Data information risk monitoring method and device for cross-border payment

Abstract

The invention provides a data information risk monitoring method and device for cross-border payment, and relates to the technical field of data risk monitoring, and the method comprises the steps: obtaining a first user database; performing multiple verification on the first real-time login identity information; dynamically monitoring the first real-time behavior information, and performing comparative analysis on the first real-time behavior information and the first user behavior information; acquiring a distributed payment architecture of the multilateral cross-border payment platform, and drawing a first payment data transmission path in combination with the first real-time behavior information; performing path risk analysis on the first payment data transmission path; performing normalized weighted calculation on the first identity risk index, the first behavior risk index and the first path risk index; and carrying out payment risk early warning on the first user. Through the method and the device, the technical problem of relatively low cross-border payment efficiency due to the fact that a centralized architecture depends on a single payment channel or a few payment channels in the prior art can be solved, and the technical effect of improving the payment efficiency is achieved.

Description

Technical Field

[0001] The present application relates to the technical field of data risk monitoring, and in particular to a method and device for monitoring data information risks for cross-border payments. Background Art

[0002] With the popularization of Internet technology and mobile payment, cross-border payment has gradually transitioned from traditional bank transfers to multilateral payment networks dominated by online payment platforms and fintech companies. However, although these emerging technologies have brought convenience and efficiency to cross-border payments, the existing cross-border payment system still has many defects and risks.

[0003] At present, existing technologies mainly rely on centralized payment architectures, which often rely on a single or a few payment channels, resulting in limited payment processing speeds, especially during peak periods when payment delays or interruptions are prone to occur. For example, traditional cross-border payments may take several days to complete, causing inconvenience to companies' cash flow management and supply chain operations. Secondly, due to differences in compliance requirements such as financial supervision and financing in different regions, cross-border payment transactions are susceptible to scrutiny and obstruction, which further increases the complexity and uncertainty of cross-border payments.

[0004] In summary, the existing technology has technical problems in that the payment processing speed is limited due to the centralized architecture relying on a single or a few payment channels, which further affects the efficiency of cross-border payments. Summary of the invention

[0005] The purpose of this application is to provide a data information risk monitoring method and device for cross-border payments, so as to solve the technical problem in the prior art that the payment processing speed is limited due to the centralized architecture relying on a single or a few payment channels, further affecting the efficiency of cross-border payments.

[0006] In view of the above problems, the present application provides a data information risk monitoring method and device for cross-border payments.

[0007] In a first aspect, the present application provides a data information risk monitoring method for cross-border payment, which is implemented by a data information risk monitoring device for cross-border payment, including: obtaining a first user database, the first user database refers to a database of a first user in the multilateral cross-border payment platform, and the first user database includes the first user identity information and the first user behavior information of the first user; performing multiple verifications on the first real-time login identity information in combination with the first user identity information to obtain a first identity risk index, wherein the first real-time login identity information refers to the real-time login identity information of the first user; dynamically monitoring the first real-time behavior information of the first user, and introducing a behavior comparison mechanism to perform a comparative analysis between the first real-time behavior information and the first user behavior information to obtain a first behavior risk index; obtaining a distributed payment architecture of the multilateral cross-border payment platform, and drawing a first payment data transmission path in combination with the first real-time behavior information; reading a predetermined path neural network strategy to perform path risk analysis on the first payment data transmission path to obtain a first path risk index; performing normalized weighted calculation on the first identity risk index, the first behavior risk index and the first path risk index to obtain a first risk value; when the first risk value is not at a risk threshold, issuing a payment risk warning to the first user.

[0008] In the second aspect, the present application also provides a data information risk monitoring device for cross-border payment, which is used to execute the data information risk monitoring method for cross-border payment as described in the first aspect, including: a first user database acquisition module, the first user database acquisition module is used to acquire a first user database, the first user database refers to the database of the first user in the multilateral cross-border payment platform, and the first user database includes the first user identity information and the first user behavior information of the first user; a first identity risk index acquisition module, the first identity risk index acquisition module is used to perform multiple verifications on the first real-time login identity information in combination with the first user identity information to obtain a first identity risk index, wherein the first real-time login identity information refers to the real-time login identity information of the first user; a first behavior risk index acquisition module, the first behavior risk index acquisition module is used to dynamically monitor the first real-time behavior information of the first user, and introduce behavior comparison The mechanism performs a comparative analysis between the first real-time behavior information and the first user behavior information to obtain a first behavior risk index; a first payment data transmission path drawing module, the first payment data transmission path drawing module is used to obtain the distributed payment architecture of the multilateral cross-border payment platform, and draw the first payment data transmission path in combination with the first real-time behavior information; a first path risk index obtaining module, the first path risk index obtaining module is used to read a predetermined path neural network strategy to perform path risk analysis on the first payment data transmission path to obtain a first path risk index; a first risk value obtaining module, the first risk value obtaining module is used to perform a normalized weighted calculation on the first identity risk index, the first behavior risk index and the first path risk index to obtain a first risk value; a payment risk warning module, the payment risk warning module is used to issue a payment risk warning to the first user when the first risk value is not within the risk threshold.

