Risk control decision optimization method and device, equipment and storage medium
By obtaining and dismantling the conditions in the target rule package, dividing the condition groups and determining dependencies, and optimizing risk control decisions, the problem of inefficiency in the existing Rete algorithm when dealing with different condition rules is solved, and more efficient rule engine processing is achieved.
Patent Information
- Application Number
- CN202411867374.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-12-18
- Publication Date
- 2025-03-28
AI Technical Summary
The existing Rete algorithms are inefficient when processing rules with different conditions, resulting in waste of computing resources and reduced processing speed, making it difficult to adapt to the data processing needs of large-scale or complex rule sets.
By obtaining the target rule package related to risk control, extracting and dismantling the target conditions in the rule, dividing the condition groups and determining the dependencies between the target conditions, and assigning the dependencies based on the current execution results until all target conditions are assigned to optimize risk control decisions.
It significantly improves the processing speed and efficiency of the rule engine, reduces the number of individual matching processes, makes full use of the dependencies between conditions, and adapts to larger-scale data processing needs.
Smart Images
Figure CN119721711A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of risk control decision technology, and in particular to a risk control decision optimization method, device, equipment and storage medium. Background Art
[0002] In key areas such as financial risk control and real-time anti-fraud, decision and reasoning engines play a vital role. These engines rely on rule matching algorithms to achieve automated risk assessment and decision making. The Rete algorithm is a widely used rule matching algorithm. By building an efficient network structure, the conditions and operations of the rules are represented as nodes, achieving fast execution and accurate matching of the rules.
[0003] The core advantage of the Rete algorithm is that it uses shared conditions between rules to reduce storage requirements and saves temporary results of the matching process to speed up subsequent matching. However, although the Rete algorithm performs well when processing conditions with the same literal, its performance is limited when facing rules with different literal conditions, especially when dealing with large-scale or complex rule sets, the efficiency problem is particularly prominent.
[0004] The existing Rete algorithm has the following disadvantages when processing rules with different conditions: for each different literal condition, the algorithm needs to perform a separate matching process, resulting in a waste of computing resources and a decrease in processing speed. Moreover, as the rule set grows and becomes more complex, the efficiency of the existing algorithm decreases, making it difficult to adapt to larger-scale data processing needs. The existing algorithm fails to fully utilize the dependencies between conditions to optimize the matching process, resulting in inefficient rule execution.
[0005] From the above, it can be seen that how to improve the processing speed and efficiency of the rule engine is an urgent problem to be solved. Summary of the invention
[0006] In view of this, the purpose of the present invention is to provide a risk control decision optimization method, device, equipment and storage medium, which can improve the processing speed and efficiency of the rule engine. The specific scheme is as follows:
[0007] In a first aspect, the present application provides a risk control decision optimization method, comprising:
[0008] Obtaining a target rule package related to risk control, determining a rule set based on the target rule package, extracting a target condition of each rule in the rule set, and decomposing the target condition to obtain components of the target condition;
[0009] Dividing the target conditions in the rule set into different condition groups according to the condition division variables in the component parts, and determining the dependency relationship between the target conditions in the condition groups;
[0010] Determine whether the current target condition in the condition group is assigned a value, and if not, execute the current target condition to obtain a corresponding current execution result;
[0011] Based on the current execution result, the target dependency condition that has the dependency relationship with the current target condition is assigned, and then the next target condition in the condition group is determined as the new current target condition, and the process jumps to the step of determining whether the current target condition in the condition group is assigned, until all the target conditions in the condition group are assigned, so as to complete the risk control decision optimization.
[0012] Optionally, the obtaining of a target rule package related to risk control includes:
[0013] In an empty rule set, target rules related to risk control are constructed using the rules of the decision and reasoning engine, and the target rules are packaged into a rule package so that the user end can determine the target rule package from the packaged rule packages.
[0014] Optionally, determining a rule set based on the target rule package includes:
[0015] The target rule package is acquired by utilizing the decision and reasoning engine, and the rules in the target rule package are compiled so as to save the rules in the target rule package into the rule set.
[0016] Optionally, the components include the condition partitioning variable, a condition comparison operator, and a condition-related threshold value.
