A payment risk assessment method and system based on data analysis

Abstract

The present invention provides a payment risk assessment method and system based on data analysis, which belongs to the technical field of data analysis, and specifically includes: determining the user payment risk and risky payment user of the payment user based on the data deviation between the verification data sources of different verification methods to be verified and the account password setting situation of the payment user, obtaining the historical payment data of the risky payment user in different risky payment intervals, determining the risk assessment amount of different risky payment users on the payment platform through the historical payment data and user payment risk, determining the payment data in the risky payment interval on the current date, and determining the payment risk level of the payment platform in combination with the risk assessment amount of the risky payment user on the payment platform, thereby realizing effective control of payment risk.

Description

Technical Field

[0001] The present invention belongs to the technical field of data analysis, and in particular to a payment risk assessment method and system based on data analysis. Background Art

[0002] In order to improve user convenience, online shopping platforms are often set up in scenarios such as smart hotels, smart campuses, and smart communities to meet users' shopping needs. However, at the same time, how to identify payment risks has become a technical problem that needs to be solved urgently. Specifically, in the invention patent application CN201210277970.7 "Payment risk identification system and method based on position change", the rationality of the payment location of the payment initiator is judged to identify the risk of the payment request, effectively reduce the risk of network payment, and improve the accuracy of payment risk identification and processing.

[0003] In existing payment platforms, differentiated identity authentication methods are often used for different payment amount ranges. Due to the differences in the number of payment orders in different payment amount ranges, there are certain differences in the payment risks of different payment platforms. Therefore, if the payment risk assessment cannot be carried out based on the settings of the payment identity authentication method and the distribution of the payment order amounts, the accuracy of the payment risk assessment results of the payment platform cannot be guaranteed.

[0004] Specifically, the present application provides a payment risk assessment method and system based on data analysis. Summary of the invention

[0005] To achieve the purpose of the present invention, the present invention adopts the following technical solutions:

[0006] According to one aspect of the present invention, a payment risk assessment method based on data analysis is provided.

[0007] A payment risk assessment method based on data analysis, specifically including:

[0008] S1 determines the order identity authentication methods of the payment platform in different payment amount intervals, and determines the payment risks of different payment amount intervals in combination with the verification data sources of different order identity authentication methods, and determines the risk payment interval using the payment risks;

[0009] S2 uses the order identity authentication method in the risk payment interval as the verification method to be verified, and determines the user payment risk and risky payment user of the payment user based on the data deviation between the verification data sources of different verification methods to be verified and the account password settings of the payment user;

[0010] S3 obtains the historical payment data of the risk payment user in different risk payment intervals, and determines the risk assessment amount of different risk payment users on the payment platform based on the historical payment data and user payment risk;

[0011] S4 determines the payment data of the current date in the risk payment interval, and determines the payment risk level of the payment platform in combination with the risk assessment amount of the risk payment user on the payment platform.

[0012] The beneficial effects of the present invention are:

[0013] 1. In the present invention, risky payment users among payment users are determined based on data deviations between verification data sources of different verification methods to be verified and account password settings. This not only considers the impact of deviations in the verification data sources of payment users on the data accuracy of the verification data sources of the verification methods to be verified, but also considers the impact of the account password settings on the identity credibility of the payment users, thereby achieving the screening of risky payment users from multiple angles.

[0014] 2. In the present invention, the payment risk level of the payment platform is determined based on the payment data in the risk payment interval on the current date and the risk assessment of the risk payment user on the payment platform, thereby achieving accurate assessment of the payment risk level from two perspectives: the risk situation of the risk payment user and the real-time payment data in the risk payment interval. It also lays the foundation for the generation of differentiated risk management measures and avoids the occurrence of payment problems due to identity leakage.

[0015] A further technical solution is that the order identity authentication method includes terminal identification verification, account and password identity authentication, location verification, face identity authentication, and fingerprint identity authentication.

