Payment security control method and system for data center

Abstract

The invention provides a payment security control method and system for a data platform. The method comprises the following steps: determining a plurality of risk-free payment permissions and a plurality of risk payment permissions which can be configured by a target customer in a payment center of the data platform; extracting an excess payment permission and a non-excess payment permission based on the limit limit, and determining a risk measure according to the non-excess payment permission; performing feature fusion on the risk measurement to obtain payment behavior features, and determining security confidence based on the security evaluation model and the payment behavior features; according to the risk payment authority and the risk measurement, payment risk cost during large-amount payment is determined; and performing permission adjustment based on the payment risk cost and the security confidence. According to the scheme, permission adjustment is performed on the payment behavior of the target customer based on the payment risk cost and the security confidence, the deviation mode of the payment amount of the payment permission on the payment behavior of the user can be identified, and timely permission adjustment is performed on the payment behavior of current large payment, so that the payment security of the system is improved.

Description

Technical Field

[0001] The present application relates to the field of payment risk management technology, and more specifically, to a payment security control method and system for a data middle station. Background Art

[0002] In modern society, payment risk management plays a vital role in the financial system. With the popularization of electronic payment, mobile payment and the increase in cross-border transactions, payment scenarios have become more diversified and complex, and payment risks have increased significantly. In order to cope with these risk challenges, payment risk management has gradually developed and improved. Through the application of advanced technologies such as artificial intelligence and big data analysis, the payment risk management system can identify and respond to potential threats in real time to ensure the security and stability of the payment process. The development of these technologies has also prompted payment risk management to shift from passive defense to active prevention, providing more reliable protection for financial institutions and users.

[0003] In the existing payment risk management, big data analysis and machine learning play a key role in payment risk management. By analyzing user behavior patterns and historical transaction data, predicting and responding to abnormal transactions in a timely manner, the development and improvement of payment risk management have effectively ensured the stability and security of the payment system; however, due to the large amount of capital flow, large-value payment transactions often become the main target of fraudsters, resulting in an increase in potential payment risks. The payment amount of large-value payment transactions is significantly different from the normal transaction pattern, which often indicates abnormal payment activities, but it may also be a legal high-value transaction. Misjudgment of legal high-value transaction behavior will affect the security and reliability of the entire system and reduce the user experience. Therefore, how to make accurate permission adjustments to the current large-value payment behavior to improve the payment security of the system has become a difficult problem faced by the industry. Summary of the invention

[0004] The present application provides a payment security control method and system for a data middle platform, which can make accurate authority adjustments to the current large-amount payment behavior, thereby improving the payment security of the system.

[0005] In a first aspect, the present application provides a payment security control method of a data middle station, comprising the following steps:

[0006] Determine the multiple risk-free payment permissions and risk-based payment permissions that can be configured by the target customer in the data middle platform payment center;

[0007] Based on the target customer's credit limit, multiple overpayment permissions and non-overpayment permissions are extracted from all risk-free payment permissions, and then the risk measurement of each overpayment permission in terms of payment amount is determined based on all non-overpayment permissions;

[0008] Perform feature fusion on all risk metrics to obtain payment behavior characteristics of target customers when performing payment operations, and determine the security confidence of the current target customer when making payments at the payment center based on the pre-trained security assessment model and the payment behavior characteristics;

[0009] Determine the payment risk cost of target customers when making large payments based on all risk payment permissions and all risk metrics;

[0010] When a target customer makes a large payment at the payment center, the payment behavior of the target customer is authorized to be adjusted based on the payment risk cost and the security confidence.

[0011] In some embodiments, extracting multiple overpayment permissions and multiple non-overpayment permissions in a risk-free state from all risk-free payment permissions based on the credit limit of the target customer specifically includes:

[0012] Get the credit limit of target customers;

[0013] Extract the payment amount for each risk-free payment authority;

[0014] Based on the credit limit and the payment amount of each risk-free payment authority, multiple overpayment authorities and multiple non-overpayment authorities are extracted from all risk-free payment authorities.

[0015] In some embodiments, determining the risk metric of each overpayment authority in terms of payment amount based on all non-overpayment authorities specifically includes:

[0016] Determine the payment margin for target customers when they make payment operations based on all non-excess payment permissions;

[0017] Set the safety margin coefficient of the payment center's payment operations under a risk-free state;

[0018] Get the payment amount for each overpayment authority;

[0019] A risk measure of the payment amount of each overpayment authority is determined based on the payment limit margin, the safety limit coefficient, and the payment amount of each overpayment authority.

[0020] In some embodiments, all risk metrics are subjected to feature fusion to obtain payment behavior features of target customers when performing payment operations, specifically including:

[0021] All risk measures are standardized to obtain the normative entropy of each risk measure;

[0022] determining multiple entropy clustering groups of all canonical entropies;

[0023] Based on all entropy clustering groups, the payment behavior characteristics of target customers when performing payment operations are extracted.

[0024] In some embodiments, determining the security confidence level of the current target customer when making a payment at the payment center based on the pre-trained security assessment model and the payment behavior characteristics specifically includes:

[0025] Collect the payment information of current target customers in the payment center;

[0026] Extracting a payment risk coefficient of the payment information based on a pre-trained security assessment model;

[0027] The security confidence level of the current target customer when making payment at the payment center is determined according to the payment risk coefficient and the payment behavior characteristics.

[0028] In some embodiments, adjusting the permission of the target customer's payment behavior based on the payment risk cost and the security confidence level specifically includes:

[0029] Determining the transaction risk level of the current transaction behavior according to the payment risk cost and the security confidence level;

[0030] Based on the transaction risk level, the transaction behavior of the target customer in the payment center is adjusted.

[0031] In some embodiments, the data middle platform is a centralized data middle platform.

