Risk control method and device for bank transfer transaction

Abstract

The present invention provides a risk control method and device for bank transfer transactions, which are applied to the field of financial technology. The method includes: constructing a transaction space; obtaining the historical transfer transaction data of the bank, and determining the first coordinate and the second coordinate of each historical transfer transaction data in the transaction space; classifying the historical transfer transaction data of the bank to obtain multiple transfer subsets; for each transfer subset, determining the corresponding relationship between the positive correlation parameter of the transfer subset and the transfer risk probability; for each customer, determining the transfer risk probability corresponding to the customer; when the customer is transferring, determining the transfer subset corresponding to the transfer based on the transaction data of the transfer; determining the positive correlation parameter corresponding to the transfer based on the corresponding relationship between the positive correlation parameter of the transfer subset corresponding to the transfer and the transfer risk probability, and the transfer risk probability corresponding to the customer. The present invention can control the risk of bank transfer transactions.

Description

Technical Field

[0001] The present invention relates to the field of financial technology, and in particular to a risk control method and device for bank transfer transactions. Background Art

[0002] At present, when a customer transfers money on a smart terminal, after entering the counterparty's account number, the system will echo some of the counterparty's information. After the customer confirms that it is correct, the server executes the transfer transaction. This process has certain risks for the customer. For example, if the customer enters the wrong counterparty account number, the customer's partial information corresponding to the account number just corresponds to the correct counterparty's partial information. Therefore, it is necessary to control the risks of bank transfer transactions. Summary of the invention

[0003] The embodiment of the present invention provides a risk control method for a bank transfer transaction, which is used to control the risk of a bank transfer transaction. The method includes:

[0004] Construct a transaction space, where each dimension of the transaction space corresponds to a transaction category of the bank;

[0005] Obtain the historical transfer transaction data of the bank, and determine the first coordinate and the second coordinate of each historical transfer transaction data in the transaction space;

[0006] Classify the historical transfer transaction data of the bank according to the first coordinate and the second coordinate to obtain multiple transfer subsets;

[0007] For each transfer subset, determining the corresponding relationship between the positive correlation parameter of the transfer subset and the transfer risk probability;

[0008] For each customer, determine the corresponding transfer risk probability of the customer;

[0009] When a customer is transferring money, the transfer sub-set corresponding to the transfer is determined based on the transaction data of the transfer;

[0010] Based on the correspondence between the positive correlation parameters of the transfer subset corresponding to this transfer and the transfer risk probability, as well as the transfer risk probability corresponding to the customer, the positive correlation parameters corresponding to this transfer are determined, and the positive correlation coefficient is used to represent the transaction parameters that are positively correlated with the risk when the bank makes a transfer.

[0011] The embodiment of the present invention provides a risk control device for a bank transfer transaction, which is used to control the risk of a bank transfer transaction. The device includes:

[0012] A transaction space construction module is used to construct a transaction space, where each dimension of the transaction space corresponds to a transaction category of the bank;

[0013] A historical transfer transaction data acquisition module is used to obtain the historical transfer transaction data of the bank and determine the first coordinate and the second coordinate of each historical transfer transaction data in the transaction space;

[0014] A transfer transaction data classification module, used to classify the historical transfer transaction data of the bank according to the first coordinate and the second coordinate to obtain multiple transfer subsets;

[0015] A relationship determination module, used to determine, for each transfer subset, a corresponding relationship between a positive correlation parameter of the transfer subset and a transfer risk probability;

[0016] A transfer risk probability determination module, used to determine the transfer risk probability corresponding to each customer;

[0017] The current transfer sub-set determination module is used to determine the transfer sub-set corresponding to the current transfer based on the transaction data of the current transfer when the customer is making a transfer;

[0018] The positive correlation parameter determination module is used to determine the positive correlation parameter corresponding to this transfer based on the correspondence between the positive correlation parameter of the transfer subset corresponding to this transfer and the transfer risk probability, and the transfer risk probability corresponding to the customer. The positive correlation coefficient is used to represent the transaction parameter that is positively correlated with the risk when the bank makes a transfer.

[0019] An embodiment of the present invention further provides a computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the risk control method for bank transfer transactions when executing the computer program.

[0020] An embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the risk control method for bank transfer transactions described above is implemented.

[0021] An embodiment of the present invention further provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the risk control method for bank transfer transactions is implemented.

