Risk control method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention provides a risk control method and device, electronic equipment and a storage medium. The method comprises the steps of obtaining a target transaction application which comprises a target payment user and target payment information, calculating a PageRank value of the target payment user according to a payment user relation graph, performing risk control on a target transaction according to the PageRank value of the target payment user and the target payment information, and after the target transaction is completed, performing payment on the target payment user according to the target payment information and the PageRank value of the target payment user. And account checking is carried out according to the target transaction identifier. According to the method, the potential risk in the payment user relation graph can be identified, risk control is performed on the target transaction according to the potential risk, risk control of a complex relation network can be realized, automatic account checking can also be realized, and thus the risk control efficiency is improved.

Description

Technical Field

[0001] Embodiments of the present disclosure relate to the field of computer technology, and in particular, to a risk control method, device, electronic device, and storage medium. Background Art

[0002] The overseas study payment service has strict compliance requirements, requiring users to be real international students and the payment behavior to be related to studying abroad. The main risks currently exist include violations such as payment on behalf of others and illegal activities such as money laundering. In addition, it is necessary to ensure the compliance of payment channels and the security of funds.

[0003] The existing risk control system mainly relies on simple rule verification and cannot cope with complex relationship networks. Summary of the invention

[0004] The embodiments described herein provide a risk control method, apparatus, electronic device, and storage medium that can implement risk control of complex relationship networks and can achieve automatic reconciliation, thereby improving risk control efficiency.

[0005] In a first aspect, the present disclosure provides a risk control method, comprising: A target transaction application is obtained, wherein the target transaction application includes a target payment user and target payment information; a PageRank value of the target payment user is calculated according to a payment user relationship graph, wherein the payment user relationship graph includes multiple nodes, two adjacent nodes are connected by weighted edges, each node represents a payment user, and the weight depends on the type and quantity of identical information in historical transaction information of the corresponding two adjacent payment users, and the target payment user is one of the multiple payment users; risk control is performed on the target transaction according to the PageRank value of the target payment user and the target payment information; after the target transaction is completed, reconciliation is performed according to a target transaction identifier, and the target transaction identifier is an identifier generated when the target transaction is completed.

[0006] In some embodiments of the present disclosure, calculating the PageRank value of the target paying user according to the paying user relationship graph includes: The PageRank value of the target paying user is calculated according to the following formula: , in, PR ( v i ) indicates the target payment user v i The PageRank value, d is the damping factor, M ( v i) is the target payment user v i A collection of other connected payment users, PR ( v j ) is the target payment user v i Other connected payment users v j The PageRank value, L ( v j ) is the target payment user v i Other connected payment users v j The out-degree of .

[0007] In some embodiments of the present disclosure, the target transaction application also includes a target receiving user, and the target payment information includes a target payment amount and a target payment time.

[0008] The risk control of the target transaction according to the PageRank value of the target paying user and the target payment information includes: The target payment amount is matched with the reasonable payment amount range of the target receiving user to determine the amount risk level of the target transaction; the target payment time is matched with the reasonable payment time of the target receiving user to determine the time risk level of the target transaction; according to the PageRank value of the target paying user, the user risk level of the target transaction is determined; according to the amount risk level, the time risk level and the user risk level of the target transaction, the target transaction is risk controlled.

[0009] In some embodiments of the present disclosure, before matching the target payment amount with the reasonable payment amount range of the target receiving user and determining the amount risk level of the target transaction, the process further includes: Based on multiple historical payment amounts of the target receiving user, determine the historical payment mean and the historical payment standard deviation; the historical payment mean plus twice the historical payment standard deviation is determined as the maximum value of the reasonable payment amount range, and the historical payment mean minus twice the historical payment standard deviation is determined as the minimum value of the reasonable payment amount range.

[0010] Before matching the target payment time with the reasonable payment time of the target receiving user and determining the time risk level of the target transaction, the method further includes: The reasonable payment time of the target receiving user is determined according to multiple historical payment times of the target receiving user.

[0011] In some embodiments of the present disclosure, the target payment information also includes a target payment channel.

[0012] Before performing risk control on the target transaction according to the amount risk level, the time risk level and the user risk level of the target transaction, the method further includes: The target payment channel is matched with the preset payment channel of the target receiving user to determine the channel risk level of the target transaction.

[0013] The performing risk control on the target transaction according to the amount risk level, the time risk level and the user risk level of the target transaction comprises: The target transaction is risk controlled according to the amount risk level, the time risk level, the user risk level and the channel risk level of the target transaction.

[0014] In some embodiments of the present disclosure, the user risk level includes a PR value risk level, a blacklist risk level, and an anti-money laundering risk level.

[0015] Determining the user risk level of the target transaction according to the PageRank value of the target paying user includes: According to the PageRank value of the target payment user, the PR value risk level of the target transaction is obtained; according to the blacklist traversal of the target payment user, the blacklist risk level of the target transaction is obtained; the anti-money laundering risk level of the target transaction is obtained by performing anti-money laundering detection on the target payment user.

[0016] In some embodiments of the present disclosure, the channel risk level includes a channel compliance risk level and a channel spot check risk level.

[0017] The matching of the target payment channel with the preset payment channel of the target receiving user to determine the channel risk level of the target transaction includes: The target payment channel is matched with the preset payment channel of the target receiving user to obtain the channel compliance risk level of the target transaction; the probability of the target transaction being spot-checked is predicted based on the spot-check model to obtain the channel spot-check risk level of the target transaction.

[0018] In a second aspect, the present disclosure provides a wind control device, comprising: An acquisition module, used to acquire a target transaction application, wherein the target transaction application includes a target payment user and target payment information; A calculation module, used to calculate the PageRank value of the target payment user according to a payment user relationship graph, wherein the payment user relationship graph includes a plurality of nodes, two adjacent nodes are connected by weighted edges, each node represents a payment user, and the weight depends on the type and quantity of the same information in the historical transaction information of the two corresponding adjacent payment users, and the target payment user is one of the plurality of payment users; A risk control module, used to perform risk control on a target transaction according to the PageRank value of the target paying user and the target payment information; The reconciliation module is used to reconcile the target transaction according to the target transaction identifier after the target transaction is completed, and the target transaction identifier is an identifier generated when the target transaction is completed.

