Multi-channel data cross validation payment method, system and device and medium

Abstract

The invention relates to a multi-channel data cross validation payment method, system and device and a medium, and the method comprises the steps: carrying out the analysis and reading of multi-channel payment data, and obtaining payment system data, user data, transaction data and payment scene information; performing identity pre-verification analysis on the user data to obtain corresponding identity verification data, and performing multi-factor authentication analysis on the user data based on the payment scene information to obtain multi-factor authentication data; performing association analysis on the payment system data according to the multi-factor authentication data to obtain corresponding verification payment system data; performing risk assessment analysis on the payment system data to obtain corresponding comprehensive risk data, and performing cross validation analysis on the comprehensive risk data based on the verification payment system data to obtain corresponding cross validation data; and comprehensively analyzing all the initial security policies to obtain a dynamic security policy. According to the invention, dynamic adjustment can be carried out according to the change of the real-time payment environment.

Description

Technical Field

[0001] The present invention relates to the technical field of payment verification, and in particular to a multi-channel data cross-verification payment method, system, device and medium. Background Art

[0002] In the current payment industry, with the diversification of payment channels and the complexity of payment scenarios, ensuring payment security has become a crucial issue. Traditional payment verification methods often rely on data from a single channel for identity authentication and risk assessment. This method is prone to security risks when facing a complex payment environment. Data from different payment channels often exist independently, and there is a lack of an effective data integration mechanism, which makes it difficult to achieve comprehensive data cross-verification, affecting the integrity of payment security. Traditional payment verification methods often rely on a single factor for identity authentication, such as a password or SMS verification code, which is easy to be cracked or forged, making it difficult to ensure the security of the payment process. Existing risk assessment methods often only consider data in a single dimension, such as user behavior data or transaction data, and lack a comprehensive analysis of multi-channel data, resulting in incomplete and inaccurate risk assessment. Traditional payment security strategies are often static and difficult to dynamically adjust according to changes in the real-time payment environment, resulting in insufficient adaptability and flexibility of security strategies. Summary of the invention

[0003] The main purpose of the present invention is to provide a multi-channel data cross-verification payment method, system, device and medium, which can be dynamically adjusted according to changes in the real-time payment environment.

[0004] To achieve the above object, the present invention provides a multi-channel data cross-verification payment method, comprising: Obtain multi-channel payment data, analyze and read multi-channel payment data, and obtain payment system data, user data, transaction data and payment scenario information; Performing identity pre-verification analysis on the user data to obtain corresponding identity verification data, and performing multi-factor authentication analysis on the user data based on the payment scenario information to obtain multi-factor authentication data; Mapping the payment system data to the identity verification data, and performing correlation analysis on the payment system data based on the multi-factor authentication data to obtain corresponding verification payment system data; Performing risk assessment analysis on the payment system data according to the transaction data to obtain corresponding comprehensive risk data, and performing cross-validation analysis on the comprehensive risk data based on the verified payment system data to obtain corresponding cross-validation data; A policy analysis is performed based on the multi-factor authentication data and the cross-validation data to obtain an initial security policy, and a comprehensive analysis is performed on all the initial security policies to obtain a dynamic security policy.

[0005] Furthermore, the multi-channel payment data is obtained, and the multi-channel payment data is analyzed and read to obtain payment system data, user data, transaction data and payment scenario information, including: Collecting and aggregating payment data from multiple payment channels to obtain the multi-channel payment data, and classifying the multi-channel payment data according to a preset data classification rule to obtain an original classification result; Perform association analysis on the original classification results according to the preset data association rules to obtain associated classification data; Perform feature extraction processing on the associated classification data to obtain a feature vector set; perform dimensionality reduction processing on the feature vector set to obtain a reduced dimensionality vector set; The dimensionality reduction vector set is segmented according to the preset data segmentation rules to obtain payment system data, user data, transaction data and payment scenario information.

[0006] Further, the performing identity pre-verification analysis on the user data to obtain corresponding identity verification data, and performing multi-factor authentication analysis on the user data based on the payment scenario information to obtain multi-factor authentication data, includes: Performing identity analysis on the user data according to preset identity authentication rules to obtain identity authentication parameters, and performing multi-dimensional comparison on the user data according to the identity authentication parameters to obtain an identity matching result; Performing credibility assessment on the user data according to the identity matching result to obtain the identity verification data; Extract keywords from the payment scenario information to obtain a scenario feature set, and perform hierarchical screening on the user data based on the scenario feature set to obtain multi-layer user features; Matching the multi-layer user features with the preset authentication factors to obtain an authentication factor set; Cross-validate the authentication factor set and the identity verification data to obtain a verification result matrix, and assign weights to the verification result matrix to obtain a weighted verification result; The user data is comprehensively evaluated based on the weighted verification result to obtain the multi-factor authentication data.

[0007] Further, mapping the payment system data to the identity verification data, and performing association analysis on the payment system data according to the multi-factor authentication data to obtain corresponding verification payment system data, includes: Performing wavelet transform on the payment system data to obtain system time-frequency characteristics, and performing Fourier transform on the identity verification data to obtain identity frequency domain representation; Integrate and reduce the dimension of the system time-frequency features and the identity frequency domain representation to obtain a reduced dimension feature set, and perform nonlinear mapping on the payment system data based on the reduced dimension feature set to obtain mapped payment system data; Performing independent component analysis on the multi-factor authentication data to extract independent features to obtain an independent feature set, and performing association analysis on the mapped payment system data and the independent feature set to obtain an association rule set; Calculate the confidence and support of the association rule set to obtain the optimized rule set; Classifying the payment system data according to the optimization rule set to obtain classification results, performing cluster analysis on the classification results to obtain cluster clusters; performing anomaly identification on each cluster cluster according to a preset anomaly factor detection rule to obtain anomaly detection results; The anomaly detection results and classification results are weighted and fused to obtain preliminary verification data, which are then filtered and completed to obtain complete verification payment system data.