[0022] In an embodiment of the present invention, a transaction space is constructed, and each dimension of the transaction space corresponds to a transaction category of the bank; historical transfer transaction data of the bank is obtained, and the first coordinate and the second coordinate of each historical transfer transaction data in the transaction space are determined; based on the first coordinate and the second coordinate, the historical transfer transaction data of the bank is classified to obtain multiple transfer subsets; for each transfer subset, the corresponding relationship between the positive correlation parameter of the transfer subset and the transfer risk probability is determined; for each customer, the transfer risk probability corresponding to the customer is determined; when the customer is making a transfer, the transfer subset corresponding to the current transfer is determined based on the transaction data of the current transfer; based on the corresponding relationship between the positive correlation parameter of the transfer subset corresponding to the current transfer and the transfer risk probability, and the transfer risk probability corresponding to the customer, the positive correlation parameter corresponding to the current transfer is determined, and the positive correlation coefficient is used to represent the transaction parameter that is positively correlated with the risk when the bank makes a transfer. In the above process, the constructed transaction space can be used to finally determine the correspondence between the positive correlation parameters of the transfer subset corresponding to this transfer and the transfer risk probability, as well as the transfer risk probability corresponding to the customer, and then determine the positive correlation parameters corresponding to this transfer. The positive correlation coefficient is used to represent the transaction parameters that are positively correlated with the risk when the bank makes a transfer, thereby quantifying the description of the risk and achieving control over the transfer risk. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. In the drawings:

[0024] Figure 1 Flow chart of a risk control method for a bank transfer transaction in an embodiment of the present invention;

[0025] Figure 2 A flowchart for determining the first coordinate and the second coordinate of each historical transfer transaction data in the transaction space in an embodiment of the present invention;

[0026] Figure 3 A flowchart of obtaining multiple transfer subsets in an embodiment of the present invention;

[0027] Figure 4 A flow chart of determining the correspondence between the positive correlation parameter of the transfer subset and the transfer risk probability in an embodiment of the present invention;

[0028] Figure 5 This is a flow chart of determining the transfer risk probability corresponding to a customer in an embodiment of the present invention;

[0029] Figure 6 This is a flow chart of determining a transfer subset corresponding to the current transfer in an embodiment of the present invention;

[0030] Figure 7 A flowchart of determining a partial order of historical transfer transaction data in an embodiment of the present invention;

[0031] Figure 8 This is a flow chart of determining the positive correlation parameters corresponding to this transfer in an embodiment of the present invention;

[0032] Fig. 9 Schematic diagram of a risk control device for bank transfer transactions in an embodiment of the present invention;

[0033] Fig.10 Schematic diagram of a computer device in an embodiment of the present invention. DETAILED DESCRIPTION

[0034] To make the purpose, technical solution and advantages of the embodiments of the present invention more clear, the embodiments of the present invention are further described in detail below in conjunction with the accompanying drawings. Here, the exemplary embodiments of the present invention and their descriptions are used to explain the present invention, but are not intended to limit the present invention.

[0035] In the description of this specification, the terms "include", "including", "have", "contain", etc. are all open terms, which mean including but not limited to. The descriptions with reference to the terms "one embodiment", "a specific embodiment", "some embodiments", "for example", etc. mean that the specific features, structures or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures or characteristics described may be combined in a suitable manner in any one or more embodiments or examples. The order of steps involved in each embodiment is used to schematically illustrate the implementation of the present application, and the order of steps is not limited and can be appropriately adjusted as needed.

[0036] Figure 1 FIG. 1 is a flow chart of a risk control method for a bank transfer transaction in an embodiment of the present invention. Figure 1 As shown, including:

[0037] Step 101, constructing a transaction space, where each dimension of the transaction space corresponds to a transaction category of the bank;

[0038] Step 102, obtaining the historical transfer transaction data of the bank, and determining the first coordinate and the second coordinate of each historical transfer transaction data in the transaction space;

[0039] Step 103, classifying the historical transfer transaction data of the bank according to the first coordinate and the second coordinate to obtain a plurality of transfer subsets;

[0040] Step 104: for each transfer subset, determine the corresponding relationship between the positive correlation parameter of the transfer subset and the transfer risk probability;

[0041] Step 105, for each customer, determining the transfer risk probability corresponding to the customer;

[0042] Step 106, when the customer is transferring money, the transfer sub-set corresponding to the transfer is determined based on the transaction data of the transfer;

[0043] Step 107, based on the correspondence between the positive correlation parameters of the transfer subset corresponding to the current transfer and the transfer risk probability, and the transfer risk probability corresponding to the customer, determine the positive correlation parameters corresponding to the current transfer, wherein the positive correlation coefficient is used to represent the transaction parameters that are positively correlated with the risk when the bank makes a transfer.

[0044] It should be noted that there can be many positive correlation parameters. For example, when a customer transfers money, the bank system will set a waiting time. The positive correlation parameter is the waiting time, such as 60 seconds. The longer this time is set, the higher the risk of the customer. The positive correlation parameter can be the waiting time and the number of password inputs, that is, when the customer enters the wrong password, he can continue to enter. The greater the number of inputs, the higher the risk of the customer.