[0016] A further technical solution is that the verification data source is determined according to the type of the order identity authentication method, wherein the terminal identification verification includes MEID, SSAID, UUID, GUID, and the location verification includes GPS, base station and IP address.

[0017] A further technical solution is that the method for determining the payment risk of the payment amount interval is:

[0018] Obtain the number of verification data sources of different order identity authentication methods, and determine the verification credibility of different order identity authentication methods in combination with the basic credibility of different order identity authentication methods;

[0019] The order identity authentication method in the payment amount range is used as the matching identity authentication method, and the payment risk in the payment amount range is determined based on the verification credibility of different matching identity authentication methods.

[0020] A further technical solution is that the value range of the payment risk of the payment amount interval is between 0 and 1, wherein when the payment risk of the payment amount interval is greater than a preset risk, the payment amount interval is determined to be a risk payment interval.

[0021] A further technical solution is that the basic credibility of the order identity authentication method is determined according to the type of the order identity authentication method, and specifically the preset credibility corresponding to the type of the order identity authentication method is used as the basic credibility of the order identity authentication method.

[0022] A further technical solution is to use the comprehensive payment risk to determine the payment risk level of the payment platform, specifically including:

[0023] The comprehensive payment risk is used to determine the payment risk range in which the payment platform is located, and the preset payment risk level corresponding to the payment risk range is used as the payment risk level of the payment platform.

[0024] In a second aspect, the present invention provides a computer system comprising: a memory and a processor that are communicatively connected, and a computer program stored in the memory and capable of running on the processor, characterized in that: when the processor runs the computer program, it executes the above-mentioned payment risk assessment method based on data analysis.

[0025] Other features and advantages will be described in the following description. The objects and other advantages of the present invention are realized and obtained by the structures particularly pointed out in the description and drawings.

[0026] 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

[0027] 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 accompanying drawings;

[0028] Figure 1 It is a flow chart of a payment risk assessment method based on data analysis;

[0029] Figure 2 It is a flow chart of a method for determining payment risk of a payment amount interval;

[0030] Figure 3is a flow chart of a method for determining user payment risk of a payment user;

[0031] Figure 4 is a flow chart of a method for determining the urgency of group recommendation for a group of similar products;

[0032] Figure 5 It is a framework diagram of a computer system. DETAILED DESCRIPTION

[0033] In order to enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this specification, not all of the embodiments. Based on the embodiments of this specification, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of this specification. Example

[0034] To solve the above problems, according to one aspect of the present invention, Figure 1 As shown, a payment risk assessment method based on data analysis is provided, which specifically includes:

[0035] S1 determines the order identity authentication methods of the payment platform in different payment amount intervals, and determines the payment risks of different payment amount intervals in combination with the verification data sources of different order identity authentication methods, and determines the risk payment interval using the payment risks;

[0036] It should be noted that the order identity authentication methods include terminal identification verification, account and password identity authentication, location verification, face identity authentication, and fingerprint identity authentication.

[0037] Furthermore, the verification data source is determined according to the type of the order identity authentication method, wherein the terminal identification verification includes MEID, SSAID, UUID, GUID, and the location verification includes GPS, base station and IP address.

[0038] It is understandable that if Figure 2 As shown, the method for determining the payment risk of the payment amount interval is:

[0039] Obtain the number of verification data sources of different order identity authentication methods, and determine the verification credibility of different order identity authentication methods in combination with the basic credibility of different order identity authentication methods;

[0040] The order identity authentication method in the payment amount range is used as the matching identity authentication method, and the payment risk in the payment amount range is determined based on the verification credibility of different matching identity authentication methods.

[0041] Furthermore, the payment risk of the payment amount interval ranges from 0 to 1, wherein when the payment risk of the payment amount interval is greater than a preset risk, the payment amount interval is determined to be a risk payment interval.