[0019] In a third aspect, the present disclosure provides an electronic device, comprising a processor, wherein the processor is configured to execute a computer program stored in a memory, wherein the computer program, when executed by the processor, implements the steps of any one of the methods provided in the first aspect.

[0020] In a fourth aspect, the present disclosure provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of any method provided in the first aspect are implemented.

[0021] In the technical solution provided by the present disclosure, by obtaining a target transaction application, the target transaction application includes a target payment user and target payment information, and calculating the PageRank value of the target payment user according to the payment user relationship map. Based on the PageRank value of the target payment user and the target payment information, risk control is performed on the target transaction. Potential risks in the payment user relationship map can be identified, and risk control is performed on the target transaction accordingly. Risk control of complex relationship networks can be achieved. After the target transaction is completed, reconciliation is performed according to the target transaction identifier, and automatic reconciliation can be achieved, thereby improving risk control efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings of the embodiments will be briefly described below. It should be noted that the drawings described below only relate to some embodiments of the present disclosure, but are not intended to limit the present disclosure, wherein: Figure 1 A schematic diagram of a flow chart of a risk control method provided in an embodiment of the present disclosure; Figure 2 A flowchart of another risk control method provided by an embodiment of the present disclosure; Figure 3 A flowchart of another risk control method provided by an embodiment of the present disclosure; Figure 4A flowchart of another risk control method provided by an embodiment of the present disclosure; Figure 5 A schematic diagram of the structure of a wind control device provided in an embodiment of the present disclosure; Figure 6 A schematic diagram of the structure of an electronic device provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0023] In order to make the purpose, technical solution and advantages of the embodiments of the present disclosure clearer, the technical solution of the embodiments of the present disclosure will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present disclosure, rather than all of the embodiments. Based on the described embodiments of the present disclosure, all other embodiments obtained by those skilled in the art without creative work also fall within the scope of protection of the present disclosure.

[0024] Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by those skilled in the art to which the subject matter of the present disclosure belongs. It will be further understood that terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with their meanings in the context of the specification and the relevant art, and will not be interpreted in an idealized or overly formal form unless otherwise explicitly defined herein. In addition, terms such as "first" and "second" are only used to distinguish one component (or a portion of a component) from another component (or another portion of a component).

[0025] The risk control method provided in the present disclosure can be applied to the scenario of the overseas study payment system, and can also be applied to the scenarios of other payment systems. The present disclosure does not make specific restrictions on this. The embodiments of the present disclosure only take the application scenario of the overseas study payment system as an example to exemplify the risk control method.

[0026] The target transaction in the disclosed embodiment is the payment of tuition fees. The target transaction application in the disclosed embodiment is the application for payment of tuition fees submitted by any user in the overseas study payment system. The target paying user in the disclosed embodiment is the payer of tuition fees, such as a student. The target receiving user in the disclosed embodiment is the recipient of tuition fees, such as a school. The target payment information in the disclosed embodiment includes at least the amount of tuition fees and the payment time of tuition fees.

[0027] The technical solution provided by the present disclosure is described in detail below with reference to several specific embodiments.

[0028] Figure 1 A flow chart of a risk control method provided by an embodiment of the present disclosure is shown as follows: Figure 1 As shown, the specific steps of the risk control method include: S101, obtaining a target transaction application.

[0029] The target transaction application includes the target payment user and target payment information.

[0030] Exemplarily, the user selects the target receiving user in the study abroad payment system and enters the identity information of the target paying user, for example, uploading materials such as the admission notice and / or student ID card to prove the identity of the target paying user, or entering the admission notice number and / or student ID number to prove the identity of the target paying user, and also enters at least part of the target payment information, for example, the target payment amount, target payment channel, target payment account and / or target payment semester.

[0031] Then, based on the above information, the target transaction application is initiated in the overseas study payment system. The system can extract key information from the identity certification materials of the target payment user through optical character recognition technology, such as student number, student name and school name, and compare the extracted key information with the registration information to determine whether the target payment user is a student of the school where the target receiving user is located, so as to verify the identity of the target payment user. In addition, the system can also collect the biometric information of the current operating user, such as FaceID, fingerprint and iris, to determine whether the current operating user is the target payment user, so as to verify the identity of the current operating user.

[0032] When the target paying user is a student of the target receiving user's school and the current operating user is the target paying user, the identity authentication of the target paying user and the identity authentication of the current operating user are passed, and the system generates a target transaction application. The generated target transaction application includes the target paying user entered by the user, the target payment information entered by the user, and the target payment information generated by the system. For example, the target payment information generated by the system may include the target payment time, which is the generation time of the target transaction application.

[0033] S102, calculating the PageRank value of the target paying user according to the paying user relationship graph.

[0034] Among them, the payment user relationship graph includes multiple nodes, two adjacent nodes are connected by weighted edges, each node represents a payment user, the weight depends on the type and quantity of the same information in the historical transaction information of the corresponding two adjacent payment users, and the target payment user is one of the multiple payment users.

[0035] Exemplarily, the system regards all payment users as a node, and based on the historical transaction information of all payment users, establishes an edge between the nodes of two payment users with at least partially identical historical transaction information to construct a payment user relationship graph, wherein the historical transaction information is divided into payment methods, device information, payers and payees, etc. according to type.

[0036] For example, when two payment users have the same payer, an edge is established between the nodes of the two payment users; when two payment users have the same payee, an edge is established between the nodes of the two payment users; when two payment users have the same device information, an edge is established between the nodes of the two payment users.