[0045] Figure 2 The flowchart of determining the first coordinate and the second coordinate of each historical transfer transaction data in the transaction space in an embodiment of the present invention, in one embodiment, obtaining the historical transfer transaction data of a bank, and determining the first coordinate and the second coordinate of each historical transfer transaction data in the transaction space, includes:

[0046] Step 201, for each historical transfer transaction data, obtaining the transfer client and transfer counterparty corresponding to the historical transfer transaction data;

[0047] Step 202, obtaining the transaction data of the transfer customer, and determining the transaction quantity of each transaction category corresponding to the transaction data of the transfer customer; determining the first coordinate of the historical transfer transaction data in the transaction space, the value of the first coordinate in each dimension being equal to the transaction quantity of the transaction category corresponding to the transaction data of the transfer customer in the dimension;

[0048] Step 203, obtain the transaction data of the transfer counterparty, and determine the transaction quantity of each transaction category corresponding to the transaction data of the transfer counterparty; determine the second coordinate of the historical transfer transaction data in the transaction space, and the value of the second coordinate in each dimension is equal to the transaction quantity of the transaction category corresponding to the transaction data of the transfer counterparty in the dimension.

[0049] Figure 3The flowchart of obtaining multiple transfer subsets in an embodiment of the present invention is as follows. In one embodiment, historical transfer transaction data of a bank is classified according to a first coordinate and a second coordinate to obtain multiple transfer subsets, including:

[0050] Step 301, determining a distance function corresponding to a transfer transaction according to a first coordinate and a second coordinate, wherein for any two transfer transactions, the corresponding distance function is used to represent a distance between the two transfer transactions, and the distance between the two transfer transactions is a weighted sum of a distance between the first coordinates of the two transfer transactions and a distance between the second coordinates of the two transfer transactions;

[0051] Step 302: cluster the historical transfer transaction data of the bank based on the distance function corresponding to the transfer transaction to obtain multiple transfer subsets.

[0052] In one embodiment, historical transfer transaction data may also be classified according to key features (such as transaction time, transfer channel, transaction amount range, customer category of transfer customers and transfer counterparties) to obtain multiple transfer categories, and then the transfer transactions included in each transfer category are clustered based on the distance function corresponding to the transfer transactions to obtain multiple transfer subsets.

[0053] In one embodiment, based on the distance function corresponding to the transfer transaction, the historical transfer transaction data of the bank is clustered to obtain multiple transfer subsets, including:

[0054] Select a clustering algorithm to cluster the historical transfer transaction data of the bank to obtain multiple transfer subsets;

[0055] For each transfer subset, determine the transfer counterparty category (customer category of the transfer counterparty) of each transfer transaction in the transfer subset; determine the quantity ratio of the transfer transactions corresponding to each transfer counterparty category in the transfer subset; determine the maximum value of the quantity ratio as the concentration index corresponding to the transfer subset; determine whether the transfer subset satisfies condition s: if the concentration index corresponding to the transfer subset is greater than a specified threshold, if not, continue to cluster the transfer subset to obtain multiple new transfer subsets until each transfer subset satisfies condition s.

[0056] Figure 4 The flowchart of determining the correspondence between the positive correlation parameter of the transfer subset and the transfer risk probability in an embodiment of the present invention, in one embodiment, for each transfer subset, determining the correspondence between the positive correlation parameter of the transfer subset and the transfer risk probability includes:

[0057] Step 401, for each transfer subset and for each positive correlation parameter value, determining the proportion of risky transfer transactions in the transfer subset when the positive correlation parameter is set to the positive correlation parameter value;

[0058] Step 402: determine the proportion as the transfer risk probability corresponding to the positive correlation parameter value.

[0059] Figure 5 The flowchart of determining the transfer risk probability corresponding to a customer in an embodiment of the present invention is as follows. In one embodiment, for each customer, determining the transfer risk probability corresponding to the customer includes:

[0060] Step 501, determining the customer category to which the customer belongs;

[0061] Step 502: Determine the transfer risk probability corresponding to the customer based on the transfer transaction data of the customer category to which the customer belongs.

[0062] In one embodiment, determining the transfer risk probability corresponding to the customer based on the transfer transaction data of the customer category to which the customer belongs includes:

[0063] Divide the transfer transaction data into multiple transfer sample data according to the sequence (such as time sequence);

[0064] For each transfer sample data, the proportion of risky transfers in the transfer sample data is determined as the transfer risk sample corresponding to the customer;

[0065] Based on the transfer risk sample corresponding to the customer, determine the sample variance μ and the sample size n;

[0066] Set the probability error threshold ε and the probability lower bound P that the probability error is less than ε;

[0067] if The transfer risk probability corresponding to the customer is determined as the mean of all transfer risk samples corresponding to the customer;

[0068] when , perform the following steps until the number of transfer risk samples m corresponding to the customer meets

[0069] Acquire new transfer transaction data of the customer category to which the customer belongs; divide the new transfer transaction data into a plurality of new transfer sample data in order; for each new transfer sample data, determine the proportion of risky transfers in the new transfer sample data as a transfer risk sample corresponding to the customer;

[0070] when When , the transfer risk probability corresponding to the customer is determined as the mean of all transfer risk samples corresponding to the customer.