[0017] Optionally, determining the dependency relationship between the target conditions of the condition group includes:
[0018] Determine the dependency relationship between the target conditions in the corresponding condition group according to the condition partitioning variable, the condition comparison symbol and the condition related threshold value;
[0019] The target dependent condition having the dependency relationship with the target condition includes any one of a necessary condition, a mutually exclusive condition and a complementary condition.
[0020] Optionally, assigning a value to a target dependency condition having the dependency relationship with the current target condition based on the current execution result includes:
[0021] If the current execution result indicates that the current target condition is true, assigning the mutually exclusive condition and the complementary condition of the current target condition to false;
[0022] If the current execution result indicates that the current target condition is false, the necessary condition of the current target condition is assigned a value of false, and the complementary condition is assigned a value of true.
[0023] Optionally, after determining whether the current target condition in the condition group is assigned a value, the step further includes:
[0024] If the current target condition is assigned a value, the next target condition in the condition group is directly determined as the new current target condition, and then the process jumps to the step of determining whether the current target condition in the condition group is assigned a value.
[0025] In a second aspect, the present application provides a risk control decision optimization device, comprising:
[0026] A component acquisition module, used to acquire a target rule package related to risk control, determine a rule set based on the target rule package, extract target conditions of each rule in the rule set, and decompose the target conditions to obtain components of the target conditions;
[0027] A dependency determination module, used to divide the target conditions in the rule set into different condition groups according to the condition division variables in the component parts, and determine the dependency between the target conditions in the condition groups;
[0028] An execution result acquisition module, used to determine whether the current target condition in the condition group is assigned a value, and if not, execute the current target condition to obtain the corresponding current execution result;
[0029] The risk control decision optimization completion module is used to assign values to the target dependency conditions that have the dependency relationship with the current target conditions based on the current execution results, and then determine the next target condition in the condition group as the new current target condition, and jump to the step of determining whether the current target condition in the condition group is assigned, until all the target conditions in the condition group are assigned, so as to complete the risk control decision optimization.
[0030] In a third aspect, the present application provides an electronic device, including:
[0031] Memory, used to store computer programs;
[0032] A processor is used to execute the computer program to implement the risk control decision optimization method as described above.
[0033] In a fourth aspect, the present application provides a computer-readable storage medium for storing a computer program; wherein, when the computer program is executed by a processor, the risk control decision optimization method as described above is implemented.
[0034] In summary, it can be seen that the present application obtains a target rule package related to risk control, determines a rule set based on the target rule package, extracts the target conditions of each rule in the rule set, and disassembles the target conditions to obtain the components of the target conditions; divides the target conditions in the rule set into different condition groups according to the condition division variables in the components, and determines the dependency relationship between the target conditions in the condition group; determines whether the current target condition in the condition group is assigned a value, and if not, executes the current target condition to obtain the corresponding current execution result; assigns a target dependency condition that has the dependency relationship with the current target condition based on the current execution result, and then determines the next target condition in the condition group as the new current target condition, and jumps to the step of determining whether the current target condition in the condition group is assigned a value, until all the target conditions in the condition group are assigned a value, so as to complete the risk control decision optimization. It can be seen that the present application first obtains a target rule package related to risk control, constructs a rule set based on the target rule package, then extracts the target conditions of each rule in the rule set, and then disassembles these target conditions to obtain the components of the target conditions. The target conditions in the rule set are divided into different condition groups according to the condition division variables in the components, and the dependencies between the target conditions in the condition group are determined. Then, it is determined whether the current target condition in the condition group has been assigned a value. If it has not been assigned a value, the current target condition is executed to obtain the current execution result. After completing these operations, the next target condition in the condition group is determined as the new current target condition, and the step of judging whether the current target condition in the condition group has been assigned a value is jumped back to, and this cycle is repeated until all the target conditions in the condition group are assigned a value, and finally the risk control decision optimization is completed. In this way, once the application determines the assignment of a certain target condition, other target conditions that depend on the target condition can directly determine the assignment result without the need for separate execution, thereby significantly improving the efficiency and performance of the rule engine. BRIEF DESCRIPTION OF THE DRAWINGS
[0035] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.