[0042] It can be understood that the basic credibility of the order identity authentication method is determined according to the type of the order identity authentication method, and specifically the preset credibility corresponding to the type of the order identity authentication method is used as the basic credibility of the order identity authentication method.

[0043] In another embodiment, the method for determining the payment risk of the payment amount interval is:

[0044] Using the order identity authentication method in the payment amount interval as the matching identity authentication method, and determining the number of verification data sources in the payment amount interval based on verification data sources of different matching identity authentication methods;

[0045] Different types of verification data sources are used to determine basic weight values ​​of different verification data sources, and the payment risk of the payment amount interval is determined by summing the weights of the basic weight values ​​of the verification data sources in the payment amount interval.

[0046] It can be understood that the basic weight value of the verification data source is determined according to the type of the verification data source.

[0047] In another embodiment, the method for determining the payment risk of the payment amount interval is:

[0048] S11 uses the order identity authentication method in the payment amount range as the matching identity authentication method, and determines whether there is a specific identity authentication method in the matching identity authentication method. If so, it is determined that the payment amount range does not belong to the risk payment range. If not, proceed to the next step;

[0049] S12 determines the number of verification data sources in the payment amount interval based on verification data sources of different matching identity authentication methods, and determines whether the number of verification data sources in the payment amount interval is greater than the preset number of data sources. If so, proceed to the next step; if not, proceed to step S14;

[0050] S13 determines the basic weight values ​​of different verification data sources by using different types of verification data sources, and determines whether the payment amount interval does not belong to the risk payment interval through the weight sum of the basic weight values ​​of the verification data sources of the payment amount interval, and if so, determines that the payment amount interval does not belong to the risk payment interval, and if not, proceeds to the next step;

[0051] S14: obtaining the number of verification data sources of different order identity authentication methods, and determining the verification credibility of different order identity authentication methods in combination with the basic credibility of different order identity authentication methods, and judging whether there is an order identity authentication method whose verification credibility is greater than a preset credibility. If so, determining that the payment amount range does not belong to the risk payment range, if not, proceeding to the next step;

[0052] S15 uses the order identity authentication method in the payment amount range as the matching identity authentication method, and determines the payment risk of the payment amount range based on the verification credibility of different matching identity authentication methods.

[0053] S2 uses the order identity authentication method in the risk payment interval as the verification method to be verified, and determines the user payment risk and risky payment user of the payment user based on the data deviation between the verification data sources of different verification methods to be verified and the account password settings of the payment user;

[0054] It can be understood that the data deviation between the verification data sources is determined according to the data deviation between the verification data sources in different historical payment times of the paying user.

[0055] Specifically, Figure 3 As shown, the method for determining the user payment risk of the payment user is:

[0056] Determine the data deviation amount between the verification data sources in different historical payment times of the verification method to be verified based on the data deviation situation, and use the data deviation amount to determine the number of deviations in the historical payment times;

[0057] The data anomaly risks of different verification methods to be verified are determined by using the number of deviations, and the verification data risk of the payment user is determined by using the weights of the data anomaly risks of different verification methods to be verified, and the password strength of the payment user is determined by the account password setting of the payment user, and the account risk of the payment user is determined by using the password strength;

[0058] The user payment risk of the paying user is determined according to the account risk and the verification data risk.

[0059] It should be noted that when the user payment risk of the payment user does not meet the requirements, the payment user is determined to be a risky payment user.

[0060] In another embodiment, the method for determining the user payment risk of the paying user is:

[0061] Determine the password strength of the payment user based on the account password setting of the payment user, and use the password strength to determine the account risk of the payment user;

[0062] Determine the data deviation amount between the verification data sources in different historical payment times of the verification method to be verified based on the data deviation situation, and use the data deviation amount to determine the number of deviations in the historical payment times;

[0063] The verification methods to be verified with the number of deviations are used as risk verification methods, and the number of risk verification methods is used to determine the verification data risk of the payment user, and the user payment risk of the payment user is determined based on the account risk and the verification data risk.

