Risk Control Method and Device for Payment Transactions

Abstract

The present invention proposes a risk control method and device for payment transactions, which relate to the field of data processing technology, and include: classifying customers of a bank; obtaining historical payment data of the bank within a predetermined range, and extracting a set of payment counterparties of the bank within the predetermined range; classifying the extracted set of payment counterparties of the bank within the predetermined range to obtain multiple payment counterparty subsets; for each payment counterparty subset, determining the indicators of each risk dimension corresponding to the payment counterparty subset and the corresponding indicator convergence value; determining a low-risk payment counterparty subset based on the indicators of each risk dimension corresponding to the payment counterparty subset and the corresponding indicator convergence value; determining the low-risk payment counterparty corresponding to the customer; for each customer, sending the low-risk payment counterparty corresponding to the customer to the customer's mobile terminal; when the network strength of the customer's mobile terminal is less than a set threshold, using the low-risk payment counterparty stored in the customer's mobile terminal to support the customer's payment transaction.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and particularly to a risk control method and device for payment transactions. Background Art

[0002] This section aims to provide background or context for the embodiments of the present invention described in the claims. The descriptions herein are not admitted to be prior art merely because they are included in this section.

[0003] In the process of bank transaction processing, risk control is usually carried out on the bank server. Therefore, customers need to be connected to the network during bank transactions for risk control. However, when the network signal is poor, customers cannot conduct transactions. For some users, they may often be in a specific location at a specific time, and the wireless signal in the specific location may be weak, resulting in customers being unable to use their terminals to conduct transaction behaviors, and the customer experience is poor.

[0004] In summary, there is an urgent need for a technical solution that can overcome the above defects and effectively control the risk of payment transactions. Summary of the Invention

[0005] To solve the problems existing in the prior art, the present invention proposes a risk control method and device for payment transactions.

[0006] In the first aspect of the embodiments of the present invention, a risk control method for payment transactions is proposed, including:

[0007] Classify the customers of the bank to obtain multiple customer categories;

[0008] Obtain the historical payment data of the bank within a predetermined range, and extract the set of payment counterparts of the bank within the predetermined range;

[0009] Classify the set of payment counterparts of the bank within the predetermined range extracted according to the customer categories to obtain multiple subsets of payment counterparts;

[0010] For each subset of payment counterparts, determine the indicators and corresponding indicator convergence values of each risk dimension corresponding to the subset of payment counterparts according to the historical payment data corresponding to the subset of payment counterparts;

[0011] Determine a subset of low-risk payment counterparts according to the indicators of each risk dimension corresponding to the subset of payment counterparts and the corresponding indicator convergence values;

[0012] For each customer, determine the low-risk payment counterparts corresponding to the customer according to the historical payment data of the customer and the subset of low-risk payment counterparts;

[0013] For each customer, send the low-risk payment counterparts corresponding to the customer to the mobile terminal of the customer;

[0014] When the network strength of the mobile terminal of the customer is less than the set threshold, the low-risk payment counterparts stored in the mobile terminal of the customer are used to support the payment transaction of the customer.

[0015] In a second aspect of the embodiments of the present invention, a risk control device for payment transactions is proposed, including:

[0016] A customer classification module, configured to classify the customers of the bank to obtain multiple customer categories;

[0017] A data acquisition module, configured to acquire the historical payment data of the bank within a predetermined range and extract the set of payment counterparts of the bank within the predetermined range;

[0018] A payment counterpart classification module, configured to classify the set of payment counterparts of the bank within the predetermined range extracted according to the customer categories to obtain multiple payment counterpart subsets;

[0019] A data analysis module, configured to, for each payment counterpart subset, determine the indicators and corresponding indicator convergence values of each risk dimension corresponding to the payment counterpart subset according to the historical payment data corresponding to the payment counterpart subset;

[0020] A low-risk payment counterpart analysis module, configured to determine a low-risk payment counterpart subset according to the indicators and corresponding indicator convergence values of each risk dimension corresponding to the payment counterpart subset;

[0021] A low-risk payment counterpart determination module, configured to, for each customer, determine the low-risk payment counterpart corresponding to the customer according to the historical payment data of the customer and the low-risk payment counterpart subset;

[0022] A sending module, configured to, for each customer, send the low-risk payment counterpart corresponding to the customer to the mobile terminal of the customer;

[0023] A transaction processing module, configured to, when the network strength of the mobile terminal of the customer is less than the set threshold, use the low-risk payment counterparts stored in the mobile terminal of the customer to support the payment transaction of the customer.

[0024] 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, and when the processor executes the computer program, a risk control method for payment transactions is implemented.

[0025] 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 payment transactions is implemented.

[0026] In a fifth aspect of the embodiments of the present invention, a computer program product is provided. The computer program product includes a computer program which, when executed by a processor, implements a risk control method for payment transactions.

[0027] The risk control method and device for payment transactions proposed by the present invention classify customers of a bank to obtain multiple customer categories; acquire historical payment data of the bank within a predetermined range, and extract a set of payment counterparts of the bank within the predetermined range; classify the extracted set of payment counterparts of the bank within the predetermined range according to the customer categories to obtain multiple subsets of payment counterparts; for each subset of payment counterparts, determine the indicators and corresponding indicator convergence values of each risk dimension corresponding to the subset of payment counterparts according to the historical payment data corresponding to the subset of payment counterparts; determine a subset of low-risk payment counterparts according to the indicators and corresponding indicator convergence values of each risk dimension corresponding to the subset of payment counterparts; for each customer, determine the low-risk payment counterparts corresponding to the customer according to the historical payment data of the customer and the subset of low-risk payment counterparts; for each customer, send the low-risk payment counterparts corresponding to the customer to the mobile terminal of the customer; when the network strength of the mobile terminal of the customer is less than a set threshold, use the low-risk payment counterparts stored in the mobile terminal of the customer to support the payment transaction of the customer. The present invention can analyze the payment counterparts of customers, send low-risk payment counterparts to the customer's mobile terminal, enable the customer to conduct payment transactions with low-risk payment counterparts when the network signal of the mobile terminal is poor, improve the customer experience, and enable the bank to effectively control the risk of payment transactions. Description of the Drawings

[0028] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for description in the embodiments will be briefly introduced below. Obviously, the drawings in the following description are some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0029] Figure 1 It is a schematic flowchart of a risk control method for payment transactions according to an embodiment of the present invention.