[0036] Figure 1 A flow chart of a risk control decision optimization method disclosed in the present invention;
[0037] Figure 2 A schematic diagram of a specific risk control decision optimization method disclosed in the present invention;
[0038] Figure 3It is a schematic diagram of the structure of a risk control decision optimization device disclosed in the present invention;
[0039] Figure 4 The present invention is a structural diagram of an electronic device disclosed in the present invention. DETAILED DESCRIPTION
[0040] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0041] At present, the existing Rete algorithm has the following shortcomings when processing rules with different conditions: for each different literal condition, the algorithm needs to perform a separate matching process, resulting in a waste of computing resources and a decrease in processing speed. Moreover, with the growth and complexity of the rule set, the efficiency of the existing algorithm decreases, and it is difficult to adapt to larger-scale data processing needs. The existing algorithm fails to fully utilize the dependencies between conditions to optimize the matching process, resulting in inefficient rule execution. In order to solve the above technical problems, the present application discloses a risk control decision optimization method, device, equipment and storage medium, which can improve the processing speed and efficiency of the rule engine.
[0042] See also Figure 1 As shown, an embodiment of the present invention discloses a risk control decision optimization method, including:
[0043] Step S11, obtaining a target rule package related to risk control, determining a rule set based on the target rule package, extracting target conditions of each rule in the rule set, and disassembling the target conditions to obtain components of the target conditions.
[0044] In this embodiment, in order to obtain the target rule package related to risk control, the target rules related to risk control are first constructed in the empty rule set using the rules of the decision and reasoning engine, and the target rules are packaged into a rule package so that the user end can determine the target rule package from the packaged rule package. Specifically, in the decision and reasoning engine, the initial rule set is empty. The user uses the rule construction language provided by the decision and reasoning engine to define a series of related rules. The user packages the rules related to the business logic into a rule package and sends the rule package to the rule set of the decision and reasoning engine for the user to subscribe. For example, the customer service department in the e-commerce platform can subscribe to the customer complaint risk judgment rule package; the risk control department can subscribe to the transaction risk identification rule package, so as to make accurate decisions in their respective business scenarios based on these rules to ensure the normal operation of the business.
[0045] In this embodiment, after obtaining the target rule package, the decision and reasoning engine is used to obtain the target rule package, and the rules in the target rule package are compiled so as to save the rules in the target rule package into the rule set. Specifically, after the user determines the rule package to be subscribed, the decision and reasoning engine loads the selected target rule package to the local computer, compiles all the rules in the target rule package, and then saves the compiled rules into the rule set.
[0046] Furthermore, after obtaining the compiled rule set, we first need to extract the target conditions contained in the rules of the rule set. These target conditions are the clear statements in the rules used to define and judge whether the relevant situation meets the requirements. Then, we disassemble each target condition and determine the components of each target condition. The components include condition division variables, condition comparison operators, and condition related thresholds.
[0047] Step S12: Divide the target conditions in the rule set into different condition groups according to the condition division variables in the component parts, and determine the dependency relationship between the target conditions in the condition groups.
[0048] In this embodiment, after the target conditions of each rule in the rule set are disassembled, the three components of the conditional division variable, the conditional comparison operator, and the conditional related threshold value are obtained. According to the conditional division variable, the corresponding target conditions in the rule set can be classified respectively, and the conditions containing the conditional division variable can be classified into the same conditional group. For example, if the rule contains the target condition "a>28", then "a" is the conditional division variable, ">" is the conditional comparison operator, and "28" is the conditional related threshold value. If other rules in the rule set also contain the conditions "a<10" and "b>2", then "a>28" and "a<10" are classified into one conditional group, and "b>2" is a separate conditional group.
[0049] In this embodiment, after the target conditions are divided into different condition groups, the dependency relationship between the target conditions in the corresponding condition groups is determined according to the condition division variables, the comparison symbols of the conditions, and the relevant threshold values of the conditions; wherein the target dependency conditions that have a dependency relationship with the target conditions include any one of necessary conditions, mutually exclusive conditions, and complementary conditions. It should be understood that if condition A can derive condition B, condition A is a sufficient condition for condition B. For example, "a>28" is a sufficient condition for "a>27". If condition B can derive condition A, condition A is a necessary condition for condition B. For example, "a>28" is a sufficient condition for "a>29". If condition A and condition B cannot be true at the same time, but may be false at the same time, condition A and condition B are mutually exclusive conditions. For example, "a>28" and "a<10" are mutually exclusive conditions. If one of the two conditions A and condition B is true, the other must be false, and condition A and condition B cover all possible situations together, then condition A and condition B are complementary conditions. For example, "a>28" and "a≤28" are complementary conditions. Further, the corresponding condition group is determined according to the condition division variable, and then different types of dependency relationships between target conditions in the corresponding condition group are determined according to different condition comparison symbols and condition related thresholds.
