Financial risk control method and device supporting rule collaborative linkage, equipment and medium
By introducing a decision engine and a real-time computing engine into the financial risk control system, and combining current transaction information with historical rule triggering status, the system achieves coordinated rule linkage, which solves the problems of insufficient coverage and accuracy of traditional risk control systems and improves risk control efficiency and flexibility.
Patent Information
- Application Number
- CN202511775579.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-11-28
- Publication Date
- 2026-03-03
AI Technical Summary
Traditional financial risk control systems rely on direct indicators of the current time, resulting in insufficient coverage and accuracy. Furthermore, business personnel need to achieve cross-rule collaboration through hard coding or manual intervention, which increases operation and maintenance costs and strategy iteration cycles.
By combining the original rule triggering conditions and the rule linkage triggering conditions with the decision engine, the risk control rules are determined using the current transaction information and historical rule triggering status. This supports rule collaboration and linkage, enables cross-rule historical status referencing and visual configuration, and reduces code development dependencies.
It improves the coverage and accuracy of the risk control process, reduces operation and maintenance costs, supports rapid response to new fraud methods, and realizes explicit dependency networks and advanced logic combinations between rules.
Smart Images
Figure CN121599780A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of financial risk decision-making, and in particular to a financial risk control method, apparatus, equipment and medium that supports rule-based collaborative linkage. Background Technology
[0002] Currently, in the financial sector, banks and payment institutions generally face increasingly complex risk control challenges such as account theft and transaction fraud. To address these challenges, risk control systems have become an indispensable core infrastructure for financial institutions. Traditional risk control systems typically employ a modular architecture design, such as... Figure 1 The diagram illustrates a traditional risk control system, primarily comprising the following core components: 1. Decision Configuration Platform: Serving as the system's strategy management center, it provides a visual interface, enabling business personnel to flexibly configure risk control events, event fields, risk rules, and monitoring indicators, facilitating rapid definition and iterative updates of risk strategies and rules. 2. Real-time Computing Engine: Responsible for high-performance streaming data processing, executing indicator calculation scripts issued by the decision platform, performing millisecond-level real-time calculations on transaction flows, and caching intermediate results for subsequent decision-making. 3. Rule Decision Engine: As the system's intelligent decision-making hub, it dynamically loads rule assets (including triggering conditions and handling strategies) configured by the decision platform, performs multi-dimensional risk assessment based on the indicator calculation results provided by the real-time computing engine, and ultimately generates risk events and pushes them to the message queue. 4. Risk Control Operation Backend: Provides complete closed-loop management of risk handling, including real-time monitoring of risk events, manual review and handling, case investigation and analysis, and full-process audit tracking, ensuring the traceability and compliance of risk control operations.
[0003] However, current risk control systems have the following significant drawbacks: 1. They are generally based on direct indicators of the current time, which makes judgments based on a single criterion and is not conducive to improving risk control coverage and accuracy; 2. Business personnel need to use hard-coded or manual intervention to achieve cross-rule collaboration, which not only increases operation and maintenance costs but also leads to long strategy iteration cycles and makes it difficult to quickly respond to new fraud methods.
[0004] In summary, improving the efficiency, coverage, and accuracy of the risk control process is an urgent problem to be solved. Summary of the Invention
[0005] In view of this, the purpose of this invention is to provide a financial risk control method, apparatus, equipment, and medium that supports rule-based collaborative linkage, which can improve the efficiency, coverage, and accuracy of the risk control process. The specific solution is as follows:
[0006] Firstly, this application discloses a financial risk control method that supports rule-based collaborative linkage, applied to a financial risk control system that supports rule-based collaborative linkage, including:
[0007] The decision engine determines the current triggering risk control rule based on the original rule triggering conditions and the rule linkage triggering conditions, as well as the current transaction information and historical rule triggering status. The original rule triggering conditions are the conditions for determining whether a rule is triggered based on the current transaction information. The rule linkage triggering conditions are the conditions for determining whether a rule is triggered based on the historical rule triggering status. Furthermore, the rule linkage triggering conditions are the triggering conditions obtained by the user through self-configuration based on the visual interface of the decision platform.
[0008] Execute the corresponding financial risk control operation according to the currently triggered risk control rule;
[0009] The real-time computing engine updates the historical rule triggering status based on the current triggering information and corresponding update rules of the currently triggered risk control rule, and jumps to the step of determining the currently triggered risk control rule based on the current transaction information and the historical rule triggering status, until the financial risk control system that supports rule coordination and linkage obtains a pause instruction.
[0010] Optionally, the historical rule triggering status includes the number of times each risk control rule has been triggered within the corresponding specified statistical time range; the risk control rule is a specified rule under a specified indicator dimension; the current triggering information includes the number of triggers and the triggering time.