[0071] Figure 6The flowchart of determining the transfer sub-set corresponding to the current transfer in an embodiment of the present invention, in one embodiment, when a customer is making a transfer, the transfer sub-set corresponding to the current transfer is determined based on the transaction data of the current transfer, including:

[0072] Step 601, obtaining the transfer customer and transfer counterparty corresponding to the transaction data of this transfer;

[0073] Step 602, determining the first coordinates of the transaction data of the current transfer in the transaction space according to the transaction data of the transfer customer, and determining the second coordinates of the transaction data of the current transfer in the transaction space according to the transaction data of the transfer counterparty;

[0074] Step 603, determining a partial order of the historical transfer transaction data according to the first coordinate and the second coordinate, wherein the partial order is used to determine whether a first transfer transaction of any two historical transfer transaction data is closer than a second transfer transaction;

[0075] Step 604, determining the maximum transfer transaction of the bank's historical transfer transaction data according to the partial order, wherein the maximum transfer transaction is the maximum element of the partial order;

[0076] Step 605: determine the transfer sub-set to which the maximum transfer transaction belongs as the transfer sub-set corresponding to the current transfer.

[0077] Figure 7 The flowchart of determining the partial order of historical transfer transaction data in an embodiment of the present invention is as follows. In one embodiment, determining the partial order of historical transfer transaction data according to the first coordinate and the second coordinate includes:

[0078] Step 701: for each historical transfer transaction data, the distance between the transaction data of the current transfer and the historical transfer transaction data in the first coordinate of the transaction space is determined as the first distance corresponding to the historical transfer transaction, and the distance between the transaction data of the current transfer and the historical transfer transaction data in the second coordinate of the transaction space is determined as the second distance corresponding to the historical transfer transaction data;

[0079] Step 702: for any two historical transfer transaction data, if a first distance corresponding to a first historical transfer transaction data of the two historical transfer transaction data is less than or equal to a first distance corresponding to a second historical transfer transaction data of the two historical transfer transaction data, and a second distance corresponding to the first historical transfer transaction data is less than or equal to a second distance corresponding to the second historical transfer transaction data, then it is determined that the first historical transfer transaction data is closer to the second historical transfer transaction data.

[0080] It should be noted that the maximum element of a partial order is the element that has no other elements closer to it in the set corresponding to the partial order.

[0081] In one embodiment, determining the maximum transfer transaction of the bank's historical transfer transaction data based on the partial order includes:

[0082] Initialize the maximum authentication value corresponding to each transfer transaction in the bank's historical transfer transaction data to be enabled, and initialize the corresponding comparison Boolean value to be yes;

[0083] The following steps are performed for each transfer transaction in the bank's historical transfer transactions:

[0084] If the maximum authentication value corresponding to the transfer transaction is not equal to "yes", the transfer transaction to be compared corresponding to the transfer transaction is set to "null"; otherwise, the transfer transaction to be compared corresponding to the transfer transaction is set to all other transfer transactions (except the transfer transaction) whose corresponding comparison Boolean values ​​are "yes" in the historical transfer transaction data of the bank;

[0085] Determine the partial order relationship between the transfer transaction and each corresponding transfer transaction to be compared in sequence: if the transfer transaction to be compared is closer to the transfer transaction, update the maximum authentication value corresponding to the transfer transaction to be compared to no; if the transfer transaction is closer to the transfer transaction to be compared, update the maximum authentication value corresponding to the transfer transaction to be compared to no, and determine the transfer transaction to be compared as a secondary transfer transaction of the transfer transaction;

[0086] If it is determined that all the transfer transactions to be compared corresponding to the transfer transaction are not close to the transfer transaction, the transfer transaction is determined to be a very large transfer transaction in the bank's historical transfer transactions, and the comparison Boolean values ​​of all minor transfer transactions of the very large transfer transaction are updated to be no.

[0087] Figure 8 The flowchart of determining the positive correlation parameter corresponding to the current transfer in an embodiment of the present invention, in one embodiment, according to the correspondence between the positive correlation parameter of the transfer subset corresponding to the current transfer and the transfer risk probability, and the transfer risk probability corresponding to the customer, the positive correlation parameter corresponding to the current transfer is determined, including:

[0088] Step 801, for each transfer subset corresponding to the current transfer, according to the corresponding relationship between the positive correlation parameter of the transfer subset and the transfer risk probability, and the transfer risk probability corresponding to the customer, determine the candidate parameter value corresponding to the current transfer;

[0089] Step 802: determine the positive correlation parameter corresponding to the current transfer as the minimum value of all candidate parameter values ​​corresponding to the current transfer.

[0090] In summary, in the method proposed in the embodiment of the present invention, a transaction space is constructed, and each dimension of the transaction space corresponds to a transaction category of the bank; the historical transfer transaction data of the bank is obtained, and the first coordinate and the second coordinate of each historical transfer transaction data in the transaction space are determined; according to the first coordinate and the second coordinate, the historical transfer transaction data of the bank is classified to obtain multiple transfer subsets; for each transfer subset, the corresponding relationship between the positive correlation parameter of the transfer subset and the transfer risk probability is determined; for each customer, the transfer risk probability corresponding to the customer is determined; when the customer is making a transfer, the transfer subset corresponding to the transfer is determined based on the transaction data of the transfer; according to the corresponding relationship between the positive correlation parameter of the transfer subset corresponding to the transfer and the transfer risk probability, and the transfer risk probability corresponding to the customer, the positive correlation parameter corresponding to the transfer is determined, and the positive correlation coefficient is used to represent the transaction parameter that is positively correlated with the risk when the bank makes a transfer. In the above process, the constructed transaction space can be used to finally determine the correspondence between the positive correlation parameters of the transfer subset corresponding to this transfer and the transfer risk probability, as well as the transfer risk probability corresponding to the customer, and then determine the positive correlation parameters corresponding to this transfer. The positive correlation coefficient is used to represent the transaction parameters that are positively correlated with the risk when the bank makes a transfer, thereby quantifying the description of the risk and achieving control over the transfer risk.