[0032] In a second aspect, the present application provides a payment security control system of a data middle platform, including:

[0033] A determination module is used to determine multiple risk-free payment permissions and multiple risk payment permissions that can be configured by the target customer in the data middle platform payment center;

[0034] A processing module, for extracting a plurality of overpayment permissions and a plurality of non-overpayment permissions in a risk-free state from all risk-free payment permissions based on the credit limit of the target customer, and then determining a risk measure of each overpayment permission in terms of payment amount based on all non-overpayment permissions;

[0035] The processing module is further used to perform feature fusion on all risk metrics to obtain payment behavior characteristics of the target customer when performing payment operations, and determine the security confidence of the current target customer when making payments at the payment center based on the pre-trained security assessment model and the payment behavior characteristics;

[0036] The processing module is also used to determine the payment risk cost when the target customer makes a large payment based on all risk payment permissions combined with all risk metrics;

[0037] The execution module is used to adjust the payment behavior of the target customer based on the payment risk cost and the security confidence when the target customer makes a large payment in the payment center.

[0038] In a third aspect, the present application provides a computer device, comprising a memory and a processor, wherein the memory stores a code, and the processor is configured to obtain the code and execute the payment security control method of the above-mentioned data middle station.

[0039] In a fourth aspect, the present application provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the payment security control method of the above-mentioned data middle station.

[0040] The technical solution provided by the embodiments disclosed in this application has the following beneficial effects:

[0041] In the payment security control method and system of the data middle platform provided in the present application, first, multiple risk-free payment permissions and multiple risky payment permissions that can be configured by the target customer in the data middle platform payment center are determined; secondly, multiple excess payment permissions and multiple non-excess payment permissions in a risk-free state are extracted from all risk-free payment permissions based on the target customer's credit limit, and the risk measurement of each excess payment permission in terms of the payment amount is determined based on all non-excess payment permissions; further, all risk measurements are feature fused to obtain the payment behavior characteristics of the target customer when performing payment operations, and the security confidence of the current target customer when making payments in the payment center is determined based on a pre-trained security assessment model and the payment behavior characteristics; then, the payment risk cost of the target customer when making large payments is determined based on all risky payment permissions combined with all risk measurements; finally, when the target customer makes large payments in the payment center, the target customer's payment behavior is subject to permission adjustment based on the payment risk cost and the security confidence.

[0042] It can be seen that the present application can identify the deviation pattern of the payment amount of the payment authority in the user's payment behavior, and make accurate authority adjustments to the current large-amount payment behavior, thereby improving the payment security of the system; first, determining the target customer's risk-free payment authority and risky payment authority can provide reliable data support for the payment security control system; secondly, extracting excess payment authority and non-excess payment authority can analyze the degree of deviation between the transaction amount and the normal transaction pattern under a risk-free state, thereby increasing the accuracy of distinguishing risk-free payment behavior; further, the payment risk cost of the target customer when making a large-amount payment is determined by the degree of deviation between the risk-free transaction amount and the payment amount when completing a large-amount payment under a risky state. , in order to effectively identify the risks and uncertainties of the target customer's transaction behavior, so as to accurately identify the deviation pattern of the payment amount in the payment behavior; then, extract the payment risk coefficient of the current transaction, and determine the security confidence of the current target customer when making a payment at the payment center through the payment risk coefficient, so as to identify the transaction risk behavior of the current payment transaction in real time; finally, based on the payment risk cost and security confidence, the permission adjustment of the target customer's payment behavior can improve the security and reliability of the system; in summary, the technical solution provided by the present application can identify the deviation pattern of the payment amount of the payment authority in the user's payment behavior, and make accurate permission adjustments to the current large-amount payment behavior, thereby improving the payment security of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 is an exemplary flow chart of a payment security control method of a data middle station according to some embodiments of the present application;

[0044] Figure 2 is an exemplary flow chart of determining payment behavior characteristics of a target customer when performing a payment operation according to some embodiments of the present application;

[0045] Figure 3 is an exemplary flow chart of determining the payment risk cost when a target customer makes a large payment according to some embodiments of the present application;

[0046] Figure 4 It is a schematic diagram of the structure of the payment security control system of the data middle platform shown in some embodiments of the present application;

[0047] Figure 5 It is a structural diagram of a computer device for implementing a payment security control method of a data middle station as shown in some embodiments of the present application. DETAILED DESCRIPTION

[0048] In order to better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0049] refer to Figure 1 , which is an exemplary flow chart of a payment security control method of a data middle station according to some embodiments of the present application. The payment security control method 100 of the data middle station mainly includes the following steps:

[0050] In step 101, multiple risk-free payment permissions and multiple risk payment permissions that can be configured by the target customer in the data middle platform payment center are determined.

[0051] In the specific implementation, multiple risk-free payment permissions and multiple risky payment permissions that can be configured for the target customer in the data middle platform payment center are determined, that is: the credit rating of the target customer in the payment center is obtained from the credit scoring system of the data middle platform, and the payment center grants corresponding risk-free payment permissions and risky payment permissions to the target customer based on the credit rating, and then the multiple risk-free payment permissions and multiple risky payment permissions that can be configured for the target customer in the data middle platform payment center can be determined. The credit rating can be obtained by the credit scoring system analyzing the customer's historical transaction behavior data. Customers with small fluctuations in payment amounts, timely transaction payments, and regular transaction locations and times can have higher credit ratings.

[0052] It should be noted that the risk-free payment authority in this application refers to the authority corresponding to the payment behavior that is considered to be risk-free (or safe and low-risk) in the transaction activities conducted by the customer in the payment center, and the risky payment authority refers to the authority corresponding to the payment behavior that is considered to be high-risk in the transactions conducted by the customer in the payment center. By determining the risk-free payment authority and the risky payment authority, the legality and security of payment can be enhanced.