[0011] Accordingly, the updating of the historical rule triggering status based on the current triggering information of the currently triggered risk control rule and the corresponding update rule includes:
[0012] Increment the trigger count of the currently triggered risk control rule by 1 to update the trigger status of historical rules;
[0013] And / or, store the trigger time corresponding to the currently triggered risk control rule in the historical rule trigger status to update the historical rule trigger status.
[0014] Optionally, the rule linkage triggering condition is that the number of times the specified risk control rule is triggered within the corresponding specified statistical time range is not less than the corresponding specified number of triggers, and / or, the earliest or latest triggering time of the specified risk control rule within the corresponding specified statistical time range meets the predetermined time requirement.
[0015] Optionally, before updating the historical rule triggering status through the real-time calculation engine based on the current triggering information of the currently triggered risk control rule and the corresponding update rule, the method further includes:
[0016] The rule code set is obtained by statistically analyzing the rule codes of the currently triggered risk control rules through the rule status processor;
[0017] Accordingly, the step of updating the historical rule triggering status based on the current triggering information of the currently triggered risk control rule and the corresponding update rule through the real-time calculation engine includes:
[0018] The real-time computing engine increments the trigger count for each rule code in the rule code set by 1 to update the historical rule trigger status.
[0019] And / or use a real-time computing engine to store the trigger time corresponding to each rule code in the rule code set into the historical rule trigger status, so as to update the historical rule trigger status.
[0020] Optionally, the step of statistically analyzing the rule codes of currently triggered risk control rules to obtain a rule code set includes:
[0021] The rule codes of the currently triggered risk control rules are counted, and the rule codes are concatenated into a string format to obtain a set of rule codes; different rule codes in the set of rule codes are separated by preset special characters.
[0022] Optionally, the financial risk control method supporting rule-based collaborative linkage also includes:
[0023] The decision-making platform updates the trigger conditions for rule linkage and the corresponding risk control rules in real time.
[0024] Secondly, this application discloses a financial risk control device that supports rule-based collaborative linkage, applied to a financial risk control system that supports rule-based collaborative linkage, comprising:
[0025] The rule determination module is used to determine the current triggering risk control rule based on the original rule triggering conditions and rule linkage triggering conditions, and based on the current transaction information and historical rule triggering status, through the decision engine. The original rule triggering conditions are the conditions for determining whether the rule is triggered based on the current transaction information. The rule linkage triggering conditions are the conditions for determining whether the rule is triggered based on the historical rule triggering status. Furthermore, the rule linkage triggering conditions are the triggering conditions obtained by the user through self-configuration based on the visual interface of the decision platform.
[0026] The risk control module is used to execute corresponding financial risk control operations based on the currently triggered risk control rules;
[0027] The update module is used to update the historical rule triggering status based on the current triggering information and corresponding update rules of the currently triggered risk control rule through the real-time calculation engine, and jump to the step of determining the currently triggered risk control rule based on the current transaction information and the historical rule triggering status, until the financial risk control system that supports rule coordination and linkage obtains a pause instruction.
[0028] Optionally, the historical rule triggering status includes the number of times each risk control rule has been triggered within the corresponding specified statistical time range; the risk control rule is a specified rule under a specified indicator dimension; the current triggering information includes the number of triggers and the triggering time.
[0029] Accordingly, the update module is specifically used to increment the trigger count of the currently triggered risk control rule by 1 to update the trigger status of the historical rule;
[0030] And / or, store the trigger time corresponding to the currently triggered risk control rule in the historical rule trigger status to update the historical rule trigger status.
[0031] Thirdly, this application discloses an electronic device, including:
[0032] Memory, used to store computer programs;
[0033] A processor is used to execute the computer program to implement the aforementioned disclosed financial risk control method that supports rule-based collaborative linkage.
[0034] Fourthly, this application discloses a computer-readable storage medium for storing a computer program; wherein, when the computer program is executed by a processor, it implements the aforementioned financial risk control method that supports rule-based collaborative linkage.
[0035] As can be seen, this application uses a decision engine to determine the currently triggered risk control rule based on the original rule triggering conditions and rule linkage triggering conditions, and based on the current transaction information and historical rule triggering status. The original rule triggering conditions are the conditions for determining whether a rule is triggered based on the current transaction information. The rule linkage triggering conditions are the conditions for determining whether a rule is triggered based on the historical rule triggering status. Furthermore, the rule linkage triggering conditions are the triggering conditions obtained by the user through self-configuration based on the visual interface of the decision platform. The real-time calculation engine updates the historical rule triggering status based on the current triggering information of the currently triggered risk control rule and the corresponding update rules, and jumps to the step of determining the currently triggered risk control rule based on the current transaction information and historical rule triggering status, until the financial risk control system supporting rule collaboration receives a pause instruction. It should be noted that this application adds the judgment of historical trigger status to determine whether the rule can be triggered during the risk control process, extending the historical trigger status to the judgment conditions, instead of only using the direct indicators of the current event, i.e., the current transaction information, as the judgment condition. This is conducive to improving the risk control coverage and accuracy of the risk control process. In addition, this application completes the judgment of whether to trigger or allow triggering by the decision engine, without the need for manual participation in the judgment process, which is conducive to improving efficiency. Moreover, this application configures the rule linkage trigger conditions through the decision platform, without the need for coding, which is conducive to reducing costs. Attached Figure Description
[0036] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.