[0050] Step S13: determine whether the current target condition in the condition group is assigned a value; if not, execute the current target condition to obtain a corresponding current execution result.
[0051] In this embodiment, after determining the dependency relationship between each target condition in the condition group, the current target condition in the condition group is determined in a predetermined order. It should be understood that the current target condition here is the target condition that is being paid attention to and needs to be operated when processing each condition in the condition group in sequence. Next, it is determined whether the current target condition has been assigned a value. The assignment means that the target condition has a clear specific value or judgment result that meets its definition and requirements. When it is found that the current target condition has not been assigned a value, the current target condition is executed to obtain the corresponding current execution result, that is, the current target condition is assigned a value, and the assignment result corresponding to the current target condition is obtained. Through such a process, it is ensured that each target condition can have a clear assignment result, thereby laying the foundation for further processing, decision-making, etc. based on these target conditions and the dependency relationship between the target conditions, so that the entire business logic or risk control based on the condition group and other related processes can be smoothly promoted.
[0052] Furthermore, after determining whether the current target condition in the condition group has been assigned a value, if the current target condition has been assigned a value, the next target condition in the condition group is directly determined as the new current target condition, and then the process jumps to the step of determining whether the current target condition in the condition group has been assigned a value. Specifically, if the current target condition has been assigned a value, it means that the condition already has a clear value or judgment state, and it is necessary to determine the next target condition in the condition group as the new current target condition. After determining the new current target condition, the process jumps to the step of determining whether the current target condition in the condition group has been assigned a value, that is, to start the verification process of whether the new current target condition already has a clear value or judgment result. Ultimately, all target conditions in the entire condition group can be assigned values one by one, and then based on the complete and clear assignment of all target conditions, relevant business goals such as risk control decisions can be achieved, and reasonable and scientific decisions can be made based on the execution results.
[0053] Step S14: assign values to the target dependency conditions that have the dependency relationship with the current target conditions based on the current execution result, then determine the next target condition in the condition group as the new current target condition, and jump to the step of determining whether the current target condition in the condition group is assigned values, until all the target conditions in the condition group are assigned values, so as to complete the risk control decision optimization.
[0054] In this embodiment, after the execution result of the current target condition is obtained, it is necessary to assign the target dependency condition that has a dependency relationship with the current target condition based on the current execution result. If the current execution result indicates that the current target condition is true, the mutually exclusive condition and the complementary condition of the current target condition are assigned to false; if the current execution result indicates that the current target condition is false, the necessary condition of the current target condition is assigned to false, and the complementary condition is assigned to true. Specifically, when the execution result of the current target condition is obtained, and the execution result indicates that the current target condition is true, it can be understood that for mutually exclusive conditions, since the definition of mutually exclusive conditions is that two conditions cannot be true at the same time, but can be false at the same time, when the current target condition has been determined to be true, the target dependency condition that is mutually exclusive with it must be false; for complementary conditions, when one of the two conditions is true, the other must be false, and the two together cover all possible situations, so when the current target condition is true, the target dependency condition that is complementary to it is assigned to false. When the current execution result obtained shows that the current target condition is false, it can be understood that the necessary condition is a necessary prerequisite for another condition to be established. Therefore, when the current target condition is false, it means that the target dependency condition that has a necessary condition relationship with the current target condition is not established, so the corresponding target dependency condition must be assigned to false; complementary conditions must be one true and one false, so when the current target condition is false, the complementary target dependency condition must be true. After completing the assignment of the dependent condition, the next target condition in the condition group is determined as the new current target condition, and then jump back to the initial step of judging whether the current target condition in the condition group is assigned. The new current target condition is judged again whether it is assigned. Through continuous repetition, each target condition in the condition group is continuously processed until all target conditions in the condition group are assigned. By strictly following the execution result of the current target condition and accurately assigning values according to the dependency relationship between different conditions, the specific status of each condition in the condition group can be gradually clarified, laying a solid foundation for the subsequent comprehensive and accurate completion of the entire risk control decision-making process, and ensuring the scientificity and rationality of risk control decisions.