[0053] It should also be noted that the data middle platform in this application is a platform for centralized management and processing of data. The main functions of the data middle platform include data integration, management, analysis and services. The data middle platform is usually used to support corporate decision-making and improve data utilization efficiency. Among them, the main service object of the data middle platform is the payment center. The data middle platform can identify abnormal transaction patterns and transaction amounts by analyzing historical payment data and provide risk feedback on potential risks in current transaction behaviors, thereby controlling payment security.

[0054] In step 102, multiple overpayment authorities and multiple non-overpayment authorities in a risk-free state are extracted from all risk-free payment authorities based on the credit limit of the target customer, and the risk measure of each overpayment authority in terms of payment amount is determined based on all non-overpayment authorities.

[0055] In some embodiments, the following method may be used to extract multiple overpayment permissions and multiple non-overpayment permissions in a risk-free state from all risk-free payment permissions based on the credit limit of the target customer, namely:

[0056] Get the credit limit of target customers;

[0057] Extract the payment amount for each risk-free payment authority;

[0058] Based on the credit limit and the payment amount of each risk-free payment authority, multiple overpayment authorities and multiple non-overpayment authorities are extracted from all risk-free payment authorities.

[0059] In the specific implementation, the credit limit of the target customer is obtained, that is, the amount of each transaction completed by the target customer in the payment center is queried through a database query statement, and the median of all the amounts is used as the credit limit of the target customer. In addition, in other embodiments, other methods can also be used to obtain the credit limit of the target customer, for example, accessing the data middle-end management system, contacting the payment center customer service team, etc., which are not limited here.

[0060] It should be noted that, in this embodiment, the limit value represents a security assessment threshold for the payment center to monitor the payment limit of the target customer. When the payment limit of a single transaction of the target customer is greater than the limit value, the single transaction is determined to be a large-amount payment, and a security assessment is required for the payment behavior of the single transaction. When the payment limit of a single transaction of the target customer is less than the limit value, the single transaction is determined to be a small-amount transaction, and there is no need to conduct a security assessment on the payment behavior of the single transaction. By determining the limit value, it is helpful to control the risks of payment behavior, thereby ensuring the security of payment operations performed by customers at the payment center.

[0061] In the specific implementation, Python's log analysis tool can be used to extract the payment amount of each risk-free payment authority from the data log file of the payment center. In addition, in other embodiments, other methods can be used to extract the payment amount of each risk-free payment authority, for example, data analysis platforms Tableau, Power BI, etc., which are not limited here.

[0062] In specific implementation, multiple overpayment permissions and multiple non-overpayment permissions are extracted from all risk-free payment permissions based on the limit value and the payment amount of each risk-free payment permission, that is: the payment amount of each risk-free payment permission is compared with the limit value, all payment amounts less than or equal to the limit value are extracted, and the risk-free payment permissions corresponding to each payment amount obtained are used as non-overpayment permissions, thereby obtaining multiple non-overpayment permissions, all payment amounts greater than the limit value are extracted, and the risk-free payment permissions corresponding to each payment amount obtained are used as overpayment permissions, thereby obtaining multiple overpayment permissions.

[0063] It should be noted that the overpayment authority in this application refers to the security transaction authority for payment behaviors that exceed the preset limit during the payment process of the target customer, and the non-overpayment authority refers to the security transaction authority for payment behaviors that do not exceed the preset limit during the payment process of the target customer. By extracting the overpayment authority and the non-overpayment authority, stricter authority management can be performed on the payment behaviors to ensure the security and compliance of the payment system.

[0064] In some embodiments, the risk metric of each overpayment authority in terms of payment amount may be determined based on all non-overpayment authorities in the following manner, namely:

[0065] Determine the payment margin for target customers when they make payment operations based on all non-excess payment permissions;

[0066] Set the safety margin coefficient of the payment center's payment operations under a risk-free state;

[0067] Get the payment amount for each overpayment authority;

[0068] A risk measure of the payment amount of each overpayment authority is determined based on the payment limit margin, the safety limit coefficient, and the payment amount of each overpayment authority.

[0069] In some embodiments, the payment limit margin of the target customer when performing a payment operation can be determined according to all non-overpayment permissions in the following manner, namely:

[0070] Determine the reference payment amount when the target customer makes a payment operation;

[0071] Extracting the amount of credit compensation for each non-overpayment authority based on the reference payment amount;

[0072] The payment limit margin of the target customer when performing payment operations is determined by all limit compensation amounts.

[0073] In specific implementation, the percentile calculation method can be used to determine the reference payment amount when the target customer performs a payment operation. Specifically, the payment amounts of all non-excess payment permissions are extracted, and all payment amounts are sorted in ascending order to obtain a payment amount sequence. The payment amounts located in the first ninety percent of the payment amount sequence are used as the reference payment amount when the target customer performs a payment operation. In addition, in other embodiments, other methods can be used to determine the reference payment amount, which are not limited here.

[0074] It should be noted that the method for extracting the payment amount for all non-overpayment permissions in this embodiment is as described above, and the percentile calculation method is an existing calculation method based on statistical distribution, and both will not be described here in detail.

[0075] In addition, it should be noted that the reference payment amount in this embodiment represents the upper limit of most transaction amounts when the target customer conducts transactions in the payment center. By determining the reference payment amount, the common transaction amount of the target customer when conducting transactions in the payment center can be determined, thereby providing security guidance for the actual payment amount.