[0037] Figure 1 This is a schematic diagram of a traditional risk control system disclosed in this application;
[0038] Figure 2 This application discloses a flowchart of a financial risk control method that supports rule-based collaborative linkage.
[0039] Figure 3 This application discloses a flowchart of a specific financial risk control method that supports coordinated and interconnected rules.
[0040] Figure 4 This is a schematic diagram of a financial risk control system that supports rule-based collaborative linkage, as disclosed in this application.
[0041] Figure 5 This is a schematic diagram of a financial risk control device that supports rule-based collaborative linkage, as disclosed in this application.
[0042] Figure 6 This is a structural diagram of an electronic device disclosed in this application. Detailed Implementation
[0043] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.
[0044] Current risk control systems have the following significant drawbacks: 1. They generally rely on direct indicators of the current time for judgment, which is based on a single criterion and is not conducive to improving risk control coverage and accuracy; 2. Business personnel need to use hard-coded or manual intervention to achieve cross-rule collaboration, which not only increases operation and maintenance costs but also leads to long strategy iteration cycles and makes it difficult to quickly respond to new fraud methods.
[0045] Therefore, this application proposes a financial risk control scheme that supports rule-based collaborative linkage, which can improve the efficiency, coverage and accuracy of the risk control process.
[0046] This application discloses a financial risk control method that supports rule-based collaborative linkage, applied to a financial risk control system that supports rule-based collaborative linkage. See [link to relevant documentation]. Figure 2 As shown, the method includes:
[0047] Step S11: The decision engine determines the current triggering risk control rule based on the original rule triggering condition and the rule linkage triggering condition, and based on the current transaction information and the historical rule triggering status. The original rule triggering condition is the condition for determining whether the rule is triggered based on the current transaction information. The rule linkage triggering condition is the condition for determining whether the rule is triggered based on the historical rule triggering status. Furthermore, the rule linkage triggering condition is the triggering condition obtained by the user through self-configuration based on the visual interface of the decision platform.
[0048] It should be noted that the current transaction information includes transaction serial number, account number, card number, ID card number, transaction amount, timestamp, etc., which will not be described in detail here.
[0049] In this embodiment, the historical rule triggering status includes the number of times each risk control rule has been triggered within the corresponding specified statistical time range; the risk control rule is a specified rule under a specified indicator dimension; the current triggering information includes the number of triggers and the triggering time; correspondingly, updating the historical rule triggering status based on the current triggering information of the currently triggered risk control rule and the corresponding update rule includes: incrementing the triggering number corresponding to the currently triggered risk control rule by 1 to update the historical rule triggering status; and / or storing the triggering time corresponding to the currently triggered risk control rule in the historical rule triggering status to update the historical rule triggering status.
[0050] It should be noted that the current trigger information includes the number of triggers and the trigger time, etc., which are not specifically limited here. As long as the corresponding update rules are set for the corresponding trigger information to realize the historical rule trigger status, and the corresponding trigger information is set with the rule linkage trigger conditions, it is acceptable.
[0051] It should be noted that the historical rule trigger status is obtained by the real-time computing engine in the system. The real-time computing engine also stores historical rule trigger information, which includes information such as the indicator dimension and trigger time corresponding to each triggered rule, making it convenient to count the historical rule trigger status.
[0052] It should be noted that the indicator dimension can be specific transaction information, such as key identifier indicators such as account indicator dimension, card number indicator dimension, ID card number indicator dimension, etc., or it can be device number indicator dimension, customer number indicator dimension, etc.; the same rule may exist under different indicator dimensions, in which case the number of times needs to be counted separately; the specified statistical time range can be a fixed time period from the current time backward, or it can be a fixed time period in history. The fixed time period is not specifically limited and can be 1 hour, 1 minute, 1 day, etc.
[0053] In one specific embodiment, the historical rule triggering status specifically includes the following: 1. Rule A is triggered 3 times within 1 hour under the account metric dimension; 2. Rule B is triggered 2 times within 30 minutes under the device number; 3. Rule C is triggered 5 times within 25 minutes under the account metric dimension; 4. Rule B is triggered 4 times within 25 minutes under the account metric dimension.
[0054] In this embodiment, the rule linkage triggering condition is that the number of times the specified risk control rule is triggered within the corresponding specified statistical time range is not less than the corresponding specified triggering number, and / or, the earliest or latest triggering time of the specified risk control rule within the corresponding specified statistical time range meets a predetermined time requirement. It should be noted that the specified risk rule can be one or more, and each risk rule has a specified statistical time range.