[0009] One or more technical solutions provided in this application have at least the following technical effects or advantages: By acquiring a first user database, the first user database refers to a database of a first user in the multilateral cross-border payment platform, and the first user database includes first user identity information and first user behavior information of the first user; performing multiple verifications on the first real-time login identity information in combination with the first user identity information to obtain a first identity risk index, wherein the first real-time login identity information refers to the real-time login identity information of the first user; dynamically monitoring the first real-time behavior information of the first user, and introducing a behavior comparison mechanism to perform a comparison analysis between the first real-time behavior information and the first user behavior information to obtain a first behavior risk index; acquiring a distributed payment architecture of the multilateral cross-border payment platform, and drawing a first payment data transmission path in combination with the first real-time behavior information; reading a predetermined path neural network strategy to perform a path risk analysis on the first payment data transmission path to obtain a first path risk index; performing normalized weighted calculations on the first identity risk index, the first behavior risk index and the first path risk index to obtain a first risk value; and when the first risk value is not at the risk threshold, issuing a payment risk warning to the first user, that is, by achieving the technical goal of combining the distributed payment architecture with dynamic risk monitoring in the cross-border payment process, the technical effects of improving payment efficiency, reducing delay risk, and enhancing data security and compliance are achieved.

[0010] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented according to the contents of the specification, and in order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are specifically cited below. It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easy to understand through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the technical solutions in the present application or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only exemplary, and for ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0012] Figure 1 A flowchart of the data information risk monitoring method for cross-border payment used in this application; Figure 2 This is a schematic diagram of the structure of the data information risk monitoring device used for cross-border payment in this application.

[0013] Description of reference numerals: A first user database acquisition module 11, a first identity risk index acquisition module 12, a first behavior risk index acquisition module 13, a first payment data transmission path drawing module 14, a first path risk index acquisition module 15, a first risk value acquisition module 16, and a payment risk early warning module 17. DETAILED DESCRIPTION

[0014] This application solves the technical problem in the prior art that the payment processing speed is limited due to the centralized architecture relying on a single or a few payment channels, which further affects the efficiency of cross-border payments by providing a data information risk monitoring method and device for cross-border payments. The technical goal of combining a distributed payment architecture with dynamic risk monitoring in the cross-border payment process is achieved, achieving the technical effect of improving payment efficiency, reducing delay risks, and enhancing data security and compliance.

[0015] Below, the technical solutions in the present application will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments of the present application. It should be understood that the present application is not limited to the example embodiments described herein. Based on the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application. It should also be noted that, for the convenience of description, only the parts related to the present application are shown in the accompanying drawings, rather than all of them.

[0016] For example, please refer to the attached Figure 1 The present application provides a data information risk monitoring method for cross-border payment, which is applied to a data information risk monitoring device for cross-border payment, and specifically includes the following steps: Step 1: Obtain a first user database, where the first user database refers to a database of a first user in the multilateral cross-border payment platform, and the first user database includes first user identity information and first user behavior information of the first user.

[0017] Specifically, the first user database is obtained. The first user database refers to the database of a random user (referred to as the first user) in the multilateral cross-border payment platform, which is used as the first user database. The first user database refers to the collection of all relevant information of the first user in the cross-border payment platform, including the identity information of the first user, such as the name, ID number or passport number of the historical login, etc., which is used to confirm the legal identity of the first user. In addition, the first user database also contains the behavior information of the first user, such as the activity information of the historical login, etc., which is used to analyze the user's transaction habits, so as to determine whether there are abnormal transactions or potential risks.

[0018] Step 2: Perform multiple verifications on the first real-time login identity information in combination with the first user identity information to obtain a first identity risk index, wherein the first real-time login identity information refers to the real-time login identity information of the first user.

[0019] Specifically, the first real-time login identity information is the dynamic login identity information provided by the first user when logging in in real time, such as an input password, a received verification code, or the biometric information used. The first real-time login identity information is verified in combination with the first user identity information using a variety of verification methods, such as biometrics, password verification, etc., to ensure the authenticity and security of the user identity.

[0020] Step three: dynamically monitor the first real-time behavior information of the first user, and introduce a behavior comparison mechanism to compare and analyze the first real-time behavior information with the first user behavior information to obtain a first behavior risk index.

[0021] Specifically, the first real-time behavior information refers to the real-time behavior activity information of the first user. The first real-time behavior information of the first user is dynamically monitored, and the real-time activity data of the user on the network or platform is continuously tracked and recorded. A behavior comparison mechanism is introduced to compare and analyze the first real-time behavior information with the first user behavior information, compare the real-time behavior of the first user with its historical behavior, find changes in the first user's behavior, determine whether the first user's behavior is abnormal, and then identify potential risks, convert it into a quantitative indicator, and obtain the first behavior risk index, which is used to determine whether additional verification or monitoring is required.

[0022] Step 4: Obtain the distributed payment architecture of the multilateral cross-border payment platform, and draw a first payment data transmission path in combination with the first real-time behavior information.

[0023] Specifically, the distributed payment architecture of the multilateral cross-border payment platform is obtained. Among them, since different parts of the cross-border payment platform may be distributed in different geographical locations or servers, the distributed payment architecture refers to the path architecture of payment data transmission. Next, the first payment data transmission path is drawn in combination with the first real-time behavior information, which means combining the real-time behavior data of the first user with the architecture of the payment platform to generate the flow of user payment data. For example, the first real-time behavior information includes the time when the first user initiated the payment, the device used, the payment amount, etc. And according to the first real-time behavior information, it is drawn how the payment data is transmitted between the various nodes of the platform. For example, if the first user initiates a payment in Beijing, the payment data first reaches the Asian node, then is transmitted to the payment processing node in Europe, and then reaches the American node where the payee is located.

[0024] Step 5: Read the predetermined path neural network strategy to perform path risk analysis on the first payment data transmission path to obtain a first path risk index.

[0025] Specifically, the neural network strategy for the predetermined path is read and a pre-set neural network-based algorithm is used to process the risk analysis of the data transmission path. The neural network strategy can identify complex patterns and make predictions by learning from a large amount of historical data. Based on previous transmission data and path performance, it can accurately assess the risk of the current path.