[0091] The embodiment of the present invention further provides a risk control device for bank transfer transactions, the principle of which is similar to the risk control method for bank transfer transactions, which will not be described in detail here.

[0092] Fig. 9 Schematic diagram of a risk control device for a bank transfer transaction in an embodiment of the present invention, comprising:

[0093] A transaction space construction module 901 is used to construct a transaction space, where each dimension of the transaction space corresponds to a transaction category of the bank;

[0094] The historical transfer transaction data acquisition module 902 is used to acquire the historical transfer transaction data of the bank and determine the first coordinate and the second coordinate of each historical transfer transaction data in the transaction space;

[0095] A transfer transaction data classification module 903, configured to classify the historical transfer transaction data of the bank according to the first coordinate and the second coordinate to obtain a plurality of transfer subsets;

[0096] A relationship determination module 904 is used to determine, for each transfer subset, a corresponding relationship between a positive correlation parameter of the transfer subset and a transfer risk probability;

[0097] A transfer risk probability determination module 905 is used to determine, for each customer, a transfer risk probability corresponding to the customer;

[0098] The current transfer sub-set determination module 906 is used to determine the transfer sub-set corresponding to the current transfer according to the transaction data of the current transfer when the customer is transferring money;

[0099] The positive correlation parameter determination module 907 is used to determine the positive correlation parameter corresponding to the current transfer based on the correspondence between the positive correlation parameter of the transfer subset corresponding to the current transfer and the transfer risk probability, and the transfer risk probability corresponding to the customer. The positive correlation coefficient is used to represent the transaction parameter that is positively correlated with the risk when the bank makes a transfer.

[0100] In one embodiment, the historical transfer transaction data acquisition module is specifically used to:

[0101] For each historical transfer transaction data, obtain the transfer client and transfer counterparty corresponding to the historical transfer transaction data;

[0102] Acquire the transaction data of the transfer customer, and determine the transaction quantity of each transaction category corresponding to the transaction data of the transfer customer; determine the first coordinate of the historical transfer transaction data in the transaction space, the value of the first coordinate in each dimension being equal to the transaction quantity of the transaction category corresponding to the transaction data of the transfer customer in the dimension;

[0103] Acquire the transaction data of the transfer counterparty, and determine the transaction quantity of each transaction category corresponding to the transaction data of the transfer counterparty; determine the second coordinate of the historical transfer transaction data in the transaction space, the value of the second coordinate in each dimension is equal to the transaction quantity of the transaction category corresponding to the transaction data of the transfer counterparty in the dimension.

[0104] In one embodiment, the transfer transaction data classification module is specifically used to:

[0105] Determine a distance function corresponding to the transfer transaction according to the first coordinate and the second coordinate, wherein for any two transfer transactions, the corresponding distance function is used to represent the distance between the two transfer transactions, and the distance between the two transfer transactions is a weighted sum of the distance between the first coordinates of the two transfer transactions and the distance between the second coordinates of the two transfer transactions;

[0106] Based on the distance function corresponding to the transfer transaction, the bank's historical transfer transaction data is clustered to obtain multiple transfer subsets.

[0107] In one embodiment, the relationship determination module is specifically used to:

[0108] For each transfer subset, for each positive correlation parameter value, determining the proportion of risky transfer transactions in the transfer subset when the positive correlation parameter is set to the positive correlation parameter value;

[0109] The proportion is determined as the transfer risk probability corresponding to the positive correlation parameter value.

[0110] In one embodiment, the transfer risk probability determination module is specifically used to:

[0111] Determine the customer category to which the customer belongs;

[0112] Based on the transfer transaction data of the customer category to which the customer belongs, the transfer risk probability corresponding to the customer is determined.

[0113] In one embodiment, the module for determining the current transfer subset is specifically used to:

[0114] Obtain the transfer customer and transfer counterparty corresponding to the transaction data of this transfer;

[0115] Determine the first coordinates of the transaction data of the current transfer in the transaction space based on the transaction data of the transfer customer, and determine the second coordinates of the transaction data of the current transfer in the transaction space based on the transaction data of the transfer counterparty;

[0116] Determine a partial order of the historical transfer transaction data according to the first coordinate and the second coordinate, wherein the partial order is used to determine whether a first transfer transaction of any two historical transfer transaction data is closer than a second transfer transaction;

[0117] According to the partial order, determining the maximum transfer transaction of the bank's historical transfer transaction data, wherein the maximum transfer transaction is the maximum element of the partial order;

[0118] The transfer sub-set to which the maximum transfer transaction belongs is determined as the transfer sub-set corresponding to this transfer.

