Transaction settlement method based on model driving and security risk identification

Through a model-driven method, combining the matching rules and abnormal characteristics of transaction request orders, abnormal transaction orders are identified and intercepted, which solves the problem of malicious order identification with high transaction volume and improves the security and efficiency of transaction settlement.

CN118982358APending Publication Date: 2024-11-19HENAN XINANLI SECURITY TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411184043.X
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-27
Publication Date
2024-11-19

AI Technical Summary

Technical Problem

In a high transaction volume environment, it is difficult for existing technology to effectively identify and intercept malicious transaction orders, resulting in excessive server processing pressure, affecting the efficiency and security of transaction settlement.

Method used

Using a model-driven method, the transaction request order data is obtained in real time, combined with matching settlement rules and abnormal characteristics, the order is associated with IP addresses, the probability of abnormal transaction orders is determined, and differentiated interception processing is implemented to evaluate the security risks of the trading platform, and optimize the Transaction settlement processing.

Benefits of technology

It improves the accuracy of identification of abnormal transaction orders, reduces server pressure, improves the security and processing efficiency of transaction settlement, and avoids security risks caused by malicious orders.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118982358A_ABST
    Figure CN118982358A_ABST
Patent Text Reader

Abstract

The invention provides a transaction settlement method based on model driving and security risk identification, and belongs to the technical field of data processing, and the method specifically comprises the steps: carrying out the determination of an abnormal transaction order and an abnormal probability through employing the matching result of the transaction features of a transaction request order and an associated order with an abnormal transaction feature, determining a differentiated interception processing strategy based on the abnormal probability of the abnormal request order and the order data, obtaining the abnormal request orders at different moments within a preset duration, and determining that the transaction settlement platform has no security risk according to the abnormal probability of the abnormal request order at different moments. And transaction settlement processing is carried out by using the matching settlement rule and model of the transaction request order from which the abnormal transaction order is removed, so that the processing efficiency of transaction settlement is improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention belongs to the field of data processing technology, and in particular relates to a transaction settlement method based on model drive and security risk identification. Background Art

[0002] As the volume of online transactions increases, how to ensure the security of online transactions has become a technical problem that needs to be solved urgently. Existing technical solutions often implement transaction settlement processing through identity authentication and other methods to ensure the security of transaction settlement. However, it is not difficult to find the following technical problems through analysis: When processing transaction settlement, different transaction settlement orders need to be settled using matching settlement processing rules. Therefore, when the transaction volume is large, if malicious orders in the transaction settlement orders cannot be identified and intercepted, it may cause excessive pressure on the server's data processing and reduce the efficiency of transaction settlement processing.

[0003] In response to the above technical problems, the present invention provides a transaction settlement method based on model-driven and security risk identification. Summary of the invention

[0004] To achieve the purpose of the present invention, the present invention adopts the following technical solutions: In order to solve the above technical problems, the present invention provides a transaction settlement method based on model-driven and security risk identification, which specifically includes: S1 obtains the transaction request order data at different times of the adjacent period in real time, and when it is determined that the settlement processing pressure of the transaction request does not meet the requirements in combination with the matching settlement rules and models of different transaction request orders, proceeds to the next step; S2 determines the associated orders of different transaction request orders according to the IP addresses of different transaction request orders, and uses the matching results of the transaction characteristics of the transaction request orders and the associated orders with the abnormal transaction characteristics to determine the abnormal transaction orders and the abnormal probability, and determines the differentiated interception processing strategy based on the abnormal probability and order data of the abnormal request orders; S3 obtains abnormal request orders at different times within a preset time period, and proceeds to the next step when it is determined that there is no security risk in the transaction settlement platform through the abnormal probability of abnormal request orders at different times; S4 performs transaction settlement processing using the matching settlement rules and models of the transaction request orders excluding abnormal transaction orders.

[0005] The beneficial effects of the present invention are: 1. Abnormal transaction orders are determined by using the matching results of transaction characteristics of transaction request orders and associated orders with abnormal transaction characteristics. Not only the matching results of transaction characteristics of transaction request orders and abnormal transaction characteristics are considered, but also the matching results of associated orders of IP addresses with abnormal transaction characteristics are further combined to achieve the determination of abnormal transaction orders from multiple angles, thus avoiding the technical problem that the recognition accuracy of abnormal transaction orders does not meet the requirements due to account switching or other methods.