[0076] In specific implementation, the amount of credit compensation for each non-excess payment authority is extracted based on the reference payment amount, that is: the payment amount of each non-excess payment authority is subtracted from the reference payment amount, and the absolute value of the difference result is used as the amount of credit compensation for the non-excess payment authority, thereby obtaining the amount of credit compensation for each non-excess payment authority. In addition, in other embodiments, other methods can be used to determine the amount of credit compensation, which are not limited here.

[0077] It should be noted that, in this embodiment, the amount of credit limit compensation represents a measure of the degree of credit limit constraint on the actual payment amount of the target customer when performing payment operations. The larger the amount of credit limit compensation, the looser the credit limit constraint on the actual payment amount of the target customer when performing payment operations; the smaller the amount of credit limit compensation, the tighter the credit limit constraint on the actual payment amount of the target customer when performing payment operations.

[0078] In specific implementation, the payment limit margin of the target customer when performing payment operations is determined by all the limit compensation amounts, that is, the average of all the limit compensation amounts is used as the payment limit margin when the target customer performs payment operations. In addition, in other embodiments, other methods can also be used to determine the payment limit margin, which are not limited here.

[0079] It should be noted that the payment limit margin in this embodiment represents an amount of space that the target customer is accustomed to providing when performing payment operations. By determining the payment limit margin, additional transaction needs can be accommodated and occasional excess situations can be dealt with, thereby improving the customer's payment flexibility and continuity, and further ensuring the ability to monitor risks during the payment process.

[0080] In specific implementation, the safety margin coefficient of the payment operation of the payment center under a risk-free state is set, that is: the safety margin coefficient of the payment operation of the payment center under a risk-free state is pre-set through all historical payment data of the payment center and combined with expert experience. The value of the safety margin coefficient can be set according to actual application requirements and is not limited here.

[0081] It should be noted that the safety margin coefficient in this embodiment represents a parameter used to monitor and adjust the payment margin. By determining the safety margin coefficient, the rationality of transaction operations can be improved, thereby effectively managing payment risks.

[0082] In some embodiments, the risk measure of each overpayment authority on the payment amount is determined based on the payment amount margin, the safety margin coefficient and the payment amount of each overpayment authority in the following manner, namely:

[0083] Obtain multiple excess payment permissions from all risk-free payment permissions, and extract the payment amount of each excess payment permission;

[0084] For each overpayment authority, the safety excess entropy corresponding to the overpayment authority is determined according to the payment limit margin, the safety limit coefficient and the payment amount of the overpayment authority, thereby obtaining the safety excess entropy corresponding to each overpayment authority;

[0085] The distribution statistics of all security excess entropies are performed to determine the risk measure of each excess payment authority in terms of payment amount.

[0086] It should be noted that the method for extracting the payment amount for each overpayment authority is as above and will not be repeated here.

[0087] In specific implementation, the safety excess entropy corresponding to the overpayment authority is determined based on the payment limit margin, the safety limit coefficient and the payment amount of the overpayment authority, that is: the product of the safety limit coefficient and the payment limit margin is used as the adjustment base, the payment amount of each overpayment authority is subtracted from the payment limit margin, and the ratio of each difference result to the adjustment base is used as the safety excess entropy of each overpayment authority.

[0088] It should be noted that, in this embodiment, the safety excess entropy represents an indicator that measures the degree of abnormality of excess transactions in payment behavior relative to normal transaction patterns. Determining the safety excess entropy can help evaluate the potential risks of each excess payment authority. The adjustment base is a normative parameter used for mathematical calculations. By determining the adjustment parameters, the range of calculation results can be rationalized, which will not be repeated here.

[0089] In the specific implementation, all the security excess entropies are distributed and statistically analyzed to determine the risk measure of each excess payment authority in terms of the payment amount, that is, each security excess entropy is subtracted from the mean of all security excess entropies, and each difference result and the standard deviation of all security excess entropies are used as the risk measure of each excess payment authority. In addition, in other embodiments, other methods can be used to determine the risk measure, which are not limited here.

[0090] It should be noted that the risk measurement in this application represents the measurement of the excess position and degree of transaction abnormality of each overpayment authority among all overpayment authorities. The larger the risk measurement, the greater the deviation of the overpayment authority from the normal transaction pattern, and the higher the risk. The smaller the risk measurement, the smaller the deviation of the overpayment authority from the normal transaction pattern, and the lower the risk. By determining the risk measurement, the payment center can identify abnormal high-risk transactions and take corresponding risk prevention and control measures.

[0091] In step 103, all risk metrics are feature fused to obtain payment behavior characteristics of the target customer when performing payment operations, and the security confidence of the current target customer when making payments at the payment center is determined based on the pre-trained security assessment model and the payment behavior characteristics.

[0092] In some embodiments, reference Figure 2 As shown in the figure, this figure is an exemplary flow chart of determining the payment behavior characteristics of the target customer when performing a payment operation according to some embodiments of the present application. In this embodiment, all risk metrics are feature fused to obtain the payment behavior characteristics of the target customer when performing a payment operation, which can be achieved by the following steps:

[0093] First, in step 1031, all risk metrics are standardized to obtain the normative entropy of each risk metric;

[0094] Then, in step 1032, a plurality of entropy clustering groups of all the canonical entropies are determined;

[0095] Finally, in step 1033, payment behavior characteristics of the target customer when performing payment operations are extracted based on all entropy clustering groups.

[0096] In specific implementation, all risk metrics are standardized to obtain the normative entropy of each risk metric, that is, each risk metric is subtracted from the mean of all risk metrics, and the difference result is used as the normative entropy of the risk metric to obtain the normative entropy of each risk metric. In addition, in other embodiments, other methods can be used to determine the normative entropy, which is not limited here. The normative entropy can ensure the consistency of data scale, thereby simplifying the calculation operation of the payment center and improving the accuracy of risk management.