[0119] In one embodiment, the current transfer subset determination module is specifically used to:

[0120] For each historical transfer transaction data, the distance between the transaction data of the current transfer and the first coordinate of the historical transfer transaction data in the transaction space is determined as the first distance corresponding to the historical transfer transaction, and the distance between the transaction data of the current transfer and the second coordinate of the historical transfer transaction data in the transaction space is determined as the second distance corresponding to the historical transfer transaction data;

[0121] For any two historical transfer transaction data, if a first distance corresponding to a first historical transfer transaction data of the two historical transfer transaction data is less than or equal to a first distance corresponding to a second historical transfer transaction data of the two historical transfer transaction data, and a second distance corresponding to the first historical transfer transaction data is less than or equal to a second distance corresponding to the second historical transfer transaction data, then it is determined that the first historical transfer transaction data is closer to the second historical transfer transaction data.

[0122] In one embodiment, the positive correlation parameter determination module is specifically used for:

[0123] For each transfer subset corresponding to the current transfer, determine the candidate parameter value corresponding to the current transfer according to the corresponding relationship between the positive correlation parameter of the transfer subset and the transfer risk probability, and the transfer risk probability corresponding to the customer;

[0124] The positive correlation parameter corresponding to this transfer is determined as the minimum value of all candidate parameter values ​​corresponding to this transfer.

[0125] In summary, in the device proposed in the embodiment of the present invention, a transaction space is constructed, and each dimension of the transaction space corresponds to a transaction category of the bank; the historical transfer transaction data of the bank is obtained, and the first coordinate and the second coordinate of each historical transfer transaction data in the transaction space are determined; according to the first coordinate and the second coordinate, the historical transfer transaction data of the bank is classified to obtain multiple transfer subsets; for each transfer subset, the corresponding relationship between the positive correlation parameter of the transfer subset and the transfer risk probability is determined; for each customer, the transfer risk probability corresponding to the customer is determined; when the customer is making a transfer, the transfer subset corresponding to the transfer is determined based on the transaction data of the transfer; according to the corresponding relationship between the positive correlation parameter of the transfer subset corresponding to the transfer and the transfer risk probability, and the transfer risk probability corresponding to the customer, the positive correlation parameter corresponding to the transfer is determined, and the positive correlation coefficient is used to represent the transaction parameter that is positively correlated with the risk when the bank makes a transfer. In the above process, the constructed transaction space can be used to finally determine the correspondence between the positive correlation parameters of the transfer subset corresponding to this transfer and the transfer risk probability, as well as the transfer risk probability corresponding to the customer, and then determine the positive correlation parameters corresponding to this transfer. The positive correlation coefficient is used to represent the transaction parameters that are positively correlated with the risk when the bank makes a transfer, thereby quantifying the description of the risk and achieving control over the transfer risk.

[0126] An embodiment of the present invention further provides a computer device, Fig.10 Schematic diagram of a computer device in an embodiment of the present invention, the computer device 1000 includes a memory 1010, a processor 1020, and a computer program 1030 stored in the memory 1010 and executable on the processor 1020, and the processor 1020 implements the risk control method for bank transfer transactions when executing the computer program 1030.

[0127] An embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the risk control method for bank transfer transactions described above is implemented.

[0128] An embodiment of the present invention further provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the risk control method for bank transfer transactions is implemented.

[0129] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program business systems. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program business system implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0130] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program business systems according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes 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 a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0131] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0132] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0133] The specific embodiments described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A risk control method for bank transfer transactions, characterized in that: include: Construct a transaction space, where each dimension of the transaction space corresponds to a transaction category of the bank; Obtain the historical transfer transaction data of the bank, and determine the first coordinate and the second coordinate of each historical transfer transaction data in the transaction space; Classify the historical transfer transaction data of the bank according to the first coordinate and the second coordinate to obtain multiple transfer subsets; For each transfer subset, determining the corresponding relationship between the positive correlation parameter of the transfer subset and the transfer risk probability; For each customer, determine the corresponding transfer risk probability of the customer; When a customer is transferring money, the transfer sub-set corresponding to the transfer is determined based on the transaction data of the transfer; According to the correspondence between the positive correlation parameters of the transfer subset corresponding to the current transfer and the transfer risk probability, and the transfer risk probability corresponding to the customer, the positive correlation parameters corresponding to the current transfer are determined, wherein the positive correlation coefficient is used to represent the transaction parameters that are positively correlated with the risk when the bank makes a transfer; the positive correlation parameters corresponding to the transfer include the waiting time and the number of password input times; Obtain the historical transfer transaction data of the bank, and determine the first coordinate and the second coordinate of each historical transfer transaction data in the transaction space, including: For each historical transfer transaction data, obtain the transfer client and transfer counterparty corresponding to the historical transfer transaction data; Acquire the transaction data of the transfer customer, and determine the transaction quantity of each transaction category corresponding to the transaction data of the transfer customer; determine the first coordinate of the historical transfer transaction data in the transaction space, the value of the first coordinate in each dimension being equal to the transaction quantity of the transaction category corresponding to the transaction data of the transfer customer in the dimension; Acquire the transaction data of the transfer counterparty, and determine the transaction quantity of each transaction category corresponding to the transaction data of the transfer counterparty; determine the second coordinate of the historical transfer transaction data in the transaction space, the value of the second coordinate in each dimension is equal to the transaction quantity of the transaction category corresponding to the transaction data of the transfer counterparty in the dimension.