[0030] Figure 2 It is a schematic flowchart of classifying the extracted set of payment counterparts of the bank within a predetermined range according to an embodiment of the present invention.

[0031] Figure 3 It is a schematic flowchart of determining the indicators and corresponding indicator convergence values of each risk dimension corresponding to a subset of payment counterparts according to an embodiment of the present invention.

[0032] Figure 4 It is a schematic flowchart of a specific process for determining a subset of low-risk payment counterparts according to an embodiment of the present invention.

[0033] Figure 5 It is a schematic flowchart showing the specific process of determining whether a payment counterparty corresponding to historical payment data belongs to a subset of low-risk payment counterparties in an embodiment of the present invention.

[0034] Figure 6 It is a schematic flowchart showing the processing procedure when a mobile terminal does not store low-risk payment counterparties in a specific embodiment of the present invention.

[0035] Figure 7 It is a schematic diagram showing the architecture of a risk control device for payment transactions in an embodiment of the present invention.

[0036] Figure 8 It is a schematic diagram showing the architecture of a risk control device for payment transactions in another embodiment of the present invention.

[0037] Figure 9 It is a schematic diagram showing the structure of a computer device in an embodiment of the present invention. Detailed Embodiments

[0038] The principles and spirit of the present invention will be described below with reference to several exemplary embodiments. It should be understood that these embodiments are provided only to enable those skilled in the art to better understand and then implement the present invention, and do not limit the scope of the present invention in any way. On the contrary, these embodiments 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.

[0039] Those skilled in the art know that the embodiments of the present invention can be implemented as a system, device, equipment, method, or computer program product. Therefore, the present disclosure can be specifically implemented in the following forms: completely hardware, completely software (including firmware, resident software, microcode, etc.), or a combination of hardware and software.

[0040] According to the embodiments of the present invention, a risk control method and device for payment transactions are proposed, which relate to the technical field of data processing.

[0041] The principles and spirit of the present invention will be elaborated below with reference to several representative embodiments of the present invention.

[0042] Figure 1 It is a schematic flowchart showing the risk control method for payment transactions in an embodiment of the present invention. As Figure 1 shown, the method includes:

[0043] S1. Classify the customers of the bank to obtain multiple customer categories;

[0044] S2. Obtain the historical payment data of the bank within a predetermined range, and extract the set of payment counterparties of the bank within the predetermined range;

[0045] S3. Classify the set of payment counterparts within a predetermined range for the bank according to the customer category to obtain multiple subsets of payment counterparts.

[0046] S4. For each subset of payment counterparts, determine the indicators and corresponding indicator convergence values for each risk dimension corresponding to the subset of payment counterparts according to the historical payment data corresponding to the subset of payment counterparts.

[0047] S5. Determine the subset of low-risk payment counterparts according to the indicators and corresponding indicator convergence values for each risk dimension corresponding to the subset of payment counterparts.

[0048] S6. For each customer, determine the low-risk payment counterparts corresponding to the customer according to the historical payment data of the customer and the subset of low-risk payment counterparts.

[0049] S7. For each customer, send the low-risk payment counterparts corresponding to the customer to the mobile terminal of the customer.

[0050] S8. When the network strength of the mobile terminal of the customer is less than the set threshold, use the low-risk payment counterparts stored in the mobile terminal of the customer to support the payment transaction of the customer.

[0051] For a clearer explanation of the above risk control method for payment transactions, the following will be a detailed description in combination with each step.

[0052] In S1, classify the customers of the bank to obtain multiple customer categories.

[0053] Specifically, the customers can be classified according to customer information, where the customer information includes at least: income, employment industry, graduation school, bank assets held, etc.

[0054] In S2, obtain the historical payment data of the bank within a predetermined range and extract the set of payment counterparts of the bank within a predetermined range.

[0055] In S3, referring to Figure 2 , the specific method for classifying the set of payment counterparts within a predetermined range for the bank according to the customer category to obtain multiple subsets of payment counterparts is as follows:

[0056] S31. For each payee in the set of payees within the predetermined range extracted for the bank, obtain the historical payment data corresponding to the payee, and determine the number of customers belonging to each customer category among the paying customers corresponding to the historical payment data; determine the paying customer vector corresponding to the payee, where the components of the paying customer vector correspond one-to-one with the customer categories, and the component value of each component is equal to the number of customers belonging to the customer category corresponding to the component among the paying customers corresponding to the historical payment data corresponding to the payee.

[0057] For each payment data, it involves two entities, "paying customer" and "payee". The paying customer is usually an individual, and the payee is usually the seller. For example, when customer P goes to the supermarket to buy things, customer P is the paying customer and supermarket M is the payee.

[0058] In this regard, the "historical payment data corresponding to the payee" obtained here refers to all the historical payment data where the payee of the historical payment data is the "payee"; for example, if the payee is supermarket M, then obtain the historical payment data where the payee is supermarket P; and then the multiple paying customers corresponding to the historical data of supermarket P can be obtained, and finally the number of customers belonging to each customer category among the multiple paying customers can be determined.

[0059] S32. Determine the distance function of the payees, where the distance function is used to determine the distance between any two payees as the distance between the paying customer vectors corresponding to the two payees.

[0060] S33. Classify the set of payees within the predetermined range extracted for the bank according to the distance function of the payees to obtain multiple subsets of payees.