[0026] Next, the path risk analysis is performed on the first payment data transmission path, and the specific payment path is detected and evaluated to determine the risks that may be encountered when transmitting payment data on this path. For example, if the transmission rate of a node in the path suddenly drops or the load is too high, the impact of the abnormal situation on data security and transmission efficiency is evaluated to obtain the first path risk index and quantify the risk level of the current path. For example, the path risk index may be 0.3 (indicating low risk) or 0.8 (indicating high risk). The higher the first path risk index, the greater the potential risk in the path, and further measures need to be taken, such as changing the transmission path or increasing data monitoring. Conversely, the risk is smaller.

[0027] Step six: Perform normalized weighted calculation on the first identity risk index, the first behavior risk index and the first path risk index to obtain a first risk value.

[0028] Specifically, the first identity risk index, the first behavior risk index, and the first path risk index are normalized and converted to the same numerical range, such as between 0 and 1. Normalization allows risks of different dimensions to be compared and calculated under the same standard, making them more comparable. Different weights are assigned to each risk index through weighted calculation. The weight reflects the degree of impact on the overall risk. Different risk types may have different influences on the final risk value. For example, identity risk may be more important, and the weight can be set to 0.5, while the weights of behavior risk and path risk are 0.3 and 0.2 respectively. Each risk index is multiplied by its respective weight through weighting, and then the results are added to obtain the first risk value, which represents an assessment of the overall risk of the entire payment process. The higher the first risk value, the greater the overall risk, and more security measures may need to be taken. Conversely, the risk is smaller.

[0029] Step 7: When the first risk value is not within the risk threshold, a payment risk warning is issued to the first user.

[0030] Specifically, when the first risk value is not within the risk threshold, after calculating the first risk value, the value is compared with the preset risk threshold. The risk threshold is a value preset by a person skilled in the art based on actual conditions to determine whether the risk is acceptable. For example, the risk threshold is set to 0.7. If the first risk value is greater than 0.7, it means that the risk exceeds the acceptable range and needs to be processed, and a risk warning is issued to the user, that is, a payment risk warning is issued; if it is lower than 0.7, it means that the risk is within a controllable range. For example, a payment risk warning includes informing the user of potential risks in the payment process through text messages, emails, or APP notifications. The content of the warning may include specific risk information, reminding the user to take measures, such as suspending payment or performing identity verification.

[0031] The data information risk monitoring method for cross-border payments is applied to a data information risk monitoring device for cross-border payments, which can achieve the technical goal of combining distributed payment architecture with dynamic risk monitoring in the cross-border payment process, and achieve the technical effects of improving payment efficiency, reducing delay risks, and enhancing data security and compliance.

[0032] Furthermore, the present application also includes: Read a predetermined identity authentication category, and extract a first category from the predetermined identity authentication category, wherein the first category has an identifier of a first importance coefficient; match the first verification information of the first category in the first real-time login identity information, wherein the first verification information includes a first verification number and a first verification duration; weight the first verification number and the first verification duration to obtain a first verification index, and combine the first importance coefficient to obtain a first effective verification risk index for the first category; establish an effective verification risk index set for the predetermined identity authentication category based on the first effective verification risk index; and select the maximum risk index in the effective verification risk index set as the first identity risk index.

[0033] Specifically, the predetermined identity authentication category is a predefined standard or step required for identity authentication, such as biometrics, password verification, etc. Reading the predetermined identity authentication category refers to reading relevant information from the pre-set identity authentication rules or categories, and the extracted first category represents a random verification method therein. The first category has an identifier of a first importance coefficient, which is used to mark the importance of the first category. The first importance coefficient is a predetermined value, such as 0.8, which is used to indicate the importance of the verification method of the first category in the predetermined identity authentication category. Among them, the importance of password verification in the predetermined identity authentication category is relatively low, and the importance of biometrics is relatively high. For example, password verification includes verification codes and digital passwords, and biometrics includes faces and fingerprints.

[0034] Next, during the real-time login process of the first user, the verification information corresponding to the first category is obtained as the first verification information. The first verification information includes the number of verifications and the verification duration, which are the first number of verifications and the first verification duration. The number of verifications is the number of times the first user uses the first category for verification within the first verification duration, and the first verification duration indicates the time spent using the first category for verification, which is then used to analyze whether the user's behavior is normal.

[0035] Then, the first verification times and the first verification duration are weighted to calculate the first verification index. For example, if the importance of the verification times is higher than the verification duration, the verification times may account for 70% of the weight and the verification duration may account for 30%. After weighting, a verification index is obtained, such as 0.6. Combined with the first importance coefficient (such as 0.8), the effective verification risk index of the first category is obtained, such as 0.48, which is used to measure the risk of this verification method.

[0036] Subsequently, according to the method for obtaining the first valid verification risk index, the valid verification risk index of each category is obtained, and multiple valid verification risk indices are grouped into a set to obtain a valid verification risk index set. The valid verification risk index set includes the risk indices of all categories.

[0037] Finally, the risk index with the maximum value in the valid verification risk index set is selected as the first identity risk index, which is used to determine the overall risk of the first user's current login. If the value of the first identity risk index is too high, further measures are taken, such as triggering additional verification or blocking login.

[0038] By reading the identity authentication category, matching the user's real-time verification information, weightedly calculating the risk index, and finally selecting the highest risk value, we can ensure the security of dynamic evaluation of user identity authentication, identify which method has greater potential risks, and thus improve security.

