Risk control method and device for real-time transfer transactions

Abstract

The present invention provides a risk control method and device for real-time transfer transactions, relating to the technical field of transaction data processing, including: classifying historical transfer transactions to obtain multiple transfer transaction categories; clustering the historical transfer transactions included in each transfer transaction category to obtain multiple transfer transaction subsets; for each transfer transaction subset, determining risk indicators of the transfer transaction subset with respect to each dimension; for each customer authentication method, determining risk indicators of the customer authentication method with respect to each dimension; for each real-time transfer transaction, determining the corresponding transfer transaction category and the corresponding transfer transaction subset of the real-time transfer transaction; based on the transfer transaction subset corresponding to the real-time transfer transaction, determining risk indicators of the real-time transfer transaction with respect to each dimension; based on the risk indicators of the real-time transfer transaction with respect to each dimension and the risk indicators of each customer authentication method with respect to each dimension, determining the corresponding customer authentication method of the real-time transfer transaction.

Description

Technical Field

[0001] The present invention relates to the technical field of transaction data processing, and in particular to a risk control method and device for real-time transfer transactions. Background Art

[0002] This section is intended to provide a background or context to the embodiments of the invention recited in the claims. No admission is made that the description herein is prior art by inclusion in this section.

[0003] Currently, customers may face various risks during the transfer transaction process, which may cause financial security issues.

[0004] In the prior art, the prevention of bank transfer security risks is mainly achieved through the following methods: 1. Extending the transfer time; 2. Limiting the transfer amount. When the transfer amount is large, it will be handled by staff; 3. Manual early warning control. For the above method 1, there is a slow deposit speed, which affects the experience of risk-free customers; for the above method 2, the large amount limit is set high and cannot be controlled in real time. For the above method 3, there is a defect of wasting manpower.

[0005] In summary, there is an urgent need for a technical solution that can overcome the above-mentioned defects and effectively control the risks of real-time transfer transactions. Summary of the invention

[0006] In order to solve the problems existing in the prior art, the present invention proposes a risk control method and device for real-time transfer transactions.

[0007] In a first aspect of an embodiment of the present invention, a risk control method for a real-time transfer transaction is proposed, comprising:

[0008] Classify historical transfer transactions and obtain multiple transfer transaction categories;

[0009] Clustering the historical transfer transactions included in each transfer transaction category to obtain multiple transfer transaction subsets;

[0010] For each transfer transaction subset, determine the risk index of the transfer transaction subset with respect to each dimension;

[0011] For each customer authentication method, determine the risk indicators of each dimension of the customer authentication method;

[0012] For each real-time transfer transaction, determine the transfer transaction category and the corresponding transfer transaction subset corresponding to the real-time transfer transaction; and determine the risk indicators of the real-time transfer transaction in various dimensions according to the transfer transaction subset corresponding to the real-time transfer transaction;

[0013] Determine the customer authentication method corresponding to the real-time transfer transaction based on the risk indicators of the real-time transfer transaction in each dimension and the risk indicators of various customer authentication methods in each dimension.

[0014] In a second aspect of the embodiments of the present invention, a risk control device for real-time transfer transactions is proposed, including:

[0015] A classification module, configured to classify historical transfer transactions to obtain multiple transfer transaction categories;

[0016] A clustering module, configured to cluster the historical transfer transactions included in each transfer transaction category to obtain multiple transfer transaction subsets;

[0017] A transfer transaction subset analysis module, configured to determine the risk indicators of each transfer transaction subset in each dimension;

[0018] A customer authentication method analysis module, configured to determine the risk indicators of each customer authentication method in each dimension;

[0019] A real-time transfer transaction analysis module, configured to determine the transfer transaction category and the corresponding transfer transaction subset corresponding to each real-time transfer transaction; based on the transfer transaction subset corresponding to the real-time transfer transaction, determine the risk indicators of the real-time transfer transaction in each dimension;

[0020] A risk control module, configured to determine the customer authentication method corresponding to the real-time transfer transaction based on the risk indicators of the real-time transfer transaction in each dimension and the risk indicators of various customer authentication methods in each dimension.

[0021] In a third aspect of the embodiments of the present invention, a computer device is proposed, including a memory, a processor, and a computer program stored on the memory and executable on the processor, where when the processor executes the computer program, a risk control method for real-time transfer transactions is implemented.

[0022] In a fourth aspect of the embodiments of the present invention, a computer-readable storage medium is proposed, where the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, a risk control method for real-time transfer transactions is implemented.

[0023] In a fifth aspect of the embodiments of the present invention, a computer program product is proposed, where the computer program product includes a computer program, and when the computer program is executed by a processor, a risk control method for real-time transfer transactions is implemented.