2. The method according to claim 1, characterized in that According to the first coordinate and the second coordinate, the historical transfer transaction data of the bank is classified to obtain multiple transfer subsets, including: Determine a distance function corresponding to the transfer transaction according to the first coordinate and the second coordinate, wherein for any two transfer transactions, the corresponding distance function is used to represent the distance between the two transfer transactions, and the distance between the two transfer transactions is a weighted sum of the distance between the first coordinates of the two transfer transactions and the distance between the second coordinates of the two transfer transactions; Based on the distance function corresponding to the transfer transaction, the bank's historical transfer transaction data is clustered to obtain multiple transfer subsets.

3. The method according to claim 1, characterized in that For each transfer subset, the corresponding relationship between the positive correlation parameter of the transfer subset and the transfer risk probability is determined, including: For each transfer subset and each positive correlation parameter value, determine the proportion of risky transfer transactions in the transfer subset when the positive correlation parameter is set to the positive correlation parameter value, and determine the proportion as the transfer risk probability corresponding to the positive correlation parameter value.

4. The method according to claim 1, characterized in that For each customer, determine the corresponding transfer risk probability of the customer, including: Determine the customer category to which the customer belongs; Based on the transfer transaction data of the customer category to which the customer belongs, the transfer risk probability corresponding to the customer is determined.

5. The method according to claim 1, characterized in that When a customer makes a transfer, the transfer sub-set corresponding to the transfer is determined based on the transaction data of the transfer, including: Obtain the transfer customer and transfer counterparty corresponding to the transaction data of this transfer; Determine the first coordinates of the transaction data of the current transfer in the transaction space based on the transaction data of the transfer customer, and determine the second coordinates of the transaction data of the current transfer in the transaction space based on the transaction data of the transfer counterparty; Determine a partial order of the historical transfer transaction data according to the first coordinate and the second coordinate, wherein the partial order is used to determine whether a first transfer transaction of any two historical transfer transaction data is closer than a second transfer transaction; According to the partial order, determining the maximum transfer transaction of the bank's historical transfer transaction data, wherein the maximum transfer transaction is the maximum element of the partial order; The transfer sub-set to which the maximum transfer transaction belongs is determined as the transfer sub-set corresponding to this transfer.

6. The method according to claim 5, characterized in that According to the first coordinate and the second coordinate, the partial order of the historical transfer transaction data is determined, including: For each historical transfer transaction data, the distance between the transaction data of the current transfer and the first coordinate of the historical transfer transaction data in the transaction space is determined as the first distance corresponding to the historical transfer transaction, and the distance between the transaction data of the current transfer and the second coordinate of the historical transfer transaction data in the transaction space is determined as the second distance corresponding to the historical transfer transaction data; For any two historical transfer transaction data, if a first distance corresponding to a first historical transfer transaction data of the two historical transfer transaction data is less than or equal to a first distance corresponding to a second historical transfer transaction data of the two historical transfer transaction data, and a second distance corresponding to the first historical transfer transaction data is less than or equal to a second distance corresponding to the second historical transfer transaction data, then it is determined that the first historical transfer transaction data is closer to the second historical transfer transaction data.

7. The method according to claim 1, characterized in that According to the correspondence between the positive correlation parameters of the transfer subset corresponding to the current transfer and the transfer risk probability, and the transfer risk probability corresponding to the customer, the positive correlation parameters corresponding to the current transfer are determined, including: For each transfer subset corresponding to the current transfer, determine the candidate parameter value corresponding to the current transfer according to the corresponding relationship between the positive correlation parameter of the transfer subset and the transfer risk probability, and the transfer risk probability corresponding to the customer; The positive correlation parameter corresponding to this transfer is determined as the minimum value of all candidate parameter values ​​corresponding to this transfer.