[0006] 2. Determine whether there is a security risk in the transaction settlement platform through the abnormal probability of abnormal request orders at different times, and accurately evaluate the transaction security risk of the current transaction settlement platform from the perspective of the distribution of abnormal request orders within a preset time period and the abnormal probability, avoiding the technical problem of high pressure on transaction settlement of the server due to a large number of abnormal request orders, and improving the security of transaction settlement.

[0007] A further technical solution is that the adjacent time period is a time period whose interval with the current moment is within a preset range.

[0008] A further technical solution is that the transaction request order data includes the quantity of different types of transaction request orders at different times.

[0009] A further technical solution is that the matching settlement rules and models of the transaction request order are determined according to the type of the transaction request order.

[0010] A further technical solution is that when the settlement processing pressure of the transaction request meets the requirements, there is no need to identify and intercept abnormal transaction orders.

[0011] A further technical solution is to carry out transaction settlement processing, which specifically includes: The transaction request orders excluding abnormal transaction orders are treated as normal transaction orders, and the settlement processing of the normal transaction orders is performed using the matching settlement rules of the normal transaction orders. The processing results of the settlement processing are stored and data exchange processing is performed between different transaction parties based on the matching model of the normal transaction orders.

[0012] Other features and advantages will be described in the following description, and partly become apparent from the description, or understood by practicing the invention. The purpose and other advantages of the invention are realized and obtained by the structures particularly pointed out in the description and the drawings.

[0013] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] The above and other features and advantages of the present invention will become more apparent by describing in detail exemplary embodiments thereof with reference to the attached drawings.

[0015] Figure 1 It is a flowchart of a method for transaction settlement based on model-driven and security risk identification; Figure 2 is a flow chart of a method for determining that settlement processing pressure for a transaction request does not meet requirements; Figure 3 It is a flow chart of a method for determining abnormal transaction orders. DETAILED DESCRIPTION

[0016] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the embodiments set forth herein; rather, these embodiments are provided so that the present invention will be comprehensive and complete and fully convey the concepts of the example embodiments to those skilled in the art. The same reference numerals in the figures represent the same or similar structures, and thus their detailed description will be omitted.

[0017] The terms "a", "an", "the", and "said" are used to indicate the presence of one or more elements / components / etc.; the terms "comprising" and "having" are used to express an open-ended inclusive meaning and mean that additional elements / components / etc. may be present in addition to the listed elements / components / etc.

[0018] To solve the above problems, according to one aspect of the present invention, Figure 1 As shown, according to one aspect of the present invention, a transaction settlement method based on model-driven and security risk identification is provided, which specifically includes: S1 obtains the transaction request order data at different times of the adjacent period in real time, and when it is determined that the settlement processing pressure of the transaction request does not meet the requirements in combination with the matching settlement rules and models of different transaction request orders, proceeds to the next step; Furthermore, the adjacent time period is a time period whose interval with the current time is within a preset range.

[0019] It can be understood that the transaction request order data includes the quantity of different types of transaction request orders at different times.

[0020] It should be noted that the matching settlement rules and models of the transaction request orders are determined according to the type of the transaction request orders.

[0021] It is understandable that if Figure 2 As shown, determining that the settlement processing pressure of the transaction request does not meet the requirements specifically includes: Determine the difficulty coefficient of settlement processing of different transaction request orders based on the matching settlement rules and models of different transaction request orders; Determine the quantity of different types of transaction request orders at different times according to the transaction request order data at different times, and determine the difficulty of settlement processing of the transaction request orders at different times in combination with the difficulty coefficient of settlement processing of different transaction request orders; The processing difficulty assessment amount of the transaction request is determined by the average value of the settlement processing difficulty of the transaction request orders at different times in a nearby time period, and based on the processing difficulty assessment amount, it is determined whether the settlement processing pressure of the transaction request meets the requirements.

[0022] Further, when the processing difficulty assessment amount is greater than a preset processing difficulty threshold, it is determined that the settlement processing pressure of the transaction request does not meet the requirement.

[0023] It is understandable that when the settlement processing pressure of the transaction request meets the requirements, there is no need to identify and intercept abnormal transaction orders.

