Methods and devices for banks to control transfer risks

Abstract

This invention proposes a method and apparatus for banks to control transfer risks, relating to the field of computer data processing technology. The method includes: a first bank system acquiring a transfer transaction initiated by a customer and confirming whether the customer is a high-risk customer; when the customer is determined to be a high-risk customer, acquiring a pre-stored correlation coefficient between the customer and the receiving customer corresponding to the transfer transaction; when the correlation coefficient between the customer and the receiving customer is less than a set correlation threshold, the first bank system sending relevant information acquisition requests to various other bank systems; each other bank system determining the relevant customer fingerprint and correlation coefficient corresponding to the customer in each other bank system based on a selected hash function, the customer's identity information, and the receiving customer's identity information; the first bank system updating the correlation coefficient between the customer and the receiving customer; and performing risk control on the transfer transaction based on the updated correlation coefficient between the customer and the receiving customer.

Description

Technical Field

[0001] This invention relates to the field of computer data processing technology, and more particularly to a method and apparatus for banks to control the risk of fund transfers. Background Technology

[0002] This section is intended to provide background or context for the embodiments of the invention set forth in the claims. The description herein is not an admission that it is prior art simply because it is included in this section.

[0003] In banking scenarios, fund transfers are common transactions. Banks need to control the risks associated with customer fund transfers to protect customer funds. However, fund transfers are usually controlled based on pre-defined risk rules, which is inefficient and ineffective for some fund transfer risks.

[0004] In summary, there is an urgent need for a technical solution that can overcome the above-mentioned shortcomings and effectively control the risks of transfer transactions. Summary of the Invention

[0005] To address the problems existing in the prior art, this invention proposes a method and apparatus for banks to control transfer risks.

[0006] In a first aspect of the present invention, a method for banks to control transfer risks is proposed, comprising:

[0007] First Bank's system retrieves transfer transactions initiated by customers and confirms whether the customer is a high-risk customer;

[0008] When a customer is identified as a high-risk customer, the First Bank system obtains the correlation coefficient between the customer and the receiving customer corresponding to the transfer transaction;

[0009] When the correlation coefficient between the customer and the transferred customer is less than the set correlation threshold, the first bank system sends a relevant information acquisition request to each other bank system. The relevant information acquisition request includes the selected hash function, the customer's identity information, and the transferred customer's identity information.

[0010] Each other bank system determines the relevant customer fingerprint of the customer in each other bank system, the correlation coefficient between the customer and the relevant customer fingerprint of the customer in each other bank system, the relevant customer fingerprint of the customer in each other bank system, and the correlation coefficient between the customer in each other bank system, based on the selected hash function, the customer's identity information, and the identity information of the transferred customer.

[0011] Each of the other banking systems will feed back the identified customer fingerprints and correlation coefficients to the first banking system;

[0012] The First Bank system updates the correlation coefficients between the customer and the transferring customer based on the relevant customer fingerprints and correlation coefficients determined by other banking systems.

[0013] The First Bank system uses the updated correlation coefficient between the customer and the receiving customer to conduct risk control for this transfer transaction.

[0014] In a second aspect of the present invention, a device for controlling transfer risks in banks is provided, comprising multiple banking systems; wherein,

[0015] The First Bank system is used to obtain transfer transactions initiated by customers and to confirm whether the customer is a high-risk customer.

[0016] When a customer is identified as a high-risk customer, the First Bank system obtains the correlation coefficient between the customer and the receiving customer corresponding to the transfer transaction;

[0017] When the correlation coefficient between the customer and the transferred customer is less than the set correlation threshold, the first bank system sends a relevant information acquisition request to each other bank system. The relevant information acquisition request includes the selected hash function, the customer's identity information, and the transferred customer's identity information.

[0018] Each other banking system is used to determine, based on the selected hash function, the customer's identity information, and the transfer-in customer's identity information, the relevant customer fingerprints of each other banking system corresponding to the customer, the correlation coefficient between the customer and the relevant customer fingerprints of each other banking system corresponding to the customer, the relevant customer fingerprints of each other banking system corresponding to the transfer-in customer, and the correlation coefficient between the transfer-in customer and the relevant customer fingerprints of each other banking system corresponding to the transfer-in customer.

[0019] The identified customer fingerprints and correlation coefficients will be fed back to the First Bank system.

[0020] The First Bank system is also used to update the correlation coefficients between the customer and the transferring customer based on the relevant customer fingerprints and correlation coefficients determined by other banking systems.

[0021] Based on the updated correlation coefficient between the current customer and the receiving customer, risk control measures are implemented for this transfer transaction.

[0022] In a third aspect of the present invention, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement a method for banks to control transfer risks.

[0023] In a fourth aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing a computer program, which, when executed by a processor, implements a method for banks to control transfer risks.

[0024] In a fifth aspect of the present invention, a computer program product is provided, the computer program product comprising a computer program, wherein when the computer program is executed by a processor, a method for banks to control transfer risks is implemented.

[0025] The method and apparatus for controlling bank transfer risks proposed in this invention analyzes customer data to determine the correlation coefficient between the customer initiating the transfer transaction and the customer receiving the transfer. Based on the correlation coefficient, the risk of the transfer transaction is effectively controlled, ensuring the safety of the assets of both the customer and the bank. Attached Figure Description

[0026] To more clearly illustrate the technical solutions of the embodiments of this application, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0027] Figure 1 This is a schematic flowchart of a bank's method for controlling transfer risks according to an embodiment of the present invention.

[0028] Figure 2 This is a schematic diagram of the process for identifying high-risk customers according to an embodiment of the present invention.