[0055] In one specific embodiment, the triggering conditions for rule linkage are: 1. Rule A is triggered no less than 2 times within 1 hour under the account metric dimension; or, 2. Rule C is triggered no less than 2 times within 25 minutes under the account metric dimension, and Rule B is triggered no less than 2 times within 30 minutes under the device number.
[0056] It should be noted that each rule linkage trigger condition also has a corresponding risk control rule, which is triggered when the linkage trigger condition is met.
[0057] In one specific embodiment, risk control rule V is triggered when the above-mentioned rule linkage triggering condition 1 is met, and risk control rule M is triggered when the above-mentioned rule linkage triggering condition 2 is met.
[0058] It should be noted that the triggering condition for the rule linkage can also be that the total number of triggers of several risk rules within the corresponding specified statistical range is not less than a specified number of triggers.
[0059] In summary, this application overcomes the limitation of traditional risk control systems that can only make decisions based on current event indicators. It enables dynamic referencing of the historical triggering states of other rules (such as whether they are triggered, the number of triggers, and the most recent trigger time) by rule conditions, establishing state dependencies between rules. Through a rule condition linkage mechanism, this application supports complex logic such as "activating rule 2 when rule 1 is triggered N times within time period T," achieving complex fraud pattern recognition through multi-rule collaboration without hard coding.
[0060] In this embodiment, the triggering condition for rule linkage is a triggering condition obtained by the user through self-configuration based on the visual interface of the decision-making platform. That is, the user can configure the triggering condition for rule linkage independently and determine the risk rule corresponding to the triggering condition during configuration.
[0061] It should be noted that the configuration operation is not limited to one-time execution. The decision-making platform can update the rule linkage trigger conditions and the corresponding risk control rules in real time without requiring code modification, making it simple and convenient. Furthermore, this application can configurably implement complex risk control scenarios that traditionally require custom development, and also supports real-time dynamic adjustment of rule association strategies to quickly respond to new types of fraud; it also improves overall risk control coverage through rule synergy.
[0062] In one specific embodiment, the above-mentioned two rule linkage triggering conditions are mentioned. Based on this, the two can be combined as a rule linkage triggering condition, and the corresponding risk rule is determined. Specifically, the configuration is as follows: when rule A is triggered no less than twice within 1 hour under the account indicator dimension, rule C is triggered no less than twice within 25 minutes under the account indicator dimension, and rule B is triggered no less than twice within 30 minutes under the device number, risk rule O is triggered.
[0063] In another specific embodiment, the risk control rule V and risk control rule M corresponding to the above two rule linkage triggering conditions can be specified. Specifically, the rule linkage triggering conditions are: 1. Risk control rule V is triggered no less than 2 times within 25 minutes (risk rule S can be triggered); 2. Risk control rule M is triggered no less than 2 times within 30 minutes (risk rule P can be triggered); 3. Risk control rule V is triggered no less than 2 times within 25 minutes and risk control rule M is triggered no less than 2 times within 30 minutes (risk rule U can be triggered).
[0064] In another specific embodiment, a new risk rule corresponding to the original rule triggering condition can be added. For example, rule F is triggered no less than twice within 40 minutes under the account indicator dimension.
[0065] Step S12: Execute the corresponding financial risk control operation according to the currently triggered risk control rule.
[0066] Step S13: The real-time calculation engine updates the historical rule triggering status based on the current triggering information and corresponding update rules of the currently triggered risk control rule, and jumps to the step of determining the currently triggered risk control rule based on the current transaction information and the historical rule triggering status, until the financial risk control system that supports rule collaboration receives a pause instruction.
[0067] In this embodiment, risk control rules may be triggered at any time, so it is necessary to update the historical rule trigger status in real time.
[0068] In summary, this application breaks through the limitations of traditional rule isolation, enabling true rule-based collaborative decision-making by sharing rule states, supporting cross-rule historical state referencing, and establishing an explicit dependency network between rules. This application supports advanced logic combinations such as "Rule 1 triggers N times during time period T → activates Rule 2". It allows for the construction of multi-rule linkage fraud detection models without code development. This application transforms rule collaboration from code-level implementation to visual configuration. Business personnel can independently adjust rule relationships, reducing development dependencies.
[0069] As can be seen, this application uses a decision engine to determine the currently triggered risk control rule based on the original rule triggering conditions and rule linkage triggering conditions, and based on the current transaction information and historical rule triggering status. The original rule triggering conditions are the conditions for determining whether a rule is triggered based on the current transaction information. The rule linkage triggering conditions are the conditions for determining whether a rule is triggered based on the historical rule triggering status. Furthermore, the rule linkage triggering conditions are the triggering conditions obtained by the user through self-configuration based on the visual interface of the decision platform. The real-time calculation engine updates the historical rule triggering status based on the current triggering information of the currently triggered risk control rule and the corresponding update rules, and jumps to the step of determining the currently triggered risk control rule based on the current transaction information and historical rule triggering status, until the financial risk control system supporting rule collaboration receives a pause instruction. It should be noted that this application adds the judgment of historical trigger status to determine whether the rule can be triggered during the risk control process, extending the historical trigger status to the judgment conditions, instead of only using the direct indicators of the current event, i.e., the current transaction information, as the judgment condition. This is conducive to improving the risk control coverage and accuracy of the risk control process. In addition, this application completes the judgment of whether to trigger or allow triggering by the decision engine, without the need for manual participation in the judgment process, which is conducive to improving efficiency. Furthermore, this application configures the rule linkage trigger conditions through the decision platform, without the need for coding, which is conducive to reducing costs and improving efficiency.