[0024] The risk control method and device for real-time transfer transactions proposed by the present invention classify historical transfer transactions to obtain multiple transfer transaction categories; cluster the historical transfer transactions included in each transfer transaction category to obtain multiple transfer transaction subsets; for each transfer transaction subset, determine the risk indicators of the transfer transaction subset with respect to each dimension; for each customer authentication method, determine the risk indicators of the customer authentication method with respect to each dimension; for each real-time transfer transaction, determine the corresponding transfer transaction category and the corresponding transfer transaction subset; based on the transfer transaction subset corresponding to the real-time transfer transaction, determine the risk indicators of the real-time transfer transaction with respect to each dimension; based on the risk indicators of the real-time transfer transaction with respect to each dimension and the risk indicators of each customer authentication method with respect to each dimension, determine the customer authentication method corresponding to the real-time transfer transaction. The overall solution can effectively control the risk of real-time transfer transactions, reduce the risk of real-time transfers, and protect the safety of customers' funds. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0026] Figure 1 It is a schematic flowchart of the risk control method for real-time transfer transactions according to an embodiment of the present invention.

[0027] Figure 2 It is a schematic flowchart of clustering the historical transfer transactions included in each transfer transaction category according to an embodiment of the present invention.

[0028] Figure 3 It is a specific schematic flowchart of determining the risk indicators of a transfer transaction subset with respect to each dimension according to an embodiment of the present invention.

[0029] Figure 4 It is a specific schematic flowchart of determining the risk indicators of a customer authentication method with respect to each dimension according to an embodiment of the present invention.

[0030] Figure 5 It is a specific schematic flowchart of determining the customer authentication method corresponding to a real-time transfer transaction according to an embodiment of the present invention.

[0031] Figure 6 It is a schematic diagram of the architecture of the risk control device for real-time transfer transactions according to an embodiment of the present invention.

[0032] Figure 7 It is a schematic diagram of the structure of a computer device according to an embodiment of the present invention. Detailed Implementation Modes

[0033] The principles and spirit of the present invention will be described below with reference to several exemplary implementation modes. It should be understood that these implementation modes are provided only to enable those skilled in the art to better understand and then implement the present invention, rather than limiting the scope of the present invention in any way. On the contrary, these implementation modes are provided to make the present disclosure more thorough and complete, and to be able to fully convey the scope of the present disclosure to those skilled in the art.

[0034] Those skilled in the art know that the implementation modes of the present invention can be realized as a system, a device, an equipment, a method or a computer program product. Therefore, the present disclosure can be specifically realized in the following forms, namely: completely hardware, completely software (including firmware, resident software, microcode, etc.), or a combination of hardware and software.

[0035] According to an implementation mode of the present invention, a risk control method and device for real-time transfer transactions are proposed, which relate to the technical field of transaction data processing.

[0036] The principles and spirit of the present invention will be elaborated in detail below with reference to several representative implementation modes of the present invention.

[0037] Figure 1 It is a schematic flowchart of a risk control method for real-time transfer transactions according to an embodiment of the present invention. As Figure 1 shown, the method includes:

[0038] S1. Classify historical transfer transactions to obtain multiple transfer transaction categories;

[0039] S2. Cluster the historical transfer transactions included in each transfer transaction category to obtain multiple transfer transaction subsets;

[0040] S3. For each transfer transaction subset, determine the risk indicators of the transfer transaction subset in each dimension;

[0041] S4. For each customer authentication method, determine the risk indicators of the customer authentication method in each dimension;

[0042] S5. For each real-time transfer transaction, determine the corresponding transfer transaction category and the corresponding transfer transaction subset of the real-time transfer transaction; according to the transfer transaction subset corresponding to the real-time transfer transaction, determine the risk indicators of the real-time transfer transaction in each dimension;

[0043] S6. According to the risk indicators of the real-time transfer transaction in each dimension and the risk indicators of each customer authentication method in each dimension, determine the customer authentication method corresponding to the real-time transfer transaction.

[0044] Among them, the dimensions at least include: transfer scenario, transfer time, transfer currency, customer category; in actual application scenarios, other dimensions may also be included.

[0045] To explain the above risk control method for real-time transfer transactions more clearly, the following will be described in detail in combination with each step.

[0046] In S1, classify historical transfer transactions to obtain multiple transfer transaction categories.

[0047] Specifically, historical transfer transactions can be classified according to transaction time, transfer channel, transaction amount level, customer category of the transfer customer, and customer category of the transfer counterparty.

[0048] In S2, refer to Figure 2 , for the historical transfer transactions included in each transfer transaction category, the specific method for clustering to obtain multiple transfer transaction subsets is as follows:

[0049] S201, according to the historical transfer transactions included in each transfer transaction category, obtain the transaction data of the transfer customer corresponding to the historical transfer transaction and the transaction data of the transfer counterparty.

[0050] S202, based on the transaction data of the transfer customer and the transaction data of the transfer counterparty, determine the first transfer vector and the second transfer vector corresponding to the historical transfer transaction.

[0051] S203, based on the first transfer vector and the second transfer vector, determine the function corresponding to the transfer transaction, where the function is used to determine the distance between any two transfer transactions.

[0052] S204, based on the function corresponding to the transfer transaction, cluster the historical transfer transactions included in the transfer transaction category to obtain multiple transfer transaction subsets.

[0053] Specifically, for any two transfer transactions, the function can be used to determine the distance between the two transfer transactions as the sum of the distances of the corresponding first transfer vectors and the corresponding second transfer vectors of the two transfer transactions, and then clustering is performed to obtain multiple transfer transaction subsets.