[0039] Furthermore, the present application also includes: Extract first historical behavior information from the first user behavior information, where the first historical behavior information refers to first historical web page browsing information of the first user; obtain a first website corresponding to the first web page in the first historical web page browsing information, and count the first browsing time of the first website; construct a first behavior portrait of the first user according to a first mapping relationship between the first website and the first browsing time; compare the first real-time behavior portrait obtained by analyzing the first real-time behavior information with the first behavior portrait to obtain a first behavior portrait similarity index; and determine the first behavior risk index based on the first behavior portrait similarity index.

[0040] Specifically, the first historical behavior information refers to the historical web browsing information of the first user. With the authorization of the first user, the historical web browsing information is extracted from the historical activity information of the first user as the first historical web browsing information.

[0041] Next, the website corresponding to the random web page in the first historical browsing web page information is obtained as the first website corresponding to the first web page. At the same time, the browsing time of the first website is counted, and the time spent by the first user on the first website is calculated as the first browsing time, which is used to analyze the interest and activity of the first user.

[0042] Then, a mapping relationship between the first website and the first browsing time is constructed as the first mapping relationship. The first mapping relationship refers to the connection between the first website and the time spent by the first user on the first website, reflecting the importance the first user attaches to the content of the website. According to the method for obtaining the first mapping relationship, multiple mapping relationships corresponding to the first historical behavior information are obtained. Multiple mapping relationships are assembled to obtain a behavior profile of the first user as the first behavior profile, forming a comprehensive image of user preferences, such as the first user may show a high interest in a certain type of product or service.

[0043] Subsequently, by analyzing the first behavior portrait corresponding to the first user behavior information, the behavior portrait of the first user corresponding to the first real-time behavior information is analyzed as the first real-time behavior portrait. The first real-time behavior portrait may include web pages browsed and operation behaviors of the first user in the current session. The first real-time behavior portrait obtained by analyzing the first real-time behavior information is compared with the first behavior portrait, that is, the current activity record of the first user is analyzed and compared with its historical record to obtain the first behavior portrait similarity index, which reflects the similarity between the current behavior of the first user and the past behavior.

[0044] Finally, the first behavior risk index is determined based on the first behavior portrait similarity index, that is, the risk level of the user behavior is quantified according to the similarity index. For example, if the first behavior risk index is 0.8, it may indicate that the user behavior is relatively normal and the first behavior risk index is low, such as 0.2; otherwise, it is high.

[0045] By extracting users' historical and real-time behavior information, a complete user behavior portrait is established, and ultimately a behavior risk index is derived, providing strong support for preventing potential risks.

[0046] Furthermore, the present application also includes: Obtain a second behavior portrait corresponding to the second historical behavior information in the first user behavior information; analyze the second behavior portrait to obtain the second browsing time of the first website; take the average of the first browsing time and the second browsing time as the first browsing time benchmark of the first user for the first website; obtain the first real-time browsing time of the first website in the first real-time behavior portrait; calculate the first time difference between the first real-time browsing time and the first browsing time benchmark; perform normalized weighted calculation on the first time difference to obtain the first behavior portrait similarity index.

[0047] Specifically, with the authorization of the first user, another historical web browsing information other than the first historical web browsing information, namely, the second historical web browsing information, is randomly extracted from the first user's behavior information. The second historical web browsing information of the first user is used as the second historical behavior information. According to the method of obtaining the first behavior portrait by analyzing the first historical behavior information in the first user's behavior information, the user behavior portrait corresponding to the second historical behavior information is analyzed as the second behavior portrait, which helps to construct the behavior pattern of the first user in different time periods, so as to facilitate the subsequent risk assessment.

[0048] Next, by examining the data in the second behavior profile, the browsing time of the first user on the first website is calculated as the second browsing time. If the second browsing time of the first user on the first website is not much different from the first browsing time, it can reflect the first user's continued attention to the content of the website, so as to evaluate the change of user interest.

[0049] Then, the average of the first browsing time and the second browsing time is taken to calculate the average of the first user's historical browsing time on the first website, which is used as a benchmark for the first user's first browsing time on the first website and as a reference for subsequent analysis to help determine whether the first user's current browsing behavior is normal.

[0050] Next, according to the mapping relationship of the first website in the first real-time behavior portrait, the browsing time corresponding to the first website is obtained as the first real-time browsing time, and the time the first user currently stays on the first website is identified.

[0051] Subsequently, the difference between the first real-time browsing time and the first browsing time benchmark is calculated as the first time difference, and the difference between the current behavior of the first user and his historical average behavior is determined to determine whether the behavior of the first user deviates from his normal mode.

[0052] Finally, the first time difference is normalized, that is, standardized so as to convert it into a comparable index, and weighted calculation is performed to obtain the first behavior portrait similarity index, which further reflects the similarity between the current behavior of the first user and his historical behavior.

[0053] By extracting relevant portraits from the user's historical behavior information, calculating the average browsing time and comparing it with the real-time browsing time, the difference between the user's current behavior and historical behavior can be analyzed. Finally, the similarity index calculated by normalization can effectively evaluate whether the user's behavior is abnormal, thereby providing strong support for security management.

[0054] Furthermore, the present application also includes: Obtain a first co-edge user set that meets a predetermined co-edge similarity constraint with the first user; obtain first co-edge real-time behavior information of the first co-edge user in the first co-edge user set; compare a first co-edge real-time behavior portrait obtained by analyzing the first co-edge real-time behavior information with the first behavior portrait to obtain a first co-edge behavior portrait similarity index; use the first co-edge behavior portrait similarity index as an adjustment coefficient to adjust the first behavior portrait similarity index in real time.