[0037] The more historical transaction information two payment users have, the higher the weight of the edge between the corresponding two nodes. For example, payment user A1 and payment user A2 have the same payee, and the node of payment user A1 is connected to the node of payment user A2 through edge B1. Payment user A1 and payment user A3 have the same payee and the same device information, and the node of payment user A1 is connected to the node of payment user A2 through edge B2. Then the weight of edge B2 is greater than the weight of edge B1.

[0038] The system assigns different weights to different types of historical transaction information. For example, the weight of the payee is greater than that of the payer, and the weight of the device information is greater than that of the payer. The types of historical transaction information shared by two paying users are different, and the weights of the edges between the corresponding two nodes are different. For example, paying user A1 and paying user A2 have the same payee, and the node of paying user A1 is connected to the node of paying user A2 through edge B1. Paying user A1 and paying user A4 have the same payer, and the node of paying user A1 is connected to the node of paying user A4 through edge B3, then the weight of edge B1 is greater than the weight of edge B3.

[0039] The system calculates the PageRank value of the target paying user according to formula (1) to determine the importance of the target paying user in the paying user relationship graph: (1) in, PR ( v i ) indicates the target payment user v i The PageRank value can be used to measure the target paying users v i The importance or risk level in the payment user relationship graph, d is the damping factor and is usually 0.85, indicating that the target paying user v i The probability of jumping to other payment users in the payment user relationship graph.

[0040] M ( v i ) is the target payment user vi A collection of other connected payment users, indicating the connection with the target payment user v i Payment users who have some kind of relationship, for example, have the same payer, payee or device information, etc. M ( v i ) and target payment users v i The weights of the connected edges are related. PR ( v j ) is the target payment user v i Other connected payment users v j The PageRank value, L ( v j ) is the target payment user v i Other connected payment users v j The out-degree of the target paying user v i The number of connected edges.

[0041] In this way, the higher the PageRank value of the target payment user, the higher the importance of the target payment user in the payment user relationship graph, which means that the target payment user has a strong association with multiple other payment users, and the other associated payment users themselves also have a high importance. In particular, when the target payment user is closely associated with multiple potentially high-risk other payment users, the PageRank value of the target payment user will increase.

[0042] S103, performing risk control on the target transaction according to the PageRank value of the target paying user and the target payment information.

[0043] Exemplarily, the system can determine whether the target payment user is likely to be involved in illegal or irregular activities based on the target payment user's PageRank value. For example, if the target payment user's PageRank value is higher than a preset value, the target payment user is marked as high risk, that is, the target payment user is a potential illegal or irregular person, and the target transaction application is rejected and / or manual review is triggered.

[0044] For another example, the system calculates the PageRank value of each paying user, arranges the PageRank values ​​of all paying users in order from large to small, and obtains a PageRank value sequence. If the PageRank value of the target paying user is within a preset proportion of the PageRank value sequence, the target paying user is marked as high risk, that is, the target paying user is a potential lawbreaker, and the target transaction application is rejected and / or manual review is triggered.

[0045] The system can determine whether the target payment amount is reasonable, and when the target payment amount is reasonable, continue the target transaction; when the target payment amount is unreasonable, reject the target transaction application, trigger manual review and / or trigger other risk control measures.

[0046] The system can determine whether the target payment channel complies with the regulations of the target recipient's school, and when the target payment channel complies with the regulations of the target recipient's school, continue the target transaction; when the target payment channel does not comply with the regulations of the target recipient's school, reject the target transaction application, trigger manual review and / or trigger other risk control measures.

[0047] The system can determine whether the target payment account is a personal account, and when the target payment account is a personal account, continue the target transaction; when the target payment account is a public account, reject the target transaction application, trigger manual review and / or trigger other risk control measures.

[0048] The system can determine whether the target payment time is reasonable, and when the target payment time is reasonable, continue the target transaction; when the target payment time is unreasonable, reject the target transaction application, trigger manual review and / or trigger other risk control measures.

[0049] The system can also determine whether the target payment semester is reasonable, and when the target payment semester is reasonable, continue the target transaction. When the target payment time is not in the semester, the target transaction application will be rejected, manual review will be triggered, and / or other risk control measures will be triggered.

[0050] S104: After the target transaction is completed, reconciliation is performed according to the target transaction identifier.

[0051] The target transaction identifier is an identifier generated when the target transaction is completed.

[0052] Exemplarily, after the target transaction is completed, the system will generate a target transaction record and a target transaction identifier corresponding to the target transaction record. For example, the target transaction record includes information such as the target payment time, the target payment amount, and the target payment channel.

[0053] The system can find the target transaction record through the target transaction identifier, and check the data in the target transaction record with the data returned by the target payment channel to achieve automatic reconciliation. When the target transaction reconciliation does not match, for example, the payment is successful but not received, the system will automatically generate an alarm and push the relevant information to the operator for manual intervention, and freeze subsequent related transactions to prevent further loss of funds.

[0054] In the disclosed embodiment, by obtaining a target transaction application, the target transaction application includes a target payment user and target payment information, and calculating the PageRank value of the target payment user according to the payment user relationship map, and performing risk control on the target transaction according to the target payment user's PageRank value and the target payment information, potential risks in the payment user relationship map can be identified, and risk control of the target transaction is performed accordingly, which can achieve risk control of complex relationship networks, and by reconciling accounts according to the target transaction identifier after the target transaction is completed, automatic reconciliation can be achieved, thereby improving risk control efficiency.

[0055] In some embodiments, Figure 2 A flow chart of another risk control method provided by an embodiment of the present disclosure is provided. Figure 2 for Figure 1 Based on the illustrated embodiment, a possible implementation method for executing S103 is specifically described as follows: S201, matching the target payment amount with the reasonable payment amount range of the target receiving user to determine the amount risk level of the target transaction.

[0056] For example, first, the system obtains multiple historical payment amounts of the target receiving user, and determines the historical payment mean and the historical payment standard deviation based on the multiple historical payment amounts of the target receiving user. 、 and , then the average of multiple historical payment amounts is , which is the historical payment mean , the standard deviation of multiple historical payment amounts is , that is, the historical payment standard deviation .