[0054] For example, execute S1 to classify historical transfer transactions, and the obtained transfer transaction categories are A, B, and C;

[0055] After S2, the multiple transfer transaction subsets obtained are:

[0056] Cluster the transactions of transfer transaction category A to obtain transfer transaction subsets A1, A2, A3, and A4;

[0057] Cluster the transactions under transfer transaction category B to obtain transfer transaction subsets B1, B2, and B3;

[0058] Cluster the transactions under transfer transaction category C to obtain transfer transaction subsets C1, C2, and C3;

[0059] That is, each transfer transaction category corresponds to multiple transfer transaction subsets.

[0060] In one embodiment, the specific method for determining the first transfer vector and the second transfer vector corresponding to the historical transfer transaction based on the transaction data of the transfer customer and the transaction data of the transfer counterparty in (S202) is as follows:

[0061] Determine the transaction quantities corresponding to each transaction category in the transaction data of the transfer customer; determine the first transfer vector corresponding to the historical transfer transaction, where the components of the first transfer vector correspond one by one to the transaction categories, and the component value of each component is equal to the transaction quantity of the transaction category corresponding to this component in the transaction data of the transfer customer;

[0062] Determine the transaction quantities corresponding to each transaction category in the transaction data of the transfer counterparty; determine the second transfer vector corresponding to the historical transfer transaction, where the components of the second transfer vector correspond one by one to the transaction categories, and the component value of each component is equal to the transaction quantity of the transaction category corresponding to this component in the transaction data of the transfer counterparty.

[0063] In one embodiment, in (S204), cluster the historical transfer transactions included in the transfer transaction category based on the function corresponding to the transfer transaction to obtain multiple transfer transaction subsets, including:

[0064] Based on the function corresponding to the transfer transaction, select a clustering algorithm to cluster the historical transfer transactions included in the transfer transaction category to obtain multiple transfer transaction subsets;

[0065] Perform the following steps on the obtained transfer transaction subsets until the consistency index corresponding to each transfer transaction subset is greater than or equal to the set value:

[0066] Select the transfer transaction subset whose corresponding consistency index is less than the set value, and cluster the selected transfer transaction subset according to the selected clustering algorithm to obtain multiple new transfer transaction subsets (replacing the selected transfer transaction subset);

[0067] Determine the consistency index corresponding to each new transfer transaction subset.

[0068] Among them, the consistency index corresponding to the subset of transfer transactions can be determined as follows: Determine the risk level of each transfer transaction in the subset of transfer transactions; Take the maximum value of the proportion of the number of transfer transactions corresponding to each risk level in the subset of transfer transactions as the consistency index corresponding to the subset of transfer transactions.

[0069] In S3, refer to Figure 3 , for each subset of transfer transactions, the specific method for determining the risk index of the subset of transfer transactions with respect to each dimension is as follows:

[0070] S301. For each subset of transfer transactions, determine the transfer transaction data corresponding to each dimension in the subset of transfer transactions;

[0071] S302. For each dimension, divide the transfer transaction data corresponding to the dimension into multiple subsets of transfer transaction data corresponding to the dimension in chronological order;

[0072] S303. Determine the risk index sample of the subset of transfer transactions with respect to the dimension as the proportion of risky transfer transactions in each subset of transfer transaction data corresponding to the dimension;

[0073] Among them, a risky transfer transaction is a transfer transaction with risks, such as a transfer transaction related to fraud or a transfer transaction with a transfer amount higher than a set value. Whether a transfer has risks can be judged by bank staff or determined by a transfer risk prediction model.

[0074] S304. Determine the risk index of the subset of transfer transactions with respect to the dimension as the mean value of the risk index sample of the subset of transfer transactions with respect to the dimension.

[0075] In one embodiment, the method further includes:

[0076] After obtaining the risk index sample of the subset of transfer transactions with respect to the dimension in (S303), based on the obtained risk index sample of the subset of transfer transactions with respect to the dimension, determine the variance μ and the sample quantity n of the risk index of the subset of transfer transactions with respect to the dimension;

[0077] Set an acceptable index error threshold ε and the probability that the acceptable index error is greater than ε;

[0078] Determine and ε 2 ×P's magnitude relationship;

[0079] When , perform the following steps until all the risk index samples m of the subset of transfer transactions with respect to the dimension obtained satisfy

[0080] Obtain the new transfer transaction data of the transfer transaction subset regarding this dimension;

[0081] Divide the new transfer transaction data into multiple new transfer transaction data subsets corresponding to this dimension in chronological order;

[0082] Determine the risk index sample of the transfer transaction subset regarding this dimension as the proportion of risky transfer transactions in each new transfer transaction data subset corresponding to this dimension;

[0083] When , determine the risk index of the transfer transaction subset regarding this dimension as the mean of all risk index samples of the transfer transaction subset regarding this dimension.

[0084] In S4, referring to Figure 4 , for each customer authentication method, the specific method for determining the risk index of this customer authentication method regarding each dimension is as follows:

[0085] S401, for each customer authentication method, obtain the authentication data of this customer authentication method;

[0086] S402, determine the authentication data corresponding to each dimension in the authentication data of this customer authentication method;

[0087] S403, for each dimension, divide the authentication data corresponding to this dimension into multiple authentication data subsets corresponding to this dimension in chronological order;

[0088] S404, determine the risk index sample of this customer authentication method regarding this dimension as the proportion of risky authentication data in each authentication data subset corresponding to this dimension;

[0089] Among them, risky authentication data is the authentication data with risks in customer authentication data, such as the password being stolen, and the face being imitated and successfully authenticated.