[0029] Figure 3 This is a schematic diagram of the process for determining the correlation coefficient according to an embodiment of the present invention.

[0030] Figure 4 This is a schematic diagram of the process for updating the correlation coefficient between the customer and the transferred customer according to an embodiment of the present invention.

[0031] Figure 5 This is a schematic diagram of the process for risk control of this transfer transaction according to an embodiment of the present invention.

[0032] Figure 6 This is a schematic diagram of a bank's device architecture for controlling transfer risks according to an embodiment of the present invention.

[0033] Figure 7 This is a schematic diagram of a computer device structure according to an embodiment of the present invention. Detailed Implementation

[0034] The principles and spirit of the invention will now be described with reference to several exemplary embodiments. It should be understood that these embodiments are given merely to enable those skilled in the art to better understand and implement the invention, and are not intended to limit the scope of the invention in any way. Rather, these embodiments are provided to make this disclosure more thorough and complete, and to fully convey the scope of this disclosure to those skilled in the art.

[0035] Those skilled in the art will recognize that embodiments of the present invention can be implemented as a system, apparatus, device, method, or computer program product. Therefore, this disclosure can be specifically implemented in the following forms: entirely hardware, entirely software (including firmware, resident software, microcode, etc.), or a combination of hardware and software.

[0036] According to an embodiment of the present invention, a method and apparatus for banks to control transfer risks are proposed, relating to the field of computer data processing technology.

[0037] The principles and spirit of the present invention will be explained in detail below with reference to several representative embodiments.

[0038] Figure 1 This is a schematic flowchart of a bank's method for controlling transfer risks according to an embodiment of the present invention. Figure 1 As shown, the method includes:

[0039] S1, the first bank system obtains the transfer transaction initiated by the customer and confirms whether the customer is a high-risk customer;

[0040] S2, When the customer is determined to be a high-risk customer, the first bank system obtains the correlation coefficient between the customer and the customer receiving the transfer transaction;

[0041] S3, when the correlation coefficient between the customer and the transferred customer is less than the set correlation threshold, the first bank system sends a relevant information acquisition request to each other bank system, wherein the relevant information acquisition request includes the selected hash function, the customer's identity information, and the transferred customer's identity information;

[0042] S4, each other bank system determines the relevant customer fingerprint of the customer corresponding to each other bank system, the correlation coefficient between the customer and the relevant customer fingerprint of the customer corresponding to each other bank system, the relevant customer fingerprint of the customer corresponding to each other bank system, and the correlation coefficient between the customer and the relevant customer fingerprint of the customer corresponding to each other bank system, based on the selected hash function, the customer's identity information, and the identity information of the transferred customer.

[0043] S5, the other banking systems will feed back the identified customer fingerprints and correlation coefficients to the first banking system;

[0044] S6, the first bank system updates the correlation coefficient between the customer and the transferred customer based on the relevant customer fingerprints and correlation coefficients determined by other bank systems;

[0045] S7, the First Bank system uses the updated correlation coefficient between the customer and the receiving customer to conduct risk control for this transfer transaction.

[0046] To provide a clearer explanation of the aforementioned methods for banks to control transfer risks, a specific embodiment will be used as an example for detailed explanation below.

[0047] In one embodiment, reference Figure 2 The present invention also includes a first banking system identifying risky customers using the following method:

[0048] S201, The First Bank System retrieves business data for various customer types from the bank's database;

[0049] S202, First Bank's system determines the business risk matrix corresponding to each customer type based on the business data of each customer type;

[0050] S203, determine the non-zero characteristic value of the business risk matrix corresponding to each customer type, and use the determined non-zero characteristic value as the risk characteristic value corresponding to that customer type;

[0051] S204. Based on the risk characteristic values ​​corresponding to each customer type, identify high-risk customers.

[0052] Specifically, for each customer type, if there exists a risk characteristic value corresponding to that customer type, and the magnitude of that risk characteristic value is greater than the set risk threshold, then customers of that customer type are considered risky customers.

[0053] Specifically, (S202) the First Bank system determines the business risk matrix corresponding to each customer type based on the business data of each customer type, including:

[0054] S202-1, The First Bank System selects transaction data corresponding to various combinations of business channels and business types from the business data of various customer types;

[0055] S202-2, Based on the transaction data corresponding to each combination of business channels and business types, determine the risk coefficient of that combination of business channels and business types corresponding to that customer type;

[0056] S202-3, determine the business risk matrix corresponding to the customer type, wherein the rows of the business risk matrix correspond to the business channels and the columns correspond to the business types. The element value of each element of the business risk matrix is ​​equal to the risk coefficient of the customer type corresponding to the combination of the business channel and the business type corresponding to the element.

[0057] S202-4. Based on the number of rows and columns of the business risk matrix corresponding to the customer type, pad with zeros to obtain a square matrix, and use the obtained square matrix as the business risk square matrix corresponding to the customer type.

[0058] In one embodiment, reference Figure 3 In S4, each of the other banking systems, based on the selected hash function, the customer's identity information, and the transferee's identity information, determines the relevant customer fingerprints of each of the other banking systems corresponding to the customer, the correlation coefficients between the customer and the relevant customer fingerprints of each of the other banking systems corresponding to the customer, the relevant customer fingerprints of each of the other banking systems corresponding to the transferee, and the correlation coefficients between the transferee and the relevant customer fingerprints of each of the other banking systems corresponding to the transferee, including:

[0059] S41, each other bank system obtains the related customers corresponding to the customer, the correlation coefficient between the customer and the corresponding related customers, and the related customers corresponding to the transferred customer and the correlation coefficient between the transferred customer and the corresponding related customers, which are pre-stored in the other bank system;

[0060] S42, the other bank system uses the hash value of the identity information of the relevant customer corresponding to the customer as the fingerprint of the relevant customer of the other bank system corresponding to the customer, and the hash value of the identity information of the relevant customer corresponding to the transferred customer as the fingerprint of the relevant customer of the other bank system corresponding to the transferred customer, based on the selected hash function.

