondary decision engine is received within the preset time period, the decision result output by the secondary decision engine is obtained as the risk control decision result; if the decision result output by the main decision engine is received within the preset time, the decision result output by the main decision engine is obtained as the risk control decision result.

[0079] Specifically, if the decision result of the main decision engine is not received within the preset time period, but the decision result of the secondary decision engine is received, the system will use the decision result of the secondary decision engine as the final risk control decision result. Although the secondary decision engine may be slightly inferior to the main decision engine in terms of data richness and algorithm complexity, it has its advantages in real-time and lightweight decision-making, and can ensure that decisions are made quickly in emergency situations. If the decision result of the main decision engine is received within the preset time, the system will directly use the decision result of the main decision engine as the final risk control decision result. This is because the main decision engine usually has more powerful processing capabilities and richer data support, and can provide more comprehensive and accurate risk assessments. By setting a preset time period, the system can ensure that decisions are made quickly in emergency situations, avoiding missing the best risk control opportunity due to waiting for the response of the main decision engine. Under normal circumstances, the system gives priority to the decision results of the main decision engine, which helps to ensure the accuracy and comprehensiveness of risk control decisions. At the same time, as a backup plan, the secondary decision engine can provide decision support when the main decision engine cannot respond in time, enhancing the fault tolerance and robustness of the system. By dynamically calling the main decision engine and the secondary decision engine according to business needs, the system can achieve reasonable allocation and efficient use of resources, which helps reduce the operating costs of enterprises and improve the overall performance of the system. In addition, fast and accurate risk control decisions can ensure the smooth progress of transactions, reduce user waiting time and unnecessary risk losses, thereby improving user experience and satisfaction.

[0080] It should be noted that the above steps A1, A2, and A3 are not intended to limit the execution order of the implementation steps of this application, but are only used to distinguish business risk control processing solutions under different business scenario categories.

[0081] In the above implementation scheme, by deploying the main decision engine and the sub-decision engine, each decision engine can be optimized for a specific scenario. The system can dynamically allocate resources according to business importance and transaction volume, avoiding the problem of single engine overload or resource waste, and improving the system's processing capacity and efficiency.

[0082] The present application also provides a business risk control device, which is arranged in a risk control system, and the risk control system is deployed with at least two different decision engines; the business risk control device includes:

[0083] An identification module, configured to respond to a business processing request for a target business and identify a business identifier contained in the business processing request;

[0084] A determination module, used to determine the business scenario category corresponding to the business processing request based on the business identifier;

[0085] The risk control module is used to call the decision engine corresponding to the business scenario category to make risk control decisions for the target business.

[0086] In a feasible implementation manner, the at least two different decision engines include a main decision engine and a sub-decision engine, and the risk control module is further used to:

[0087] When the business scenario category belongs to the important business scenario category, the main decision engine and the sub-decision engine are called respectively to make risk control decisions on the target business to obtain risk control decision results.

[0088] In a feasible implementation manner, the above-mentioned risk control module is also used for:

[0089] If the decision result output by the main decision engine is not received within the preset time period and the decision result output by the secondary decision engine is received within the preset time period, the decision result output by the secondary decision engine is obtained as the risk control decision result;

[0090] If the decision result output by the main decision engine is received within the preset time, the decision result output by the main decision engine is obtained as the risk control decision result.

[0091] In a feasible implementation manner, the at least two different decision engines include a main decision engine and a sub-decision engine, and the processing performance of the main decision engine is better than that of the sub-decision engine; the risk control module is also used for:

[0092] When the business scenario category belongs to the high transaction volume scenario category, the main decision engine is called to make risk control decisions for the target business;

[0093] When the business scenario category belongs to the low transaction volume scenario category, the sub-decision engine is called to make risk control decisions for the target business.

[0094] In a feasible implementation manner, the above-mentioned risk control module is also used for:

[0095] Calling a target decision engine so that the target decision engine reads data related to the business processing request from a preset database configured corresponding to the target decision engine, where the target decision engine is a decision engine corresponding to the business scenario category;

[0096] The relevant data is evaluated through the risk control rules predefined by the target decision engine to obtain the risk control decision result. The relevant data is the data read out and related to the business processing request.

[0097] The business risk control device provided by the present application can solve the technical problem that the relevant risk control schemes use the same decision engine to make business risk control decisions, resulting in poor flexibility. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided by the present application are the same as the beneficial effects of the business risk control method provided by the above embodiment, and will not be repeated here.

[0098] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the business risk control method of the present application. More simple transformations based on this technical concept are all within the scope of protection of the present application.

[0099] The present application provides a business risk control device, which includes: at least one processor; and a memory that is communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the business risk control method in the above-mentioned embodiment one.

[0100] Reference below Figure 3 , which shows a schematic diagram of the structure of a business risk control device suitable for implementing the embodiment of the present application. The business risk control device in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 3 The business risk control device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0101] like Figure 3As shown, the business risk control device may include a processing device 1001 (such as a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM: Random Access Memory) 1004. In RAM1004, various programs and data required for the operation of the business risk control device are also stored. The processing device 1001, ROM1002 and RAM1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems can be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touchpad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD: Liquid Crystal Display), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the business risk control device to communicate with other devices wirelessly or wired to exchange data. Although the figure shows a business risk control device with various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems can be implemented or have alternatively.