[0061] In one embodiment, (S33) classifying the set of payees within the predetermined range extracted for the bank according to the distance function of the payees to obtain multiple subsets of payees includes:

[0062] S331. Select multiple payees from the set of payees within the predetermined range extracted for the bank as the centers of the payee subsets. Each center of the payee subset corresponds to a payee subset. Initially, the payee subset only contains the corresponding center of the payee subset.

[0063] S332. For each payee and each payee subset, loop through the following steps until the change rate of the paying customer vectors corresponding to all the centers of the payee subsets is less than the set threshold:

[0064] For each obtained payee, perform the following 4 steps:

[0065] Calculate the distance between the center of each opponent subset and the payment opponent based on the distance function of the payment opponent, and use this distance as the payment distance corresponding to the center of the opponent subset.

[0066] Select multiple opponent subset centers from all opponent subset centers that have the same risk level as the payment opponent.

[0067] Take the minimum value of the payment distances corresponding to the selected opponent subset centers as the payment distance D1 corresponding to the payment opponent, and take the payment opponent subset corresponding to the opponent subset center corresponding to the minimum value as the payment opponent subset corresponding to the payment opponent; take the minimum value of the payment distances corresponding to the unselected opponent subset centers as the payment distance D2 corresponding to the payment opponent.

[0068] If the difference between the corresponding payment distance D2 and the corresponding payment distance D1 is greater than the specified threshold, create a new opponent subset center based on the payment opponent. The newly created opponent subset center corresponds to a new payment opponent subset, and initially, the new payment opponent subset only contains the payment opponent; otherwise, divide the payment opponent into the payment opponent subset corresponding to the payment opponent.

[0069] S333, after performing the above steps for all payment opponents, for each payment opponent subset, perform the following steps:

[0070] Update the payment customer vector corresponding to the opponent subset center corresponding to the payment opponent subset to the mean value of the payment customer vectors corresponding to all payment opponents in the payment opponent subset; the risk level of the opponent subset center corresponding to the payment opponent subset remains unchanged.

[0071] In S4, refer to Figure 3 , for each payment opponent subset, the specific method for determining the indicators corresponding to each risk dimension and the corresponding indicator convergence values based on the historical payment data corresponding to the payment opponent subset is as follows:

[0072] S41, for each risk dimension, select the historical payment data corresponding to the risk dimension from the historical payment data corresponding to the payment opponent subset.

[0073] Among them, if the payment opponent of the historical payment data belongs to the payment opponent subset, then consider this historical payment data as "the historical payment data of the payment opponent subset".

[0074] S42. Divide the historical payment data corresponding to each risk dimension into multiple historical payment data subsets corresponding to the risk dimension in chronological order, where the number of payment transactions included in each historical payment data subset corresponding to the risk dimension is greater than the first threshold, and the difference in the number of payment transactions included in any two historical payment data subsets corresponding to the risk dimension is less than the second threshold;

[0075] S43. Take the proportion of risky payment data in each historical payment data subset corresponding to each risk dimension as the index sample corresponding to the risk dimension;

[0076] S44. Based on the index sample corresponding to each risk dimension, determine the index mean, index variance, and index sample size corresponding to the risk dimension;

[0077] S45. Determine the index corresponding to each risk dimension of the payment counterparty subset as the index mean corresponding to the risk dimension;

[0078] S46. Determine the index convergence value corresponding to the index corresponding to each risk dimension of the payment counterparty subset as the ratio of the square of the index variance corresponding to the risk dimension to the index sample size corresponding to the risk dimension.

[0079] In S5, refer to Figure 4 , and the specific method for determining the low-risk payment counterparty subset based on the indexes corresponding to each risk dimension of the payment counterparty subset and the corresponding index convergence values is as follows:

[0080] S51. Determine the partial order of the payment counterparty subset based on the indexes corresponding to each risk dimension of the payment counterparty subset and the corresponding index convergence values, where the partial order is used to determine whether payment counterparty subset A is lower than payment counterparty subset B in any two payment counterparty subsets;

[0081] S52. Select the maximal payment counterparty subsets from the multiple payment counterparty subsets according to the partial order of the payment counterparty subset, where the maximal payment counterparty subsets are the maximal elements of the partial order;

[0082] S53. Determine the low-risk payment counterparty subset based on the maximal payment counterparty subsets.

[0083] In one embodiment, (S51) determining the partial order of the payment counterparty subset based on the indexes corresponding to each risk dimension of the payment counterparty subset and the corresponding index convergence values includes:

[0084] For any two subsets of payment counterparts, if for each risk metric, the metric of the subset of payment counterparts A in the two subsets of payment counterparts corresponding to this risk dimension is less than or equal to the metric of the subset of payment counterparts B in the two subsets of payment counterparts corresponding to this risk dimension, and the metric convergence values corresponding to the metrics of the subset of payment counterparts A for each risk dimension are less than the metric convergence threshold, then it is determined that the subset of payment counterparts A is lower than the subset of payment counterparts B.

[0085] In one embodiment, the metric convergence threshold is set as follows:

[0086] Set the metric error threshold and the probability that the metric error is greater than this metric error threshold;

[0087] Set the metric convergence threshold as the product of the square of the metric error threshold and the probability that the metric error is greater than this metric error threshold.

[0088] In S6, for each customer, based on the historical payment data of this customer and the subset of low-risk payment counterparts, determine the low-risk payment counterparts corresponding to this customer, including:

[0089] For each historical payment data of this customer, determine whether the payment counterpart corresponding to this historical payment data belongs to the subset of low-risk payment counterparts. If so, use the payment counterpart corresponding to this historical payment data as the low-risk payment counterpart corresponding to this customer.