[0097] In specific implementation, the K-means clustering algorithm can be used to determine multiple entropy clustering groups of all standard entropies. The K-means clustering algorithm is a calculation method for data processing, which will not be described here. In addition, in other embodiments, other clustering algorithms can also be used to determine multiple entropy clustering groups, such as hierarchical clustering, density clustering, etc., which are not limited here.

[0098] It should be noted that, in this embodiment, the entropy clustering group represents a collection of different clusters formed by clustering analysis of standard entropies. There are multiple standard entropies with similar characteristics in one entropy clustering group. By determining the entropy clustering group, different patterns and structures of standard entropies can be reflected, thereby providing support for payment decisions and risk analysis.

[0099] In the specific implementation, the payment behavior characteristics of the target customers when performing payment operations are extracted based on all entropy clustering groups, that is: for each entropy clustering group, the clustering characteristics corresponding to the entropy clustering group are determined by all the normative entropies in the entropy clustering group, and then the clustering characteristics corresponding to each entropy clustering group are obtained, and all the clustering characteristics are vectorized to obtain the payment behavior characteristics of the target customers when performing payment operations, and the clustering characteristics represent the mean of all the normative entropies in the entropy clustering group.

[0100] Specifically, the numpy component in Python can be used to convert all cluster features into vectors, which will not be repeated here. In addition, in other embodiments, other methods can be used to convert all cluster features into vectors to extract payment behavior features, which is not limited here.

[0101] It should be noted that the payment behavior characteristics in this embodiment represent characteristic correlation indicators used to describe the actual payment amount of the target customer when completing various payment behaviors. By determining the payment behavior characteristics, the payment behavior pattern of the target customer in terms of transaction amount can be effectively understood, thereby providing data support for payment risk assessment and personalized services.

[0102] In some embodiments, the security confidence level of the current target customer when making a payment at the payment center based on the pre-trained security assessment model and the payment behavior characteristics may be determined in the following manner, namely:

[0103] Collect the payment information of current target customers in the payment center;

[0104] Extracting a payment risk coefficient of the payment information based on a pre-trained security assessment model;

[0105] The security confidence level of the current target customer when making payment at the payment center is determined according to the payment risk coefficient and the payment behavior characteristics.

[0106] In specific implementation, the payment information of the current target customer in the payment center can be collected through the application programming interface (API) provided by the payment center. In addition, in other embodiments, other methods can be used to collect payment information, such as event-driven mechanism, database query or message queue, etc., which are not limited here.

[0107] It should be noted that the payment information in this application refers to various detailed transaction-related data when the target customer performs transaction operations in the payment center, including but not limited to the payment initiation time, payment initiation location, etc. By collecting payment information, the current payment behavior of the target customer can be effectively reflected, which is beneficial for the payment center to conduct security monitoring, analysis and management of the target customer's current transaction activities.

[0108] In some embodiments, the payment risk coefficient of the payment information may be extracted based on a pre-trained security assessment model in the following manner, namely:

[0109] Initialize a pre-trained security assessment model;

[0110] Extract various transaction data of the payment information as input parameters of the security assessment model, call the security assessment model to perform security assessment on various transaction data, and use the assessment result as the payment risk coefficient.

[0111] It should be noted that the security assessment model in the present application represents a machine learning or deep learning model that has been trained using a large amount of historical transaction data, such as a random forest model. In addition, in other embodiments, other security assessment models may also be used, which are not limited here.

[0112] It should also be noted that the payment risk coefficient in this application represents an indicator used to quantify the risk level of a specific payment process. By determining the payment risk coefficient, it is helpful for the payment center to identify and manage potential transaction risks, thereby improving the security of the payment process.

[0113] In specific implementation, the security confidence of the current target customer when making a payment at the payment center is determined based on the payment risk coefficient and the payment behavior characteristics, that is, the mean of all clustered features in the payment behavior characteristics and the payment risk coefficient are weighted and summed, and the sum is used as the security confidence of the current target customer at the payment center. The specific weights can be set according to actual application requirements. For example, the mean of all clustered features in the payment behavior characteristics described in this application and the weight of the payment risk coefficient are set to 0.55 and 0.45, respectively, which are not limited here. In addition, in other embodiments, other methods can be used to determine the security confidence, which are not limited here.

[0114] It should be noted that the security confidence level in this application represents an indicator for measuring and evaluating the degree of risk that may be involved in the payment operations of the current target customers. The higher the security confidence level, the smaller the degree of risk that may be involved in the payment operations of the current target customers. The lower the security confidence level, the greater the degree of risk that may be involved in the payment operations of the current target customers. By determining the security confidence level, the risk of each payment by the payment center can be evaluated in real time, thereby immediately identifying potential risky behaviors when payment occurs, thereby protecting the customer's funds.

[0115] In step 104, the payment risk cost of the target customer when making a large payment is determined based on all risk payment authorities combined with all risk metrics.

[0116] In some embodiments, reference Figure 3 As shown, this figure is an exemplary flow chart of determining the payment risk cost of a target customer when making a large payment according to some embodiments of the present application. In this embodiment, the payment risk cost of a target customer when making a large payment is determined based on all risk payment permissions combined with all risk metrics, which can be implemented by the following steps:

[0117] First, in step 1041, the deviation adjustment amount of the payment operation of the payment center under the risk state is determined;

[0118] Then, in step 1042, the payment skewness value of the target customer when completing all large payments is determined based on the deviation adjustment amount;

[0119] Then, in step 1043, the amount abnormality index of each risk payment authority is determined by the payment skewness value;

[0120] Finally, in step 1044, the payment risk cost of the target customer when making a large payment is determined based on all amount anomaly indexes and all risk metrics.