[0070] This application discloses a specific financial risk control method supporting rule-based collaborative linkage, applied to a financial risk control system that supports rule-based collaborative linkage. Compared to the previous embodiment, this embodiment further explains and optimizes the technical solution. See also... Figure 3 As shown, it specifically includes:
[0071] Step S21: The decision engine determines the current triggering risk control rule based on the original rule triggering condition and the rule linkage triggering condition, and based on the current transaction information and the historical rule triggering status. The original rule triggering condition is the condition for determining whether the rule is triggered based on the current transaction information. The rule linkage triggering condition is the condition for determining whether the rule is triggered based on the historical rule triggering status. Furthermore, the rule linkage triggering condition is the triggering condition obtained by the user through self-configuration based on the visual interface of the decision platform.
[0072] Step S22: Execute the corresponding financial risk control operation according to the currently triggered risk control rule.
[0073] Step S23: Obtain the rule code set by statistically analyzing the rule codes of the currently triggered risk control rules through the rule status processor.
[0074] In this embodiment, the step of statistically analyzing the rule codes of the currently triggered risk control rules to obtain a set of rule codes includes: statistically analyzing the rule codes of the currently triggered risk control rules and concatenating the rule codes into strings to obtain a set of rule codes; different rule codes in the set of rule codes are separated by preset special characters.
[0075] It should be noted that no specific limitations are imposed on the preset special characters; in one specific embodiment, the preset special characters can be English semicolons, and the rule codes include RULE_CODE_001, RULE_CODE_002, and RULE_CODE_010, thus obtaining the rule code set as "RULE_CODE_001; RULE_CODE_002; RULE_CODE_010;". Subsequently, the processed rule code set can be stored in the ruleCodeListStr field on the local side of the rule state processor, and the rule code set can be sent to the real-time computing engine.
[0076] It should be noted that the presence of preset special characters can avoid misidentification of rule encodings. For example, it can prevent RULE_CODE_01 from being interpreted as RULE_CODE_010. When a semicolon is present, "RULE_CODE_01;" will not be interpreted as "RULE_CODE_010;".
[0077] Step S24: Increment the trigger count of each rule code in the rule code set by 1 through the real-time calculation engine to update the historical rule trigger status; and / or, store the trigger time of each rule code in the rule code set to the historical rule trigger status through the real-time calculation engine to update the historical rule trigger status, and jump to the step of determining the currently triggered risk control rule based on the current transaction information and the historical rule trigger status, until the financial risk control system that supports rule collaboration obtains a pause instruction.
[0078] In this embodiment, the real-time computing engine updates the historical rule triggering status based on the acquired ruleCodeListStr field. Specifically, the calculation logic is as follows: rule matching statistics are performed based on the ruleCodeListStr field; filtering conditions: condition type: judgment type, filtering object: ruleCodeListStr, operator: contains a specific string, matching value: rule code + ";" (e.g., RULE_CODE_001;).
[0079] In this embodiment, the decision platform has a ruleCodeListStr field that stores rule codes. After determining the currently triggered risk control rule, the risk control rule containing the rule code is sent to the rule status processor so that the rule status processor can extract the rule code. The ruleCodeListStr field that stores the rule code can also be given to the real-time computing engine so that the real-time computing engine can determine the trigger status of the historical rule that needs to be updated.
[0080] It should be noted that this application can extract and process rule states in the existing risk control system architecture without adding an additional rule state component. The same effect can be achieved by extracting and processing rule states in the risk control backend component or other existing components, but this will increase the coupling and complexity between the risk control backend or other components and the real-time computing engine. In this application, rule codes are separated by ";" to improve matching accuracy when concatenating rule codes. In actual configuration and processing, other special characters can also achieve the same effect.
[0081] See Figure 4 The diagram shown is a schematic of a financial risk control system that supports rule-based collaborative linkage. Figure 1 Compared to adding a rule status processor, apart from the newly added full-step process of triggering risk control rules based on rule linkage, the other steps are consistent with the traditional risk control system. Specifically, the role of the rule status processor is to extract the rule code from the rule information of the currently triggered risk rule, and concatenate the rule codes in string format to obtain a set of rule codes.