[0061] S43, For each relevant customer fingerprint of the customer corresponding to other banking systems, the correlation coefficient between the customer and the relevant customer fingerprint is determined as the correlation coefficient between the customer and the relevant customer corresponding to the relevant customer fingerprint;

[0062] S44, for each relevant customer fingerprint of the transfer-in customer corresponding to the other bank system, the correlation coefficient between the transfer-in customer and the relevant customer fingerprint is determined as the correlation coefficient between the transfer-in customer and the relevant customer corresponding to the fingerprint.

[0063] In one embodiment, reference Figure 4 In S6, the first bank system updates the correlation coefficient between the customer and the transferring customer based on the relevant customer fingerprints and correlation coefficients determined by other bank systems, including:

[0064] S61, the first bank system determines the fingerprint of the customer corresponding to the first bank system, the correlation coefficient between the customer and the corresponding related customers, the correlation coefficient between the customer and the corresponding related customers, the correlation coefficient between the customer and the corresponding related customers, the correlation coefficient between the customer and the corresponding related customers, the correlation coefficient between the customer and the corresponding related customers, based on the selected hash function and the database of the first bank system.

[0065] S62, the first bank system determines the public related fingerprints corresponding to this transfer transaction based on the relevant customer fingerprints determined by each other bank system, as well as the relevant customer fingerprints of the first bank system corresponding to the customer and the relevant customer fingerprints of the first bank system corresponding to the receiving customer.

[0066] S63, for each public related fingerprint corresponding to this transfer transaction, the correlation coefficient between the customer and the public related fingerprint is determined based on the correlation coefficient determined by each other bank system and the correlation coefficient between the customer and the related customer fingerprint of the first bank system corresponding to the customer; and the correlation coefficient between the transfer customer and the public related fingerprint is determined based on the correlation coefficient determined by each other bank system and the correlation coefficient between the transfer-in customer and the related customer fingerprint of the first bank system corresponding to the transfer-in customer.

[0067] S64, based on the correlation coefficients of the customer and the various public related fingerprints corresponding to this transfer transaction, and the correlation coefficients of the receiving customer and the various public related fingerprints corresponding to this transfer transaction, update the correlation coefficients of the customer and the receiving customer.

[0068] The correlation coefficient between the customer and the transferred customer is updated according to the following formula:

[0069]

[0070] Where r is the correlation coefficient between the customer and the transferred customer; r i 1 It is the correlation coefficient between the customer and the i-th public related fingerprint corresponding to this transfer transaction; r i 2 It is the correlation coefficient between the receiving customer and the i-th public related fingerprint corresponding to this transfer transaction.

[0071] Specifically, (S62) the first bank system determines the public related fingerprints corresponding to this transfer transaction based on the relevant customer fingerprints determined by various other bank systems, as well as the relevant customer fingerprints of the first bank system corresponding to the customer and the relevant customer fingerprints of the receiving customer corresponding to the first bank system. These fingerprints include:

[0072] S62-1, the union of the relevant customer fingerprints of the customer corresponding to the first bank system and the relevant customer fingerprints of the customer corresponding to each other bank system shall be the relevant customer fingerprints of the customer.

[0073] S62-2, the union of the relevant customer fingerprints of the first bank system corresponding to the transferred customer and the relevant customer fingerprints of each other bank system corresponding to the transferred customer is taken as the relevant customer fingerprint of the transferred customer.

[0074] S62-3, the intersection of the relevant customer fingerprint corresponding to the current customer and the relevant customer fingerprint corresponding to the receiving customer shall be used as the common relevant fingerprint corresponding to this transfer transaction.

[0075] In one embodiment, reference Figure 5 In S7, the First Bank system uses the updated correlation coefficients between the customer and the receiving customer to perform risk control on this transfer transaction, including:

[0076] S71, The First Bank system determines the security matrix corresponding to this transfer transaction based on the updated correlation coefficient between the customer and the receiving customer;

[0077] S72, Based on the security matrix corresponding to this transfer transaction, determine the security matrix corresponding to this transfer transaction;

[0078] Specifically, the security matrix is ​​padded with zeros according to the number of rows and columns to obtain a security square matrix.

[0079] S73, the feature value of the security matrix corresponding to this transfer transaction is used as the security feature value corresponding to this transfer transaction;

[0080] S74. Risk control is performed on this transfer transaction based on the security feature value corresponding to this transfer transaction.

[0081] Specifically, (S71) the first bank system determines the security matrix corresponding to this transfer transaction based on the updated correlation coefficients between the customer and the receiving customer, including:

[0082] S71-1, First Bank System obtains historical transfer data;

[0083] S71-2, For each historical transfer data, if the absolute value of the difference between the correlation coefficient of the updated customer and the transfer-in customer and the correlation coefficient of the two customers corresponding to the historical transfer data is less than the correlation threshold, then the historical transfer data shall be used as the historical transfer data corresponding to the current transfer transaction.