[0121] In some embodiments, the deviation adjustment amount of the payment operation of the payment center under the risk state may be determined in the following manner, namely:

[0122] The number of permissions to obtain risk payment permissions;

[0123] Setting a first adjustment constant and a second adjustment constant;

[0124] A deviation adjustment amount of a payment operation of a payment center under a risk state is determined according to the authority quantity, the first adjustment constant, and the second adjustment constant.

[0125] It should be noted that, in this embodiment, the first adjustment constant and the second adjustment constant are two calculation constants preset based on historical experience, and can be set according to actual application requirements, and are not limited here.

[0126] In specific implementation, the deviation adjustment amount of the payment operation of the payment center under the risk state is determined based on the authority quantity, the first adjustment constant and the second adjustment constant, that is: first, the authority quantity is subtracted from the first adjustment constant and the second adjustment constant respectively, and the two difference results are used as the first coefficient and the second coefficient respectively, and then, the authority quantity is multiplied by the product of the first coefficient and the second coefficient to calculate the ratio, and the ratio result is used as the deviation adjustment amount of the payment operation of the payment center under the risk state. In addition, in other embodiments, other methods can also be used to determine the deviation adjustment amount, which are not limited here.

[0127] It should be noted that the deviation adjustment amount in this embodiment represents the adjustment range used to adjust the normality of the payment operation. By determining the deviation adjustment amount, the risk control strategy of the payment center can be dynamically adjusted. In addition, the first coefficient and the second coefficient in this embodiment are intermediate variables in the calculation process and will not be repeated here.

[0128] In some embodiments, the payment skewness value of the target customer when completing all large payments based on the deviation adjustment amount may be determined in the following manner, namely:

[0129] Get the payment amount for each risk payment authority;

[0130] Determine the amount at risk measure based on all payment amounts;

[0131] A payment skewness value of the target customer when completing all large payments is determined based on the risk amount metric and the deviation adjustment amount.

[0132] In specific implementation, the risk amount measurement is determined based on all payment amounts, that is: the payment amount of each risk payment authority is subtracted from the mean of the payment amounts of all risk payment authorities, the square value of each difference result is ratioed to the cube value of the standard deviation of all payment amounts, all ratio results are added up, and the accumulated result is used as the risk amount measurement. In addition, in other embodiments, other methods can be used to determine the risk amount measurement, which is not limited here.

[0133] It should be noted that the risk amount measurement in this embodiment represents an indicator that measures the degree of deviation of the payment amount relative to the overall risk payment behavior under a risk state. By determining the risk amount measurement, abnormal behaviors and potential risks in the payment process can be effectively identified and managed, thereby ensuring the security and reliability of the transaction.

[0134] In specific implementation, the payment skewness value of the target customer when completing all large payments is determined based on the risk amount measurement and the deviation adjustment amount, that is, the product of the risk amount measurement and the deviation adjustment amount is used as the payment skewness value of the target customer when completing all large payments. In addition, in other embodiments, other methods can also be used to determine the payment skewness value, which is not limited here.

[0135] It should be noted that the payment skewness value in this embodiment represents an indicator for measuring the degree of asymmetry of the payment amount distribution. Determining the payment skewness value can help understand the overall distribution of target customers' payment behavior, thereby improving the management reliability of the payment center.

[0136] In specific implementation, the amount abnormality index of each risk payment authority is determined by the payment skewness value, that is: for each risk payment authority, the payment amount of the risk payment authority is subtracted from the payment skewness value to obtain the amount abnormality index of the risk payment authority, and then the amount abnormality index of each risk payment authority is obtained. In addition, in other embodiments, other methods can also be used to determine the amount abnormality index, which is not limited here.

[0137] It should be noted that the amount abnormality index in this application indicates the degree of deviation of the risk payment authority in terms of payment amount when processing large-amount payment behavior relative to normal payment behavior. If the amount abnormality index is a positive value, it means that the corresponding risk payment authority deviates greatly from the normal payment behavior in terms of payment amount when processing large-amount payment behavior, and has a higher risk. If the amount abnormality index is a negative value, it means that the corresponding risk payment authority deviates less from the normal payment behavior in terms of payment amount when processing large-amount payment behavior, and has a lower risk.

[0138] In specific implementation, the payment risk cost of the target customer when making large payments is determined based on all amount anomaly indexes and all risk metrics, that is, the mean of all amount anomaly indexes and the mean of all risk metrics are weighted and summed, and the sum is used as the payment risk cost of the target customer when making large payments. The specific weights can be set according to actual application requirements. For example, in this application, the weights of the mean of all amount anomaly indexes and the mean of all risk metrics are set to 0.65 and 0.35, respectively, which are not limited here. In addition, in other embodiments, other methods can be used to determine the payment risk cost, which are not limited here.

[0139] It should be noted that the payment risk cost in this application is used to measure the extent to which the target customer needs to bear additional risks when making large payments at the payment center. The greater the payment risk cost, the greater the extent to which the target customer may need to bear additional risks when making large payments at the payment center. The smaller the payment risk cost, the smaller the extent to which the target customer may need to bear additional risks when making large payments at the payment center. By determining the payment risk cost, the risks and uncertainties of the target customer's transaction behavior can be more accurately reflected, thereby providing the payment center with a more precise risk control strategy.

[0140] In step 105, when the target customer makes a large payment at the payment center, the payment behavior of the target customer is authorized to be adjusted based on the payment risk cost and the security confidence.

[0141] In some embodiments, the following methods may be used to adjust the rights of the target customer's payment behavior based on the payment risk cost and the security confidence level, namely:

[0142] Determining the transaction risk level of the current transaction behavior according to the payment risk cost and the security confidence level;

[0143] Based on the transaction risk level, the transaction behavior of the target customer in the payment center is adjusted.