[0055] Specifically, the predetermined common edge similarity constraint is used to identify users with common or similar characteristics, such as multiple users working in imported textiles in adjacent areas, etc. A first common edge user set that meets the predetermined common edge similarity constraint with the first user is obtained, and other users similar to the first user in certain characteristics are identified for subsequent comparative analysis.

[0056] Next, a first co-edge user randomly extracted from the first co-edge user set is obtained, and the co-edge real-time behavior information of the first co-edge user is obtained as the first co-edge real-time behavior information, that is, a user is selected from the co-edge user set, and his current behavior data is extracted to reflect the current interest and activity level of the user.

[0057] Then, according to the method of analyzing the first behavior portrait corresponding to the first user behavior information, the first co-edge real-time behavior information is analyzed to obtain the first co-edge real-time behavior portrait. The first co-edge real-time behavior portrait is compared with the first behavior portrait, that is, the behavior characteristics of the first co-edge user are matched with the behavior characteristics of the first user, and the first co-edge behavior portrait similarity index is calculated to reflect the similarity between the two user behaviors.

[0058] Finally, the first co-edge behavior portrait similarity index is used as the adjustment coefficient to make real-time adjustments to the first behavior portrait similarity index. That is, the similarity of the co-edge users is used to correct the behavior similarity index of the first user. The risk level of the first user is assessed more accurately through the information of the co-edge users.

[0059] By identifying the set of co-edge users with similar characteristics to the first user, obtaining their real-time behavior information and comparing them, the co-edge behavior portrait similarity index is calculated. Finally, using this index as an adjustment coefficient, the behavior portrait similarity index of the first user can be corrected in real time, thereby improving the accuracy of the system's analysis of user behavior, enhancing the understanding of user behavior, and providing more powerful data support for risk management.

[0060] Furthermore, the present application also includes: The predetermined common edge similarity constraints include predetermined domain scope constraints and predetermined trade industry constraints.

[0061] Specifically, the predetermined common edge similarity constraints include predetermined domain range constraints. When selecting common edge users, the user's geographical location or activity area is considered to ensure that the selected users are in a similar geographical range. For example, if the first user is located in Beijing, users who are also in the Beijing area are given priority to improve the effectiveness of the similarity analysis.

[0062] In addition, the predetermined co-edge similarity constraints include predetermined trade industry constraints, so when selecting co-edge users, the industry background or business activities of the users are considered. For example, if the first user is engaged in a company selling electronic products, other users engaged in similar industries, such as companies selling home appliances or mobile phone accessories, are selected, thereby better evaluating users with similar business characteristics to the first user and enhancing the relevance of the co-edge user set.

[0063] By pre-setting common edge similarity constraints, we ensure that the selected common edge users are not only geographically close, but also have certain similarities in business activities, thereby providing a more accurate data basis for subsequent risk assessment and behavior analysis.

[0064] Furthermore, the present application also includes: Acquire a first transmission node of the first payment data transmission path; obtain a first-level neighborhood node set of the first transmission node in combination with the distributed payment architecture; randomly sample the first-level neighborhood node set to obtain a first preset number of first target neighborhood nodes, the first target neighborhood nodes including the first neighborhood node; obtain a second-level neighborhood node set of the first neighborhood node in combination with the distributed payment architecture; randomly sample the second-level neighborhood node set to obtain a second preset number of second target neighborhood nodes; obtain a second-level state index based on the second node transmission state fused with the second target neighborhood node, calibrate the first neighborhood node transmission state of the first neighborhood node, and obtain a first neighborhood node effective transmission state index; calibrate the first transmission state of the first transmission node according to the first neighborhood node effective transmission state index to obtain a first effective transmission state index; establish a first effective transmission state index set of the first payment data transmission path based on the first effective transmission state index; determine the first path risk index based on the minimum effective transmission state index value obtained by screening the first effective transmission state index set.

[0065] Specifically, a first transmission node of a first payment data transmission path is randomly obtained. For example, the first transmission node is a server or a data processing center responsible for receiving and transmitting payment data.

[0066] Next, based on the distributed architecture, other nodes directly connected to the first transmission node are determined as a first-level neighbor node set. For example, the first-level neighbor node set includes other data processing servers in Asia.

[0067] Then, a certain number of nodes are randomly selected from the first-level neighborhood node set for detailed analysis as first target neighborhood nodes for subsequent transmission status analysis. The first preset number is customized by those skilled in the art according to actual conditions. The first target neighborhood node includes one or more first neighborhood nodes.

[0068] Next, the secondary neighborhood node set of the first neighborhood node is obtained in combination with the distributed payment architecture, that is, other nodes connected to the first neighborhood node are identified as the secondary neighborhood node set, such as the secondary neighborhood node set includes nodes in other regions, such as a European data processing node connected to an Asian server.

[0069] Then, the secondary neighborhood node set is randomly sampled, and a certain number of nodes are selected from the secondary neighborhood node set for further analysis to obtain a second preset number of second target neighborhood nodes to provide information for subsequent transmission state calibration.

[0070] Next, the secondary state index is obtained according to the second node transmission state of the fused second target neighboring node, such as by monitoring the transmission rate, transmission load and transmission accuracy of the second node. The first neighboring node transmission state of the first neighboring node is calibrated by the secondary state index, and the transmission state of the first neighboring node is corrected to obtain the effective transmission state index of the first neighboring node. For example, the transmission state of the second target neighboring node is delayed, resulting in the need to adjust the transmission state of the first neighboring node.