[0084] S71-3, For each business channel and each risk type, select the historical transfer data corresponding to that business channel and that risk type from the historical transfer data corresponding to this transfer transaction;

[0085] S71-4, the proportion of transfer data that does not involve risk in the historical transfer data corresponding to the business channel and the risk type shall be used as the security coefficient corresponding to the business channel and the risk type.

[0086] S71-5, determine the security matrix corresponding to this transfer transaction, wherein the rows of the security matrix correspond to the business channels, the columns correspond to the risk types, and the value of each element of the security matrix is ​​equal to the security coefficient corresponding to the business channel and the risk type of the element.

[0087] Specifically, (S74) based on the security feature value corresponding to this transfer transaction, risk control is carried out on this transfer transaction, including:

[0088] S74-1, Determine the security threshold based on historical transfer transaction data;

[0089] S74-2: When each non-zero security feature value corresponding to this transfer transaction is greater than the security threshold, no risk control shall be performed on this transfer transaction.

[0090] In one embodiment, (S74-1) determining a security threshold based on historical transfer transaction data includes:

[0091] Set multiple discrete correlation coefficients;

[0092] For each historical transfer data point, the correlation coefficient between the two customers corresponding to that historical transfer data point is taken as the correlation coefficient corresponding to that historical transfer data point.

[0093] For each discrete correlation coefficient, the historical transfer data in which the absolute value of the difference between the corresponding correlation coefficient and the discrete correlation coefficient is less than the correlation threshold is taken as the historical transfer data corresponding to the discrete correlation coefficient.

[0094] Based on the historical transfer data corresponding to the discrete correlation coefficient, determine the security factor corresponding to the discrete correlation coefficient;

[0095] Based on the safety factor corresponding to each discrete correlation coefficient, a function is fitted to obtain the functional relationship between the safety factor and the correlation coefficient, where the correlation coefficient is the independent variable and the safety factor is the function value.

[0096] Determine multiple monotonic intervals corresponding to the functional relationship between the safety factor and the correlation coefficient, wherein any two adjacent monotonic intervals have opposite increasing or decreasing properties;

[0097] Select the monotonic interval with the largest correlation coefficient from the determined monotonic intervals, and use the left endpoint of the selected monotonic interval as the correlation threshold.

[0098] Based on the historical transfer data corresponding to the relevant thresholds, determine the security matrix corresponding to the relevant thresholds; (In practical applications, the method for determining the security matrix corresponding to the relevant thresholds can be found in S71.)

[0099] Based on the number of rows and columns of the security matrix corresponding to the relevant threshold, zeros are padded to obtain a square matrix, and the minimum non-zero eigenvalue of the obtained square matrix is ​​used as the security threshold.

[0100] In one embodiment, the method further includes determining the correlation coefficient between the various customers as follows:

[0101] The bank server retrieves the relevant customers corresponding to each customer and the correlation coefficient between each customer and its corresponding relevant customers, which are pre-stored on the bank server.

[0102] For any two customers, if there exists a related customer corresponding to the first customer of the two customers, such that the related customer is a related customer corresponding to the second customer, then the first customer is regarded as a potential related customer corresponding to the second customer; for each related customer corresponding to the first customer, if the related customer is a related customer corresponding to the second customer, then the related customer is regarded as a related common customer corresponding to the first customer and the second customer.

[0103] Initialize the correlation coefficient between the first customer and the second customer using the following formula:

[0104] P = MAX(P) i 1 ×P i 2 ),

[0105] Where P is the correlation coefficient between the first customer and the second customer; P i 1 P is the correlation coefficient between the first customer and the i-th related common customer corresponding to the first customer and the second customer; i 2 It is the correlation coefficient between the second customer and the i-th related common customer corresponding to the first and second customers;

[0106] The change in the correlation coefficient between the first customer and the second customer is initialized to a fixed number greater than the change threshold;

[0107] The following steps are repeated until no two customers meet condition t: the third customer is a potential related customer of the fourth customer, and the change in the correlation coefficient between the third and fourth customers is greater than the change threshold.

[0108] Identify two customers who satisfy condition t.

[0109] For each related customer corresponding to the third customer among the two customers, if the related customer is also a related customer corresponding to the fourth customer among the two customers, then the related customer is regarded as a related common customer corresponding to the third customer and the fourth customer.

[0110] Update the correlation coefficient between the third and fourth customers according to the following formula:

[0111]

[0112] Where Q is the correlation coefficient between the third customer and the fourth customer; It is the correlation coefficient between the third customer and the i-th related common customer corresponding to the third customer and the fourth customer; It is the correlation coefficient between the fourth customer and the i-th related common customer corresponding to the third and fourth customers;

[0113] The change in correlation coefficient is updated based on the correlation coefficient between the third and fourth customers after the update and the correlation coefficient before the update.

[0114] It should be noted that although the operation of the method of the present invention has been described in a specific order in the above embodiments and figures, this does not require or imply that the operations must be performed in that specific order, or that all the operations shown must be performed to achieve the desired result. Additionally or alternatively, certain steps may be omitted, multiple steps may be combined into one step, and / or one step may be broken down into multiple steps.

[0115] After introducing the method of exemplary embodiments of the present invention, the following references are made. Figure 6 An exemplary embodiment of the present invention will be described for a bank's apparatus for controlling transfer risks.

[0116] The implementation of the bank's device for controlling transfer risks can refer to the implementation of the above method, and repeated details will not be elaborated further. The terms "module" or "unit" used below can refer to a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0117] Based on the same inventive concept, this invention also proposes a device for banks to control transfer risks, such as... Figure 6 As shown, the device includes: multiple banking systems; wherein,

[0118] The First Bank system is used to obtain transfer transactions initiated by customers and to confirm whether the customer is a high-risk customer.