8. A risk control device for bank transfer transactions, characterized in that: include: A transaction space construction module is used to construct a transaction space, where each dimension of the transaction space corresponds to a transaction category of the bank; A historical transfer transaction data acquisition module is used to obtain the historical transfer transaction data of the bank and determine the first coordinate and the second coordinate of each historical transfer transaction data in the transaction space; A transfer transaction data classification module, used to classify the historical transfer transaction data of the bank according to the first coordinate and the second coordinate to obtain multiple transfer subsets; A relationship determination module, used to determine, for each transfer subset, a corresponding relationship between a positive correlation parameter of the transfer subset and a transfer risk probability; A transfer risk probability determination module, used to determine the transfer risk probability corresponding to each customer; The current transfer sub-set determination module is used to determine the transfer sub-set corresponding to the current transfer based on the transaction data of the current transfer when the customer is making a transfer; A positive correlation parameter determination module is used to determine the positive correlation parameter corresponding to the current transfer based on the corresponding relationship between the positive correlation parameter of the transfer subset corresponding to the current transfer and the transfer risk probability, and the transfer risk probability corresponding to the customer, wherein the positive correlation coefficient is used to represent the transaction parameter that is positively correlated with the risk when the bank makes a transfer; the positive correlation parameters corresponding to the transfer include the waiting time and the number of password input times; The historical transfer transaction data acquisition module is specifically used for: For each historical transfer transaction data, obtain the transfer client and transfer counterparty corresponding to the historical transfer transaction data; Acquire the transaction data of the transfer customer, and determine the transaction quantity of each transaction category corresponding to the transaction data of the transfer customer; determine the first coordinate of the historical transfer transaction data in the transaction space, the value of the first coordinate in each dimension being equal to the transaction quantity of the transaction category corresponding to the transaction data of the transfer customer in the dimension; Acquire the transaction data of the transfer counterparty, and determine the transaction quantity of each transaction category corresponding to the transaction data of the transfer counterparty; determine the second coordinate of the historical transfer transaction data in the transaction space, the value of the second coordinate in each dimension is equal to the transaction quantity of the transaction category corresponding to the transaction data of the transfer counterparty in the dimension.

9. The device according to claim 8, characterized in that The transfer transaction data classification module is specifically used for: Determine a distance function corresponding to the transfer transaction according to the first coordinate and the second coordinate, wherein for any two transfer transactions, the corresponding distance function is used to represent the distance between the two transfer transactions, and the distance between the two transfer transactions is a weighted sum of the distance between the first coordinates of the two transfer transactions and the distance between the second coordinates of the two transfer transactions; Based on the distance function corresponding to the transfer transaction, the bank's historical transfer transaction data is clustered to obtain multiple transfer subsets.

10. The device according to claim 8, characterized in that The relationship determination module is specifically used for: For each transfer subset and each positive correlation parameter value, determine the proportion of risky transfer transactions in the transfer subset when the positive correlation parameter is set to the positive correlation parameter value, and determine the proportion as the transfer risk probability corresponding to the positive correlation parameter value.

11. The device according to claim 8, characterized in that The transfer risk probability determination module is specifically used for: Determine the customer category to which the customer belongs; Based on the transfer transaction data of the customer category to which the customer belongs, the transfer risk probability corresponding to the customer is determined.

12. The device according to claim 8, characterized in that The module for determining the sub-collection of this transfer is specifically used for: Obtain the transfer customer and transfer counterparty corresponding to the transaction data of this transfer; Determine the first coordinates of the transaction data of the current transfer in the transaction space based on the transaction data of the transfer customer, and determine the second coordinates of the transaction data of the current transfer in the transaction space based on the transaction data of the transfer counterparty; Determine a partial order of the historical transfer transaction data according to the first coordinate and the second coordinate, wherein the partial order is used to determine whether a first transfer transaction of any two historical transfer transaction data is closer than a second transfer transaction; According to the partial order, determining the maximum transfer transaction of the bank's historical transfer transaction data, wherein the maximum transfer transaction is the maximum element of the partial order; The transfer sub-set to which the maximum transfer transaction belongs is determined as the transfer sub-set corresponding to this transfer.

13. The device according to claim 12, characterized in that The module for determining the sub-collection of this transfer is specifically used for: For each historical transfer transaction data, the distance between the transaction data of the current transfer and the first coordinate of the historical transfer transaction data in the transaction space is determined as the first distance corresponding to the historical transfer transaction, and the distance between the transaction data of the current transfer and the second coordinate of the historical transfer transaction data in the transaction space is determined as the second distance corresponding to the historical transfer transaction data; For any two historical transfer transaction data, if a first distance corresponding to a first historical transfer transaction data of the two historical transfer transaction data is less than or equal to a first distance corresponding to a second historical transfer transaction data of the two historical transfer transaction data, and a second distance corresponding to the first historical transfer transaction data is less than or equal to a second distance corresponding to the second historical transfer transaction data, then it is determined that the first historical transfer transaction data is closer to the second historical transfer transaction data.

14. The device according to claim 8, characterized in that The positive correlation parameter determination module is specifically used for: For each transfer subset corresponding to the current transfer, determine the candidate parameter value corresponding to the current transfer according to the corresponding relationship between the positive correlation parameter of the transfer subset and the transfer risk probability, and the transfer risk probability corresponding to the customer; The positive correlation parameter corresponding to this transfer is determined as the minimum value of all candidate parameter values ​​corresponding to this transfer.

15. A computer device comprising a memory, a processor and a computer program stored in 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 7 is implemented.

16. 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 7 is implemented.

17. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images