[0024] It should also be noted that determining that the settlement processing pressure of the transaction request does not meet the requirements specifically includes: S11 obtains the number of transaction request orders at different times in the adjacent time period, and determines whether the total number of transaction request orders in the adjacent time period is greater than a preset number. If so, proceed to the next step; if not, proceed to step; S12 determines whether there is a moment in the near period when the number of transaction request orders is greater than the preset order number. If so, proceed to the next step. If not, proceed to step; S13: The time when the number of transaction request orders is greater than the preset number of orders is used as the transaction settlement busy time, and whether the number of the transaction settlement busy time meets the requirement is determined. If so, the next step is entered; if not, it is determined that the settlement processing pressure of the transaction request does not meet the requirement; S14 determines the processing busyness of the transaction request orders in the adjacent time period based on the number of transaction request orders at different times, and judges whether the processing busyness of the transaction request orders in the adjacent time period meets the requirement. If so, proceed to the next step; if not, it is determined that the settlement processing pressure of the transaction request does not meet the requirement; S15 determines the difficulty coefficients of settlement processing of different transaction request orders based on the matching settlement rules and models of different transaction request orders, determines the number of different types of transaction request orders at different times according to the transaction request order data at different times, and determines the settlement processing difficulty of the transaction request orders at different times in combination with the difficulty coefficients of settlement processing of different transaction request orders, and determines whether the number of times when the settlement processing difficulty does not meet the requirement meets the requirement, if so, proceeds to the next step, if not, determines that the settlement processing pressure of the transaction request does not meet the requirement; S16 determines the processing difficulty assessment amount of the transaction request by averaging the settlement processing difficulties of the transaction request orders at different times in an adjacent time period, and determines whether the settlement processing pressure of the transaction request meets the requirements based on the processing difficulty assessment amount.

[0025] S2 determines the associated orders of different transaction request orders according to the IP addresses of different transaction request orders, and uses the matching results of the transaction characteristics of the transaction request orders and the associated orders with the abnormal transaction characteristics to determine the abnormal transaction orders and the abnormal probability, and determines the differentiated interception processing strategy based on the abnormal probability and order data of the abnormal request orders; Furthermore, the associated order of the transaction request order is an order having the same IP address as the transaction request order.

[0026] It is understandable that the abnormal transaction characteristics include the creation time of the transaction order, the creation interval between different transaction orders of the same account, and the number of transaction orders submitted within a unit time.

[0027] Specifically, Figure 3 As shown, the method for determining the abnormal transaction order is: Determining the number of matches of the abnormal transaction features of the transaction request order based on the matching result of the transaction features of the transaction request order and the abnormal transaction features, and determining the basic abnormal probability of the transaction request order by using the number of matches of the abnormal transaction features; Determining order abnormality probabilities of different associated orders according to the matching number of abnormal transaction features of associated orders of the transaction request order; The abnormal probability of the transaction request order is determined by using the normalized sum of the basic abnormal probability of the transaction request order and the order abnormal probabilities of different associated orders, and whether the transaction request order is an abnormal transaction order is determined by using the abnormal probability.

[0028] Further, when the abnormal probability of the transaction request order is greater than a preset abnormal probability, the transaction request order is determined to be an abnormal transaction order.

[0029] It should also be noted that the method for determining the abnormal transaction order is: S21: obtaining the number of associated orders of the transaction request order, and determining whether the number of associated orders of the transaction request order is less than a preset quantity limit value; if so, proceeding to the next step; if not, proceeding to step S25; S22 determines whether the transaction request order has a matching abnormal transaction feature based on the matching result of the transaction feature of the transaction request order and the abnormal transaction feature. If yes, proceed to step S25; if not, proceed to the next step; S23 determines whether the associated orders of the transaction request order have matching abnormal transaction features, if yes, proceeds to the next step, if no, determines that the transaction request order does not belong to an abnormal transaction order; S24 determines the order abnormality probabilities of different associated orders according to the matching number of abnormal transaction features of the associated orders of the transaction request order, and judges whether there are associated orders whose order abnormality probabilities do not meet the requirements. If so, proceeds to the next step; if not, determines that the transaction request order does not belong to an abnormal transaction order; S25 determines the basic abnormal probability of the transaction request order by using the matching number of the abnormal transaction features, determines the abnormal probability of the transaction request order by using the normalized sum of the basic abnormal probability of the transaction request order and the order abnormal probabilities of different associated orders, and determines whether the transaction request order is an abnormal transaction order by using the abnormal probability.