[0119] When a customer is identified as a high-risk customer, the First Bank system obtains the correlation coefficient between the customer and the receiving customer corresponding to the transfer transaction;

[0120] When the correlation coefficient between the customer and the transferred customer is less than the set correlation threshold, the first bank system sends a relevant information acquisition request to each other bank system. The relevant information acquisition request includes the selected hash function, the customer's identity information, and the transferred customer's identity information.

[0121] Each other banking system is used to determine, based on the selected hash function, the customer's identity information, and the transfer-in customer's identity information, the relevant customer fingerprints of each other banking system corresponding to the customer, the correlation coefficient between the customer and the relevant customer fingerprints of each other banking system corresponding to the customer, the relevant customer fingerprints of each other banking system corresponding to the transfer-in customer, and the correlation coefficient between the transfer-in customer and the relevant customer fingerprints of each other banking system corresponding to the transfer-in customer.

[0122] The identified customer fingerprints and correlation coefficients will be fed back to the First Bank system.

[0123] The First Bank system is also used to update the correlation coefficients between the customer and the transferring customer based on the relevant customer fingerprints and correlation coefficients determined by other banking systems.

[0124] Based on the updated correlation coefficient between the current customer and the receiving customer, risk control measures are implemented for this transfer transaction.

[0125] In one embodiment, the first bank system is further configured to identify high-risk customers as follows:

[0126] Retrieve business data for various customer types from the bank's database;

[0127] Based on the business data of each customer type, determine the corresponding business risk matrix for each customer type;

[0128] Determine the non-zero eigenvalues ​​of the business risk matrix corresponding to each customer type, and use the determined non-zero eigenvalues ​​as the risk eigenvalues ​​corresponding to that customer type.

[0129] Based on the risk characteristic values ​​corresponding to each customer type, high-risk customers are identified.

[0130] In one embodiment, the first bank system is specifically used for:

[0131] Transaction data corresponding to various combinations of business channels and business types are selected from the business data of various customer types;

[0132] Based on the transaction data corresponding to each combination of business channels and business types, determine the risk coefficient of that combination of business channels and business types for that customer type;

[0133] Determine the business risk matrix corresponding to this customer type, where the rows of the business risk matrix correspond to business channels and the columns correspond to business types. The element value of each element of the business risk matrix is ​​equal to the risk coefficient of the customer type, which is the combination of the business channel and the business type corresponding to that element.

[0134] Based on the number of rows and columns of the business risk matrix corresponding to this customer type, zeros are padded to obtain a square matrix, which is then used as the business risk square matrix corresponding to this customer type.

[0135] In one embodiment, the various other banking systems are specifically used for:

[0136] Each other bank system obtains the related customers corresponding to the customer, the correlation coefficient between the customer and the corresponding related customers, and the related customers corresponding to the transferred customer, as well as the correlation coefficient between the transferred customer and the corresponding related customers, which are pre-stored in the other bank system;

[0137] The other banking system uses the hash value of the identity information of the relevant customer corresponding to the customer as the fingerprint of the relevant customer of the other banking system, based on the selected hash function, and uses the hash value of the identity information of the relevant customer corresponding to the transferred customer as the fingerprint of the relevant customer of the other banking system.

[0138] For each related customer fingerprint of this customer in other banking systems, the correlation coefficient between this customer and the related customer fingerprint is determined as the correlation coefficient between this customer and the related customer corresponding to the related customer fingerprint.

[0139] For each related customer fingerprint in other banking systems corresponding to the transferred customer, the correlation coefficient between the transferred customer and the related customer fingerprint is determined as the correlation coefficient between the transferred customer and the related customer corresponding to the fingerprint.

[0140] In one embodiment, the first bank system is specifically used for:

[0141] Based on the selected hash function, and the relevant customers corresponding to the customer, the correlation coefficient between the customer and the relevant customers pre-stored in the database of the first bank system, as well as the relevant customers corresponding to the transferred customer, and the correlation coefficient between the transferred customer and the relevant customers, the fingerprints of the relevant customers in the first bank system corresponding to the customer, the correlation coefficient between the customer and the relevant customer fingerprints of the customer in the first bank system, the fingerprints of the relevant customers in the first bank system corresponding to the transferred customer, and the correlation coefficients between the transferred customer and the relevant customer fingerprints of the customer in the first bank system corresponding to the transferred customer are determined.

[0142] Based on the relevant customer fingerprints determined by various other banking systems, as well as the relevant customer fingerprints of the first banking system corresponding to the customer and the relevant customer fingerprints of the receiving customer corresponding to the first banking system, the common relevant fingerprints corresponding to this transfer transaction are determined.

[0143] For each public related fingerprint corresponding to this transfer transaction, the correlation coefficient between the customer and the public related fingerprint is determined based on the correlation coefficients determined by each other bank system and the correlation coefficient between the customer and the relevant customer fingerprints of the first bank system corresponding to the customer; and the correlation coefficient between the transfer customer and the public related fingerprint is determined based on the correlation coefficients determined by each other bank system and the correlation coefficient between the transfer-in customer and the relevant customer fingerprints of the first bank system corresponding to the transfer-in customer.

[0144] Based on the correlation coefficients of the customer and the various public related fingerprints corresponding to this transfer transaction, and the correlation coefficients of the receiving customer and the various public related fingerprints corresponding to this transfer transaction, update the correlation coefficients of the customer and the receiving customer.