[0082] It should be pointed out that, Figure 4 In the decision-making platform, indicators are configured, and calculation scripts are generated based on these indicators. A real-time calculation engine subscribes to these scripts, performs real-time calculations based on transaction flows and the calculation scripts, and stores the results. The calculation scripts described in this application define how and whether transaction flows can be calculated. The decision-making engine is used to determine the triggered risk rules based on the original rule triggering conditions and rule linkage triggering conditions (the decision-making engine can obtain risk assets from the decision-making platform, post-event flows from the device under risk control, and calculation results from the real-time calculation engine to determine the triggered risk rules) (risk assets include the original rule triggering conditions, rule linkage triggering conditions, and the corresponding risk rules). A message queue is used to store risk data (including risk rules, ...). (Transaction information, etc.) is used by other devices for retrieval; the risk control backend is used to retrieve risk rules from the message queue and execute financial risk control operations; the rule status processor is used to extract the rule code from the rule information of the currently triggered risk rule, concatenate the rule codes into a string format to obtain a rule code set, and store it in the ruleCodeListStr field; the decision engine pushes the triggered rule information to the message queue, the rule status processor retrieves the rule information from the message queue, parses, processes and encapsulates it, and then pushes the encapsulated data to the real-time computing engine; the corresponding transaction information of the risk control device will be sent to the decision engine and the real-time computing engine so that the decision engine and the real-time computing engine can complete their respective operations.
[0083] As can be seen, this application uses a decision engine to determine the currently triggered risk control rule based on the original rule triggering conditions and rule linkage triggering conditions, and based on the current transaction information and historical rule triggering status. The original rule triggering conditions are conditions for determining whether a rule is triggered based on the current transaction information. The rule linkage triggering conditions are conditions for determining whether a rule is triggered based on the historical rule triggering status. Furthermore, the rule linkage triggering conditions are triggering conditions obtained by the user through self-configuration based on the visual interface of the decision platform. The application executes the corresponding financial risk control operation according to the currently triggered risk control rule. The rule status processor counts the rule codes of the currently triggered risk control rule to obtain a rule code set. The real-time calculation engine increments the trigger count corresponding to each rule code in the rule code set by 1 to update the historical rule triggering status. And / or, the real-time calculation engine stores the trigger time corresponding to each rule code in the rule code set into the historical rule triggering status to update the historical rule triggering status, and jumps to the step of determining the currently triggered risk control rule based on the current transaction information and historical rule triggering status, until the financial risk control system supporting rule linkage obtains a pause instruction. Therefore, it is evident that this application can improve speed by updating the trigger count based on rule encoding; this application uses preset special characters to concatenate rule encoding, which is beneficial to improving the accuracy of subsequent identification and further improving the accuracy of the risk control process.
[0084] Accordingly, this application also discloses a financial risk control device that supports rule-based collaborative linkage, applied to a financial risk control system that supports rule-based collaborative linkage. See [link to relevant documentation]. Figure 5 As shown, the device includes:
[0085] The rule determination module 11 is used to determine the currently triggered risk control rule through the decision engine based on the original rule triggering conditions and the rule linkage triggering conditions, and based on the current transaction information and the historical rule triggering status. The original rule triggering conditions are the conditions for determining whether the rule is triggered based on the current transaction information. The rule linkage triggering conditions are the conditions for determining whether the rule is triggered based on the historical rule triggering status. Furthermore, the rule linkage triggering conditions are the triggering conditions obtained by the user through self-configuration based on the visual interface of the decision platform.
[0086] Risk control module 12 is used to execute corresponding financial risk control operations according to the currently triggered risk control rules;
[0087] The update module 13 is used to update the historical rule triggering status based on the current triggering information and corresponding update rules of the currently triggered risk control rule through the real-time calculation engine, and jump to the step of determining the currently triggered risk control rule based on the current transaction information and the historical rule triggering status, until the financial risk control system that supports rule coordination and linkage obtains a pause instruction.
[0088] As can be seen, this application uses a decision engine to determine the currently triggered risk control rule based on the original rule triggering conditions and rule linkage triggering conditions, and based on the current transaction information and historical rule triggering status. The original rule triggering conditions are the conditions for determining whether a rule is triggered based on the current transaction information. The rule linkage triggering conditions are the conditions for determining whether a rule is triggered based on the historical rule triggering status. Furthermore, the rule linkage triggering conditions are the triggering conditions obtained by the user through self-configuration based on the visual interface of the decision platform. The real-time calculation engine updates the historical rule triggering status based on the current triggering information of the currently triggered risk control rule and the corresponding update rules, and jumps to the step of determining the currently triggered risk control rule based on the current transaction information and historical rule triggering status, until the financial risk control system supporting rule collaboration receives a pause instruction. It should be noted that this application adds the judgment of historical trigger status to determine whether the rule can be triggered during the risk control process, extending the historical trigger status to the judgment conditions, instead of only using the direct indicators of the current event, i.e., the current transaction information, as the judgment condition. This is conducive to improving the risk control coverage and accuracy of the risk control process. In addition, this application completes the judgment of whether to trigger or allow triggering by the decision engine, without the need for manual participation in the judgment process, which is conducive to improving efficiency. Moreover, this application configures the rule linkage trigger conditions through the decision platform, without the need for coding, which is conducive to reducing costs.