[0090] S405, determine the risk index of this customer authentication method regarding this dimension as the mean of the risk index samples of this customer authentication method regarding this dimension.

[0091] In S5, for each real-time transfer transaction, determine the corresponding transfer transaction category and the corresponding transfer transaction subset; based on the transfer transaction subset corresponding to this real-time transfer transaction, determine the risk index of this real-time transfer transaction regarding each dimension;

[0092] In S6, referring to Figure 5 , based on the risk index of this real-time transfer transaction regarding each dimension and the risk index of each customer authentication method regarding each dimension, the specific method for determining the customer authentication method corresponding to this real-time transfer transaction is as follows:

[0093] S601. Determine the priority probability of each customer authentication method based on the risk indicators of the real-time transfer transaction in each dimension and the risk indicators of various customer authentication methods in each dimension.

[0094] S602. Determine the customer authentication method corresponding to the real-time transfer transaction based on the priority probability of each customer authentication method.

[0095] In one embodiment, the specific method for (S601) determining the priority probability of each customer authentication method based on the risk indicators of the real-time transfer transaction in each dimension and the risk indicators of various customer authentication methods in each dimension is as follows:

[0096] S6011. For each customer authentication method, determine the magnitude relationship between the risk indicators of this customer authentication method in each dimension and the risk indicators of the real-time transfer transaction in each dimension.

[0097] S6012. For each dimension, if the risk indicator of this customer authentication method in this dimension is greater than the risk indicator of the real-time transfer transaction in this dimension, then use the difference between the risk indicator of this customer authentication method in this dimension and the risk indicator of the real-time transfer transaction in this dimension as the first dimension difference corresponding to this customer authentication method.

[0098] S6013. For each dimension, if the risk indicator of the real-time transfer transaction in this dimension is greater than the risk indicator of this customer authentication method in this dimension, then use the difference between the risk indicator of the real-time transfer transaction in this dimension and the risk indicator of this customer authentication method in this dimension as the second dimension difference corresponding to this customer authentication method.

[0099] S6014. Determine the priority probability of each customer authentication method based on the first dimension difference and the corresponding second dimension difference corresponding to each customer authentication method. Among them, the priority probability of the i-th customer authentication method is determined as:

[0100]

[0101] Among them, and are respectively the sum of the first dimension differences corresponding to the i-th customer authentication method and the sum of the corresponding second dimension differences; and are respectively the sum of the first dimension differences corresponding to the j-th customer authentication method and the sum of the corresponding second dimension differences.

[0102] In one embodiment, the specific method for (S602) determining the customer authentication method corresponding to the real-time transfer transaction based on the priority probability of each customer authentication method is as follows:

[0103] S6021. Obtain a probability density function f, and divide the domain of f into multiple non - overlapping intervals. Among them, each interval corresponds to a customer authentication method, and the integral of f over each interval is equal to the priority probability of the customer authentication method corresponding to that interval.

[0104] S6022. Based on f, generate a random number, and determine the customer authentication method corresponding to the real - time transfer transaction as the customer authentication method corresponding to the interval in which the random number is located.

[0105] It should be noted that although the operations of the method of the present invention are described in a specific order in the above embodiments and accompanying drawings, this does not require or imply that these operations must be performed in that specific order, or that all the shown operations must be performed to achieve the desired result. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step for execution, and / or one step may be decomposed into multiple steps for execution.

[0106] After introducing the method of the exemplary embodiment of the present invention, next, reference is made to Figure 6 introduce the risk control device for real - time transfer transactions of the exemplary embodiment of the present invention.

[0107] The implementation of the risk control device for real - time transfer transactions can refer to the implementation of the above - mentioned method, and the repeated parts will not be elaborated. The terms "module" or "unit" used hereinafter can be a combination of software and / or hardware that realizes a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, implementation in hardware, or a combination of software and hardware is also possible and contemplated.

[0108] Based on the same inventive concept, the present invention also proposes a risk control device for real - time transfer transactions, as Figure 6 shown, the device includes:

[0109] A classification module 610, configured to classify historical transfer transactions to obtain multiple transfer transaction categories;

[0110] A clustering module 620, configured to cluster the historical transfer transactions included in each transfer transaction category to obtain multiple transfer transaction subsets;

[0111] A transfer transaction subset analysis module 630, configured to determine the risk indicators of each transfer transaction subset with respect to each dimension;

[0112] A customer authentication method analysis module 640, configured to determine the risk indicators of each customer authentication method with respect to each dimension;

[0113] The real-time transfer transaction analysis module 650 is used to determine the transfer transaction category corresponding to each real-time transfer transaction and the corresponding subset of transfer transactions; and determine the risk indicators of the real-time transfer transaction in each dimension based on the subset of transfer transactions corresponding to the real-time transfer transaction.