[0071] Next, the first transmission state of the first transmission node is calibrated according to the first neighboring node effective transmission state index, and the state of the first transmission node is corrected using the transmission state of the first neighboring node to obtain a first effective transmission state index.

[0072] Based on the first valid transmission status index, a first valid transmission status index set of the first payment data transmission path is formed, and the valid status indexes of all transmission nodes are combined together to construct a complete data transmission status as the first valid transmission status index set.

[0073] Finally, according to the minimum valid transmission state index value obtained by screening the first valid transmission state index set, by analyzing the state indexes of all transmission nodes, the lowest state value is screened out, and the first path risk index is determined, which is used as the basis for risk assessment of the path, indicating that the path has a higher risk.

[0074] By identifying the transmission nodes and their neighboring nodes in the payment path, the transmission status of each node is gradually calibrated, and finally a valid state index set of the transmission path is constructed. The minimum state value is screened out, and the overall risk index of the path is determined, providing more accurate risk management for payment data transmission.

[0075] Furthermore, the present application also includes: Read the predetermined transmission status characteristics, and monitor the transmission status of each transmission node based on the predetermined transmission status characteristics to obtain the transmission status of each node, wherein the predetermined transmission status characteristics include transmission rate, transmission load and transmission accuracy.

[0076] Specifically, the predetermined transmission status characteristics refer to the parameters or indicators of the transmission status that are pre-set, which are used to measure the performance of data transmission. Reading the predetermined transmission status characteristics ensures that the performance of each node can be fully understood when monitoring the payment path. For example, the predetermined transmission status characteristics include transmission rate, transmission load and transmission accuracy, which reflect the quality of data transmission.

[0077] Based on the predetermined transmission status characteristics, the transmission status of each transmission node is monitored, and the status of each node in the path is detected in real time. For example, the current data transmission rate and load of each node are detected to find potential performance bottlenecks or abnormal nodes.

[0078] The transmission rate refers to the amount of data that each node can process per unit time. The higher the transmission rate, the better the performance of the node, and vice versa.

[0079] The transmission load refers to the ratio of the amount of data a node is processing at a certain moment to its maximum processing capacity. The higher the transmission load, the performance of the node may be affected, and the possibility of transmission delay or failure will increase. Conversely, the lower the transmission load, the better.

[0080] Transmission accuracy refers to the proportion of data that is transmitted without errors or packet loss. The higher the transmission accuracy, the more reliable the data transmission, and vice versa.

[0081] By reading predetermined transmission status characteristics such as transmission rate, transmission load and transmission accuracy, it is possible to monitor each transmission node in the payment path, promptly discover and resolve node performance issues, and ensure stable and secure data transmission during cross-border payments.

[0082] In summary, the data information risk monitoring method for cross-border payment provided by this application has the following technical effects: By acquiring a first user database, the first user database refers to a database of a first user in the multilateral cross-border payment platform, and the first user database includes first user identity information and first user behavior information of the first user; performing multiple verifications on the first real-time login identity information in combination with the first user identity information to obtain a first identity risk index, wherein the first real-time login identity information refers to the real-time login identity information of the first user; dynamically monitoring the first real-time behavior information of the first user, and introducing a behavior comparison mechanism to perform a comparison analysis between the first real-time behavior information and the first user behavior information to obtain a first behavior risk index; acquiring a distributed payment architecture of the multilateral cross-border payment platform, and drawing a first payment data transmission path in combination with the first real-time behavior information; reading a predetermined path neural network strategy to perform a path risk analysis on the first payment data transmission path to obtain a first path risk index; performing normalized weighted calculations on the first identity risk index, the first behavior risk index and the first path risk index to obtain a first risk value; and when the first risk value is not at the risk threshold, issuing a payment risk warning to the first user, that is, by achieving the technical goal of combining the distributed payment architecture with dynamic risk monitoring in the cross-border payment process, the technical effects of improving payment efficiency, reducing delay risk, and enhancing data security and compliance are achieved.

[0083] Embodiment 2: Based on the data information risk monitoring method for cross-border payment in the above embodiment, the present application also provides a data information risk monitoring device for cross-border payment, please refer to the attached Figure 2 ,include: A first user database acquisition module 11, the first user database acquisition module 11 is used to acquire a first user database, the first user database refers to a database of a first user in a multilateral cross-border payment platform, and the first user database includes the first user identity information and the first user behavior information of the first user; a first identity risk index acquisition module 12, the first identity risk index acquisition module 12 is used to perform multiple verifications on the first real-time login identity information in combination with the first user identity information to obtain a first identity risk index, wherein the first real-time login identity information refers to the real-time login identity information of the first user; a first behavior risk index acquisition module 13, the first behavior risk index acquisition module 13 is used to dynamically monitor the first real-time behavior information of the first user, and introduce a behavior comparison mechanism to compare and analyze the first real-time behavior information with the first user behavior information to obtain A first behavioral risk index; a first payment data transmission path drawing module 14, the first payment data transmission path drawing module 14 is used to obtain the distributed payment architecture of the multilateral cross-border payment platform, and draw the first payment data transmission path in combination with the first real-time behavioral information; a first path risk index obtaining module 15, the first path risk index obtaining module 15 is used to read a predetermined path neural network strategy to perform path risk analysis on the first payment data transmission path to obtain a first path risk index; a first risk value obtaining module 16, the first risk value obtaining module 16 is used to perform normalized weighted calculation on the first identity risk index, the first behavioral risk index and the first path risk index to obtain a first risk value; a payment risk warning module 17, the payment risk warning module 17 is used to issue a payment risk warning to the first user when the first risk value is not within the risk threshold.