[0008] Further, the performing risk assessment analysis on the payment system data according to the transaction data to obtain corresponding comprehensive risk data, and performing cross-validation analysis on the comprehensive risk data based on the verified payment system data to obtain corresponding cross-validation data, includes: Performing time series analysis on the transaction data to obtain a transaction time series pattern, and classifying the payment system data according to the transaction time series pattern to obtain a system risk classification result; Performing deviation detection on the payment system data according to the system risk classification result to obtain a system deviation index, and performing risk quantitative analysis on the payment system data according to the system deviation index and preset risk assessment rules to obtain a system risk value; Conduct trend analysis on system risk values ​​according to preset risk calculation rules to obtain risk change data; conduct comprehensive analysis on risk change data and system risk values ​​to generate comprehensive risk data; Performing a correlation analysis on the comprehensive risk data based on the verified payment system data to obtain a risk correlation factor, and cross-validating the comprehensive risk data based on the risk correlation factor to obtain a preliminary cross-validation result; Correct the preliminary crossover results according to the preset correction rules to obtain the correction verification results, and perform grade analysis on the correction verification results according to the preset verification standards to obtain the verification grade; The validation level and correction validation results are processed comprehensively to obtain cross-validation data.

[0009] Further, the policy analysis is performed based on the multi-factor authentication data and the cross-validation data to obtain an initial security policy, and all the initial security policies are comprehensively analyzed to obtain a dynamic security policy, including: Fusing the multi-factor authentication data and the cross-validation data to obtain fused data, and performing policy matching on the fused data according to a preset security rule set to obtain an initial security policy; Perform hierarchical analysis on the initial security policy to obtain the policy hierarchy, and perform matrix analysis based on the policy hierarchy to obtain the decision weight set; Iteratively optimize the decision weight set to obtain an optimized weight set, and perform statistical analysis on the optimized weight set to obtain a statistical analysis result; Perform random numerical simulation based on statistical analysis results, generate simulation strategies, and obtain corresponding historical security strategies based on statistical analysis results; Compare and analyze the simulation strategy with the historical security strategy to obtain strategy difference data; The simulation strategy is adjusted according to the strategy difference data to obtain the adjusted strategy, and a sensitivity analysis is performed on the adjusted strategy to obtain a sensitivity score; The adjustment strategies are screened according to the sensitivity scores to obtain a screening strategy set; The screening policy set is dynamically adjusted according to preset dynamic adjustment rules to obtain the dynamic security policy.

[0010] The present invention also provides a multi-channel data cross-verification payment system, which is applied to any of the multi-channel data cross-verification payment methods mentioned above, comprising: A collection module, which is used to obtain multi-channel payment data, analyze and read the multi-channel payment data, and obtain payment system data, user data, transaction data and payment scenario information; An analysis module, the analysis module is used to perform identity pre-verification analysis on the user data to obtain corresponding identity verification data, and perform multi-factor authentication analysis on the user data based on the payment scenario information to obtain the multi-factor authentication data; an association module, the association module being used to map the payment system data to the identity verification data, and to perform association analysis on the payment system data according to the multi-factor authentication data to obtain corresponding verification payment system data; A processing module, the processing module is used to perform risk assessment analysis on the payment system data according to the transaction data to obtain corresponding comprehensive risk data, and to perform cross-validation analysis on the comprehensive risk data based on the verification payment system data to obtain corresponding cross-validation data; A control module is used to perform a policy analysis based on the multi-factor authentication data and the cross-validation data to obtain an initial security policy, and to perform a comprehensive analysis on all the initial security policies to obtain a dynamic security policy.

[0011] The present invention also provides a multi-channel data cross-verification payment device, comprising: Memory, used to store programs; The processor is used to execute the program to implement each step of the multi-channel data cross-verification payment method described in any one of the above.

[0012] The present invention also provides a storage medium storing computer instructions, wherein the computer instructions are used to enable a computer to execute any of the above methods.

[0013] The present invention provides the following beneficial effects: By acquiring payment data from multiple channels and conducting comprehensive analysis and reading of these data, comprehensive data integration is achieved. This not only improves the utilization rate of data, but also ensures data consistency in the payment process, enhancing overall security and reliability. Through multi-factor authentication analysis, combined with payment scenario information, multi-dimensional identity authentication of user data is performed, which improves the accuracy and security of identity authentication and effectively prevents the security risks caused by the limitations of a single authentication method. By mapping payment system data with identity authentication data, and combining multi-factor authentication data for correlation analysis, generating verification payment system data, and then combining transaction data for risk assessment analysis, more comprehensive and accurate comprehensive risk data is obtained. This helps to discover potential risks in a timely manner and improve the effectiveness of risk control. By conducting strategy analysis based on multi-factor authentication data and cross-validation data, generating initial security strategies, and obtaining dynamic security strategies through comprehensive analysis, payment security strategies can be dynamically adjusted according to changes in the real-time payment environment, improving the adaptability and flexibility of security strategies. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 It is a flow chart of a multi-channel data cross-verification payment method provided by the present invention; Figure 2 It is a structural diagram of a multi-channel data cross-verification payment system provided by the present invention; Figure 3 It is a structural diagram of a multi-channel data cross-verification payment device provided by the present invention.