[0114] The risk control module 660 is used to determine the customer authentication method corresponding to the real-time transfer transaction based on the risk indicators of the real-time transfer transaction in each dimension and the risk indicators of various customer authentication methods in each dimension.

[0115] In one embodiment, the clustering module is specifically used for:

[0116] Obtain the transaction data of the transfer customer and the transaction data of the transfer counterparty corresponding to the historical transfer transaction according to the historical transfer transactions included in each transfer transaction category;

[0117] Determine the first transfer vector and the second transfer vector corresponding to the historical transfer transaction based on the transaction data of the transfer customer and the transaction data of the transfer counterparty;

[0118] Determine the function corresponding to the transfer transaction based on the first transfer vector and the second transfer vector, where the function is used to determine the distance between any two transfer transactions;

[0119] Cluster the historical transfer transactions included in the transfer transaction category based on the function corresponding to the transfer transaction to obtain multiple subsets of transfer transactions.

[0120] In one embodiment, the clustering module is specifically used for:

[0121] Determine the number of transactions corresponding to each transaction category in the transaction data of the transfer customer; determine the first transfer vector corresponding to the historical transfer transaction, where the components of the first transfer vector correspond one by one to the transaction categories, and the component value of each component is equal to the number of transactions corresponding to the transaction category corresponding to the component in the transaction data of the transfer customer;

[0122] Determine the number of transactions corresponding to each transaction category in the transaction data of the transfer counterparty; determine the second transfer vector corresponding to the historical transfer transaction, where the components of the second transfer vector correspond one by one to the transaction categories, and the component value of each component is equal to the number of transactions corresponding to the transaction category corresponding to the component in the transaction data of the transfer counterparty.

[0123] In one embodiment, the transfer transaction subset analysis module is specifically used for:

[0124] For each subset of transfer transactions, determine the transfer transaction data corresponding to each dimension in the subset of transfer transactions;

[0125] For each dimension, divide the transfer transaction data corresponding to that dimension into multiple subsets of transfer transaction data corresponding to that dimension in chronological order;

[0126] Determine the risk index sample of the transfer transaction subset with respect to that dimension as the proportion of risky transfer transactions in each subset of transfer transaction data corresponding to that dimension;

[0127] Determine the risk index of the transfer transaction subset with respect to that dimension as the mean value of the risk index samples of the transfer transaction subset with respect to that dimension.

[0128] In one embodiment, the customer authentication method analysis module is specifically configured to:

[0129] For each customer authentication method, obtain the authentication data of that customer authentication method;

[0130] Determine the authentication data corresponding to each dimension in the authentication data of that customer authentication method;

[0131] For each dimension, divide the authentication data corresponding to that dimension into multiple subsets of authentication data corresponding to that dimension in chronological order;

[0132] Determine the risk index sample of the customer authentication method with respect to that dimension as the proportion of risky authentication data in each subset of authentication data corresponding to that dimension;

[0133] Determine the risk index of the customer authentication method with respect to that dimension as the mean value of the risk index samples of the customer authentication method with respect to that dimension.

[0134] In one embodiment, the risk control module is specifically configured to:

[0135] Based on the risk indices of the real-time transfer transaction with respect to each dimension and the risk indices of each customer authentication method with respect to each dimension, determine the priority probabilities of each customer authentication method;

[0136] Based on the priority probabilities of each customer authentication method, determine the customer authentication method corresponding to the real-time transfer transaction.

[0137] In one embodiment, the risk control module is specifically configured to:

[0138] For each customer authentication method, determine the magnitude relationship between the risk index of that customer authentication method with respect to each dimension and the risk index of the real-time transfer transaction with respect to each dimension;

[0139] For each dimension, if the risk indicator of the customer authentication method for this dimension is greater than the risk indicator of the real-time transfer transaction for this dimension, then the difference between the risk indicator of the customer authentication method for this dimension and the risk indicator of the real-time transfer transaction for this dimension is used as the first dimension difference corresponding to the customer authentication method;

[0140] For each dimension, if the risk indicator of the real-time transfer transaction for this dimension is greater than the risk indicator of the customer authentication method for this dimension, then the difference between the risk indicator of the real-time transfer transaction for this dimension and the risk indicator of the customer authentication method for this dimension is used as the second dimension difference corresponding to the customer authentication method;

[0141] Based on the first dimension differences and the corresponding second dimension differences corresponding to each customer authentication method, determine the priority probabilities of each customer authentication method; among them, the priority probability of the i-th customer authentication method is determined as:

[0142]

[0143] Among them, and are respectively the sum of the first dimension differences and the sum of the corresponding second dimension differences corresponding to the i-th customer authentication method; and are respectively the sum of the first dimension differences and the sum of the corresponding second dimension differences corresponding to the j-th customer authentication method.

[0144] It should be noted that although several modules of the risk control device for real-time transfer transactions are mentioned in the above detailed description, this division is only exemplary and not mandatory. In fact, according to the embodiments of the present invention, the features and functions of the two or more modules described above can be embodied in one module. Conversely, the features and functions of one module described above can be further divided and embodied by multiple modules.