[0055] It can be seen that the embodiment of the present application first obtains the target rule package related to risk control, builds a rule set based on the target rule package, then extracts the target conditions of each rule in the rule set, and then disassembles these target conditions to obtain the components of the target conditions. The target conditions in the rule set are divided into different condition groups according to the condition division variables in the components, and the dependencies between the target conditions in the condition group are determined. After that, it is determined whether the current target condition in the condition group has been assigned a value. If it has not been assigned, the current target condition is executed to obtain the current execution result. After completing these operations, the next target condition in the condition group is determined as the new current target condition, and the step of jumping back to determining whether the current target condition in the condition group is assigned a value is repeated, and the target conditions in the condition group are all assigned a value, and the risk control decision optimization is finally completed. In this way, once the application determines the assignment of a certain target condition, other target conditions that depend on the target condition can directly determine the assignment result without separate execution, thereby significantly improving the efficiency and performance of the rule engine.
[0056] Based on the above embodiment, it can be seen that the present application discloses a risk control decision optimization method, which can improve the processing speed and efficiency of the rule engine. Next, a specific risk control decision optimization method will be described in detail.
[0057] This application first obtains the target rule package related to risk control. After obtaining the target rule package, the selected target rule package is loaded locally through the decision and reasoning engine, and then all the rules in the target rule package are compiled. After that, the compiled rules are saved in the rule set. Next, the target conditions contained in the rules of the rule set are extracted, and each target condition is disassembled to determine the components of each target condition. After the target conditions of each rule in the rule set are disassembled, the corresponding target conditions in the rule set can be classified according to the conditional division variables of the target conditions, and the conditions containing the conditional division variables can be classified into the same condition group, and the different types of dependencies between the target conditions in the corresponding condition group are determined according to the comparison operators of the different conditions in the target conditions and the relevant thresholds in the target conditions. Afterwards, when the dependencies between the target conditions are determined, the rule decision of the fact can be made. Whenever a target condition is encountered, the following is executed. Figure 2The logic shown. Specifically, after determining the dependency relationship between the target conditions in the condition group, determine whether the current target condition has been assigned a value. When it is found that the current target condition has not been assigned a value, execute the current target condition to obtain the corresponding current execution result. If the current target condition is assigned a value, directly determine the next target condition in the condition group as the new current target condition, and then jump to the step of determining whether the current target condition in the condition group is assigned a value. After obtaining the execution result of the current target condition, it is necessary to assign a value to the target dependency condition that has a dependency relationship with the current target condition based on the current execution result, and then determine the next target condition in the condition group as the new current target condition, and again determine whether the new current target condition is assigned a value. Through continuous reciprocation, each target condition in the condition group is continuously processed until all target conditions in the condition group are assigned a value. In this way, when all target conditions have been assigned a value, more scientific and reasonable risk control decisions can be made based on these complete and accurate condition results and in accordance with established risk control rules and logic.
[0058] See also Figure 3 As shown, an embodiment of the present invention discloses a risk control decision optimization device, comprising:
[0059] The component acquisition module 11 is used to acquire a target rule package related to risk control, determine a rule set based on the target rule package, extract the target condition of each rule in the rule set, and disassemble the target condition to obtain components of the target condition;
[0060] A dependency determination module 12, configured to divide the target conditions in the rule set into different condition groups according to the condition division variables in the component parts, and determine the dependency between the target conditions in the condition groups;
[0061] An execution result acquisition module 13 is used to determine whether the current target condition in the condition group is assigned a value, and if not, execute the current target condition to obtain the corresponding current execution result;
[0062] The risk control decision optimization completion module 14 is used to assign values to the target dependency conditions that have the dependency relationship with the current target conditions based on the current execution results, and then determine the next target condition in the condition group as the new current target condition, and jump to the step of determining whether the current target condition in the condition group is assigned a value, until all the target conditions in the condition group are assigned a value, so as to complete the risk control decision optimization.