[0030] Specifically, the method for determining the interception processing strategy is: Determine a matching settlement rule and model for the abnormal request order using the order data of the abnormal request order, and determine a difficulty coefficient of settlement processing for the abnormal request order based on the matching settlement rule and model; The interception processing requirement coefficient of the abnormal request order is determined based on the abnormal probability of the abnormal request order and the difficulty coefficient of settlement processing, and the interception processing strategy of the abnormal request order is determined according to the interception processing requirement coefficient.

[0031] S3 obtains abnormal request orders at different times within a preset time period, and proceeds to the next step when it is determined that there is no security risk in the transaction settlement platform through the abnormal probability of abnormal request orders at different times; Specifically, determining the interception processing strategy of the abnormal request order according to the interception processing demand coefficient specifically includes: The preset types of interception processing for different abnormal request orders are determined based on the interception processing demand coefficient, and the interception processing strategy for the abnormal request order is determined according to the preset interception strategy corresponding to the preset type.

[0032] It is understandable that the interception and processing strategies for the abnormal request orders include direct interception and processing and delayed processing with different delay processing durations.

[0033] Furthermore, it is determined that there are no security risks in the transaction settlement platform, including: Obtain the number of abnormal request orders at different times within a preset time period and their proportion in the number of transaction request orders, and determine the order abnormality assessment amount at different times based on the abnormal probability of different abnormal request orders; The transaction security risk coefficient of the transaction settlement platform within a preset period of time is determined based on the order anomaly assessment amount at different times, and the transaction security risk coefficient is used to determine whether the transaction settlement platform has a security risk.

[0034] It can be understood that when the transaction security risk coefficient of the transaction settlement platform is not within the preset risk coefficient range, it is determined that there is no security risk on the transaction settlement platform.

[0035] It should also be noted that when there is a security risk on the transaction settlement platform, all transaction request orders on the transaction settlement platform are intercepted and processed using a preset interception processing time.

[0036] It should also be noted that the transaction settlement platform is guaranteed to have no security risks, including: S31 determines the total number of abnormal request orders within the preset time period by using the number of abnormal request orders at different times within the preset time period, and determines whether the total number of abnormal request orders within the preset time period is greater than the preset number of abnormal orders. If so, it is determined that there is a security risk in the transaction settlement platform. If not, proceed to the next step. S32 determines the comprehensive abnormal probability within the preset time period based on the total number of abnormal request orders within the preset time period and the abnormal probabilities of different abnormal request orders, and determines whether the comprehensive abnormal probability within the preset time period is greater than the preset probability threshold. If so, proceed to the next step; if not, proceed to step S34; S33 obtains the number of abnormal request orders at different times within a preset time period, and takes the time when the number of abnormal request orders is greater than the order quantity limit value as the abnormal time, and determines whether the number at the abnormal time meets the requirement. If so, proceed to the next step; if not, it is determined that there is a security risk in the transaction settlement platform; S34 obtains the number of abnormal request orders at different times within a preset time period and the proportion of the number of transaction request orders, and determines the order abnormality assessment amount at different times in combination with the abnormal probability of different abnormal request orders, and determines whether the number of times when the order abnormality assessment amount does not meet the requirement meets the requirement, if so, proceeds to the next step, if not, determines that the transaction settlement platform has a security risk; S35 determines the transaction security risk coefficient of the transaction settlement platform within a preset time period based on the order anomaly assessment amount at different times, and uses the transaction security risk coefficient to determine whether there is a security risk on the transaction settlement platform.

[0037] S4 performs transaction settlement processing using the matching settlement rules and models of the transaction request orders excluding abnormal transaction orders.

[0038] Specifically, transaction settlement processing is carried out, including: The transaction request orders excluding abnormal transaction orders are treated as normal transaction orders, and the settlement processing of the normal transaction orders is performed using the matching settlement rules of the normal transaction orders. The processing results of the settlement processing are stored and data exchange processing is performed between different transaction parties based on the matching model of the normal transaction orders.

[0039] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device, equipment, and non-volatile computer storage medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0040] The above is a description of a specific embodiment of the present specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0041] The above description is only one or more embodiments of this specification and is not intended to limit this specification. For those skilled in the art, one or more embodiments of this specification may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of one or more embodiments of this specification shall be included in the scope of the claims of this specification.