[0145] Based on the foregoing inventive concept, as Figure 7 shown, the present invention also proposes a computer device 700, including a memory 710, a processor 720, and a computer program 730 stored on the memory 710 and executable on the processor 720. When the processor 720 executes the computer program 730, the foregoing risk control method for real-time transfer transactions is implemented.

[0146] Based on the foregoing inventive concept, the present invention proposes a computer-readable storage medium. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the foregoing risk control method for real-time transfer transactions is implemented.

[0147] Based on the foregoing inventive concept, the present invention provides a computer program product, which includes a computer program that, when executed by a processor, implements a risk control method for real-time transfer transactions.

[0148] The risk control method and apparatus for real-time transfer transactions proposed by the present invention classify historical transfer transactions to obtain multiple transfer transaction categories; cluster the historical transfer transactions included in each transfer transaction category to obtain multiple transfer transaction subsets; for each transfer transaction subset, determine the risk indicators of the transfer transaction subset with respect to each dimension; for each customer authentication method, determine the risk indicators of the customer authentication method with respect to each dimension; for each real-time transfer transaction, determine the corresponding transfer transaction category and the corresponding transfer transaction subset; based on the transfer transaction subset corresponding to the real-time transfer transaction, determine the risk indicators of the real-time transfer transaction with respect to each dimension; based on the risk indicators of the real-time transfer transaction with respect to each dimension and the risk indicators of each customer authentication method with respect to each dimension, determine the customer authentication method corresponding to the real-time transfer transaction. The overall solution can effectively control the risks of real-time transfer transactions, reduce the risks of real-time transfers, and protect the safety of customers' funds.

[0149] Those skilled in the art should understand that the embodiments of the present invention can be provided as methods, apparatuses, or computer program products. Therefore, the present invention can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memories, CD-ROMs, optical memories, etc.) containing computer-usable program code.

[0150] The present invention is described with reference to the flowcharts and / or block diagrams of methods and computer program products according to embodiments of the present invention. It should be understood that each flow and / or block in the flowchart and / or block diagram, and the combination of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing devices generate an apparatus for implementing the functions specified in Figure 1 one or more of the processes or multiple processes and / or blocks Figure 1 one or more of the blocks or multiple blocks.

[0151] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to operate in a particular manner, such that the instructions stored in the computer-readable memory produce a manufacture including an instruction device that implements the functions specified in one or more of the processes and / or blocks Figure 1 in one or more of the processes and / or blocks Figure 1 specified in one or more of the blocks or blocks.

[0152] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus, such that a series of operational steps are performed on the computer or other programmable apparatus to produce a computer-implemented process, whereby the instructions executed on the computer or other programmable apparatus provide steps for implementing the functions specified in one or more of the processes and / or blocks Figure 1 in one or more of the processes and / or blocks Figure 1 specified in one or more of the blocks or blocks.

[0153] Finally, it should be noted that the above-described embodiments are only specific embodiments of the present invention, which are used to illustrate the technical solutions of the present invention, rather than to limit them. The protection scope of the present invention is not limited thereto. Although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: any person skilled in the art can still modify the technical solutions described in the foregoing embodiments, or can easily conceive of changes, or equivalently replace some of the technical features; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be covered by the protection scope of the present invention. Therefore, the protection scope of the present invention should be determined by the protection scope of the claims.

Claims

1. A risk control method for real-time transfer transactions, characterized in that, Including: Classify historical transfer transactions to obtain multiple transfer transaction categories; Cluster the historical transfer transactions included in each transfer transaction category to obtain multiple transfer transaction subsets; For each transfer transaction subset, determine the risk indicators of this transfer transaction subset for each dimension; For each customer authentication method, determine the risk indicators of this customer authentication method for each dimension; For each real-time transfer transaction, determine the corresponding transfer transaction category and the corresponding transfer transaction subset of this real-time transfer transaction; based on the transfer transaction subset corresponding to this real-time transfer transaction, determine the risk indicators of this real-time transfer transaction for each dimension; Based on the risk indicators of this real-time transfer transaction for each dimension and the risk indicators of various customer authentication methods for each dimension, determine the customer authentication method corresponding to this real-time transfer transaction; Among them, based on the risk indicators of this real-time transfer transaction for each dimension and the risk indicators of various customer authentication methods for each dimension, determining the customer authentication method corresponding to this real-time transfer transaction includes: Based on the risk indicators of this real-time transfer transaction for each dimension and the risk indicators of various customer authentication methods for each dimension, determine the priority probabilities of each customer authentication method; Based on the priority probabilities of each customer authentication method, determine the customer authentication method corresponding to this real-time transfer transaction; Among them, based on the risk indicators of this real-time transfer transaction for each dimension and the risk indicators of various customer authentication methods for each dimension, determining the priority probabilities of each customer authentication method includes: For each customer authentication method, determine the magnitude relationship between the risk indicators of this customer authentication method for each dimension and the risk indicators of this real-time transfer transaction for each dimension; For each dimension, if the risk indicator of this customer authentication method for this dimension is greater than the risk indicator of this real-time transfer transaction for this dimension, then use the difference between the risk indicator of this customer authentication method for this dimension and the risk indicator of this real-time transfer transaction for this dimension as the first dimension difference corresponding to this customer authentication method; For each dimension, if the risk indicator of this real-time transfer transaction for this dimension is greater than the risk indicator of this customer authentication method for this dimension, then use the difference between the risk indicator of this real-time transfer transaction for this dimension and the risk indicator of this customer authentication method for this dimension as the second dimension difference corresponding to this customer authentication method; Based on the first dimension differences and the corresponding second dimension differences corresponding to each customer authentication method, determine the priority probabilities of each customer authentication method; among them, the priority probability of the i-th customer authentication method is determined as: Among them, and are respectively the sum of the first - dimension differences and the sum of the second - dimension differences corresponding to the i - th customer authentication method; and are respectively the sum of the first - dimension differences and the sum of the second - dimension differences corresponding to the j - th customer authentication method; Among them, based on the priority probabilities of each customer authentication method, determining the customer authentication method corresponding to this real-time transfer transaction includes: Obtain a probability density function f, divide the domain of f into multiple non-overlapping intervals, where each interval corresponds to a customer authentication method, and the integral of f over each interval is equal to the priority probability of the customer authentication method corresponding to this interval; Based on f, generate a random number, and determine the customer authentication method corresponding to this real-time transfer transaction as the customer authentication method corresponding to the interval where this random number is located.