[0015] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0016] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0017] The present invention is further described below in conjunction with the accompanying drawings and specific implementation methods.

[0018] Reference Figure 1 As shown, a multi-channel data cross-verification payment method includes: Step S1: Obtain multi-channel payment data, analyze and read the multi-channel payment data, and obtain payment system data, user data, transaction data and payment scenario information; Step S2: Perform identity pre-verification analysis on the user data to obtain corresponding identity verification data, and perform multi-factor authentication analysis on the user data based on the payment scenario information to obtain multi-factor authentication data; Step S3: mapping the payment system data to the identity verification data, and performing correlation analysis on the payment system data based on the multi-factor authentication data to obtain corresponding verification payment system data; Step S4: performing risk assessment analysis on the payment system data according to the transaction data to obtain corresponding comprehensive risk data, and performing cross-validation analysis on the comprehensive risk data based on the verified payment system data to obtain corresponding cross-validation data; Step S5: Perform policy analysis based on multi-factor authentication data and cross-validation data to obtain an initial security policy, and perform comprehensive analysis on all initial security policies to obtain a dynamic security policy.

[0019] Based on the above steps, the detailed process is as follows: Step S1: Collect data from different payment channels to obtain payment system data, user data, transaction data and payment scenario information, such as bank transfer, credit card payment, mobile payment (such as Alipay, WeChat Pay), etc. These data can come from different financial institutions and third-party payment platforms.

[0020] Step S2: Confirm the authenticity of the user's identity by comparing the basic information provided by the user with the records in the database. Check whether there are any unusual behavior patterns, such as frequent changes of login passwords, etc.

[0021] In addition to traditional usernames and passwords, there are multiple authentication methods, including SMS verification codes, fingerprint recognition, facial recognition, etc. The required identity verification strength is dynamically adjusted according to the risk level of the payment scenario, for example, more verification steps are required for high-risk transactions.

[0022] Step S3: Match each transaction record of the payment system with the user's identity verification information to ensure that each transaction is associated with a legitimate user. Ensure the consistency between the payment system data and the identity verification data to prevent fraud caused by inconsistent data.

[0023] The validity and security of the transaction is further confirmed by analyzing the relationship between the payment system data and the multi-factor authentication data. At this stage, further investigation is carried out to find any possible signs of abnormal activity, such as a large number of small transactions in a short period of time.

[0024] Step S4: Assess the risk level of each transaction based on the transaction data and assign a risk score to each transaction. Continuously monitor all ongoing transactions to detect any potential risks in a timely manner.

[0025] Verified payment system data is combined with the previously derived risk score for secondary confirmation to ensure payment security. The final transaction risk level is determined through comprehensive analysis of these data, and a decision is made based on this whether to continue the transaction.

[0026] Perform risk assessment analysis on payment system data based on transaction data to obtain corresponding comprehensive risk data, and perform cross-validation analysis on the comprehensive risk data based on verified payment system data to obtain corresponding cross-validation data; Step S5: Based on the multi-factor authentication data and cross-validation data, a preliminary security strategy is formulated, and the specific implementation details of the security strategy are refined for different types of transactions and different payment scenarios.

[0027] Through comprehensive analysis of all initial security strategies, we continuously optimize and improve them to make them more in line with actual needs. According to market changes and technological advances, we adjust security strategies regularly or as needed to respond to new threats and challenges and ensure the continued security and efficient operation of the payment system.

[0028] A multi-channel data cross-verification payment method provided by the present invention realizes comprehensive integration of data by acquiring multi-channel payment data and performing comprehensive analysis and reading of the data. This not only improves the utilization rate of data, but also ensures the consistency of data in the payment process, and enhances the overall security and reliability. Through multi-factor authentication analysis, combined with payment scenario information, multi-dimensional identity authentication is performed on user data, the accuracy and security of identity authentication are improved, and the security risks caused by the limitations of a single authentication method are effectively prevented. By mapping payment system data with identity authentication data, and performing correlation analysis in combination with multi-factor authentication data, verifying payment system data is generated, and then risk assessment analysis is performed in combination with transaction data, thereby obtaining more comprehensive and accurate comprehensive risk data. This helps to discover potential risks in a timely manner and improve the effectiveness of risk control. By performing strategy analysis based on multi-factor authentication data and cross-verification data, generating an initial security strategy, and obtaining a dynamic security strategy through comprehensive analysis, the payment security strategy can be dynamically adjusted according to changes in the real-time payment environment, thereby improving the adaptability and flexibility of the security strategy.

[0029] In one embodiment, multi-channel payment data is obtained, and the multi-channel payment data is analyzed and read to obtain payment system data, user data, transaction data, and payment scenario information, including: Connect to multiple payment channels, such as bank interfaces, third-party payment platform APIs, etc., automatically capture the latest payment transaction records, and form a preliminary multi-channel payment data pool. According to the preset data classification rules, these data are preliminarily classified, for example, the data is classified according to the payment method (such as bank card payment, e-wallet payment, etc.), transaction amount, occurrence time and other dimensions, so as to obtain the original classification results. Classification rules include: classification by payment channel (such as Alipay, WeChat payment, etc.), classification by payment type (such as consumption, transfer, recharge, etc.), classification by transaction amount (such as small transactions, large transactions, etc.), classification by user type (such as individual users, corporate users, etc.).

[0030] Apply preset data association rules to perform association analysis on data under different categories, for example, associate the cross-channel payment behaviors of the same user through user ID to form associated classification data. Data association rules include: user behavior association (such as frequently used payment channels, common transaction types, etc.), time series association (such as transaction frequency, transaction time pattern, etc.), geographic location association (such as common payment locations, non-local payment behaviors, etc.), merchant association (such as common merchant types, new merchants, etc.).