[0090] Specifically, refer to Figure 5 , (S6) determine whether the payment counterpart corresponding to this historical payment data belongs to the subset of low-risk payment counterparts, including:

[0091] S61, when the payment counterpart a corresponding to this historical payment data is not a payment counterpart within the predetermined range of the bank, obtain the historical payment data corresponding to this payment counterpart and determine the payment customer vector corresponding to this payment counterpart a, where the components of this payment customer vector correspond one-to-one with customer categories, and the component value of each component is equal to the number of customers belonging to the customer category corresponding to this component among the payment customers corresponding to the historical payment data corresponding to this payment counterpart a;

[0092] It should be noted that "the payment counterpart a corresponding to this historical payment data is not a payment counterpart within the predetermined range of the bank" means that when determining the subset of payment counterparts in (S3), this payment counterpart a did not participate in the classification of the subset of payment counterparts.

[0093] S62, for each payment counterpart b within the predetermined range of the bank, use the absolute value of the vector difference between the payment customer vector corresponding to the payment counterpart a and the payment customer vector corresponding to the payment counterpart b as the customer gap vector corresponding to this payment counterpart b;

[0094] Among them, the absolute value of the vector difference is the vector obtained by taking the absolute value of each component of the vector difference.

[0095] S63. Determine the partial order of the payment counterparts. Among them, for any two payment counterparts within a predetermined range, determine the difference between the customer gap vector of the first payment counterpart and the customer gap vector of the second payment counterpart of the two payment counterparts. If each component of the difference is less than or equal to 0, determine that the first payment counterpart is closer to the second payment counterpart;

[0096] S64. Select the maximal payment counterparts from all the payment counterparts of the bank within a predetermined range according to the partial order of the payment counterparts. Among them, the maximal payment counterparts are the maximal elements of the partial order;

[0097] S65. Determine whether the payment counterpart corresponding to the historical payment data belongs to the subset of low-risk payment counterparts according to the maximal payment counterparts.

[0098] In specific implementation, determining whether the payment counterpart corresponding to the historical payment data belongs to the subset of low-risk payment counterparts according to the maximal payment counterparts can be that when there is a maximal payment counterpart belonging to the subset of low-risk payment counterparts, determine that the payment counterpart corresponding to the historical payment data belongs to the subset of low-risk payment counterparts; or when most of the maximal payment counterparts belong to the subset of low-risk payment counterparts, determine that the payment counterpart corresponding to the historical payment data belongs to the subset of low-risk payment counterparts; in actual application scenarios, other methods can also be adopted.

[0099] In one embodiment, selecting the maximal payment counterparts from all the payment counterparts of the bank within a predetermined range according to the partial order of the payment counterparts includes:

[0100] S01. Initialize the set of payment counterparts to be determined and the set of payment counterparts to be compared as all the payment counterparts of the bank within a predetermined range;

[0101] S02. Loop and execute the following 3 steps until the set of payment counterparts to be determined is empty:

[0102] Take out a payment counterpart c from the set of payment counterparts to be determined, delete the payment counterpart c from the set of payment counterparts to be determined, and compare the payment counterpart c with each payment counterpart d other than the payment counterpart c in the set of payment counterparts to be compared;

[0103] If the payment counterpart d is closer to the payment counterpart c, delete the payment counterpart c from the set of payment counterparts to be determined; if the payment counterpart c is closer to the payment counterpart d, delete the payment counterpart d from the set of payment counterparts to be determined, and determine the payment counterpart d as the secondary payment counterpart of the payment counterpart c;

[0104] If it is confirmed that each payment counterparty in the set of payment counterparties to be compared, except for the payment counterparty c, is not closer to the payment counterparty c, then the payment counterparty c is regarded as a maximum payment counterparty, and all secondary payment counterparties of the payment counterparty c are deleted from the set of payment counterparties to be compared.

[0105] In S7, for each customer, the low-risk payment counterparties corresponding to the customer are sent to the mobile terminal of the customer;

[0106] In S8, when the network strength of the mobile terminal of the customer is less than the set threshold, the low-risk payment counterparties stored in the mobile terminal of the customer are used to support the payment transaction of the customer.

[0107] In one embodiment, referring to Figure 6 , the method further includes:

[0108] S9. When the network strength of the mobile terminal of the customer is less than the threshold and there are no low-risk payment counterparties stored in the mobile terminal of the customer, the information of the received payment counterparty is encrypted with the public key of the bank server, and the encrypted information of the payment counterparty is sent to the bank server through the device of the payment counterparty;

[0109] S10. The bank server determines whether the received payment counterparty belongs to the subset of low-risk payment counterparties, and encrypts the determination result with the public key of the customer, and transmits it to the mobile terminal of the customer through the device of the payment counterparty;

[0110] S11. The mobile terminal of the customer determines whether to support the current payment transaction of the customer according to the received determination result.

[0111] 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 the accompanying drawings, this does not require or imply that these operations must be performed in this specific order, or that all the operations shown 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.

[0112] After introducing the method of the exemplary embodiment of the present invention, next, referring to Figure 7 the risk control device for payment transactions of the exemplary embodiment of the present invention is introduced.

[0113] The implementation of the risk control device for payment transactions can refer to the implementation of the above method, and the repeated parts will not be described again. The terms "module" or "unit" used below 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.

[0114] Based on the same inventive concept, the present invention also proposes a risk control device for payment transactions, as Figure 7 shown, the device includes:

[0115] A customer classification module 710, configured to classify the customers of the bank to obtain multiple customer categories;

[0116] A data acquisition module 720, configured to acquire historical payment data of the bank within a predetermined range, and extract a set of payment counterparts of the bank within the predetermined range;

[0117] A payment counterpart classification module 730, configured to classify the extracted set of payment counterparts of the bank within the predetermined range according to the customer categories to obtain multiple subsets of payment counterparts;

[0118] A data analysis module 740, configured to, for each subset of payment counterparts, determine the indicators and corresponding indicator convergence values of each risk dimension corresponding to the subset of payment counterparts according to the historical payment data corresponding to the subset of payment counterparts;

[0119] A low-risk payment counterpart analysis module 750, configured to determine a subset of low-risk payment counterparts according to the indicators and corresponding indicator convergence values of each risk dimension corresponding to the subset of payment counterparts;

[0120] A low-risk payment counterpart determination module 760, configured to, for each customer, determine the low-risk payment counterparts corresponding to the customer according to the historical payment data of the customer and the subset of low-risk payment counterparts;

[0121] A sending module 770, configured to, for each customer, send the low-risk payment counterparts corresponding to the customer to the mobile terminal of the customer;

[0122] A transaction processing module 780, configured to, when the network strength of the mobile terminal of the customer is less than a set threshold, use the low-risk payment counterparts stored in the mobile terminal of the customer to support the payment transaction of the customer.