[0084] Furthermore, the data information risk monitoring device for cross-border payment is also used to: Read a predetermined identity authentication category, and extract a first category from the predetermined identity authentication category, wherein the first category has an identifier of a first importance coefficient; match the first verification information of the first category in the first real-time login identity information, wherein the first verification information includes a first verification number and a first verification duration; weight the first verification number and the first verification duration to obtain a first verification index, and combine the first importance coefficient to obtain a first effective verification risk index for the first category; establish an effective verification risk index set for the predetermined identity authentication category based on the first effective verification risk index; and select the maximum risk index in the effective verification risk index set as the first identity risk index.

[0085] Furthermore, the data information risk monitoring device for cross-border payment is also used to: Extract first historical behavior information from the first user behavior information, where the first historical behavior information refers to first historical web page browsing information of the first user; obtain a first website corresponding to the first web page in the first historical web page browsing information, and count the first browsing time of the first website; construct a first behavior portrait of the first user according to a first mapping relationship between the first website and the first browsing time; compare the first real-time behavior portrait obtained by analyzing the first real-time behavior information with the first behavior portrait to obtain a first behavior portrait similarity index; and determine the first behavior risk index based on the first behavior portrait similarity index.

[0086] Furthermore, the data information risk monitoring device for cross-border payment is also used to: Obtain a second behavior portrait corresponding to the second historical behavior information in the first user behavior information; analyze the second behavior portrait to obtain the second browsing time of the first website; take the average of the first browsing time and the second browsing time as the first browsing time benchmark of the first user for the first website; obtain the first real-time browsing time of the first website in the first real-time behavior portrait; calculate the first time difference between the first real-time browsing time and the first browsing time benchmark; perform normalized weighted calculation on the first time difference to obtain the first behavior portrait similarity index.

[0087] Furthermore, the data information risk monitoring device for cross-border payment is also used to: Obtain a first co-edge user set that meets a predetermined co-edge similarity constraint with the first user; obtain first co-edge real-time behavior information of the first co-edge user in the first co-edge user set; compare a first co-edge real-time behavior portrait obtained by analyzing the first co-edge real-time behavior information with the first behavior portrait to obtain a first co-edge behavior portrait similarity index; use the first co-edge behavior portrait similarity index as an adjustment coefficient to adjust the first behavior portrait similarity index in real time.

[0088] Furthermore, the data information risk monitoring device for cross-border payment is also used to: The predetermined common edge similarity constraints include predetermined domain scope constraints and predetermined trade industry constraints.

[0089] Furthermore, the data information risk monitoring device for cross-border payment is also used to: Acquire a first transmission node of the first payment data transmission path; obtain a first-level neighborhood node set of the first transmission node in combination with the distributed payment architecture; randomly sample the first-level neighborhood node set to obtain a first preset number of first target neighborhood nodes, the first target neighborhood nodes including the first neighborhood node; obtain a second-level neighborhood node set of the first neighborhood node in combination with the distributed payment architecture; randomly sample the second-level neighborhood node set to obtain a second preset number of second target neighborhood nodes; obtain a second-level state index based on the second node transmission state fused with the second target neighborhood node, calibrate the first neighborhood node transmission state of the first neighborhood node, and obtain a first neighborhood node effective transmission state index; calibrate the first transmission state of the first transmission node according to the first neighborhood node effective transmission state index to obtain a first effective transmission state index; establish a first effective transmission state index set of the first payment data transmission path based on the first effective transmission state index; determine the first path risk index based on the minimum effective transmission state index value obtained by screening the first effective transmission state index set.

[0090] Furthermore, the data information risk monitoring device for cross-border payment is also used to: Read the predetermined transmission status characteristics, and monitor the transmission status of each transmission node based on the predetermined transmission status characteristics to obtain the transmission status of each node, wherein the predetermined transmission status characteristics include transmission rate, transmission load and transmission accuracy.

[0091] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The data information risk monitoring method for cross-border payments and the specific examples in the aforementioned embodiment one are also applicable to the data information risk monitoring device for cross-border payments in this embodiment. Through the aforementioned detailed description of the data information risk monitoring method for cross-border payments, those skilled in the art can clearly understand the data information risk monitoring device for cross-border payments in this embodiment, so for the sake of brevity of the specification, it will not be described in detail here.

[0092] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

[0093] 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 belong to the scope of the present application and its equivalent technology, the present application is also intended to include these modifications and variations.

Claims

1. A data information risk monitoring method for cross-border payments, characterized in that: The data information risk monitoring method for cross-border payment is applied to a data information risk monitoring device for cross-border payment, the data information risk monitoring device for cross-border payment is communicatively connected with a multilateral cross-border payment platform, and the data information risk monitoring method for cross-border payment includes: Acquire a first user database, where the first user database refers to a database of a first user in the multilateral cross-border payment platform, and the first user database includes first user identity information and first user behavior information of the first user; Perform multiple verifications on the first real-time login identity information in combination with the first user identity information to obtain a first identity risk index, wherein the first real-time login identity information refers to the real-time login identity information of the first user; Dynamically monitor first real-time behavior information of the first user, and introduce a behavior comparison mechanism to compare and analyze the first real-time behavior information with the first user behavior information to obtain a first behavior risk index; Acquire the distributed payment architecture of the multilateral cross-border payment platform, and draw a first payment data transmission path in combination with the first real-time behavior information; Reading a predetermined path neural network strategy to perform path risk analysis on the first payment data transmission path to obtain a first path risk index; Performing normalized weighted calculation on the first identity risk index, the first behavior risk index, and the first path risk index to obtain a first risk value; When the first risk value is not within the risk threshold, a payment risk warning is issued to the first user.