[0089] In one embodiment, the historical rule triggering status includes the number of times each triggered rule has been triggered within the corresponding specified indicator dimension and specified statistical time range; the current triggering information includes the number of triggers and the triggering time.
[0090] Accordingly, the update module is specifically used to increment the trigger count of the currently triggered risk control rule by 1 to update the trigger status of the historical rule;
[0091] Alternatively, the trigger time corresponding to the currently triggered risk control rule can be stored in the historical rule trigger status to update the historical rule trigger status.
[0092] In one embodiment, the rule linkage triggering condition is that the number of times the specified risk control rule is triggered within the corresponding specified statistical time range is not less than the corresponding specified number of triggers, and / or, the earliest or latest triggering time of the specified risk control rule within the corresponding specified statistical time range meets the predetermined time requirement.
[0093] In one embodiment, the financial risk control device supporting rule-based collaborative linkage further includes:
[0094] The rule code set determination module is used to obtain the rule code set by statistically analyzing the rule codes of the currently triggered risk control rules through the rule status processor;
[0095] Accordingly, the update module includes:
[0096] The update unit is used to increment the trigger count of each rule code in the rule code set by 1 through the real-time computing engine to update the historical rule trigger status.
[0097] And / or, by using a real-time computing engine, the trigger time corresponding to each rule code in the rule code set is stored in the historical rule trigger status to update the historical rule trigger status.
[0098] In one embodiment, the rule code set determination module is specifically used to count the rule codes of the currently triggered risk control rules and concatenate the rule codes into a string format to obtain a rule code set; different rule codes in the rule code set are separated by preset special characters.
[0099] In one specific embodiment, the financial risk control device supporting rule-based collaborative linkage further includes:
[0100] The real-time update module is used to update the trigger conditions for rule linkage and the corresponding risk control rules through the decision-making platform in real time.
[0101] Furthermore, embodiments of this application also provide an electronic device. Figure 6This is a structural diagram of an electronic device 20 according to an exemplary embodiment. The content of the diagram should not be construed as limiting the scope of this application.
[0102] Figure 6 This is a schematic diagram of the structure of an electronic device 20 provided in an embodiment of this application. The electronic device 20 may specifically include: at least one processor 21, at least one memory 22, a display screen 23, an input / output interface 24, a communication interface 25, a power supply 26, and a communication bus 27. The memory 22 stores a computer program, which is loaded and executed by the processor 21 to implement the relevant steps in the financial risk control method supporting rule-based collaborative linkage disclosed in any of the foregoing embodiments. Furthermore, the electronic device 20 in this embodiment may specifically be an electronic computer.
[0103] In this embodiment, the power supply 26 is used to provide operating voltage for each hardware device on the electronic device 20; the communication interface 25 can create a data transmission channel between the electronic device 20 and external devices, and the communication protocol it follows can be any communication protocol applicable to the technical solution of this application, and is not specifically limited here; the input / output interface 24 is used to acquire 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.
[0104] Furthermore, the memory 22, as a carrier for resource storage, can be a read-only memory, random access memory, disk, or optical disk, etc. The resources stored thereon can include computer programs 221, and the storage method can be temporary storage or permanent storage. The computer programs 221, in addition to including computer programs capable of performing the rule-based collaborative financial risk control method executed by the electronic device 20 as disclosed in any of the foregoing embodiments, may further include computer programs capable of performing other specific tasks.
[0105] Furthermore, embodiments of this application also disclose a computer-readable storage medium for storing a computer program; wherein, when the computer program is executed by a processor, it implements the aforementioned financial risk control method that supports rule-based collaborative linkage.
[0106] The specific steps of this method can be found in the corresponding content disclosed in the foregoing embodiments, and will not be repeated here.
[0107] The various embodiments in this application are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. For the same or similar parts between the various embodiments, refer to each other. As for the apparatus disclosed in the embodiments, since it corresponds to the method disclosed in the embodiments, the description is relatively simple, and relevant parts can be referred to in the method section.
[0108] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.
[0109] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein can be implemented directly by hardware, a software module executed by a processor, or a combination of both. The software module can be located in random access memory (RAM), main memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art.
[0110] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.
[0111] The foregoing has provided a detailed description of a financial risk control method, apparatus, device, and storage medium that supports rule-based collaborative linkage. Specific examples have been used to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.