2. The method according to claim 1, wherein Cluster the historical transfer transactions included in each transfer transaction category to obtain multiple transfer transaction subsets, including: According to the historical transfer transactions included in each transfer transaction category, obtain the transaction data of the transfer customers corresponding to the historical transfer transactions and the transaction data of the transfer counterparts; Based on the transaction data of the transfer customers and the transaction data of the transfer counterparts, determine the first transfer vector and the second transfer vector corresponding to the historical transfer transaction; Based on the first transfer vector and the second transfer vector, determine the function corresponding to the transfer transaction, where the function is used to determine the distance between any two transfer transactions; Based on the function corresponding to the transfer transaction, cluster the historical transfer transactions included in the transfer transaction category to obtain multiple transfer transaction subsets.

3. The method according to claim 2, wherein Based on the transaction data of the transfer customers and the transaction data of the transfer counterparts, determine the first transfer vector and the second transfer vector corresponding to the historical transfer transaction, including: Determine the transaction quantities corresponding to each transaction category in the transaction data of the transfer customers; determine the first transfer vector corresponding to the historical transfer transaction, where the components of the first transfer vector correspond one-to-one with the transaction categories, and the component value of each component is equal to the transaction quantity corresponding to the transaction category corresponding to the component in the transaction data of the transfer customers; Determine the transaction quantities corresponding to each transaction category in the transaction data of the transfer counterparts; determine the second transfer vector corresponding to the historical transfer transaction, where the components of the second transfer vector correspond one-to-one with the transaction categories, and the component value of each component is equal to the transaction quantity corresponding to the transaction category corresponding to the component in the transaction data of the transfer counterparts.

4. The method according to claim 1, characterized in that, For each transfer transaction subset, determine the risk indicators of the transfer transaction subset for each dimension, including: For each transfer transaction subset, determine the transfer transaction data corresponding to each dimension in the transfer transaction subset; For each dimension, divide the transfer transaction data corresponding to the dimension into multiple transfer transaction data subsets corresponding to the dimension in chronological order; Determine the risk indicator sample of the transfer transaction subset for the dimension as the proportion of risky transfer transactions in each transfer transaction data subset corresponding to the dimension; Determine the risk indicator of the transfer transaction subset for the dimension as the mean of the risk indicator samples of the transfer transaction subset for the dimension.

5. The method according to claim 1, characterized in that For each customer authentication method, determine the risk indicators of the customer authentication method for each dimension, including: For each customer authentication method, obtain the authentication data of the customer authentication method; Determine the authentication data corresponding to each dimension in the authentication data of the customer authentication method; For each dimension, divide the authentication data corresponding to the dimension into multiple authentication data subsets corresponding to the dimension in chronological order; Determine the risk indicator sample of the customer authentication method for the dimension as the proportion of risky authentication data in each authentication data subset corresponding to the dimension; Determine the risk indicator of the customer authentication method for the dimension as the mean of the risk indicator samples of the customer authentication method for the dimension.