[0064] It should be further explained that the method for determining the user payment risk of the payment user is:

[0065] S21 determines the password strength of the payment user according to the account password setting of the payment user, and uses the password strength to determine the account risk of the payment user, and judges whether the account risk of the payment user meets the requirements. If yes, proceed to the next step, if not, proceed to step S25;

[0066] S22 determines the data deviation amount between the verification data sources in different historical payment times of the verification method to be verified based on the data deviation situation, and uses the data deviation amount to determine whether there is a deviation number of times in the historical payment times of the verification method to be verified, if so, proceeds to the next step, if not, determines that the payment user does not belong to the risk payment user;

[0067] S23 determines the number of deviations of different verification methods to be verified based on the data deviation amount, and judges whether the total number of deviations of different verification methods to be verified meets the requirements. If so, it is determined that the payment user does not belong to the risk payment user. If not, proceed to the next step;

[0068] S24 uses the number of deviations to determine the data anomaly risks of different verification methods to be verified, and determines whether there is a verification method to be verified whose data anomaly risk does not meet the requirements. If so, proceed to the next step; if not, determine that the payment user does not belong to the risk payment user;

[0069] S24 utilizes the weights of the data anomaly risks of different verification methods to be verified and determines the verification data risk of the payment user, and determines the user payment risk of the payment user according to the account risk and the verification data risk.

[0070] S3 obtains the historical payment data of the risk payment user in different risk payment intervals, and determines the risk assessment amount of different risk payment users on the payment platform based on the historical payment data and user payment risk;

[0071] Specifically, Figure 4 As shown, the method for determining the risk assessment amount of the risk payment user on the payment platform is:

[0072] Determine the number of historical payment orders of the risk payment user in different risk payment intervals according to the historical payment data, and determine the payment risk assessment amount of the risk payment user in different risk payment intervals in combination with the payment amounts of different historical payment orders and the payment risks of the risk payment intervals;

[0073] Determine a matching risk payment interval in the risk payment interval by using the payment risk assessment amount, and determine the payment risk compensation amount of the risk payment user by the proportion of the matching risk payment interval in the risk payment interval;

[0074] The risk assessment amount of the risk payment user on the payment platform is determined by the sum of the payment risk compensation amount and the user payment risk.

[0075] S4 determines the payment data of the current date in the risk payment interval, and determines the payment risk level of the payment platform in combination with the risk assessment amount of the risk payment user on the payment platform.

[0076] It can be understood that the historical payment data includes the number of historical payment orders of the risk payment user and the payment amounts of different historical payment orders.

[0077] Furthermore, the method for determining the payment risk level of the payment platform is:

[0078] Determine the number of payment users in different risk payment intervals and the proportion of risk payment users on the current date based on the payment data in the risk payment interval on the current date, and determine the real-time risk assessment amounts of different risk payment intervals in combination with the number of payment orders of different payment users and the proportion of payment orders of risk payment users, and determine the real-time payment risk of the payment platform according to the real-time risk assessment amounts of different risk payment intervals;

[0079] Determine the risk value of the payment user based on the weight of the risk assessment amount of the different risk payment users on the payment platform;

[0080] The comprehensive payment risk of the payment platform is determined by the payment user risk value and the real-time payment risk, and the payment risk level of the payment platform is determined by using the comprehensive payment risk.

[0081] It should be noted that the payment risk level of the payment platform is determined by using the comprehensive payment risk, specifically including:

[0082] The comprehensive payment risk is used to determine the payment risk range in which the payment platform is located, and the preset payment risk level corresponding to the payment risk range is used as the payment risk level of the payment platform.