[0031] After the data association process is completed, the associated classification data is subjected to feature extraction. This process aims to mine the key features in the data set that help understand payment behavior, such as transaction frequency, payment preference, geographic location, etc. The key features are converted into numerical feature vector sets through feature extraction tools. The feature vector set is subjected to dimensionality reduction processing. Dimensionality reduction techniques such as principal component analysis (PCA) and linear discriminant analysis (LDA) are used to reduce the data dimension while retaining the main information to generate a dimensionality reduction vector set.

[0032] According to the preset data segmentation rules, the dimensionality reduction vector set is further segmented to divide the data into payment system data, user data, transaction data and payment scenario information. The payment system data includes the performance indicators of each payment channel, system load, interface call frequency, etc. For example, payment system data is mainly used to monitor the health and performance of the payment system; user data helps understand the user's payment habits and credit status; transaction data reveals specific transaction behaviors and their trends; and payment scenario information provides the context in which the transaction occurs.

[0033] This embodiment significantly improves the speed and efficiency of data processing through automated data collection and preprocessing, enabling the payment system to process a large amount of transaction information in a short period of time, meeting the needs of the rapid development of modern payment services. By adopting strict data classification, association analysis, and feature extraction steps, the quality and integrity of the data are ensured, providing a reliable basis for subsequent decision-making analysis. By performing detailed classification and feature extraction of payment data, the system can more accurately identify the behavior patterns of different user groups, creating conditions for providing personalized services. With the help of dimensionality reduction technology and data segmentation rules, potential transaction risk points can be identified more effectively, early warnings can be given, and measures can be taken to prevent fraud and ensure transaction security.

[0034] In one embodiment, the user data is subjected to identity pre-verification analysis to obtain corresponding identity verification data, and the user data is subjected to multi-factor authentication analysis based on the payment scenario information to obtain multi-factor authentication data, including: According to the preset identity authentication rules, the user data is analyzed to obtain the identity authentication parameters. These identity authentication parameters include the user's basic information, such as name, ID number, contact information, etc. Then, the user data is compared in multiple dimensions based on these identity authentication parameters to obtain the identity matching result. The multi-dimensional comparison includes data from multiple dimensions such as the user's historical transaction records, device information, and geographic location, including the consistency between the name and ID number, the real-name authentication information of the mobile phone number, and the user information in the historical transaction records.

[0035] The credibility of the user data is evaluated based on the identity matching results to obtain identity verification data. The credibility evaluation mainly determines the credibility of the user's identity by comparing the degree of match between the information currently submitted by the user and the historical records. If the degree of match is high, the credibility is high, otherwise it is low.

[0036] After obtaining the identity authentication data, the payment scenario information is subjected to keyword extraction to obtain the scenario feature set. The payment scenario information includes the time, location, transaction amount, transaction type, etc. of the transaction. By extracting keywords from this information, the main features of the payment scenario are extracted. Based on these scenario feature sets, the user data is layered and screened to obtain multi-layer user features. These user features can reflect the user's behavior patterns and characteristics in different scenarios. Multi-layer user features include: basic layer: age, gender, geographic location; behavioral layer: historical shopping preferences, common payment methods; risk layer: credit score, transaction amount threshold.

[0037] The multi-layer user features are matched with the preset authentication factors to obtain the authentication factor set. The preset authentication factors include the user's biometric information (such as fingerprint, facial recognition, etc.), device fingerprint information, IP address, etc. By matching these authentication factors with user features, the accuracy of identity authentication can be further improved.

[0038] The authentication factor set and identity verification data are cross-validated to obtain the verification result matrix. Cross-validation is to compare and verify data from different sources through multiple verification mechanisms to ensure the consistency and accuracy of the data. Weights are assigned to the verification result matrix to obtain weighted verification results. For example, fingerprint recognition: weight 0.3, score 0.27; payment password: weight 0.3, score 0.3; device recognition: weight 0.2, score 0.16; operation habits: weight 0.2, score 0.12. The total weighted score is 0.85.

[0039] Weight allocation is to assign different weights to the verification results according to the importance of each verification factor to obtain a comprehensive verification result.

[0040] Based on the weighted verification results, the user data is comprehensively evaluated to obtain multi-factor authentication data. The comprehensive evaluation is to analyze the weighted verification results, combine the user's historical behavior data and current transaction information, and comprehensively evaluate the user's identity credibility and transaction risk, so as to obtain the final multi-factor authentication data.

[0041] This embodiment can accurately identify the user's identity through identity pre-verification analysis and multi-dimensional comparison, thereby improving the accuracy and credibility of identity verification. Secondly, by performing keyword extraction and hierarchical screening of payment scenario information, customized multi-factor authentication analysis can be performed for different payment scenarios to ensure that fraud can be effectively prevented in various transaction environments. By matching user characteristics with preset authentication factors and obtaining a verification result matrix through cross-validation, data verification can be performed at multiple levels and angles to avoid the limitations of a single verification method, thereby more comprehensively ensuring the authenticity of the user's identity. The weight distribution mechanism further optimizes the comprehensive evaluation of the verification results, making the final multi-factor authentication data more accurate and reliable.

[0042] In one embodiment, the payment system data is mapped to the identity verification data, and the payment system data is analyzed for association based on the multi-factor authentication data to obtain corresponding verification payment system data, including: The payment system data is mapped to the identity verification data, and the payment system data is analyzed for correlation based on the multi-factor authentication data to obtain the corresponding verification payment system data. Specifically, the payment system data is subjected to wavelet transform to obtain the time-frequency characteristics of the system. These time-frequency characteristics can capture the changes in the payment system data in time and frequency, and the time-frequency characteristics include the frequency information at different time points. At the same time, the identity verification data is subjected to Fourier transform to obtain the frequency domain representation of the identity. The identity verification data is converted from the time domain to the frequency domain through Fourier transform, which facilitates the analysis of the frequency characteristics of the data.