[0145] In one embodiment, the first bank system is specifically used for:

[0146] The union of the customer fingerprints corresponding to the first bank system and the customer fingerprints corresponding to the customer in each of the other bank systems is taken as the customer fingerprint corresponding to the customer.

[0147] The union of the relevant customer fingerprints of the first bank system corresponding to the transferred customer and the relevant customer fingerprints of each other bank system corresponding to the transferred customer is taken as the relevant customer fingerprint of the transferred customer.

[0148] The intersection of the relevant customer fingerprints corresponding to the current customer and the relevant customer fingerprints corresponding to the receiving customer is taken as the common relevant fingerprint for this transfer transaction.

[0149] In one embodiment, the first bank system is specifically used for:

[0150] Based on the updated correlation coefficients between the current customer and the receiving customer, determine the security matrix corresponding to this transfer transaction;

[0151] Based on the security matrix corresponding to this transfer transaction, determine the security square matrix corresponding to this transfer transaction;

[0152] The feature value of the security matrix corresponding to this transfer transaction will be used as the security feature value corresponding to this transfer transaction.

[0153] Based on the security feature value corresponding to this transfer transaction, risk control measures will be implemented for this transfer transaction.

[0154] In one embodiment, the first bank system is specifically used for:

[0155] Retrieve historical transfer data;

[0156] For each historical transfer data, if the absolute value of the difference between the correlation coefficient of the updated customer and the transfer-in customer and the correlation coefficient of the two customers corresponding to the historical transfer data is less than the correlation threshold, then the historical transfer data is used as the historical transfer data corresponding to the current transfer transaction.

[0157] For each business channel and each risk type, select the historical transfer data corresponding to that business channel and risk type from the historical transfer data corresponding to this transfer transaction;

[0158] The proportion of historical transfer data that does not involve risk in the corresponding business channel and risk type is used as the safety factor for the corresponding business channel and risk type.

[0159] Determine the security matrix corresponding to this transfer transaction. In this security matrix, the rows correspond to the business channels and the columns correspond to the risk types. The value of each element of the security matrix is ​​equal to the security coefficient corresponding to the business channel and the risk type of the element.

[0160] It should be noted that although several modules of a bank's risk control device for transfers have been mentioned in the detailed description above, this division is merely exemplary and not mandatory. In fact, according to embodiments of the present invention, the features and functions of two or more modules described above can be embodied in a single module. Conversely, the features and functions of a single module described above can be further divided and embodied by multiple modules.

[0161] Based on the aforementioned inventive concept, such as Figure 7 As shown, the present invention also proposes a computer device 700, including a memory 710, a processor 720, and a computer program 730 stored in the memory 710 and executable on the processor 720. When the processor 720 executes the computer program 730, it implements the aforementioned method for controlling bank transfer risks.

[0162] Based on the aforementioned inventive concept, the present invention proposes a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the aforementioned method for controlling transfer risks in banks.

[0163] Based on the aforementioned inventive concept, the present invention proposes a computer program product, which includes a computer program, and the computer program, when executed by a processor, implements a method for banks to control transfer risks.

[0164] The method and apparatus for controlling bank transfer risks proposed in this invention analyzes customer data to determine the correlation coefficient between the customer initiating the transfer transaction and the customer receiving the transfer. Based on the correlation coefficient, the risk of the transfer transaction is effectively controlled, ensuring the safety of the assets of both the customer and the bank.

[0165] The acquisition, storage, use, and processing of data in this application all comply with the relevant provisions of national laws and regulations.

[0166] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, apparatus, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied 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.