[0123] In an embodiment, the payment counterpart classification module is specifically configured to:

[0124] For each payment counterpart in the extracted set of payment counterparts of the bank within the predetermined range, acquire the historical payment data corresponding to the payment counterpart, and determine the number of customers belonging to each customer category among the payment customers corresponding to the historical payment data; determine the payment customer vector corresponding to the payment counterpart, where the components of the payment customer vector correspond one-to-one with the customer categories, and the component value of each component is equal to the number of customers belonging to the customer category corresponding to the component among the payment customers corresponding to the historical payment data corresponding to the payment counterpart;

[0125] Determine a distance function for payment counterparts, where the distance function is used to determine the distance between any two payment counterparts as the distance between the payment customer vectors corresponding to the two payment counterparts;

[0126] Classify the set of payment counterparts of the bank within a predetermined range according to the distance function of the payment counterparts to obtain multiple subsets of payment counterparts.

[0127] In one embodiment, the data analysis module is specifically configured to:

[0128] For each risk dimension, select the historical payment data corresponding to the risk dimension from the historical payment data corresponding to the subset of payment counterparts;

[0129] Divide the historical payment data corresponding to each risk dimension into multiple historical payment data subsets corresponding to the risk dimension in chronological order, where the number of payment transactions included in each historical payment data subset corresponding to the risk dimension is greater than a first threshold, and the difference in the number of payment transactions included in any two historical payment data subsets corresponding to the risk dimension is less than a second threshold;

[0130] Based on the index samples corresponding to each risk dimension, determine the index mean, index variance, and index sample size corresponding to the risk dimension;

[0131] Based on the index samples corresponding to each risk dimension, determine the index mean and index variance corresponding to the risk dimension;

[0132] Determine the index corresponding to each risk dimension of the subset of payment counterparts as the index mean corresponding to the risk dimension;

[0133] Determine the index convergence value corresponding to each risk dimension of the subset of payment counterparts as the ratio of the square of the index variance corresponding to the risk dimension to the index sample size corresponding to the risk dimension.

[0134] In one embodiment, the low-risk payment counterpart analysis module is specifically configured to:

[0135] Determine the partial order of the subset of payment counterparts according to the indexes and the corresponding index convergence values corresponding to each risk dimension of the subset of payment counterparts, where the partial order is used to determine whether payment counterpart subset A is lower than payment counterpart subset B in any two subsets of payment counterparts;

[0136] Select the maximal subset of payment counterparts from the multiple subsets of payment counterparts according to the partial order of the subset of payment counterparts, where the maximal subset of payment counterparts is the maximal element of the partial order;

[0137] Determine the low-risk subset of payment counterparts according to the maximal subset of payment counterparts.

[0138] In one embodiment, the low-risk payment counterparty analysis module is specifically configured to:

[0139] For any two subsets of payment counterparties, if for each risk metric, the metrics of the payment counterparty subset A in the two subsets of payment counterparties corresponding to this risk dimension are less than or equal to the metrics of the payment counterparty subset B in the two subsets of payment counterparties corresponding to this risk dimension, and the index convergence values corresponding to the metrics of the payment counterparty subset A corresponding to each risk dimension are less than the index convergence threshold, then it is determined that the payment counterparty subset A is lower than the payment counterparty subset B.

[0140] In one embodiment, the low-risk payment counterparty determination module is specifically configured to:

[0141] For each historical payment data of the customer, determine whether the payment counterparty corresponding to the historical payment data belongs to the low-risk payment counterparty subset. If so, use the payment counterparty corresponding to the historical payment data as the low-risk payment counterparty corresponding to the customer.

[0142] In one embodiment, the low-risk payment counterparty determination module is specifically configured to:

[0143] When the payment counterparty a corresponding to the historical payment data is not a payment counterparty of the bank within a predetermined range, obtain the historical payment data corresponding to the payment counterparty, and determine the payment customer vector corresponding to the payment counterparty a, where the components of the payment customer vector correspond one-to-one with customer categories, and the component value of each component is equal to the number of customers belonging to the customer category corresponding to the component among the payment customers corresponding to the historical payment data corresponding to the payment counterparty a;

[0144] For each payment counterparty b of the bank within a predetermined range, use the absolute value of the vector difference between the payment customer vector corresponding to the payment counterparty a and the payment customer vector corresponding to the payment counterparty b as the customer gap vector corresponding to the payment counterparty b;

[0145] Determine the partial order of the payment counterparties. Specifically, for any two payment counterparties within a predetermined range, determine the difference between the customer gap vector of the first payment counterparty of the two payment counterparties and the customer gap vector of the second payment counterparty of the two payment counterparties. If each component of the difference is less than or equal to 0, then it is determined that the first payment counterparty is closer to the second payment counterparty;

[0146] According to the partial order of the payment counterparties, select the maximal payment counterparties from all the payment counterparties of the bank within a predetermined range, where the maximal payment counterparties are the maximal elements of the partial order;

[0147] According to the maximal payment counterparties, determine whether the payment counterparty corresponding to the historical payment data belongs to the low-risk payment counterparty subset.