[0144] In some embodiments, the transaction risk level of the current transaction behavior can be determined according to the payment risk cost and the security confidence level in the following manner, namely:

[0145] Obtain the preset payment risk cost and preset risk safety confidence level;

[0146] The payment risk cost is compared with the preset payment risk cost. When the payment risk cost is greater than the preset payment risk cost, the payment risk cost is determined as a loss-making cost. When the payment risk cost is less than or equal to the preset payment risk cost, the payment risk cost is determined as a non-loss-making cost.

[0147] The safety confidence is compared with a preset risk safety confidence; when the safety confidence is greater than the preset risk safety confidence, the safety confidence is determined as a risk-free confidence value; when the safety confidence is less than or equal to the preset risk safety confidence, the safety confidence is determined as a risk confidence value;

[0148] When the payment risk cost is determined to be a lossless cost and the security confidence is determined to be a risk-free confidence value, the transaction risk level of the current transaction behavior is determined to be a low risk level;

[0149] When the payment risk cost is determined to be a lossless cost and the security confidence is determined to be a risk confidence value, or when the payment risk cost is determined to be a lossy cost and the security confidence is determined to be a risk-free confidence value, the transaction risk level of the current transaction behavior is determined to be a medium risk level;

[0150] When the payment risk cost is determined to be a lossy cost and the security confidence is determined to be a risk confidence value, the transaction risk level of the current transaction behavior is determined to be a high risk level.

[0151] It should be noted that the preset payment risk cost and the preset risk security confidence in this embodiment are monitoring thresholds preset by the payment center for controlling payment security. The specific values ​​can be set according to actual application requirements and will not be repeated here.

[0152] In specific implementation, if the payment risk cost is greater than the preset payment risk cost, it means that the target customer is likely to suffer a loss when making large payments at the payment center, and the payment risk cost is judged as a loss-making cost; if the payment risk cost is less than or equal to the preset payment risk cost, it means that the target customer is unlikely to suffer a loss when making large payments at the payment center, and the payment risk cost is judged as a lossless cost.

[0153] In specific implementation, if the security confidence level is greater than the preset risk security confidence level, it indicates that the payment operation of the current target customer may involve a relatively low risk, and the security confidence level is determined as a risk-free confidence value; if the security confidence level is less than or equal to the preset risk security confidence level, it indicates that the payment operation of the current target customer may involve a relatively high risk, and the security confidence level is determined as a risk confidence value.

[0154] In some embodiments, the following methods may be used to adjust the rights of target customers' transaction behaviors in the payment center based on the transaction risk level, namely:

[0155] If the transaction risk level of the current transaction is low, no security permission adjustment will be made and the transaction will continue;

[0156] If the transaction risk level of the current transaction is medium risk, the target customer will be required to undergo additional security permission verification. The transaction can continue after the permission verification is passed.

[0157] If the transaction risk level of the current transaction behavior is a high risk level, the detailed transaction information is collected and uploaded to the payment center. The payment center issues a transaction behavior warning to the target customer, prevents the target customer from approving any payment authority, and the transaction behavior is interrupted.

[0158] It should be noted that the additional security authority verification performed by the target customer in this embodiment refers to the payment authority authentication method provided by the payment center in addition to managing the customer's payment security, including but not limited to SMS verification code verification, dynamic password verification, biometric recognition verification, etc. In addition, in other embodiments, the additional security authority verification may also include other authentication methods, which are not limited here.

[0159] In addition, in another aspect of the present application, in some embodiments, the present application provides a payment security control system of a data middle station, referring to Figure 4 , which is a schematic diagram of the structure of the payment security control system of the data middle station according to some embodiments of the present application. The payment security control system 200 of the data middle station includes: a determination module 201, a processing module 202 and an execution module 203, which are respectively described as follows:

[0160] Determination module 201, in this application, determination module 201 is mainly used to determine multiple risk-free payment permissions and multiple risk payment permissions that can be configured by the target customer in the data middle station payment center;

[0161] Processing module 202, in this application, processing module 202 is mainly used to extract multiple overpayment permissions and multiple non-overpayment permissions in a risk-free state from all risk-free payment permissions based on the credit limit of the target customer, and determine the risk measurement of each overpayment permission in terms of payment amount based on all non-overpayment permissions;

[0162] The processing module 202 is further used to perform feature fusion on all risk metrics to obtain payment behavior characteristics of the target user when performing payment operations, and determine the security confidence of the current target customer when making payments at the payment center based on the pre-trained security assessment model and the payment behavior characteristics;

[0163] In addition, the processing module 202 is also used to determine the payment risk cost when the target customer makes a large payment based on all risk payment permissions combined with all risk metrics;

[0164] Execution module 203, in this application, execution module 203 is mainly used to adjust the payment behavior of the target customer based on the payment risk cost and the security confidence when the target customer makes a large payment in the payment center.

[0165] In addition, the present application also provides a computer device, which includes a memory and a processor, the memory stores code, and the processor is configured to obtain the code and execute the payment security control method of the above-mentioned data middle station.

[0166] In some embodiments, reference Figure 5, which is a schematic diagram of the structure of a computer device for implementing a payment security control method of a data middle station according to some embodiments of the present application. The payment security control method of the data middle station in the above embodiment can be Figure 5 The computer device 300 shown in the figure is implemented, and the computer device 300 includes at least one processor 301, a communication bus 302, a memory 303 and at least one communication interface 304.

[0167] Processor 301 can be a general-purpose central processing unit (CPU), or an application-specific integrated circuit (ASIC) or one or more devices for controlling the execution of the payment security control method of the data center in this application.

[0168] The communication bus 302 may be used to transmit information between the above-mentioned components.