[0167] This invention is described with reference to flowchart illustrations and / or block diagrams of methods and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0168] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0169] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0170] Finally, it should be noted that the above-described embodiments are merely specific implementations of the present invention, used to illustrate the technical solutions of the present invention, and not to limit it. The scope of protection of the present invention is not limited thereto. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that any person skilled in the art can still modify or easily conceive of changes to the technical solutions described in the foregoing embodiments within the technical scope disclosed in the present invention, or make equivalent substitutions for some of the technical features; and these modifications, changes, or substitutions 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 scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A method for banks to control transfer risks, characterized in that, include: First Bank's system retrieves transfer transactions initiated by customers and confirms whether the customer is a high-risk customer; When a customer is identified as a high-risk customer, the First Bank system obtains the correlation coefficient between the customer and the receiving customer corresponding to the transfer transaction; When the correlation coefficient between the customer and the transferred customer is less than the set correlation threshold, the first bank system sends a relevant information acquisition request to each other bank system. The relevant information acquisition request includes the selected hash function, the customer's identity information, and the transferred customer's identity information. Each other bank system determines the relevant customer fingerprint of the customer in each other bank system, the correlation coefficient between the customer and the relevant customer fingerprint of the customer in each other bank system, the relevant customer fingerprint of the customer in each other bank system, and the correlation coefficient between the customer in each other bank system, based on the selected hash function, the customer's identity information, and the identity information of the transferred customer. Each of the other banking systems will feed back the identified customer fingerprints and correlation coefficients to the first banking system; The First Bank system updates the correlation coefficients between the customer and the transferring customer based on the relevant customer fingerprints and correlation coefficients determined by other banking systems. The First Bank system uses the updated correlation coefficient between the customer and the receiving customer to conduct risk control for this transfer transaction; Specifically, the First Bank system updates the correlation coefficients between the customer and the transferring customer based on the relevant customer fingerprints and correlation coefficients determined by other banking systems, including: The First Bank System determines the fingerprints of the relevant customers in the First Bank System, the correlation coefficients between the customer and the relevant customers, the correlation coefficients between the customer and the relevant customers, the correlation coefficients between the transfer-in customer and the relevant customers, and the correlation coefficients between the transfer-in customer and the relevant customers in the First Bank System based on the selected hash function, the database of the First Bank System, the relevant customer fingerprints of the transfer-in customer, and the correlation coefficients between the transfer-in customer and the relevant customer fingerprints of the transfer-in customer in the First Bank System. The First Bank system determines the public related fingerprints for this transfer transaction based on the relevant customer fingerprints determined by various other banking systems, as well as the relevant customer fingerprints of the First Bank system corresponding to the customer and the relevant customer fingerprints of the receiving customer corresponding to the First Bank system. For each public related fingerprint corresponding to this transfer transaction, the correlation coefficient between the customer and the public related fingerprint is determined based on the correlation coefficients determined by each other bank system and the correlation coefficient between the customer and the relevant customer fingerprints of the first bank system corresponding to the customer; and the correlation coefficient between the transfer customer and the public related fingerprint is determined based on the correlation coefficients determined by each other bank system and the correlation coefficient between the transfer-in customer and the relevant customer fingerprints of the first bank system corresponding to the transfer-in customer. Based on the correlation coefficients of the customer and the various public related fingerprints corresponding to this transfer transaction, and the correlation coefficients of the receiving customer and the various public related fingerprints corresponding to this transfer transaction, update the correlation coefficients of the customer and the receiving customer. Specifically, the First Bank system determines the public related fingerprints for this transfer transaction based on the relevant customer fingerprints identified by other banking systems, as well as the relevant customer fingerprints of the receiving customer and the First Bank system, including: The union of the customer fingerprints corresponding to the first bank system and the customer fingerprints corresponding to the customer in each of the other bank systems is taken as the customer fingerprint corresponding to the customer. The union of the relevant customer fingerprints of the first bank system corresponding to the transferred customer and the relevant customer fingerprints of each other bank system corresponding to the transferred customer is taken as the relevant customer fingerprint of the transferred customer. The intersection of the relevant customer fingerprints corresponding to the current customer and the relevant customer fingerprints corresponding to the receiving customer is taken as the common relevant fingerprint for this transfer transaction.

2. The method as described in claim 1, characterized in that, This also includes the method used by the First Bank system to identify high-risk customers: The First Bank system retrieves business data for various customer types from the bank's database; First Bank's system determines the corresponding business risk matrix for each customer type based on business data for each customer type. Determine the non-zero eigenvalues ​​of the business risk matrix corresponding to each customer type, and use the determined non-zero eigenvalues ​​as the risk eigenvalues ​​corresponding to that customer type. Based on the risk characteristic values ​​corresponding to each customer type, high-risk customers are identified.

3. The method as described in claim 2, characterized in that, First Bank's system determines the corresponding business risk matrix for each customer type based on business data, including: The First Bank system selects transaction data corresponding to various combinations of business channels and business types from the business data of various customer types; Based on the transaction data corresponding to each combination of business channels and business types, determine the risk coefficient of that combination of business channels and business types for that customer type; Determine the business risk matrix corresponding to the customer type, where the rows of the business risk matrix correspond to business channels and the columns correspond to business types. The element value of each element of the business risk matrix is ​​equal to the risk coefficient of the customer type, which is the combination of the business channel and the business type corresponding to that element. Based on the number of rows and columns of the business risk matrix corresponding to this customer type, zeros are padded to obtain a square matrix, which is then used as the business risk square matrix corresponding to this customer type.

4. The method as described in claim 1, characterized in that, Each other banking system, based on the selected hash function, the customer's identity information, and the transferee's identity information, determines the relevant customer fingerprints of each other banking system, the correlation coefficient between the customer and the relevant customer fingerprints of each other banking system, the relevant customer fingerprints of each other banking system, and the correlation coefficient between the transferee and the relevant customer fingerprints of each other banking system, including: Each other bank system obtains the related customers corresponding to the customer, the correlation coefficient between the customer and the corresponding related customers, and the related customers corresponding to the transferred customer, as well as the correlation coefficient between the transferred customer and the corresponding related customers, which are pre-stored in the other bank system; The other banking system uses the hash value of the identity information of the relevant customer corresponding to the customer as the fingerprint of the relevant customer of the other banking system, based on the selected hash function, and uses the hash value of the identity information of the relevant customer corresponding to the transferred customer as the fingerprint of the relevant customer of the other banking system. For each related customer fingerprint of this customer in other banking systems, the correlation coefficient between this customer and the related customer fingerprint is determined as the correlation coefficient between this customer and the related customer corresponding to the related customer fingerprint. For each related customer fingerprint in other banking systems corresponding to the transferred customer, the correlation coefficient between the transferred customer and the related customer fingerprint is determined as the correlation coefficient between the transferred customer and the related customer corresponding to the fingerprint.

5. The method as described in claim 1, characterized in that, First Bank's system uses the updated correlation coefficients between the customer and the receiving customer to conduct risk control for this transfer transaction, including: The First Bank system determines the security matrix corresponding to this transfer transaction based on the updated correlation coefficients between the customer and the receiving customer. Based on the security matrix corresponding to this transfer transaction, determine the security square matrix corresponding to this transfer transaction; The feature value of the security matrix corresponding to this transfer transaction will be used as the security feature value corresponding to this transfer transaction. Based on the security feature value corresponding to this transfer transaction, risk control measures will be implemented for this transfer transaction.