[0148] In one embodiment, refer toFigure 8 , the device further includes: an information processing module 790; wherein,

[0149] The information processing module 790 is configured to, when the network strength of the customer's mobile terminal is less than a threshold and there is no low-risk payment counterparty stored on the customer's mobile terminal, encrypt the received information of the payment counterparty with the public key of the bank server, and send the encrypted information of the payment counterparty to the bank server through the device of the payment counterparty;

[0150] The low-risk payment counterparty determination module 760 is disposed in the bank server and is further configured to determine whether the received payment counterparty belongs to the low-risk payment counterparty subset, encrypt the determination result with the public key of the customer, and transmit it to the customer's mobile terminal through the device of the payment counterparty;

[0151] The customer's mobile terminal determines whether to support the customer's current payment transaction based on the received determination result.

[0152] It should be noted that although several modules of the risk control device for payment transactions are mentioned in the above detailed description, this division is merely exemplary and not mandatory. In fact, according to the embodiments of the present invention, the features and functions of two or more of the above-described modules may be embodied in one module. Conversely, the features and functions of one module described above may be further divided and embodied by multiple modules.

[0153] Based on the foregoing inventive concept, as Figure 9 shown, the present invention also provides a computer device 900, including a memory 910, a processor 920, and a computer program 930 stored on the memory 910 and executable on the processor 920. When the processor 920 executes the computer program 930, the risk control method for the foregoing payment transaction is implemented.

[0154] Based on the foregoing inventive concept, the present invention provides a computer-readable storage medium storing a computer program, and when the computer program is executed by a processor, the risk control method for the foregoing payment transaction is implemented.

[0155] Based on the foregoing inventive concept, the present invention provides a computer program product including a computer program, and when the computer program is executed by a processor, the risk control method for payment transactions is implemented.

[0156] The risk control method and device for payment transactions proposed by the present invention classify customers of a bank to obtain multiple customer categories; obtain historical payment data of the bank within a predetermined range, and extract a set of payment counterparts of the bank within the predetermined range; classify the extracted set of payment counterparts of the bank within the predetermined range according to the customer categories to obtain multiple subsets of payment counterparts; for each subset of payment counterparts, determine the indicators and corresponding indicator convergence values of each risk dimension corresponding to the subset of payment counterparts according to the historical payment data corresponding to the subset of payment counterparts; determine a subset of low-risk payment counterparts according to the indicators and corresponding indicator convergence values of each risk dimension corresponding to the subset of payment counterparts; for each customer, determine the low-risk payment counterparts corresponding to the customer according to the historical payment data of the customer and the subset of low-risk payment counterparts; for each customer, send the low-risk payment counterparts corresponding to the customer to the mobile terminal of the customer; when the network strength of the mobile terminal of the customer is less than a set threshold, use the low-risk payment counterparts stored in the mobile terminal of the customer to support the payment transaction of the customer. The present invention can analyze the payment counterparts of customers, send low-risk payment counterparts to the customer mobile terminal, enable the customer to conduct payment transactions with low-risk payment counterparts when the mobile terminal network signal is poor, improve the customer experience, and enable the bank to effectively control the risk of payment transactions.

[0157] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a device, or a computer program product. 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 storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0158] 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 realized 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, so that the instructions executed by the processor of the computer or other programmable data processing devices generate a device for realizing the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0159] 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 procedures Figure 1 or steps and / or Figure 1 boxes or more boxes.

[0160] 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 procedures Figure 1 or steps and / or Figure 1 boxes or more boxes.

[0161] Finally, it should be noted that the above-described embodiments are only specific embodiments of the present invention, used to illustrate the technical solutions of the present invention, rather than limiting it. 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 within the technical scope disclosed by the present invention can still modify the technical solutions described in the foregoing embodiments, or can easily think of changes, or perform equivalent replacements on some of the technical features; and these modifications, changes or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be covered within 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 payment transactions, characterized in that, comprising: classifying customers of a bank to obtain multiple customer categories; acquiring historical payment data of the bank within a predetermined range and extracting a set of payment counterparts of the bank within the predetermined range; classifying the extracted set of payment counterparts of the bank within the predetermined range according to the customer categories to obtain multiple subsets of payment counterparts; for each subset of payment counterparts, determining indicators and corresponding indicator convergence values for each risk dimension corresponding to the subset of payment counterparts based on the historical payment data corresponding to the subset of payment counterparts; determining a subset of low-risk payment counterparts based on the indicators and corresponding indicator convergence values for each risk dimension corresponding to the subset of payment counterparts; for each customer, determining the low-risk payment counterparts corresponding to the customer based on the historical payment data of the customer and the subset of low-risk payment counterparts; for each customer, sending the low-risk payment counterparts corresponding to the customer to the mobile terminal of the customer; when the network strength of the mobile terminal of the customer is less than a set threshold, using the low-risk payment counterparts stored in the mobile terminal of the customer to support the payment transaction of the customer; wherein, classifying the extracted set of payment counterparts of the bank within the predetermined range according to the customer categories to obtain multiple subsets of payment counterparts includes: for each payment counterpart in the extracted set of payment counterparts of the bank within the predetermined range, acquiring the historical payment data corresponding to the payment counterpart and determining the number of customers belonging to each customer category among the payment customers corresponding to the historical payment data; determining the payment customer vector corresponding to the payment counterpart, wherein the components of the payment customer vector correspond one-to-one with the customer categories, and the component value of each component is equal to the number of customers belonging to the customer category corresponding to the component among the payment customers corresponding to the historical payment data corresponding to the payment counterpart; determining a distance function for the payment counterparts, wherein the distance function is used to determine the distance between any two payment counterparts as the distance between the payment customer vectors corresponding to the two payment counterparts; classifying the extracted set of payment counterparts of the bank within the predetermined range according to the distance function of the payment counterparts to obtain multiple subsets of payment counterparts.