6. A risk control device for real-time transfer transactions, characterized in that, Including: A classification module for classifying historical transfer transactions to obtain multiple transfer transaction categories; A clustering module, which is used to cluster the historical transfer transactions included in each transfer transaction category to obtain multiple subsets of transfer transactions; A transfer transaction subset analysis module, which is used to determine the risk indicators of each transfer transaction subset with respect to each dimension; A customer authentication method analysis module, which is used to determine the risk indicators of each customer authentication method with respect to each dimension; A real-time transfer transaction analysis module, which is used to determine the transfer transaction category corresponding to each real-time transfer transaction and the corresponding subset of transfer transactions; and determine the risk indicators of the real-time transfer transaction with respect to each dimension according to the subset of transfer transactions corresponding to the real-time transfer transaction; A risk control module, which is used to determine the customer authentication method corresponding to the real-time transfer transaction according to the risk indicators of the real-time transfer transaction with respect to each dimension and the risk indicators of various customer authentication methods with respect to each dimension; Among them, the risk control module is specifically used for: Determining the priority probabilities of each customer authentication method according to the risk indicators of the real-time transfer transaction with respect to each dimension and the risk indicators of various customer authentication methods with respect to each dimension; Determining the customer authentication method corresponding to the real-time transfer transaction according to the priority probabilities of each customer authentication method; Among them, determining the priority probabilities of each customer authentication method according to the risk indicators of the real-time transfer transaction with respect to each dimension and the risk indicators of various customer authentication methods with respect to each dimension includes: For each customer authentication method, determining the magnitude relationship between the risk indicators of the customer authentication method with respect to each dimension and the risk indicators of the real-time transfer transaction with respect to each dimension; For each dimension, if the risk indicator of the customer authentication method with respect to the dimension is greater than the risk indicator of the real-time transfer transaction with respect to the dimension, then taking the difference between the risk indicator of the customer authentication method with respect to the dimension and the risk indicator of the real-time transfer transaction with respect to the dimension as the first dimension difference corresponding to the customer authentication method; For each dimension, if the risk indicator of the real-time transfer transaction with respect to the dimension is greater than the risk indicator of the customer authentication method with respect to the dimension, then taking the difference between the risk indicator of the real-time transfer transaction with respect to the dimension and the risk indicator of the customer authentication method with respect to the dimension as the second dimension difference corresponding to the customer authentication method; Determining the priority probabilities of each customer authentication method according to the first dimension differences and the corresponding second dimension differences corresponding to each customer authentication method; among them, the priority probability of the i-th customer authentication method is determined as: Among them, and are the sum of the first-dimensional differences and the sum of the second-dimensional differences corresponding to the i-th customer authentication method, respectively; and are the sum of the first-dimensional differences and the sum of the second-dimensional differences corresponding to the j-th customer authentication method, respectively; Among them, determining the customer authentication method corresponding to the real-time transfer transaction according to the priority probabilities of each customer authentication method includes: Obtaining a probability density function f, dividing the domain of f into multiple non-overlapping intervals, where each interval corresponds to a customer authentication method, and the integral of f over each interval is equal to the priority probability of the customer authentication method corresponding to the interval; Generating a random number based on f, and determining the customer authentication method corresponding to the real-time transfer transaction as the customer authentication method corresponding to the interval where the random number is located.

7. The device according to claim 6, characterized in that, The clustering module is specifically used for: Obtain the transaction data of the transfer customer and the transaction data of the transfer counterparty corresponding to the historical transfer transaction according to the historical transfer transactions included in each transfer transaction category; Determine the first transfer vector and the second transfer vector corresponding to the historical transfer transaction based on the transaction data of the transfer customer and the transaction data of the transfer counterparty; Determine the function corresponding to the transfer transaction based on the first transfer vector and the second transfer vector, where the function is used to determine the distance between any two transfer transactions; Cluster the historical transfer transactions included in the transfer transaction category based on the function corresponding to the transfer transaction to obtain multiple transfer transaction subsets.

8. The device according to claim 7, characterized in that The clustering module is specifically used for: Determine the number of transactions corresponding to each transaction category in the transaction data of the transfer customer; determine the first transfer vector corresponding to the historical transfer transaction, where the components of the first transfer vector correspond one-to-one with the transaction categories, and the component value of each component is equal to the number of transactions corresponding to the transaction category corresponding to the component in the transaction data of the transfer customer; Determine the number of transactions corresponding to each transaction category in the transaction data of the transfer counterparty; determine the second transfer vector corresponding to the historical transfer transaction, where the components of the second transfer vector correspond one-to-one with the transaction categories, and the component value of each component is equal to the number of transactions corresponding to the transaction category corresponding to the component in the transaction data of the transfer counterparty.

9. The device according to claim 6, characterized in that, The transfer transaction subset analysis module is specifically used for: For each transfer transaction subset, determine the transfer transaction data corresponding to each dimension in the transfer transaction subset; For each dimension, divide the transfer transaction data corresponding to the dimension into multiple transfer transaction data subsets corresponding to the dimension in chronological order; Determine the risk index sample of the transfer transaction subset with respect to the dimension as the proportion of risky transfer transactions in each transfer transaction data subset corresponding to the dimension; Determine the risk index of the transfer transaction subset with respect to the dimension as the mean of the risk index samples of the transfer transaction subset with respect to the dimension.

10. The device according to claim 6, characterized in that, The customer authentication method analysis module is specifically used for: For each customer authentication method, obtain the authentication data of the customer authentication method; Determine the authentication data corresponding to each dimension in the authentication data of the customer authentication method; For each dimension, divide the authentication data corresponding to the dimension into multiple authentication data subsets corresponding to the dimension in chronological order; Determine the risk index sample of the customer authentication method with respect to the dimension as the proportion of risky authentication data in each authentication data subset corresponding to the dimension; Determine the risk index of the customer authentication method with respect to the dimension as the mean of the risk index samples of the customer authentication method with respect to the dimension.

11. A computer device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, When the processor executes the computer program, the method according to any one of claims 1 to 5 is implemented.

12. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 5 is implemented.

13. A computer program product, characterized in that, The computer program product includes a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 5 is implemented.

Images