[0057] Secondly, the historical payment mean plus twice the historical payment standard deviation is determined as the maximum value of the reasonable payment amount range, and the historical payment mean minus twice the historical payment standard deviation is determined as the minimum value of the reasonable payment amount range to obtain a reasonable payment amount range. Determined as the minimum value of the reasonable payment amount range, The maximum value of the reasonable payment amount range is determined as , where the historical payment amounts are normally distributed. When the coefficient of the historical payment standard deviation item in the reasonable payment amount range is 2, the reasonable payment amount range can cover 95% of the historical payment amount range.

[0058] Finally, the target payment amount is matched with the reasonable payment amount range of the target receiving user to determine whether the target payment amount exceeds the reasonable payment amount range of the target receiving user, so as to determine the amount risk level of the target transaction, where the amount risk level is divided into high risk and low risk. For example, when the target payment amount exceeds the reasonable payment amount range of the target receiving user, the amount risk level of the target transaction is high risk, and when the target payment amount does not exceed the reasonable payment amount range of the target receiving user, the amount risk level of the target transaction is low risk.

[0059] S202, matching the target payment time with the reasonable payment time of the target receiving user to determine the time risk level of the target transaction.

[0060] Exemplarily, first, the system obtains multiple historical payment times of the target receiving user, and determines the reasonable payment time of the target receiving user based on the historical payment time of the target receiving user. For example, if the historical payment time of the target receiving user is from August 30 to September 1, it can be determined that the reasonable payment time of the target receiving user is from August 30 to September 1.

[0061] Secondly, the target payment time is matched with the reasonable payment time of the target receiving user to determine whether the target payment time exceeds the reasonable payment time, so as to determine the time risk level of the target transaction, where the time risk level is divided into high risk and low risk. For example, when the target payment time exceeds the reasonable payment time, the time risk level of the target transaction is high risk, and when the target payment time does not exceed the reasonable payment time, the time risk level of the target transaction is low risk.

[0062] In this way, based on historical data, the reasonable payment amount range and reasonable payment time of the target recipient can be determined through statistical analysis and dynamic calculation methods. Compared with traditional static calculation methods, this method is more flexible and has higher accuracy.

[0063] S203, determining the user risk level of the target transaction according to the PageRank value of the target paying user.

[0064] Exemplarily, the system compares the PageRank value of the target payment user with a preset value to determine whether the PageRank value of the target payment user is higher than the preset value, so as to determine the user risk level of the target transaction, wherein the user risk level is divided into high risk and low risk. For example, when the PageRank value of the target payment user is higher than the preset value, the user risk level of the target transaction is high risk, and when the PageRank value of the target payment user is not higher than the preset value, the user risk level of the target transaction is low risk.

[0065] In other embodiments, the system compares the sequence number of the PageRank value of the target payment user in the PageRank value sequence with the preset sequence number to determine whether the sequence number of the PageRank value of the target payment user in the PageRank value sequence is less than the preset sequence number, so as to determine the user risk level of the target transaction, wherein the user risk level is divided into high risk and low risk. For example, when the sequence number of the PageRank value of the target payment user in the PageRank value sequence is less than the preset sequence number, the user risk level of the target transaction is high risk, and when the sequence number of the PageRank value of the target payment user in the PageRank value sequence is not less than the preset sequence number, the user risk level of the target transaction is low risk.

[0066] S204: Perform risk control on the target transaction according to the amount risk level, time risk level and user risk level of the target transaction.

[0067] Exemplarily, risk control includes executing transactions, rejecting transaction applications, triggering manual review and / or triggering other risk control measures. When at least one of the amount risk level, time risk level and user risk level of the target transaction is high risk, the target transaction application is rejected, manual review is triggered and / or other risk control measures are triggered. When the amount risk level, time risk level and user risk level of the target transaction are low risk, the target transaction is executed.

[0068] For example, when the amount risk level of the target transaction is high risk, the system rejects the target transaction application, triggers manual review and / or triggers other risk control measures; when the time risk level of the target transaction is high risk, the system rejects the target transaction application, triggers manual review and / or triggers other risk control measures; when the user risk level of the target transaction is high risk, the system rejects the target transaction application, triggers manual review and / or triggers other risk control measures.

[0069] In other implementations, the amount risk, time risk and user risk of the target transaction have different priorities, for example, the priority of the amount risk is higher than the priority of the user risk, and the priority of the time risk is the same as the priority of the amount risk. The system can perform risk control on the target transaction according to the risk priority, according to the amount risk level, time risk level and user risk level of the target transaction, wherein the risk control also includes continuing the transaction application.

[0070] For example, based on the above embodiment, risk control is performed on the target transaction according to the amount risk level and time risk level of the target transaction. When the amount risk level or time risk level of the target transaction is high risk, the target transaction application is rejected, manual review and / or other risk control measures are triggered. When the amount risk level and time risk level of the target transaction are low risk, risk control is performed on the target transaction according to the user risk level of the target transaction.

[0071] When the user risk level of the target transaction is high risk, the target transaction application is rejected, manual review and / or other risk control measures are triggered; when the user risk level of the target transaction is low risk, the target transaction is executed.

[0072] In some embodiments, Figure 3 A flow chart of another risk control method provided in an embodiment of the present disclosure is provided. Figure 3 for Figure 2 Based on the embodiment shown, before executing S204, the following step is also included: S301, matching the target payment channel with the preset payment channel of the target receiving user to determine the channel risk level of the target transaction.

[0073] Exemplarily, the target payment information also includes a target payment channel, and the preset payment channel of the target receiving user is a payment channel allowed by the country where the target receiving user is located or a payment channel allowed by the school where the target receiving user is located.