[0102] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0103] The business risk control device provided by this application adopts the business risk control method in the above embodiment, which can solve the technical problem of poor flexibility caused by the related risk control schemes using the same decision engine to make business risk control decisions. Compared with the prior art, the beneficial effects of the business risk control device provided by this application are the same as the beneficial effects of the business risk control method provided by the above embodiment, and the other technical features in the business risk control device are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0104] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0105] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0106] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, and the computer-readable program instructions are used to execute the business risk control method in the above-mentioned embodiment.

[0107] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination of the above.

[0108] The above-mentioned computer-readable storage medium may be included in the business risk control device; or it may exist independently without being installed in the business risk control device.

[0109] The above-mentioned computer-readable storage medium carries one or more programs. When the above-mentioned one or more programs are executed by the business risk control device, the business risk control device: displays the playback interface of the target audio / video in response to the audio / video playback operation performed by the user; the playback interface includes a progress display area; when the target audio / video is played to the display trigger time node of any stage, a virtual reward package is displayed at a position associated with the stage in the progress display area; when the target audio / video is played, a virtual reward is issued to the user based on the virtual reward package.

[0110] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0111] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0112] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.

[0113] The readable storage medium provided by the present application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned business risk control method, and can solve the technical problem that the relevant risk control schemes use the same decision engine to make business risk control decisions, resulting in poor flexibility. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided by the present application are the same as the beneficial effects of the business risk control method provided by the above-mentioned embodiment, and will not be repeated here.

[0114] The present application also provides a computer program product, including a computer program, which implements the steps of the business risk control method as described above when executed by a processor.

[0115] The computer program product provided by this application can solve the technical problem that related risk control solutions use the same decision engine to make business risk control decisions, resulting in the inability to reasonably utilize resources. Compared with the prior art, the beneficial effects of the computer program product provided by this application are the same as the beneficial effects of the business risk control method provided by the above embodiment, and will not be repeated here.

[0116] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A business risk control method, characterized in that: The business risk control method is applied to a risk control system, wherein the risk control system is deployed with at least two different decision engines; the business risk control method comprises: In response to a service processing request for a target service, identifying a service identifier included in the service processing request; Determining a business scenario category corresponding to the business processing request based on the business identifier; Calling a decision engine corresponding to the business scenario category to make a risk control decision on the target business.

2. The method according to claim 1, characterized in that The at least two different decision engines include a main decision engine and a secondary decision engine; The processing performance of the main decision engine is better than the processing performance of the secondary decision engine; The step of calling the decision engine corresponding to the business scenario category to make a risk control decision on the target business includes: In the case where the business scenario category belongs to a multi-transaction volume scenario category, calling the main decision engine to make a risk control decision on the target business; When the business scenario category belongs to a low transaction volume scenario category, the sub-decision engine is called to make a risk control decision on the target business.

3. The method according to claim 1, characterized in that The at least two different decision engines include a main decision engine and a secondary decision engine; The step of calling the decision engine corresponding to the business scenario category to make a risk control decision on the target business includes: In the case where the business scenario category belongs to the important business scenario category, the main decision engine and the deputy decision engine are respectively called to perform risk control decision on the target business to obtain a risk control decision result.

4. The method according to claim 3, characterized in that When the business scenario category belongs to the important business scenario category, the steps of respectively calling the main decision engine and the sub-decision engine to make a risk control decision on the target business to obtain a risk control decision result include: If the decision result output by the main decision engine is not received within the preset time period and the decision result output by the secondary decision engine is received within the preset time period, the decision result output by the secondary decision engine is obtained as the risk control decision result; If the decision result output by the main decision engine is received within a preset time, the decision result output by the main decision engine is obtained as the risk control decision result.

5. The method according to claim 1, characterized in that The step of calling the decision engine corresponding to the business scenario category to make a risk control decision on the target business includes: Calling a target decision engine, so that the target decision engine reads data related to the business processing request from a preset database configured corresponding to the target decision engine, wherein the target decision engine is a decision engine corresponding to the business scenario category; The relevant data is processed through the risk control rules predefined by the target decision engine to obtain a risk control decision result, wherein the relevant data is the data read out and related to the business processing request.

6. The method according to any one of claims 1 to 5, characterized in that The at least two different decision engines include a main decision engine and a sub-decision engine, the data storage component of the main decision engine adopts a preset first database, the data storage component of the sub-decision engine adopts a preset second database, and the storage capacity of the preset first database is greater than the storage capacity of the preset second database; The preset first database is deployed on a physical machine; The preset second database is deployed on the virtual machine.

7. A business risk control device, characterized in that: The business risk control device is arranged in a risk control system, and the risk control system is deployed with at least two different decision engines; the business risk control device comprises: An identification module, configured to respond to a service processing request for a target service and identify a service identifier included in the service processing request; A determination module, configured to determine a business scenario category corresponding to the business processing request based on the business identifier; The risk control module is used to call the decision engine corresponding to the business scenario category to make a risk control decision on the target business.

8. A business risk control device, characterized in that: The business risk control device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the business risk control method according to any one of claims 1 to 6.

9. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the business risk control method according to any one of claims 1 to 6 are implemented.

10. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the steps of the business risk control method according to any one of claims 1 to 6 are implemented.