[0083] In another embodiment, the method for determining the payment risk level of the payment platform is:

[0084] S41 obtains the number of risk payment users in the payment platform, and determines whether the number of risk payment users is greater than the preset number of payment users. If so, proceeds to the next step; if not, proceeds to step S45;

[0085] S42 determines whether the average value of the risk assessment of different risk payment users on the payment platform is greater than a preset risk threshold, if so, determines the payment risk level of the payment platform based on the preset risk level, if not, proceeds to the next step;

[0086] S43 determines the risk value of the payment user according to the weight of the risk assessment amount of the different risk payment users on the payment platform and determines whether the risk value of the payment user meets the requirements. If so, proceed to the next step. If not, determine the payment risk level of the payment platform based on the preset risk level;

[0087] S44 determines the number of payment users in different risk payment intervals on the current date and the proportion of the number of risk payment users based on the payment data in the risk payment interval on the current date, and determines whether there is a risk payment interval in which the number of payment users or the number of risk payment users does not meet the requirements. If so, the payment risk level of the payment platform is determined based on the preset risk level. If not, proceed to the next step;

[0088] S45 determines the number of historical payment orders of the risk payment user in different risk payment intervals according to the historical payment data, and determines the payment risk assessment amount of the risk payment user in different risk payment intervals in combination with the payment amount of different historical payment orders and the payment risk of the risk payment interval, and judges whether there is a risk payment interval whose payment risk assessment amount does not meet the requirements. If so, determines the payment risk level of the payment platform based on the preset risk level, if not, proceeds to the next step;

[0089] S46 determines the real-time payment risk of the payment platform according to the real-time risk assessment amount of different risk payment intervals, determines the comprehensive payment risk of the payment platform through the payment user risk value and the real-time payment risk, and determines the payment risk level of the payment platform using the comprehensive payment risk. Example

[0090] Second, as Figure 5 As shown, the present invention provides a computer system, comprising: a memory and a processor connected in communication, and a computer program stored in the memory and capable of running on the processor, characterized in that: when the processor runs the computer program, it executes the above-mentioned payment risk assessment method based on data analysis.

[0091] The above-mentioned payment risk assessment method based on data analysis specifically includes:

[0092] Determine the order identity verification methods of the payment platform within different payment amount intervals, and determine the payment risks of different payment amount intervals in combination with the verification data sources of different order identity verification methods, and use the payment risks to determine the risk payment interval;

[0093] Determine the data deviation amount between the verification data sources in different historical payment times of the verification method to be verified based on the data deviation situation, and use the data deviation amount to determine the number of deviations in the historical payment times;

[0094] The data anomaly risks of different verification methods to be verified are determined by using the number of deviations, and the verification data risk of the payment user is determined by using the weights of the data anomaly risks of different verification methods to be verified, and the password strength of the payment user is determined by the account password setting of the payment user, and the account risk of the payment user is determined by using the password strength;

[0095] Determine the user payment risk of the payment user according to the account risk and the verification data risk, and determine the risky payment user by using the user spending risk;

[0096] Obtain the historical payment data of the risk payment user in different risk payment intervals, and determine the risk assessment amount of different risk payment users on the payment platform based on the historical payment data and user payment risk;

[0097] Determine the number of payment users in different risk payment intervals and the proportion of risk payment users on the current date based on the payment data in the risk payment interval on the current date, and determine the real-time risk assessment amounts of different risk payment intervals in combination with the number of payment orders of different payment users and the proportion of payment orders of risk payment users, and determine the real-time payment risk of the payment platform according to the real-time risk assessment amounts of different risk payment intervals;

[0098] The risk value of the payment user is determined based on the weight of the risk assessment amount of different risk payment users on the payment platform, the comprehensive payment risk of the payment platform is determined by the payment user risk value and the real-time payment risk, and the payment risk level of the payment platform is determined using the comprehensive payment risk.

[0099] 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.

[0100] The above is a description of a specific embodiment of the 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.