[0043] The system time-frequency features and identity frequency domain representation are integrated and reduced to obtain a reduced-dimensionality feature set. Integrated dimensionality reduction is to merge and simplify multi-dimensional features to reduce the dimension of the data while retaining key features. On this basis, the payment system data is nonlinearly mapped based on the reduced-dimensionality feature set to obtain mapped payment system data. Nonlinear mapping is to map the payment system data to a new feature space through complex mathematical transformations.

[0044] Independent component analysis is performed on multi-factor authentication data to extract independent features and obtain independent feature sets. Independent component analysis can extract independent features from multi-factor authentication data, thereby reducing data redundancy. Association analysis is performed on the mapped payment system data and the independent feature set to obtain an association rule set. Association analysis is to discover potential rules and patterns between data by analyzing the association relationship between data.

[0045] Calculate the confidence and support of the association rule set to obtain the optimized rule set. Confidence and support are important indicators for measuring the reliability of association rules. Through these calculations, the optimal association rules can be screened out. Classify the payment system data according to the optimized rule set to obtain the classification results. Classification is achieved by assigning data to different categories.

[0046] Perform cluster analysis on the classification results to obtain clusters. Cluster analysis is to group similar data points together to form clusters in order to better understand the structure and pattern of the data. Perform anomaly identification on each cluster according to the preset anomaly factor detection rules to obtain anomaly detection results. Anomaly detection is to discover potential risks and problems by identifying anomalies in the data.

[0047] The anomaly detection results and classification results are weighted and fused to obtain preliminary verification data. Weighted fusion is to obtain more accurate verification data by weighting the anomaly detection results and classification results. The preliminary verification data is filtered and supplemented to obtain complete verification payment system data. The filtering and supplementation process is to clean and supplement the preliminary verification data.

[0048] This embodiment can significantly improve the accuracy and security of data verification of the payment system by mapping the payment system data to the identity authentication data and combining the multi-factor authentication data for association analysis. First, the system time-frequency characteristics and identity frequency domain representation are extracted respectively by wavelet transform and Fourier transform, effectively capturing the time domain and frequency domain characteristics of the data, and enhancing the comprehensiveness of data analysis. Secondly, the integration of dimensionality reduction and nonlinear mapping steps reduces the data dimension, retains the key features, and thus improves the data processing efficiency. Independent component analysis further extracts independent features in the multi-factor authentication data, reduces data redundancy, and improves the accuracy of association analysis. The association rule set is optimized by confidence and support calculation to ensure that the selected rules have high reliability. The combination of classification and cluster analysis not only realizes the refined management of data, but also identifies potential risks through anomaly detection, thereby enhancing the security of the system. Finally, the weighted fusion and filtering and completion processing steps ensure the integrity and accuracy of the verification data, thereby providing users with more reliable payment verification results. The combined effect of these measures has significantly improved the security, reliability and user experience of the payment system.

[0049] In one embodiment, risk assessment analysis is performed on payment system data according to transaction data to obtain corresponding comprehensive risk data, and cross-validation analysis is performed on the comprehensive risk data based on verified payment system data to obtain corresponding cross-validation data, including: By performing time series analysis on transaction data, the time series pattern of the transaction is determined. Based on the time series pattern, the data of the payment system is classified to obtain the risk classification result. For example, if a user performs a large number of high-value transactions in a short period of time, this behavior may be identified as high risk by the system and classified into the high-risk category.

[0050] Based on the results of system risk classification, deviation detection is performed on the data of the payment system. The system deviation index is obtained by calculation, and the risk quantitative analysis of the deviation index is performed according to the preset risk assessment rules, and finally the risk value is obtained. Among them, the risk assessment rules include: transaction frequency rule: define the transaction frequency threshold within a certain period of time, and transactions exceeding this threshold will be marked as high risk. Transaction amount rule: define the upper limit of single transaction and cumulative transaction amount, and transactions exceeding this upper limit will be marked as high risk. Transaction type rule: set different risk levels for different types of transactions (such as transfers, purchases, withdrawals, etc.).

[0051] According to the preset risk calculation rules, these system risk values ​​are trend analyzed to generate risk change data, and the risk change data and system risk values ​​are comprehensively analyzed to generate comprehensive risk data. The risk calculation rules are used to calculate the comprehensive risk value and trend, including the time weighted rule: weighted calculation of risk values ​​in different time periods to reflect the trend of risk changes. Historical data comparison rule: compare the current risk value with historical data to identify the trend of risk changes.

[0052] Verify the comprehensive risk data, conduct correlation analysis based on the data of the verified payment system, and obtain the risk correlation factor. Through the risk correlation factor, cross-validate the comprehensive risk data to obtain preliminary cross-validation results. According to the preset correction rules, correct the preliminary cross-validation results to generate the corrected verification results.

[0053] According to the preset validation standard, the corrected validation results are graded and analyzed to obtain the validation grade. The validation grade and the corrected validation results are processed comprehensively to generate cross-validation data.

[0054] Among them, the verification standards include: Risk level standards: define the thresholds of different risk levels, such as low risk (0-30 points), medium risk (31-70 points), and high risk (71-100 points). Verification accuracy standards: set the accuracy requirements of the verification results, such as the accuracy rate must be higher than 95%.