[0063] It can be seen that the present application first obtains the target rule package related to risk control, builds a rule set based on the target rule package, then extracts the target conditions of each rule in the rule set, and then disassembles these target conditions to obtain the components of the target conditions. The target conditions in the rule set are divided into different condition groups according to the condition division variables in the components, and the dependencies between the target conditions in the condition group are determined. After that, it is determined whether the current target condition in the condition group has been assigned. If it has not been assigned, the current target condition is executed to obtain the current execution result. After completing these operations, the next target condition in the condition group is determined as the new current target condition, and the step of jumping back to determining whether the current target condition in the condition group has been assigned is repeated until all the target conditions in the condition group are assigned, and finally the risk control decision optimization is completed. In this way, once the present application determines the assignment of a certain target condition, other target conditions that depend on the target condition can directly determine the assignment result without separate execution, thereby significantly improving the efficiency and performance of the rule engine.
[0064] In some specific implementations, the component acquisition module 11 may specifically include:
[0065] The target rule package determination unit is used to construct target rules related to risk control in an empty rule set using the rules of the decision and reasoning engine, and package the target rules into a rule package so that the user end can determine the target rule package from the packaged rule packages.
[0066] In some specific implementations, the component acquisition module 11 may specifically include:
[0067] A rule compiling unit is used to obtain the target rule package by using the decision and reasoning engine, and compile the rules in the target rule package so as to save the rules in the target rule package into the rule set.
[0068] In some specific implementations, the components include the condition partitioning variable, the condition comparison symbol, and the condition-related threshold.
[0069] In some specific implementations, the dependency determination module 12 may specifically include:
[0070] A dependency determination unit is used to determine the dependency between the target conditions in the corresponding condition group according to the condition division variables, the condition comparison operator and the relevant threshold of the condition; wherein the target dependency condition that has the dependency relationship with the target condition includes any one of a necessary condition, a mutually exclusive condition and a complementary condition.
[0071] In some specific implementations, the risk control decision optimization completion module 14 may specifically include:
[0072] A first current execution result determination unit, configured to assign false values to the mutually exclusive condition and the complementary condition of the current target condition if the current execution result indicates that the current target condition is true;
[0073] The second current execution result determination unit is configured to assign the necessary condition of the current target condition to be false and assign the complementary condition to be true if the current execution result indicates that the current target condition is false.
[0074] In some specific implementations, the risk control decision optimization device may further include:
[0075] A new current target condition determination module is used to directly determine the next target condition in the condition group as the new current target condition if the current target condition is assigned a value, and then jump to the step of determining whether the current target condition in the condition group is assigned a value.
[0076] Furthermore, the present application also discloses an electronic device. Figure 4 This is a structural diagram of an electronic device 20 according to an exemplary embodiment. The content in the diagram cannot be regarded as any limitation on the scope of use of the present application.
[0077] Figure 4 A schematic diagram of the structure of an electronic device 20 provided in an embodiment of the present application. The electronic device 20 may specifically include: at least one processor 21, at least one memory 22, a power supply 23, a communication interface 24, an input / output interface 25, and a communication bus 26. The memory 22 is used to store a computer program, which is loaded and executed by the processor 21 to implement the relevant steps in the risk control decision optimization method disclosed in any of the aforementioned embodiments. In addition, the electronic device 20 in this embodiment may specifically be an electronic computer.
[0078] In this embodiment, the power supply 23 is used to provide working voltage for each hardware device on the electronic device 20; the communication interface 24 can create a data transmission channel between the electronic device 20 and the external device, and the communication protocol it follows is any communication protocol that can be applied to the technical solution of the present application, and is not specifically limited here; the input and output interface 25 is used to obtain external input data or output data to the outside world, and its specific interface type can be selected according to specific application needs and is not specifically limited here.
[0079] In addition, the memory 22, as a carrier for storing resources, can be a read-only memory, a random access memory, a disk or an optical disk, etc. The resources stored thereon can include an operating system 221, a computer program 222, etc., and the storage method can be temporary storage or permanent storage.
[0080] The operating system 221 is used to manage and control the hardware devices and computer program 222 on the electronic device 20, which can be Windows Server, Netware, Unix, Linux, etc. In addition to including a computer program that can be used to complete the risk control decision optimization method performed by the electronic device 20 disclosed in any of the aforementioned embodiments, the computer program 222 can further include a computer program that can be used to complete other specific tasks.
[0081] Furthermore, the present application also discloses a computer-readable storage medium for storing a computer program; wherein, when the computer program is executed by a processor, the aforementioned risk control decision optimization method is implemented. The specific steps of the method can refer to the corresponding contents disclosed in the aforementioned embodiments, and will not be repeated here.