2. The data information risk monitoring method for cross-border payment according to claim 1 is characterized in that: include: Reading predetermined identity verification categories, and extracting a first category from the predetermined identity verification categories, wherein the first category has an identifier of a first importance coefficient; Matching first verification information of the first category in the first real-time login identity information, where the first verification information includes a first verification number and a first verification duration; Weighting the first verification times and the first verification duration to obtain a first verification index, and combining the first importance coefficient to obtain a first effective verification risk index for the first category; Forming a valid verification risk index set for the predetermined identity authentication category based on the first valid verification risk index; The maximum risk index in the valid verification risk index set is selected as the first identity risk index.

3. The data information risk monitoring method for cross-border payment according to claim 1 is characterized in that: include: Extracting first historical behavior information from the first user behavior information, where the first historical behavior information refers to first historical web browsing information of the first user; Acquire a first website corresponding to the first webpage in the first historical webpage browsing information, and count the first browsing time of the first website; constructing a first behavior profile of the first user according to a first mapping relationship between the first website and the first browsing time; comparing a first real-time behavior profile obtained by analyzing the first real-time behavior information with the first behavior profile to obtain a first behavior profile similarity index; The first behavior risk index is determined based on the first behavior portrait similarity index.

4. The data information risk monitoring method for cross-border payment according to claim 3 is characterized in that: include: Obtaining a second behavior portrait corresponding to the second historical behavior information in the first user behavior information; Analyze the second behavior portrait to obtain a second browsing time of the first website; Taking the average of the first browsing time and the second browsing time as a first browsing time benchmark of the first user on the first website; Obtaining a first real-time browsing duration of the first website in the first real-time behavior portrait; Calculate a first time difference between the first real-time browsing time and the first browsing time benchmark; The first behavior portrait similarity index is obtained by performing a normalized weighted calculation on the first time difference.

5. The data information risk monitoring method for cross-border payment according to claim 4 is characterized in that: Also includes: Acquire a first co-edge user set that meets a predetermined co-edge similarity constraint with the first user; Acquire first edge co-edge real-time behavior information of a first edge co-edge user in the first edge co-edge user set; Comparing a first edge sharing real-time behavior portrait obtained by analyzing the first edge sharing real-time behavior information with the first behavior portrait to obtain a first edge sharing behavior portrait similarity index; The first co-edge behavior portrait similarity index is used as an adjustment coefficient to adjust the first behavior portrait similarity index in real time.

6. The data information risk monitoring method for cross-border payment according to claim 5 is characterized in that: The predetermined common edge similarity constraints include predetermined domain scope constraints and predetermined trade industry constraints.

7. The data information risk monitoring method for cross-border payment according to claim 1 is characterized in that: include: Acquire a first transmission node of the first payment data transmission path; In combination with the distributed payment architecture, a set of first-level neighboring nodes of the first transmission node is obtained; Randomly sampling the first-level neighborhood node set to obtain a first preset number of first target neighborhood nodes, where the first target neighborhood nodes include the first neighborhood node; In combination with the distributed payment architecture, a set of secondary neighboring nodes of the first neighboring node is obtained; Randomly sampling the secondary neighborhood node set to obtain a second preset number of second target neighborhood nodes; Obtaining a secondary state index according to the second node transmission state of the second target neighboring node, calibrating the first neighboring node transmission state of the first neighboring node to obtain an effective transmission state index of the first neighboring node; Calibrate the first transmission state of the first transmission node according to the first neighborhood node effective transmission state index to obtain a first effective transmission state index; Establishing a first valid transmission status index set for the first payment data transmission path based on the first valid transmission status index; The first path risk index is determined according to a minimum valid transmission state index value obtained by screening the first valid transmission state index set.

8. The data information risk monitoring method for cross-border payment according to claim 7 is characterized in that: Read the predetermined transmission status characteristics, and monitor the transmission status of each transmission node based on the predetermined transmission status characteristics to obtain the transmission status of each node, wherein the predetermined transmission status characteristics include transmission rate, transmission load and transmission accuracy.

9. A data information risk monitoring device for cross-border payment, characterized in that: The steps for implementing the data information risk monitoring method for cross-border payment according to any one of claims 1 to 8 include: A first user database acquisition module, the first user database acquisition module is used to acquire a first user database, the first user database refers to a database of a first user in a multilateral cross-border payment platform, and the first user database includes first user identity information and first user behavior information of the first user; a first identity risk index obtaining module, the first identity risk index obtaining module being used to perform multiple checks on the first real-time login identity information in combination with the first user identity information to obtain a first identity risk index, wherein the first real-time login identity information refers to the real-time login identity information of the first user; a first behavior risk index obtaining module, wherein the first behavior risk index obtaining module is used to dynamically monitor first real-time behavior information of the first user, and introduce a behavior comparison mechanism to compare and analyze the first real-time behavior information with the first user behavior information to obtain a first behavior risk index; a first payment data transmission path drawing module, the first payment data transmission path drawing module being used to obtain the distributed payment architecture of the multilateral cross-border payment platform and draw a first payment data transmission path in combination with the first real-time behavior information; A first path risk index obtaining module, the first path risk index obtaining module is used to read a predetermined path neural network strategy to perform path risk analysis on the first payment data transmission path to obtain a first path risk index; a first risk value obtaining module, wherein the first risk value obtaining module is used to perform normalized weighted calculation on the first identity risk index, the first behavior risk index and the first path risk index to obtain a first risk value; A payment risk warning module is used to issue a payment risk warning to the first user when the first risk value is not within a risk threshold.

Images