2. The method according to claim 1, characterized in that, for each subset of payment counterparts, determining indicators and corresponding indicator convergence values for each risk dimension corresponding to the subset of payment counterparts based on the historical payment data corresponding to the subset of payment counterparts includes: for each risk dimension, selecting the historical payment data corresponding to the risk dimension from the historical payment data corresponding to the subset of payment counterparts; dividing the historical payment data corresponding to each risk dimension into multiple historical payment data subsets corresponding to the risk dimension in chronological order, wherein the number of payment transactions included in each historical payment data subset corresponding to the risk dimension is greater than a first threshold, and the difference in the number of payment transactions included in any two historical payment data subsets corresponding to the risk dimension is less than a second threshold; taking the proportion of risk payment data in each historical payment data subset corresponding to each risk dimension as the index sample corresponding to the risk dimension; Based on the index samples corresponding to each risk dimension, determine the index mean, index variance, and the number of index samples corresponding to this risk dimension; Determine the index corresponding to each risk dimension of this subset of payment counterparts as the index mean corresponding to this risk dimension; Determine the index convergence value corresponding to the index of each risk dimension of this subset of payment counterparts as the ratio of the square of the index variance corresponding to this risk dimension to the number of index samples corresponding to this risk dimension.

3. The method according to claim 1, characterized in that determine a subset of low-risk payment counterparts based on the indexes and corresponding index convergence values of each risk dimension corresponding to the subset of payment counterparts, including: Determine the partial order of the subset of payment counterparts based on the indexes and corresponding index convergence values of each risk dimension corresponding to the subset of payment counterparts, wherein this partial order is used to determine whether a subset of payment counterparts A is lower than a subset of payment counterparts B among any two subsets of payment counterparts; Select a maximal subset of payment counterparts from these multiple subsets of payment counterparts according to the partial order of the subset of payment counterparts, wherein this maximal subset of payment counterparts is the maximal element of this partial order; Determine a subset of low-risk payment counterparts based on the maximal subset of payment counterparts.

4. The method according to claim 3, characterized in that Determine the partial order of the subset of payment counterparts based on the indexes and corresponding index convergence values of each risk dimension corresponding to the subset of payment counterparts, including: For any two subsets of payment counterparts, if for each risk index, the index corresponding to this risk dimension of the subset of payment counterparts A in these two subsets of payment counterparts is less than or equal to the index corresponding to this risk dimension of the subset of payment counterparts B in these two subsets of payment counterparts, and the index convergence value corresponding to the indexes of each risk dimension of the subset of payment counterparts A is less than the index convergence threshold, then determine that the subset of payment counterparts A is lower than the subset of payment counterparts B.

5. The method according to claim 1, characterized in that For each customer, based on the historical payment data of this customer and the subset of low-risk payment counterparts, determine the low-risk payment counterpart corresponding to this customer, including: For each historical payment data of this customer, determine whether the payment counterpart corresponding to this historical payment data belongs to the subset of low-risk payment counterparts. If so, use the payment counterpart corresponding to this historical payment data as the low-risk payment counterpart corresponding to this customer.

6. The method according to claim 5, characterized in that Determine whether the payment counterpart corresponding to this historical payment data belongs to the subset of low-risk payment counterparts, including: When the payment counterpart a corresponding to this historical payment data is not a payment counterpart within the predetermined range of the bank, obtain the historical payment data corresponding to this payment counterpart, and determine the payment customer vector corresponding to this payment counterpart a, wherein the components of this payment customer vector correspond one by one to customer categories, and the component value of each component is equal to the number of customers belonging to the customer category corresponding to this component among the payment customers corresponding to the historical payment data corresponding to this payment counterpart a; For each payment counterpart b within the predetermined range of the bank, use the absolute value of the vector difference between the payment customer vector corresponding to the payment counterpart a and the payment customer vector corresponding to the payment counterpart b as the customer gap vector corresponding to this payment counterpart b; Determine the partial order of payment counterparts. For any two payment counterparts within a predetermined range, determine the difference between the customer gap vector of the first payment counterpart and the customer gap vector of the second payment counterpart of these two payment counterparts. If each component of this difference is less than or equal to 0, determine that the first payment counterpart is closer to the second payment counterpart; According to the partial order of payment counterparts, select the maximal payment counterparts from all the payment counterparts of the bank within a predetermined range, where the maximal payment counterparts are the maximal elements of this partial order; Based on the maximal payment counterparts, determine whether the payment counterpart corresponding to the historical payment data belongs to the subset of low-risk payment counterparts.

7. The method according to claim 1, characterized in that it further includes: When the network strength of the customer's mobile terminal is less than the threshold and there is no low-risk payment counterpart stored on the customer's mobile terminal, encrypt the received information of the payment counterpart with the public key of the bank server, and send the encrypted information of the payment counterpart to the bank server through the device of the payment counterpart; The bank server determines whether the received payment counterpart belongs to the subset of low-risk payment counterparts, encrypts the determination result with the public key of the customer, and transmits it to the customer's mobile terminal through the device of the payment counterpart; The customer's mobile terminal determines whether to support the customer's current payment transaction based on the received determination result.

8. A risk control device for payment transactions, characterized in that it includes: A customer classification module for classifying the customers of the bank to obtain multiple customer categories; A data acquisition module for acquiring the historical payment data of the bank within a predetermined range and extracting the set of payment counterparts of the bank within a predetermined range; A payment counterpart classification module for classifying the set of payment counterparts of the bank within a predetermined range extracted according to the customer categories to obtain multiple subsets of payment counterparts; A data analysis module for determining, for each subset of payment counterparts, the indicators and corresponding indicator convergence values of the respective risk dimensions corresponding to the subset of payment counterparts based on the historical payment data corresponding to the subset of payment counterparts; A low-risk payment counterpart analysis module for determining the subset of low-risk payment counterparts based on the indicators of the respective risk dimensions corresponding to the subset of payment counterparts and the corresponding indicator convergence values; A low-risk payment counterpart determination module for determining, for each customer, the low-risk payment counterparts corresponding to the customer based on the historical payment data of the customer and the subset of low-risk payment counterparts; A sending module for sending, for each customer, the low-risk payment counterparts corresponding to the customer to the customer's mobile terminal; A transaction processing module for supporting the customer's payment transaction using the low-risk payment counterparts stored on the customer's mobile terminal when the network strength of the customer's mobile terminal is less than the set threshold; wherein the payment counterpart classification module is specifically used for: For each payment counterparty in the set of payment counterparties of the bank extracted within a predetermined range, obtain the historical payment data corresponding to the payment counterparty, and determine the number of customers belonging to each customer category among the payment customers corresponding to the historical payment data; determine the payment customer vector corresponding to the payment counterparty, where the components of the payment customer vector correspond one-to-one with the customer categories, and the component value of each component is equal to the number of customers belonging to the customer category corresponding to the component among the payment customers corresponding to the historical payment data corresponding to the payment counterparty. Determine the distance function of the payment counterparties, where the distance function is used to determine the distance between any two payment counterparties as the distance between the payment customer vectors corresponding to the two payment counterparties. Classify the set of payment counterparties of the bank extracted within a predetermined range according to the distance function of the payment counterparties to obtain multiple subsets of payment counterparties.