[0074] The system matches the target payment channel with the preset payment channel of the target receiving user, determines whether the target payment channel is included in the preset payment channel of the target receiving user, and determines the channel risk level of the target transaction, where the channel risk level is divided into high risk and low risk. For example, when the target payment channel is not included in the preset payment channel of the target receiving user, the channel risk level of the target transaction is high risk, and when the target payment channel is included in the preset payment channel of the target receiving user, the channel risk level of the target transaction is low risk.

[0075] Continue to see Figure 3 Based on the above embodiment, a possible implementation method of executing S204 is described in detail as follows: S204', performing risk control on the target transaction according to the amount risk level, time risk level, user risk level and channel risk level of the target transaction.

[0076] Exemplarily, risk control also includes selecting a low-risk payment channel and / or disabling a high-risk payment channel. When the amount risk level, time risk level, user risk level and channel risk level of the target transaction are low risk, the target transaction is executed. When at least one of the amount risk level, time risk level and user risk level of the target transaction is high risk, the system rejects the target transaction application, triggers manual review and / or triggers other risk control measures. When the channel risk level of the target transaction is high risk, the system selects a low-risk payment channel and / or disables the target payment channel.

[0077] For example, when the country where the target receiving user is located does not allow the use of the target payment channel, that is, the preset payment channel of the target receiving user does not include the target payment channel, the system automatically disables the target payment channel and / or automatically selects a low-risk payment channel.

[0078] In other embodiments, the system may perform risk control on the target transaction according to the priority of the risk, for example, the priority of channel risk is lower than the priority of user risk, the priority of user risk is lower than the priority of amount risk, the priority of amount risk is the same as the priority of time risk, and according to the amount risk level, time risk level, user risk level and channel risk level of the target transaction.

[0079] For example, based on the above embodiment, risk control is performed on the target transaction according to the amount risk level and time risk level of the target transaction. When the amount risk level or time risk level of the target transaction is high risk, the target transaction application is rejected, manual review and / or other risk control measures are triggered. When the amount risk level and time risk level of the target transaction are low risk, risk control is performed on the target transaction according to the user risk level of the target transaction.

[0080] When the user risk level of the target transaction is high risk, the target transaction application is rejected, manual review is triggered and / or other risk control measures are triggered. When the user risk level of the target transaction is low risk, the target transaction is risk controlled according to the channel risk level of the target transaction. When the channel risk level of the target transaction is high risk, a low-risk payment channel is selected and / or the target payment channel is disabled. When the channel risk level of the target transaction is low risk, the target transaction is executed.

[0081] In some embodiments, user risk levels include PR value risk level, blacklist risk level and anti-money laundering risk level, wherein the PR value risk level is divided into high risk and low risk, the blacklist risk level is divided into high risk and low risk, and the anti-money laundering risk level is divided into high risk and low risk.

[0082] Figure 4 A flow chart of another risk control method provided in an embodiment of the present disclosure is provided. Figure 4 for Figure 2 Based on the illustrated embodiment, a possible implementation method for executing S203 is specifically described as follows: S401, obtaining the PageRank value risk level of the target transaction according to the PageRank value of the target paying user.

[0083] Exemplarily, when the PageRank value of the target paying user is higher than a preset value, the PR value risk level of the target transaction is high risk; when the PageRank value of the target paying user is not higher than the preset value, the PR value risk level of the target transaction is low risk.

[0084] In other embodiments, when the PageRank value of the target paying user is less than the preset number in the PageRank value sequence, the PR value risk level of the target transaction is high risk; when the PageRank value of the target paying user is not less than the preset number in the PageRank value sequence, the PR value risk level of the target transaction is low risk.

[0085] S402, traverse the blacklist according to the target payment user to obtain the blacklist risk level of the target transaction.

[0086] Exemplarily, the system queries the target payment user in the blacklist database through an external interface to determine whether the target payment user is included in the blacklist to obtain the blacklist risk level of the target transaction. For example, when the target payment user is included in the blacklist, the blacklist risk level of the target transaction is high risk; when the target payment user is not included in the blacklist, the blacklist risk level of the target transaction is low risk.

[0087] S403, performing anti-money laundering detection on the target payment user to obtain the anti-money laundering risk level of the target transaction.

[0088] Exemplarily, the system uses the anti-money laundering detection platform to analyze indicators such as the target payment user's transaction frequency, transaction amount, and transaction object, and identifies whether the target payment user has potential money laundering behavior to obtain an anti-money laundering risk level. For example, when the target payment user frequently conducts large-scale cross-border transfers in a short period of time, the anti-money laundering risk level of the target transaction is high risk.

[0089] Continue to see Figure 4Based on the above embodiment, another possible implementation method when executing S204 is specifically described as follows: Conduct risk control on target transactions based on the target transaction’s amount risk level, time risk level, PR value risk level, blacklist risk level and anti-money laundering risk level.

[0090] Exemplarily, when at least one of the target transaction's amount risk level, time risk level, and PR value risk level is high risk, the system rejects the target transaction application, triggers manual review and / or triggers other risk control measures; when the target transaction's blacklist risk level or anti-money laundering risk level is high risk, the system rejects the target transaction application; when the target transaction's amount risk level, time risk level, PR value risk level, blacklist risk level, and anti-money laundering risk level are low risk, the target transaction is executed.

[0091] In other embodiments, the system may perform risk control on the target transaction according to the priority of the risk, for example, the priority of anti-money laundering risk is lower than the priority of blacklist risk, the priority of blacklist risk is lower than the priority of PR value risk, the priority of PR value risk is lower than the priority of amount risk, and the priority of amount risk is the same as the priority of time risk. According to the amount risk level, time risk level, PR value risk level, blacklist risk level and anti-money laundering risk level of the target transaction.

[0092] For example, based on the above embodiment, risk control is performed on the target transaction according to the amount risk level and time risk level of the target transaction. When the amount risk level or time risk level of the target transaction is high risk, the target transaction application is rejected, manual review and / or other risk control measures are triggered. When the amount risk level and time risk level of the target transaction are low risk, risk control is performed on the target transaction according to the PR value risk level of the target transaction.