[0101] 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 payment risk assessment method based on data analysis, characterized in that: Specifically include: Determine the order identity verification methods of the payment platform within different payment amount intervals, and determine the payment risks of different payment amount intervals in combination with the verification data sources of different order identity verification methods, and use the payment risks to determine the risk payment interval; The order identity authentication method in the risky payment interval is used as the verification method to be verified, and the user payment risk and risky payment user of the payment user are determined based on the data deviation between the verification data sources of different verification methods to be verified and the account password settings of the payment user; Obtain the historical payment data of the risk payment user in different risk payment intervals, and determine the risk assessment amount of different risk payment users on the payment platform based on the historical payment data and user payment risk; Determine the payment data in the risk payment interval on the current date, and determine the payment risk level of the payment platform in combination with the risk assessment of the risk payment user on the payment platform; The method for determining the payment risk level of the payment platform is: Determine the number of payment users in different risk payment intervals and the proportion of risk payment users on the current date based on the payment data in the risk payment interval on the current date, and determine the real-time risk assessment amounts of different risk payment intervals in combination with the number of payment orders of different payment users and the proportion of payment orders of risk payment users, and determine the real-time payment risk of the payment platform according to the real-time risk assessment amounts of different risk payment intervals; Determine the risk value of the payment user based on the weight of the risk assessment amount of the different risk payment users on the payment platform; The comprehensive payment risk of the payment platform is determined by the payment user risk value and the real-time payment risk, and the payment risk level of the payment platform is determined by using the comprehensive payment risk.

2. The payment risk assessment method based on data analysis as claimed in claim 1, characterized in that: The order identity authentication methods include terminal identification verification, account and password identity authentication, location verification, face identity authentication, and fingerprint identity authentication.

3. The payment risk assessment method based on data analysis as claimed in claim 2, characterized in that: The verification data source is determined according to the type of the order identity authentication method, wherein the terminal identification verification includes MEID, SSAID, UUID, GUID, and the location verification includes GPS, base station and IP address.

4. The payment risk assessment method based on data analysis as claimed in claim 1, characterized in that: The method for determining the payment risk of the payment amount interval is: Obtain the number of verification data sources of different order identity authentication methods, and determine the verification credibility of different order identity authentication methods in combination with the basic credibility of different order identity authentication methods; The order identity authentication method in the payment amount range is used as the matching identity authentication method, and the payment risk in the payment amount range is determined based on the verification credibility of different matching identity authentication methods.

5. The payment risk assessment method based on data analysis as claimed in claim 4, characterized in that: The basic credibility of the order identity authentication method is determined according to the type of the order identity authentication method, and specifically, the preset credibility corresponding to the type of the order identity authentication method is used as the basic credibility of the order identity authentication method.

6. The payment risk assessment method based on data analysis as claimed in claim 1, characterized in that: The data deviation between the verification data sources is determined according to the data deviation between the verification data sources in different historical payment times of the paying user.

7. The payment risk assessment method based on data analysis as claimed in claim 1, characterized in that: Method for determining the user payment risk of the payment user: Determine the data deviation amount between the verification data sources in different historical payment times of the verification method to be verified based on the data deviation situation, and use the data deviation amount to determine the number of deviations in the historical payment times; The data anomaly risks of different verification methods to be verified are determined by using the number of deviations, and the verification data risk of the payment user is determined by using the weights of the data anomaly risks of different verification methods to be verified, and the password strength of the payment user is determined by the account password setting of the payment user, and the account risk of the payment user is determined by using the password strength; The user payment risk of the paying user is determined according to the account risk and the verification data risk.

8. The payment risk assessment method based on data analysis as claimed in claim 1, characterized in that: When the user payment risk of the payment user does not meet the requirement, the payment user is determined to be a risky payment user.

9. A computer system comprising: A memory and a processor that are communicatively connected, and a computer program stored in the memory and capable of running on the processor, characterized in that: when the processor runs the computer program, a payment risk assessment method based on data analysis as described in any one of claims 1-8 is executed.

Images