[0082] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.
[0083] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.
[0084] The steps of the method or algorithm described in conjunction with the embodiments disclosed herein may be implemented directly using hardware, a software module executed by a processor, or a combination of the two. The software module may be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
[0085] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.
[0086] The technical solution provided by the present application is introduced in detail above. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea. At the same time, for general technicians in this field, according to the idea of the present application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.
Claims
1. A risk control decision optimization method, characterized in that: include: Obtaining a target rule package related to risk control, determining a rule set based on the target rule package, extracting a target condition of each rule in the rule set, and decomposing the target condition to obtain components of the target condition; Dividing the target conditions in the rule set into different condition groups according to the condition division variables in the component parts, and determining the dependency relationship between the target conditions in the condition groups; Determine whether the current target condition in the condition group is assigned a value, and if not, execute the current target condition to obtain a corresponding current execution result; Based on the current execution result, the target dependency condition that has the dependency relationship with the current target condition is assigned, and then the next target condition in the condition group is determined as the new current target condition, and the process jumps to the step of determining whether the current target condition in the condition group is assigned, until all the target conditions in the condition group are assigned, so as to complete the risk control decision optimization.
2. The risk control decision optimization method according to claim 1, characterized in that: The obtaining of a target rule package related to risk control includes: In an empty rule set, target rules related to risk control are constructed using the rules of the decision and reasoning engine, and the target rules are packaged into a rule package so that the user end can determine the target rule package from the packaged rule packages.
3. The risk control decision optimization method according to claim 2 is characterized in that: The determining of a rule set based on the target rule package includes: The target rule package is acquired by utilizing the decision and reasoning engine, and the rules in the target rule package are compiled so as to save the rules in the target rule package into the rule set.
4. The risk control decision optimization method according to claim 1, characterized in that: The components include the condition partitioning variable, the condition comparison symbol, and the condition-related threshold value.
5. The risk control decision optimization method according to claim 4 is characterized in that: The determining the dependency relationship between the target conditions of the condition group includes: Determine the dependency relationship between the target conditions in the corresponding condition group according to the condition partitioning variable, the condition comparison symbol and the condition related threshold value; The target dependent condition having the dependency relationship with the target condition includes any one of a necessary condition, a mutually exclusive condition and a complementary condition.
6. The risk control decision optimization method according to claim 5, characterized in that: The assigning of a value to the target dependency condition having the dependency relationship with the current target condition based on the current execution result includes: If the current execution result indicates that the current target condition is true, assigning the mutually exclusive condition and the complementary condition of the current target condition to false; If the current execution result indicates that the current target condition is false, the necessary condition of the current target condition is assigned a value of false, and the complementary condition is assigned a value of true.
7. The risk control decision optimization method according to any one of claims 1 to 6, characterized in that: After determining whether the current target condition in the condition group is assigned a value, the method further includes: If the current target condition is assigned a value, the next target condition in the condition group is directly determined as the new current target condition, and then the process jumps to the step of determining whether the current target condition in the condition group is assigned a value.
8. A risk control decision optimization device, characterized in that: include: A component acquisition module, used to acquire a target rule package related to risk control, determine a rule set based on the target rule package, extract target conditions of each rule in the rule set, and decompose the target conditions to obtain components of the target conditions; A dependency determination module, used to divide the target conditions in the rule set into different condition groups according to the condition division variables in the component parts, and determine the dependency between the target conditions in the condition groups; An execution result acquisition module, used to determine whether the current target condition in the condition group is assigned a value, and if not, execute the current target condition to obtain the corresponding current execution result; The risk control decision optimization completion module is used to assign values to the target dependency conditions that have the dependency relationship with the current target conditions based on the current execution results, and then determine the next target condition in the condition group as the new current target condition, and jump to the step of determining whether the current target condition in the condition group is assigned, until all the target conditions in the condition group are assigned, so as to complete the risk control decision optimization.
9. An electronic device, characterized in that: include: Memory, used to store computer programs; A processor, used to execute the computer program to implement the risk control decision optimization method as described in any one of claims 1 to 7.
10. A computer-readable storage medium, characterized in that: Used to store computer programs; wherein, when the computer program is executed by a processor, it implements the risk control decision optimization method according to any one of claims 1 to 7.