[0169] The memory 303 may be a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, an optical disc storage (including a compressed optical disc, a laser disc, an optical disc, a digital versatile disc, a Blu-ray disc, etc.), a magnetic disk or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of an instruction or data structure and can be accessed by a computer, but is not limited thereto. The memory 303 may exist independently and be connected to the processor 301 via the communication bus 302. The memory 303 may also be integrated with the processor 301.

[0170] Among them, the memory 303 is used to store the program code for executing the solution of the present application, and the execution is controlled by the processor 301. The processor 301 is used to execute the program code stored in the memory 303. The program code may include one or more software modules. The determination of the payment security control method of the data middle station in the above embodiment can be implemented by the processor 301 and one or more software modules in the program code in the memory 303.

[0171] The communication interface 304 uses any transceiver or other device for communicating with other devices or communication networks, such as Ethernet, radio access network (RAN), wireless local area networks (WLAN), etc.

[0172] In a specific implementation, as an embodiment, a computer device may include multiple processors, each of which may be a single-CPU processor or a multi-CPU processor. The processor here may refer to one or more devices, circuits, and / or processing cores for processing data (e.g., computer program instructions).

[0173] The above-mentioned computer device can be a general-purpose computer device or a special-purpose computer device. In a specific implementation, the computer device can be a desktop computer, a portable computer, a network server, a personal digital assistant (PDA), a mobile phone, a tablet computer, a wireless terminal device, a communication device or an embedded device. The embodiment of the present application does not limit the type of computer device.

[0174] In addition, the present application also provides a computer-readable storage medium, which stores a computer program, and when the computer program is executed by a processor, it implements the payment security control method of the above-mentioned data center.

[0175] Although the preferred embodiments of the present application have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present application.

[0176] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A payment security control method for a data middle station, characterized in that: The steps include: Determine the multiple risk-free payment permissions and risk-based payment permissions that can be configured by the target customer in the data middle platform payment center; Based on the target customer's credit limit, multiple overpayment permissions and non-overpayment permissions are extracted from all risk-free payment permissions, and then the risk measurement of each overpayment permission in terms of payment amount is determined based on all non-overpayment permissions; Perform feature fusion on all risk metrics to obtain payment behavior characteristics of target customers when performing payment operations, and determine the security confidence of the current target customer when making payments at the payment center based on the pre-trained security assessment model and the payment behavior characteristics; Determine the payment risk cost of target customers when making large payments based on all risk payment permissions and all risk metrics; When a target customer makes a large payment at the payment center, the payment behavior of the target customer is authorized to be adjusted based on the payment risk cost and the security confidence.

2. The method according to claim 1, characterized in that Based on the target customer's credit limit, multiple excess payment permissions and non-excess payment permissions are extracted from all risk-free payment permissions in a risk-free state, including: Get the credit limit of target customers; Extract the payment amount for each risk-free payment authority; Based on the credit limit and the payment amount of each risk-free payment authority, multiple overpayment authorities and multiple non-overpayment authorities are extracted from all risk-free payment authorities.

3. The method according to claim 1, characterized in that The risk measurement of the payment amount for each overpayment authority is determined based on all non-overpayment authorities, including: Determine the payment margin for target customers when they make payment operations based on all non-excess payment permissions; Set the safety margin coefficient of the payment center's payment operations under a risk-free state; Get the payment amount for each overpayment authority; A risk measure of the payment amount of each overpayment authority is determined based on the payment limit margin, the safety limit coefficient, and the payment amount of each overpayment authority.

4. The method according to claim 1, characterized in that By integrating all risk metrics, we can obtain the payment behavior characteristics of target customers when they make payment operations, including: All risk measures are standardized to obtain the normative entropy of each risk measure; determining multiple entropy clustering groups of all canonical entropies; Based on all entropy clustering groups, the payment behavior characteristics of target customers when performing payment operations are extracted.

5. The method according to claim 1, characterized in that Determining the security confidence level of the current target customer when making a payment at the payment center based on the pre-trained security assessment model and the payment behavior characteristics specifically includes: Collect the payment information of current target customers in the payment center; Extracting a payment risk coefficient of the payment information based on a pre-trained security assessment model; The security confidence level of the current target customer when making payment at the payment center is determined according to the payment risk coefficient and the payment behavior characteristics.

6. The method according to claim 1, characterized in that The permission adjustment of the payment behavior of the target customer based on the payment risk cost and the security confidence level specifically includes: Determining the transaction risk level of the current transaction behavior according to the payment risk cost and the security confidence level; Based on the transaction risk level, the transaction behavior of the target customer in the payment center is adjusted.

7. The method according to claim 1, characterized in that The data center is a centralized data center.

8. A payment security control system for a data center, characterized in that: include: A determination module is used to determine multiple risk-free payment permissions and multiple risk payment permissions that can be configured by the target customer in the data middle platform payment center; A processing module, for extracting a plurality of overpayment permissions and a plurality of non-overpayment permissions in a risk-free state from all risk-free payment permissions based on the credit limit of the target customer, and then determining a risk measure of each overpayment permission in terms of payment amount based on all non-overpayment permissions; The processing module is further used to perform feature fusion on all risk metrics to obtain payment behavior characteristics of the target customer when performing payment operations, and determine the security confidence of the current target customer when making payments at the payment center based on the pre-trained security assessment model and the payment behavior characteristics; The processing module is also used to determine the payment risk cost when the target customer makes a large payment based on all risk payment permissions combined with all risk metrics; The execution module is used to adjust the payment behavior of the target customer based on the payment risk cost and the security confidence when the target customer makes a large payment in the payment center.

9. A computer device, characterized in that: The computer device includes a memory and a processor, the memory stores codes, and the processor is configured to obtain the codes and execute the payment security control method of the data middle station as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by the processor, the payment security control method of the data middle station as described in any one of claims 1 to 7 is implemented.

Images