9. The apparatus according to claim 8, characterized in that the data analysis module is specifically configured to: For each risk dimension, select the historical payment data corresponding to the risk dimension from the historical payment data corresponding to the subset of payment counterparties; Divide the historical payment data corresponding to each risk dimension into multiple subsets of historical payment data corresponding to the risk dimension in chronological order, where the number of payment transactions included in each subset of historical payment data corresponding to the risk dimension is greater than a first threshold, and the difference in the number of payment transactions included in any two subsets of historical payment data corresponding to the risk dimension is less than a second threshold; Take the proportion of risky payment data in each subset of historical payment data corresponding to each risk dimension as the index sample corresponding to the risk dimension; Based on the index samples corresponding to each risk dimension, determine the index mean, index variance, and index sample size corresponding to the risk dimension; Determine the index corresponding to each risk dimension of the subset of payment counterparties as the index mean corresponding to the risk dimension; Determine the index convergence value corresponding to the index of each risk dimension of the subset of payment counterparties as the ratio of the square of the index variance corresponding to the risk dimension to the index sample size corresponding to the risk dimension.

10. The apparatus according to claim 8, characterized in that the low-risk payment counterparty analysis module is specifically configured to: Determine the partial order of the subset of payment counterparties according to the indexes corresponding to each risk dimension of the subset of payment counterparties and the corresponding index convergence values, where the partial order is used to determine whether a subset of payment counterparties A is lower than a subset of payment counterparties B among any two subsets of payment counterparties; Select the maximal subset of payment counterparties from the multiple subsets of payment counterparties according to the partial order of the subset of payment counterparties, where the maximal subset of payment counterparties is the maximal element of the partial order; Determine the low-risk subset of payment counterparties according to the maximal subset of payment counterparties.

11. The apparatus according to claim 10, characterized in that the low-risk payment counterparty analysis module is specifically configured to: For any two subsets of payment counterparts, if for each risk metric, the metrics of payment counterpart subset A in these two subsets of payment counterparts corresponding to this risk dimension are less than or equal to the metrics of payment counterpart subset B in these two subsets of payment counterparts corresponding to this risk dimension, and the metric convergence values corresponding to the metrics of payment counterpart subset A corresponding to each risk dimension are less than the metric convergence threshold, then it is determined that payment counterpart subset A is lower than payment counterpart subset B.

12. The apparatus according to claim 8, wherein, the low-risk payment counterpart determination module is specifically configured to: For each historical payment data of the customer, determine whether the payment counterpart corresponding to the historical payment data belongs to the low-risk payment counterpart subset. If so, use the payment counterpart corresponding to the historical payment data as the low-risk payment counterpart corresponding to the customer.

13. The apparatus according to claim 12, wherein, the low-risk payment counterpart determination module is specifically configured to: When the payment counterpart a corresponding to the historical payment data is not a payment counterpart within the predetermined range of the bank, obtain the historical payment data corresponding to the payment counterpart, and determine the payment customer vector corresponding to the payment counterpart a, where the components of the payment customer vector correspond one-to-one with the customer categories, and the component value of each component is equal to the number of customers belonging to the customer category corresponding to the component among the payment customers corresponding to the historical payment data corresponding to the payment counterpart a; For each payment counterpart b within the predetermined range of the bank, use the absolute value of the vector difference between the payment customer vector corresponding to the payment counterpart a and the payment customer vector corresponding to the payment counterpart b as the customer gap vector corresponding to the payment counterpart b; Determine the partial order of the payment counterparts. Among them, for any two payment counterparts within the predetermined range, determine the difference between the customer gap vector of the first payment counterpart of the two payment counterparts and the customer gap vector of the second payment counterpart of the two payment counterparts. If each component of the difference is less than or equal to 0, it is determined that the first payment counterpart is closer to the second payment counterpart; According to the partial order of the payment counterparts, select the maximal payment counterparts from all the payment counterparts within the predetermined range of the bank, where the maximal payment counterpart is the maximal element of this partial order; According to the maximal payment counterparts, determine whether the payment counterpart corresponding to the historical payment data belongs to the low-risk payment counterpart subset.

14. The apparatus according to claim 8, wherein, it further includes: an information processing module; where the information processing module is configured to, when the network strength of the customer's mobile terminal is less than the threshold and the low-risk payment counterparts are not stored on the customer's mobile terminal, encrypt the received information of the payment counterpart with the public key of the bank server, and send the encrypted information of the payment counterpart to the bank server through the device of the payment counterpart; the low-risk payment counterpart determination module, provided on the bank server, is further configured to determine whether the received payment counterpart belongs to the low-risk payment counterpart subset, and encrypt the determination result with the public key of the customer, and transmit it to the mobile terminal of the customer through the device of the payment counterpart; The mobile terminal of the customer determines whether to support the customer's current payment transaction according to the received determination result.

15. A computer device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein, 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, wherein, 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, wherein, 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 7 is implemented.

Images