Claims
1. A financial risk control method supporting rule-based collaborative linkage, characterized in that, Applied to financial risk control systems that support rule-based collaborative mechanisms, including: The decision engine determines the current triggering risk control rule based on the original rule triggering conditions and the rule linkage triggering conditions, as well as the current transaction information and historical rule triggering status. The original rule triggering conditions are the conditions for determining whether a rule is triggered based on the current transaction information. The rule linkage triggering conditions are the conditions for determining whether a rule is triggered based on the historical rule triggering status. Furthermore, the rule linkage triggering conditions are the triggering conditions obtained by the user through self-configuration based on the visual interface of the decision platform. Execute the corresponding financial risk control operation according to the currently triggered risk control rule; The real-time computing engine updates the historical rule triggering status based on the current triggering information and corresponding update rules of the currently triggered risk control rule, and jumps to the step of determining the currently triggered risk control rule based on the current transaction information and the historical rule triggering status, until the financial risk control system that supports rule coordination and linkage obtains a pause instruction.
2. The financial risk control method supporting rule-based collaborative linkage according to claim 1, characterized in that, The historical rule trigger status includes the number of times each risk control rule has been triggered within the corresponding specified statistical time range; the risk control rule is a specified rule under a specified indicator dimension; the current trigger information includes the number of triggers and the trigger time. Accordingly, the updating of the historical rule triggering status based on the current triggering information of the currently triggered risk control rule and the corresponding update rule includes: Increment the trigger count of the currently triggered risk control rule by 1 to update the trigger status of historical rules; And / or, store the trigger time corresponding to the currently triggered risk control rule in the historical rule trigger status to update the historical rule trigger status.
3. The financial risk control method supporting rule-based collaborative linkage according to claim 2, characterized in that, The triggering condition for the rule linkage is that the number of times the specified risk control rule is triggered within the corresponding specified statistical time range is not less than the corresponding specified number of triggers, and / or, the earliest or latest triggering time of the specified risk control rule within the corresponding specified statistical time range meets the predetermined time requirement.
4. The financial risk control method supporting rule-based collaborative linkage according to claim 2, characterized in that, Before updating the historical rule triggering status through the real-time computing engine based on the current triggering information of the currently triggered risk control rule and the corresponding update rule, the process also includes: The rule code set is obtained by statistically analyzing the rule codes of the currently triggered risk control rules through the rule status processor; Accordingly, the step of updating the historical rule triggering status based on the current triggering information of the currently triggered risk control rule and the corresponding update rule through the real-time calculation engine includes: The real-time computing engine increments the trigger count for each rule code in the rule code set by 1 to update the historical rule trigger status. And / or, by using a real-time computing engine, the trigger time corresponding to each rule code in the rule code set is stored in the historical rule trigger status to update the historical rule trigger status.
5. The financial risk control method supporting rule-based collaborative linkage according to claim 4, characterized in that, The rule codes of the currently triggered risk control rules are statistically analyzed to obtain a set of rule codes, including: The rule codes of the currently triggered risk control rules are counted, and the rule codes are concatenated into a string format to obtain a set of rule codes; different rule codes in the set of rule codes are separated by preset special characters.
6. The financial risk control method supporting rule-based collaborative linkage according to any one of claims 1 to 5, characterized in that, Also includes: The decision-making platform updates the trigger conditions for rule linkage and the corresponding risk control rules in real time.
7. A financial risk control device that supports rule-based collaborative linkage, characterized in that, Applied to financial risk control systems that support rule-based collaborative mechanisms, including: The rule determination module is used to determine the current triggering risk control rule based on the original rule triggering conditions and rule linkage triggering conditions, and based on the current transaction information and historical rule triggering status, through the decision engine. The original rule triggering conditions are the conditions for determining whether the rule is triggered based on the current transaction information. The rule linkage triggering conditions are the conditions for determining whether the rule is triggered based on the historical rule triggering status. Furthermore, the rule linkage triggering conditions are the triggering conditions obtained by the user through self-configuration based on the visual interface of the decision platform. The risk control module is used to execute corresponding financial risk control operations based on the currently triggered risk control rules; The update module is used to update the historical rule triggering status based on the current triggering information and corresponding update rules of the currently triggered risk control rule through the real-time calculation engine, and jump to the step of determining the currently triggered risk control rule based on the current transaction information and the historical rule triggering status, until the financial risk control system that supports rule coordination and linkage obtains a pause instruction.
8. The financial risk control device supporting rule-based collaborative linkage according to claim 7, characterized in that, The historical rule triggering status includes the number of times each triggered rule has been triggered within the corresponding specified indicator dimension and specified statistical time range; the current triggering information includes the number of triggers and the triggering time. Accordingly, the update module is specifically used to increment the trigger count of the currently triggered risk control rule by 1 to update the trigger status of the historical rule; And / or, store the trigger time corresponding to the currently triggered risk control rule in the historical rule trigger status to update the historical rule trigger status.
9. An electronic device, characterized in that, include: Memory, used to store computer programs; A processor is used to execute the computer program to implement the financial risk control method supporting rule-based collaborative linkage as described in any one of claims 1 to 6.
10. A computer-readable storage medium, characterized in that, Used to store computer programs; wherein, when the computer programs are executed by a processor, they implement the financial risk control method supporting rule-based collaborative linkage as described in any one of claims 1 to 6.