[0093] When the PR value risk level of the target transaction is high risk, the target transaction application is rejected, manual review is triggered and / or other risk control measures are triggered. When the PR value risk level of the target transaction is low risk, risk control is performed on the target transaction according to the blacklist risk level of the target transaction. When the blacklist risk level of the target transaction is high risk, the target transaction application is rejected. When the blacklist risk level of the target transaction is low risk, risk control is performed on the target transaction according to the anti-money laundering risk level of the target transaction. When the anti-money laundering risk level of the target transaction is high risk, the target transaction application is rejected. When the anti-money laundering risk level of the target transaction is low risk, the target transaction is executed.

[0094] In some embodiments, the channel risk level includes a channel compliance risk level and a channel spot check risk level, wherein the channel compliance risk level is divided into high risk and low risk, and the channel spot check risk level is divided into high risk and low risk.

[0095] A specific description of a possible implementation method when executing S301 is as follows: Match the target payment channel with the preset payment channel of the target receiving user to obtain the channel compliance risk level of the target transaction. Based on the spot check model, predict the probability of the target transaction being spot checked to obtain the channel spot check risk level of the target transaction.

[0096] Exemplarily, the system matches the target payment channel with the preset payment channel of the target receiving user, determines whether the target payment channel is included in the preset payment channel of the target receiving user, and obtains the channel compliance risk level of the target transaction. For example, when the target payment channel is not included in the preset payment channel of the target receiving user, the channel compliance risk level of the target transaction is high risk; when the target payment channel is included in the preset payment channel of the target receiving user, the channel compliance risk level of the target transaction is low risk.

[0097] The spot check model is a machine learning model trained based on features such as payment amount, historical payer and payee account. The target transaction application is input into the spot check model to predict the probability of the target transaction being spot checked by a third-party institution such as a bank, and the probability of the target transaction being spot checked is compared with the preset probability to determine whether the probability of the target transaction being spot checked is greater than the preset probability, so as to obtain the channel spot check risk level of the target transaction. For example, when the probability of the target transaction being spot checked is greater than the preset probability, the channel spot check risk level of the target transaction is high risk, and when the probability of the target transaction being spot checked is not greater than the preset probability, the channel spot check risk level of the target transaction is low risk.

[0098] Based on the above embodiment, a possible implementation method of executing S204' is specifically described as follows: Conduct risk control on target transactions based on their amount risk level, time risk level, user risk level, channel compliance risk level and channel spot check risk level.

[0099] Exemplarily, when the target transaction's amount risk level, time risk level, user risk level, channel compliance risk level, and channel spot check risk level are low risk, the target transaction is executed; when at least one of the target transaction's amount risk level, time risk level, and user risk level is high risk, the system rejects the target transaction application, triggers manual review, and / or triggers other risk control measures; when the channel compliance risk level or channel spot check risk level is high risk, the system selects a low-risk payment channel and / or disables the target payment channel.

[0100] In other embodiments, the system may perform risk control on the target transaction according to the priority of the risk, for example, the priority of channel spot check risk is lower than the priority of channel compliance risk, the priority of channel compliance risk is lower than the priority of user risk, the priority of user risk is lower than the priority of amount risk, and the priority of amount risk is the same as the priority of time risk. According to the amount risk level, time risk level, user risk level, channel compliance risk level and channel spot check risk level of the target transaction.

[0101] For example, based on the above embodiment, risk control is performed on the target transaction according to the amount risk level and time risk level of the target transaction. When the amount risk level or time risk level of the target transaction is high risk, the target transaction application is rejected, manual review and / or other risk control measures are triggered. When the amount risk level and time risk level of the target transaction are low risk, risk control is performed on the target transaction according to the user risk level of the target transaction.

[0102] When the user risk level of the target transaction is high risk, the target transaction application is rejected, manual review is triggered, and / or other risk control measures are triggered. When the user risk level of the target transaction is low risk, risk control is performed on the target transaction according to the channel compliance risk level of the target transaction. When the channel compliance risk level of the target transaction is high risk, a low-risk payment channel is selected and / or the target payment channel is disabled. When the channel compliance risk level of the target transaction is low risk, risk control is performed on the target transaction according to the channel spot check risk level of the target transaction. When the channel spot check risk level of the target transaction is high risk, a low-risk payment channel is selected and / or the target payment channel is disabled. When the channel spot check risk level of the target transaction is low risk, the target transaction is executed.

[0103] In this way, the probability of the target transaction being spot-checked is predicted by the spot-check model, and the channel spot-check risk level of the target transaction is obtained. Based on the channel spot-check risk level of the target transaction, the target transaction is risk-controlled, which can avoid high-risk payment channels and reduce the time delay and cost caused by spot checks.

[0104] The present disclosure also provides a wind control device for executing the steps of any of the above method embodiments.

[0105] Figure 5 is a schematic diagram of the structure of a wind control device provided by an embodiment of the present disclosure, such as Figure 5 As shown, the wind control device includes: The acquisition module 110 is used to acquire a target transaction application, where the target transaction application includes a target payment user and target payment information.

[0106] The calculation module 120 is used to calculate the PageRank value of the target payment user according to the payment user relationship graph, wherein the payment user relationship graph includes multiple nodes, two adjacent nodes are connected by weighted edges, each node represents a payment user, and the weight depends on the type and quantity of the same information in the historical transaction information of the corresponding two adjacent payment users. The target payment user is one of the multiple payment users.

[0107] The risk control module 130 is used to perform risk control on the target transaction according to the PageRank value of the target paying user and the target payment information.

[0108] The reconciliation module 140 is used to reconcile accounts according to the target transaction identifier after the target transaction is completed. The target transaction identifier is an identifier generated when the target transaction is completed.