[0055] This embodiment can realize the time series analysis of transaction data through the multi-channel data cross-validation payment method of the above embodiment, thereby establishing a transaction time series model, effectively classifying payment system data and classifying system risks. This classification obtains the system deviation index by detecting the deviation of the payment system data, and performs risk quantification analysis based on the preset risk assessment rules, and finally obtains the system risk value. Then, by performing trend analysis on the system risk value, risk change data is obtained, and a comprehensive analysis is performed in combination with the system risk value to generate comprehensive risk data. This method obtains risk correlation factors through correlation analysis, and cross-validates the comprehensive risk data based on this to obtain preliminary cross-results. The preliminary cross-results are corrected according to the preset correction rules to generate correction verification results, and the correction verification results are graded according to the preset verification standards to obtain the verification level. Finally, cross-validation data is obtained through comprehensive processing of the verification level and the correction verification results. This embodiment can not only refine and accurately identify the risk points in the payment system, but also significantly improve the accuracy and reliability of risk assessment through multi-level analysis and cross-validation. In the process of risk assessment and cross-validation, potential deviations can be dynamically adjusted and corrected, thereby improving the security and stability of the payment system. Through multi-dimensional analysis of comprehensive risk data, the efficiency and credibility of the final cross-validation data are ensured, greatly enhancing the risk management capabilities of the payment system.

[0056] In one embodiment, a policy analysis is performed based on multi-factor authentication data and cross-validation data to obtain an initial security policy, and a comprehensive analysis is performed on all initial security policies to obtain a dynamic security policy, including: The collected multi-factor authentication data and cross-validation data are processed and integrated to obtain integrated data. The integrated data is matched according to the preset security rule set to obtain the initial security policy. The preset security rule set includes security judgment criteria for different data indicators, such as abnormal behavior detection rules, device fingerprint matching rules, etc.

[0057] Perform hierarchical analysis on the initial security policy to form a policy hierarchy. The analytic hierarchy process is a multi-criteria decision-making method that decomposes complex policy issues into several levels by building a policy hierarchy, and conducts detailed analysis on each level. The initial security policy can be divided into user authentication policy, network traffic monitoring policy, abnormal behavior detection policy, etc.

[0058] Perform matrix analysis based on the policy hierarchy, and calculate the decision weight set through the preset decision weight rules. The decision weight set reflects the importance and priority of each policy at different levels. Among them, the decision weight rules include: Hierarchy rules: define how to decompose the initial security policy into multiple levels, such as user authentication layer, network monitoring layer, incident response layer, etc. Weight allocation rules: such as using the AHP (Analytic Hierarchy Process) method to assign weights to each policy based on expert opinions or historical data. Conflict resolution rules: such as when two policies conflict, decide which policy to execute first based on the weight.

[0059] After obtaining the initial decision weight set, it is optimized through an iterative optimization algorithm to obtain an optimized weight set. During the optimization process, the weight adjustment of different factors is considered to achieve the optimal security strategy combination. The optimized weight set is statistically analyzed to obtain statistical analysis results. These results include the application frequency and effectiveness score of each strategy.

[0060] Based on the statistical analysis results, random numerical simulation is performed to generate simulation strategies. These simulation strategies can be generated through methods such as Monte Carlo simulation to ensure their effectiveness in different scenarios. At the same time, the corresponding historical security strategies are obtained based on the statistical analysis results. These historical security strategies are generated based on past experience and data and have been verified to be safe.

[0061] Compare and analyze the simulation strategy with the historical security strategy to obtain strategy difference data. The strategy difference data reflects the similarities and differences between the simulation strategy and the historical strategy in different aspects. Adjust the simulation strategy based on the strategy difference data to obtain the adjusted strategy. Perform sensitivity analysis on the adjusted strategy to obtain a sensitivity score. Sensitivity analysis can evaluate the stability and reliability of the adjusted strategy under different conditions.

[0062] The adjustment policies are screened according to the sensitivity scores to obtain the screening policy set. The policies in the screening policy set are all verified by sensitivity analysis and have high security and stability. The screening policy set is dynamically adjusted according to the preset dynamic adjustment rules to obtain the final dynamic security policy. Dynamic adjustment rules include time window adjustment rules: when a certain type of event occurs frequently within a specific time window, the weight of the relevant policies is automatically increased. Event-driven rules: when a new threat pattern is detected, the policy is dynamically adjusted according to predefined rules. Environmental change rules: when the system environment changes (such as changes in network topology, new equipment access, etc.), the relevant policies are automatically adjusted. Feedback mechanism rules: such as regular adjustment and optimization of the policy set through user feedback or system self-learning mechanism.

[0063] This embodiment can comprehensively consider multiple security factors and generate a more comprehensive initial security strategy through the fusion and strategy matching of multi-factor authentication data and cross-validation data, thereby reducing the security blind spots that may be caused by a single data source. Secondly, through hierarchical analysis and matrix analysis, the security strategy can be effectively decomposed and refined to ensure that the strategies at each level can be fully considered and optimized, and then the accuracy and applicability of the strategy can be further improved through iterative optimization and statistical analysis. Through the comparative analysis of random numerical simulation and historical security strategies, potential strategy differences can be discovered and adjusted in a timely manner to ensure that the generated security strategy can remain efficient and stable in different scenarios. Sensitivity analysis and screening mechanisms ensure the reliability and adaptability of the final strategy in practical applications. Finally, the introduction of dynamic adjustment rules enables the security strategy to be dynamically adjusted according to real-time data, greatly improving the ability and flexibility of the payment system to cope with various emergencies. In summary, this embodiment provides a comprehensive, dynamic, and intelligent payment security strategy generation method, which not only improves the security of the payment system, but also enhances the system's adaptability and response speed in different environments.