Claims

1. A transaction settlement method based on model-driven and security risk identification, characterized in that: Specifically include: Acquire transaction request order data at different times of the adjacent time period in real time, and when it is determined that the settlement processing pressure of the transaction request does not meet the requirements in combination with the matching settlement rules and models of different transaction request orders, proceed to the next step; Determine the associated orders of different transaction request orders according to the IP addresses of different transaction request orders, and use the matching results of the transaction characteristics of the transaction request orders and the associated orders with the abnormal transaction characteristics to determine the abnormal transaction orders and the abnormal probability, and determine the differentiated interception processing strategy based on the abnormal probability and order data of the abnormal request orders; Obtain abnormal request orders at different times within a preset time period, and when it is determined that there is no security risk in the transaction settlement platform through the abnormal probability of abnormal request orders at different times, proceed to the next step; Transaction settlement processing is performed using matching settlement rules and models of transaction request orders excluding abnormal transaction orders.

2. The transaction settlement method based on model-driven and security risk identification as claimed in claim 1, characterized in that: The adjacent time period is a time period whose interval with the current time is within a preset range.

3. The transaction settlement method based on model-driven and security risk identification as claimed in claim 1, characterized in that: The transaction request order data includes the quantity of different types of transaction request orders at different times.

4. The transaction settlement method based on model-driven and security risk identification as claimed in claim 1, characterized in that: Determining that the settlement processing pressure of the transaction request does not meet the requirements, specifically including: Determine the difficulty coefficient of settlement processing of different transaction request orders based on the matching settlement rules and models of different transaction request orders; Determine the quantity of different types of transaction request orders at different times according to the transaction request order data at different times, and determine the difficulty of settlement processing of the transaction request orders at different times in combination with the difficulty coefficient of settlement processing of different transaction request orders; The processing difficulty assessment amount of the transaction request is determined by the average value of the settlement processing difficulty of the transaction request orders at different times in a nearby time period, and based on the processing difficulty assessment amount, it is determined whether the settlement processing pressure of the transaction request meets the requirements.

5. The transaction settlement method based on model-driven and security risk identification as claimed in claim 4, characterized in that: When the settlement processing pressure of the transaction request meets the requirements, there is no need to identify and intercept abnormal transaction orders.

6. The transaction settlement method based on model drive and security risk identification as claimed in claim 1, characterized in that: The associated order of the transaction request order is an order that is consistent with the IP address of the transaction request order.

7. The transaction settlement method based on model drive and security risk identification as claimed in claim 1, characterized in that: The method for determining the abnormal transaction order is: Determining the number of matches of the abnormal transaction features of the transaction request order based on the matching result of the transaction features of the transaction request order and the abnormal transaction features, and determining the basic abnormal probability of the transaction request order by using the number of matches of the abnormal transaction features; Determining order abnormality probabilities of different associated orders according to the matching number of abnormal transaction features of associated orders of the transaction request order; The abnormal probability of the transaction request order is determined by using the normalized sum of the basic abnormal probability of the transaction request order and the order abnormal probabilities of different associated orders, and whether the transaction request order is an abnormal transaction order is determined by using the abnormal probability.

8. The transaction settlement method based on model drive and security risk identification as claimed in claim 7, characterized in that: When the abnormal probability of the transaction request order is greater than a preset abnormal probability, the transaction request order is determined to be an abnormal transaction order.

9. The transaction settlement method based on model drive and security risk identification as claimed in claim 1, characterized in that: The method for determining the interception processing strategy is: Determine a matching settlement rule and model for the abnormal request order using the order data of the abnormal request order, and determine a difficulty coefficient of settlement processing for the abnormal request order based on the matching settlement rule and model; The interception processing requirement coefficient of the abnormal request order is determined based on the abnormal probability of the abnormal request order and the difficulty coefficient of settlement processing, and the interception processing strategy of the abnormal request order is determined according to the interception processing requirement coefficient.

10. The transaction settlement method based on model drive and security risk identification as claimed in claim 1, characterized in that: Carry out transaction settlement processing, including: The transaction request orders excluding abnormal transaction orders are treated as normal transaction orders, and the settlement processing of the normal transaction orders is performed using the matching settlement rules of the normal transaction orders. The processing results of the settlement processing are stored and data exchange processing is performed between different transaction parties based on the matching model of the normal transaction orders.