[0109] In some embodiments, the calculation module 120 is further used to calculate the PageRank value of the target paying user according to the following formula: , in, PR ( v i ) indicates the target payment user v i The PageRank value, d is the damping factor, M ( v i ) is the target payment user v i A collection of other connected payment users, PR ( v j ) is the target payment user v i Other connected payment users v j The PageRank value, L ( v j ) is the target payment user v i Other connected payment users v j The out-degree of .

[0110] In some embodiments, the target transaction application also includes a target receiving user, and the target payment information includes a target payment amount and a target payment time.

[0111] The risk control module 130 is further used to match the target payment amount with the reasonable payment amount range of the target receiving user to determine the amount risk level of the target transaction; match the target payment time with the reasonable payment time of the target receiving user to determine the time risk level of the target transaction; determine the user risk level of the target transaction according to the PageRank value of the target paying user; and perform risk control on the target transaction according to the amount risk level, time risk level and user risk level of the target transaction.

[0112] In some embodiments, the wind control device further includes: A determination module is used to determine a historical payment mean and a historical payment standard deviation based on multiple historical payment amounts of the target receiving user; the historical payment mean plus twice the historical payment standard deviation is determined as the maximum value of the reasonable payment amount range, and the historical payment mean minus twice the historical payment standard deviation is determined as the minimum value of the reasonable payment amount range; and the reasonable payment time of the target receiving user is determined based on multiple historical payment times of the target receiving user.

[0113] In some embodiments, the target payment information also includes a target payment channel.

[0114] The risk control module 130 is further used to match the target payment channel with the preset payment channel of the target receiving user to determine the channel risk level of the target transaction.

[0115] The risk control module 130 is further used to perform risk control on the target transaction according to the amount risk level, the time risk level, the user risk level and the channel risk level of the target transaction.

[0116] In some embodiments, the user risk level includes a PR value risk level, a blacklist risk level, and an anti-money laundering risk level.

[0117] The risk control module 130 is further used to obtain the PR value risk level of the target transaction according to the PageRank value of the target payment user; obtain the blacklist risk level of the target transaction by traversing the blacklist according to the target payment user; and perform anti-money laundering detection on the target payment user to obtain the anti-money laundering risk level of the target transaction.

[0118] In some embodiments, the channel risk level includes a channel compliance risk level and a channel spot check risk level.

[0119] The risk control module 130 is further used to match the target payment channel with the preset payment channel of the target receiving user to obtain the channel compliance risk level of the target transaction; and predict the probability of the target transaction being spot-checked based on the spot-check model to obtain the channel spot-check risk level of the target transaction.

[0120] The wind control device provided in the embodiment of the present disclosure is used to execute the steps provided in any of the above method embodiments, has functional modules corresponding to the method embodiments, and has the beneficial effects of the method embodiments, which will not be repeated here.

[0121] The present disclosure further provides an electronic device, comprising: a processor, wherein the processor is configured to execute a computer program stored in a memory, wherein the computer program implements the steps of the above method embodiment when executed by the processor.

[0122] Figure 6 A schematic diagram of the structure of an electronic device provided in an embodiment of the present disclosure is provided. Figure 6 A block diagram of an exemplary electronic device suitable for implementing the embodiments of the present disclosure is shown. Figure 6 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0123] like Figure 6 As shown, the electronic device 12 is in the form of a general purpose computing device. The components of the electronic device 12 may include, but are not limited to: one or more processors 16, a system memory 28, and a bus 18 that connects various system components (including the system memory 28 and the processor 16).

[0124] Bus 18 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor or a local bus using any of a variety of bus architectures. By way of example, these architectures include, but are not limited to, an Industry Standard Architecture (ISA) bus, a Micro Channel Architecture (MAC) bus, an Enhanced ISA bus, a Video Electronics Standards Association (VESA) local bus, and a Peripheral Component Interconnect (PCI) bus.

[0125] The electronic device 12 typically includes a variety of computer system readable media. These media can be any media that can be accessed by the electronic device 12, including volatile and non-volatile media, removable and non-removable media.

[0126] The system memory 28 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 30 and / or cache memory 32. The electronic device 12 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, the storage system 34 may be used to read and write non-removable, non-volatile magnetic media (commonly referred to as "hard drives"). A disk drive for reading and writing removable non-volatile disks (such as "floppy disks"), and an optical disk drive for reading and writing removable non-volatile optical disks (such as CD-ROMs, DVD-ROMs, or other optical media) may be provided. In these cases, each drive may be connected to the bus 18 via one or more data media interfaces. The system memory 28 may include at least one program product having a set (e.g., at least one) of program modules that are configured to perform the functions of the various embodiments of the present disclosure.

[0127] A program / utility 40 having a set (at least one) of program modules 42 may be stored, for example, in system memory 28, such program modules 42 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which or some combination thereof may include an implementation of a network environment. Program modules 42 generally perform the functions and / or methods of the embodiments described in the embodiments of the present disclosure.

[0128] The processor 16 executes various functional applications and data processing by running at least one program among a plurality of programs stored in the system memory 28 , such as implementing the method embodiment provided in the embodiment of the present disclosure.

[0129] The present disclosure also provides a computer-readable storage medium having a computer program stored thereon, and the computer program implements the steps of the above method embodiment when executed by a processor.

[0130] Any combination of one or more computer-readable media can be used. Computer-readable media can be computer-readable signal media or computer-readable storage media. Computer-readable storage media can be, for example, but not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or devices, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: electrical connections with one or more wires, portable computer disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), optical fibers, portable compact disk read-only memories (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the above. In this document, computer-readable storage media can be any tangible medium containing or storing a program, which can be used by an instruction execution system, device or device or used in combination with it.

[0131] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0132] The program code embodied on the computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0133] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN) domain, or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0134] The flow chart and block diagram in the accompanying drawings show the possible architecture, function and operation of the device and method according to multiple embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a part of a module, a program segment or an instruction, and a part of the module, a program segment or an instruction includes one or more executable instructions for realizing the specified logical function. In some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two continuous square boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or action, or can be implemented with a combination of special hardware and computer instructions.