[0064] Reference Figure 2 As shown, a multi-channel data cross-verification payment system is applied to any of the multi-channel data cross-verification payment methods mentioned above, comprising: The collection module is used to obtain multi-channel payment data, analyze and read the multi-channel payment data, and obtain payment system data, user data, transaction data and payment scenario information; The analysis module is used to perform identity pre-verification analysis on user data to obtain corresponding identity authentication data, and perform multi-factor authentication analysis on user data based on payment scenario information to obtain multi-factor authentication data; An association module, the association module is used to map the payment system data to the identity verification data, and perform association analysis on the payment system data based on the multi-factor authentication data to obtain corresponding verification payment system data; A processing module, the processing module is used to perform risk assessment analysis on the payment system data according to the transaction data to obtain corresponding comprehensive risk data, and to perform cross-validation analysis on the comprehensive risk data based on the verified payment system data to obtain corresponding cross-validation data; The control module is used to perform policy analysis based on multi-factor authentication data and cross-validation data to obtain an initial security policy, and to perform a comprehensive analysis on all initial security policies to obtain a dynamic security policy.

[0065] A multi-channel data cross-verification payment system provided by the present invention realizes comprehensive data integration by acquiring multi-channel payment data and performing comprehensive analysis and reading of the data. This not only improves the utilization rate of data, but also ensures the consistency of data in the payment process, and enhances the overall security and reliability. Through multi-factor authentication analysis, combined with payment scenario information, multi-dimensional identity authentication is performed on user data, the accuracy and security of identity authentication are improved, and the security risks caused by the limitations of a single authentication method are effectively prevented. By mapping payment system data with identity authentication data, and performing correlation analysis in combination with multi-factor authentication data, verification payment system data is generated, and then risk assessment analysis is performed in combination with transaction data, so as to obtain more comprehensive and accurate comprehensive risk data. This helps to discover potential risks in a timely manner and improve the effectiveness of risk control. By performing strategy analysis based on multi-factor authentication data and cross-verification data, generating an initial security strategy, and obtaining a dynamic security strategy through comprehensive analysis, the payment security strategy can be dynamically adjusted according to changes in the real-time payment environment, thereby improving the adaptability and flexibility of the security strategy.

[0066] Reference Figure 3 As shown, the present invention also provides a multi-channel data cross-verification payment device, comprising: Memory, used to store programs; The processor is used to execute the program to implement each step of any one of the multi-channel data cross-verification payment methods mentioned above.

[0067] In this embodiment, the processor and the memory may be connected via a bus or other means. The memory may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a read-only memory, a flash memory, a hard disk, or a solid-state drive. The processor may be a general-purpose processor, such as a central processing unit, a digital signal processor, an application-specific integrated circuit, or one or more integrated circuits configured to implement the embodiments of the present invention.

[0068] The present invention also provides a storage medium storing computer instructions, wherein the computer instructions are used to enable a computer to execute any of the above methods.

[0069] It should be noted that technicians in the relevant technical field can clearly understand that for the convenience and conciseness of description, the specific working process of the system and each module described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0070] The above description is only a preferred embodiment of the present invention, and does not limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made by using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A multi-channel data cross-verification payment method, characterized in that: include: Obtain multi-channel payment data, analyze and read multi-channel payment data, and obtain payment system data, user data, transaction data and payment scenario information; Performing identity pre-verification analysis on the user data to obtain corresponding identity verification data, and performing multi-factor authentication analysis on the user data based on the payment scenario information to obtain multi-factor authentication data; Mapping the payment system data to the identity verification data, and performing correlation analysis on the payment system data based on the multi-factor authentication data to obtain corresponding verification payment system data; Performing risk assessment analysis on the payment system data according to the transaction data to obtain corresponding comprehensive risk data, and performing cross-validation analysis on the comprehensive risk data based on the verified payment system data to obtain corresponding cross-validation data; A policy analysis is performed based on the multi-factor authentication data and the cross-validation data to obtain an initial security policy, and a comprehensive analysis is performed on all the initial security policies to obtain a dynamic security policy.

2. The multi-channel data cross-verification payment method according to claim 1, characterized in that: The obtaining of multi-channel payment data, analyzing and reading the multi-channel payment data, and obtaining payment system data, user data, transaction data, and payment scenario information include: Collecting and aggregating payment data from multiple payment channels to obtain the multi-channel payment data, and classifying the multi-channel payment data according to a preset data classification rule to obtain an original classification result; Perform association analysis on the original classification results according to the preset data association rules to obtain associated classification data; Perform feature extraction processing on the associated classification data to obtain a feature vector set; perform dimensionality reduction processing on the feature vector set to obtain a reduced dimensionality vector set; The dimensionality reduction vector set is segmented according to the preset data segmentation rules to obtain payment system data, user data, transaction data and payment scenario information.

3. The multi-channel data cross-verification payment method according to claim 1, characterized in that: The performing identity pre-verification analysis on the user data to obtain corresponding identity verification data, and performing multi-factor authentication analysis on the user data based on the payment scenario information to obtain multi-factor authentication data, includes: Performing identity analysis on the user data according to preset identity authentication rules to obtain identity authentication parameters, and performing multi-dimensional comparison on the user data according to the identity authentication parameters to obtain an identity matching result; Performing credibility assessment on the user data according to the identity matching result to obtain the identity verification data; Extract keywords from the payment scenario information to obtain a scenario feature set, and perform hierarchical screening on the user data based on the scenario feature set to obtain multi-layer user features; Matching the multi-layer user features with the preset authentication factors to obtain an authentication factor set; Cross-validate the authentication factor set and the identity verification data to obtain a verification result matrix, and assign weights to the verification result matrix to obtain a weighted verification result; The user data is comprehensively evaluated based on the weighted verification result to obtain the multi-factor authentication data.