[0135] Unless the context clearly indicates otherwise, the singular form of the words used herein and in the appended claims includes the plural and vice versa. Thus, when referring to the singular, the plural form of the corresponding term is generally included. Similarly, the words "comprise" and "include" are to be interpreted as inclusive rather than exclusive. Likewise, the terms "include" and "or" should be interpreted as inclusive unless such interpretation is expressly prohibited herein. Where the term "example" is used herein, particularly when it is located after a group of terms, the "example" is merely exemplary and illustrative and should not be considered exclusive or comprehensive.

[0136] Further aspects and scopes of adaptability become apparent from the description provided herein. It should be understood that various aspects of the present disclosure can be implemented individually or in combination with one or more other aspects. It should also be understood that the description and specific embodiments herein are intended for purposes of illustration only and are not intended to limit the scope of the present disclosure.

[0137] Several embodiments of the present disclosure are described in detail above, but it is obvious that those skilled in the art can make various modifications and variations to the embodiments of the present disclosure without departing from the spirit and scope of the present disclosure. The protection scope of the present disclosure is defined by the attached claims.

Claims

1. A risk control method, characterized in that: include: Obtaining a target transaction application, wherein the target transaction application includes a target payment user and target payment information; Calculate the PageRank value of the target payment user according to the payment user relationship graph, wherein the payment user relationship graph includes multiple nodes, two adjacent nodes are connected by weighted edges, each node represents a payment user, and the weight depends on the type and quantity of the same information in the historical transaction information of the corresponding two adjacent payment users, and the target payment user is one of the multiple payment users; Perform risk control on the target transaction according to the PageRank value of the target paying user and the target payment information; After the target transaction is completed, reconciliation is performed according to the target transaction identifier, where the target transaction identifier is an identifier generated when the target transaction is completed.

2. The method according to claim 1, characterized in that Calculating the PageRank value of the target paying user according to the paying user relationship graph includes: The PageRank value of the target paying user is calculated according to the following formula: ， in, PR ( v i ) indicates the target payment user v i The PageRank value, d is the damping factor, M ( v i ) for target paying users v i A collection of other connected payment users, PR ( v j ) is the target payment user v i Other connected payment users v j The PageRank value, L ( v j ) is the target payment user v i Other connected payment users v j The out-degree of .

3. The method according to claim 1, characterized in that: The target transaction application also includes a target receiving user, and the target payment information includes a target payment amount and a target payment time; The risk control of the target transaction according to the PageRank value of the target paying user and the target payment information includes: Matching the target payment amount with the reasonable payment amount range of the target receiving user to determine the amount risk level of the target transaction; Matching the target payment time with the reasonable payment time of the target receiving user to determine the time risk level of the target transaction; Determine the user risk level of the target transaction according to the PageRank value of the target paying user; The target transaction is risk controlled according to the amount risk level, the time risk level and the user risk level of the target transaction.

4. The method according to claim 3, characterized in that Before matching the target payment amount with the reasonable payment amount range of the target receiving user and determining the amount risk level of the target transaction, the method further includes: Determine a historical payment mean and a historical payment standard deviation based on multiple historical payment amounts of the target receiving user; The historical payment mean plus two times the historical payment standard deviation is determined as the maximum value of the reasonable payment amount range, and the historical payment mean minus two times the historical payment standard deviation is determined as the minimum value of the reasonable payment amount range; Before matching the target payment time with the reasonable payment time of the target receiving user and determining the time risk level of the target transaction, the method further includes: The reasonable payment time of the target receiving user is determined according to multiple historical payment times of the target receiving user.

5. The method according to claim 3, characterized in that: The target payment information also includes a target payment channel; Before performing risk control on the target transaction according to the amount risk level, the time risk level and the user risk level of the target transaction, the method further includes: Matching the target payment channel with the preset payment channel of the target receiving user to determine the channel risk level of the target transaction; The performing risk control on the target transaction according to the amount risk level, the time risk level and the user risk level of the target transaction comprises: The target transaction is risk controlled according to the amount risk level, the time risk level, the user risk level and the channel risk level of the target transaction.

6. The method according to claim 3, characterized in that The user risk level includes PR value risk level, blacklist risk level and anti-money laundering risk level; Determining the user risk level of the target transaction according to the PageRank value of the target paying user includes: According to the PageRank value of the target paying user, the PR value risk level of the target transaction is obtained; Traversing the blacklist according to the target paying user, obtaining the blacklist risk level of the target transaction; Perform anti-money laundering detection on the target payment user to obtain the anti-money laundering risk level of the target transaction.

7. The method according to claim 5, characterized in that The channel risk level includes the channel compliance risk level and the channel spot check risk level; The matching of the target payment channel with the preset payment channel of the target receiving user to determine the channel risk level of the target transaction includes: Matching the target payment channel with the preset payment channel of the target receiving user to obtain the channel compliance risk level of the target transaction; The probability of the target transaction being spot-checked is predicted based on the spot-check model, and the channel spot-check risk level of the target transaction is obtained.

8. A wind control device, characterized in that: include: An acquisition module, used to acquire a target transaction application, wherein the target transaction application includes a target payment user and target payment information; A calculation module, used to calculate the PageRank value of the target payment user according to a payment user relationship graph, wherein the payment user relationship graph includes a plurality of nodes, two adjacent nodes are connected by weighted edges, each node represents a payment user, and the weight depends on the type and quantity of the same information in the historical transaction information of the two corresponding adjacent payment users, and the target payment user is one of the plurality of payment users; A risk control module, used to perform risk control on a target transaction according to the PageRank value of the target paying user and the target payment information; The reconciliation module is used to reconcile the target transaction according to the target transaction identifier after the target transaction is completed, and the target transaction identifier is an identifier generated when the target transaction is completed.

9. An electronic device, characterized in that: include: A processor, wherein the processor is used to execute a computer program stored in a memory, wherein the computer program, when executed by the processor, implements the steps of the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images