4. The multi-channel data cross-verification payment method according to claim 1, characterized in that: The mapping of the payment system data to the identity verification data, and performing correlation analysis on the payment system data according to the multi-factor authentication data to obtain corresponding verification payment system data, includes: Performing wavelet transform on the payment system data to obtain system time-frequency characteristics, and performing Fourier transform on the identity verification data to obtain identity frequency domain representation; Integrate and reduce the dimension of the system time-frequency features and the identity frequency domain representation to obtain a reduced dimension feature set, and perform nonlinear mapping on the payment system data based on the reduced dimension feature set to obtain mapped payment system data; Performing independent component analysis on the multi-factor authentication data to extract independent features to obtain an independent feature set, and performing association analysis on the mapped payment system data and the independent feature set to obtain an association rule set; Calculate the confidence and support of the association rule set to obtain the optimized rule set; Classifying the payment system data according to the optimization rule set to obtain classification results, performing cluster analysis on the classification results to obtain cluster clusters; performing anomaly identification on each cluster cluster according to a preset anomaly factor detection rule to obtain anomaly detection results; The anomaly detection results and classification results are weighted and fused to obtain preliminary verification data, which are then filtered and completed to obtain complete verification payment system data.

5. The multi-channel data cross-verification payment method according to claim 1, characterized in that: The step of performing risk assessment analysis on the payment system data according to the transaction data to obtain corresponding comprehensive risk data, and performing cross-validation analysis on the comprehensive risk data based on the verified payment system data to obtain corresponding cross-validation data includes: Performing time series analysis on the transaction data to obtain a transaction time series pattern, and classifying the payment system data according to the transaction time series pattern to obtain a system risk classification result; Performing deviation detection on the payment system data according to the system risk classification result to obtain a system deviation index, and performing risk quantitative analysis on the payment system data according to the system deviation index and preset risk assessment rules to obtain a system risk value; Conduct trend analysis on system risk values ​​according to preset risk calculation rules to obtain risk change data; conduct comprehensive analysis on risk change data and system risk values ​​to generate comprehensive risk data; Performing a correlation analysis on the comprehensive risk data based on the verified payment system data to obtain a risk correlation factor, and cross-validating the comprehensive risk data based on the risk correlation factor to obtain a preliminary cross-validation result; Correct the preliminary crossover results according to the preset correction rules to obtain the correction verification results, and perform grade analysis on the correction verification results according to the preset verification standards to obtain the verification grade; The validation level and correction validation results are processed comprehensively to obtain cross-validation data.

6. The multi-channel data cross-verification payment method according to claim 1, characterized in that: The performing of policy analysis based on the multi-factor authentication data and the cross-validation data to obtain an initial security policy, and performing a comprehensive analysis on all the initial security policies to obtain a dynamic security policy, including: Fusing the multi-factor authentication data and the cross-validation data to obtain fused data, and performing policy matching on the fused data according to a preset security rule set to obtain an initial security policy; Perform hierarchical analysis on the initial security policy to obtain the policy hierarchy, and perform matrix analysis based on the policy hierarchy to obtain the decision weight set; Iteratively optimize the decision weight set to obtain an optimized weight set, and perform statistical analysis on the optimized weight set to obtain a statistical analysis result; Perform random numerical simulation based on statistical analysis results, generate simulation strategies, and obtain corresponding historical security strategies based on statistical analysis results; Compare and analyze the simulation strategy with the historical security strategy to obtain strategy difference data; The simulation strategy is adjusted according to the strategy difference data to obtain the adjusted strategy, and a sensitivity analysis is performed on the adjusted strategy to obtain a sensitivity score; The adjustment strategies are screened according to the sensitivity scores to obtain a screening strategy set; The screening policy set is dynamically adjusted according to preset dynamic adjustment rules to obtain the dynamic security policy.

7. A multi-channel data cross-verification payment system, characterized in that: The multi-channel data cross-verification payment method applied to any one of claims 1 to 6 above comprises: A collection module, which is used to obtain multi-channel payment data, analyze and read the multi-channel payment data, and obtain payment system data, user data, transaction data and payment scenario information; An analysis module, the analysis module is used to perform identity pre-verification analysis on the user data to obtain corresponding identity verification data, and perform multi-factor authentication analysis on the user data based on the payment scenario information to obtain the multi-factor authentication data; an association module, the association module being used to map the payment system data to the identity verification data, and to perform association analysis on the payment system data according to the multi-factor authentication data to obtain corresponding verification payment system data; A processing module, the processing module is used to perform risk assessment analysis on the payment system data according to the transaction data to obtain corresponding comprehensive risk data, and to perform cross-validation analysis on the comprehensive risk data based on the verification payment system data to obtain corresponding cross-validation data; A control module is used to perform a policy analysis based on the multi-factor authentication data and the cross-validation data to obtain an initial security policy, and to perform a comprehensive analysis on all the initial security policies to obtain a dynamic security policy.

8. A multi-channel data cross-verification payment device, characterized in that: include: Memory, used to store programs; A processor is used to execute the program to implement each step of a multi-channel data cross-verification payment method as described in any one of claims 1-6.

9. A storage medium, characterized in that: Computer instructions are stored, and the computer instructions are used to make a computer execute the method according to any one of claims 1 to 6.

Images