6. The method as described in claim 5, characterized in that, First Bank's system determines the security matrix corresponding to this transfer transaction based on the updated correlation coefficients between the customer and the receiving customer, including: First Bank's system retrieves historical transfer data; For each historical transfer data, if the absolute value of the difference between the correlation coefficient of the updated customer and the transfer-in customer and the correlation coefficient of the two customers corresponding to the historical transfer data is less than the correlation threshold, then the historical transfer data is used as the historical transfer data corresponding to the current transfer transaction. For each business channel and each risk type, select the historical transfer data corresponding to that business channel and risk type from the historical transfer data corresponding to this transfer transaction; The proportion of historical transfer data that does not involve risk in the corresponding business channel and risk type is used as the safety factor for the corresponding business channel and risk type. Determine the security matrix corresponding to this transfer transaction. In this security matrix, the rows correspond to the business channels and the columns correspond to the risk types. The value of each element of the security matrix is ​​equal to the security coefficient corresponding to the business channel and the risk type of the element.

7. A device for banks to control transfer risks, characterized in that, Including multiple banking systems; among them, The First Bank system is used to obtain transfer transactions initiated by customers and to confirm whether the customer is a high-risk customer. When a customer is identified as a high-risk customer, the First Bank system obtains the correlation coefficient between the customer and the receiving customer corresponding to the transfer transaction; When the correlation coefficient between the customer and the transferred customer is less than the set correlation threshold, the first bank system sends a relevant information acquisition request to each other bank system. The relevant information acquisition request includes the selected hash function, the customer's identity information, and the transferred customer's identity information. Each other banking system is used to determine, based on the selected hash function, the customer's identity information, and the transfer-in customer's identity information, the relevant customer fingerprints of each other banking system corresponding to the customer, the correlation coefficient between the customer and the relevant customer fingerprints of each other banking system corresponding to the customer, the relevant customer fingerprints of each other banking system corresponding to the transfer-in customer, and the correlation coefficient between the transfer-in customer and the relevant customer fingerprints of each other banking system corresponding to the transfer-in customer. The identified customer fingerprints and correlation coefficients will be fed back to the First Bank system. The First Bank system is also used to update the correlation coefficients between the customer and the transferring customer based on the relevant customer fingerprints and correlation coefficients determined by other banking systems. Based on the updated correlation coefficient between the current customer and the receiving customer, risk control measures are implemented for this transfer transaction. Specifically, the First Bank System is used for: Based on the selected hash function, and the relevant customers corresponding to the customer, the correlation coefficient between the customer and the relevant customers pre-stored in the database of the first bank system, as well as the relevant customers corresponding to the transferred customer, and the correlation coefficient between the transferred customer and the relevant customers, the fingerprints of the relevant customers in the first bank system corresponding to the customer, the correlation coefficient between the customer and the relevant customer fingerprints of the customer in the first bank system, the fingerprints of the relevant customers in the first bank system corresponding to the transferred customer, and the correlation coefficients between the transferred customer and the relevant customer fingerprints of the customer in the first bank system corresponding to the transferred customer are determined. Based on the relevant customer fingerprints determined by various other banking systems, as well as the relevant customer fingerprints of the first banking system corresponding to the customer and the relevant customer fingerprints of the receiving customer corresponding to the first banking system, the common relevant fingerprints corresponding to this transfer transaction are determined. For each public related fingerprint corresponding to this transfer transaction, the correlation coefficient between the customer and the public related fingerprint is determined based on the correlation coefficients determined by each other bank system and the correlation coefficient between the customer and the relevant customer fingerprints of the first bank system corresponding to the customer; and the correlation coefficient between the transfer customer and the public related fingerprint is determined based on the correlation coefficients determined by each other bank system and the correlation coefficient between the transfer-in customer and the relevant customer fingerprints of the first bank system corresponding to the transfer-in customer. Based on the correlation coefficients of the customer and the various public related fingerprints corresponding to this transfer transaction, and the correlation coefficients of the receiving customer and the various public related fingerprints corresponding to this transfer transaction, update the correlation coefficients of the customer and the receiving customer. Specifically, the First Bank System is used for: The union of the customer fingerprints corresponding to the first bank system and the customer fingerprints corresponding to the customer in each of the other bank systems is taken as the customer fingerprint corresponding to the customer. The union of the relevant customer fingerprints of the first bank system corresponding to the transferred customer and the relevant customer fingerprints of each other bank system corresponding to the transferred customer is taken as the relevant customer fingerprint of the transferred customer. The intersection of the relevant customer fingerprints corresponding to the current customer and the relevant customer fingerprints corresponding to the receiving customer is taken as the common relevant fingerprint for this transfer transaction.

8. The apparatus as claimed in claim 7, characterized in that, The First Bank system is also used to identify high-risk customers using the following methods: Retrieve business data for various customer types from the bank's database; Based on the business data of each customer type, determine the corresponding business risk matrix for each customer type; Determine the non-zero eigenvalues ​​of the business risk matrix corresponding to each customer type, and use the determined non-zero eigenvalues ​​as the risk eigenvalues ​​corresponding to that customer type. Based on the risk characteristic values ​​corresponding to each customer type, high-risk customers are identified.

9. The apparatus as claimed in claim 8, characterized in that, The First Bank system is specifically used for: Transaction data corresponding to various combinations of business channels and business types are selected from the business data of various customer types; Based on the transaction data corresponding to each combination of business channels and business types, determine the risk coefficient of that combination of business channels and business types for that customer type; Determine the business risk matrix corresponding to the customer type, where the rows of the business risk matrix correspond to business channels and the columns correspond to business types. The element value of each element of the business risk matrix is ​​equal to the risk coefficient of the customer type, which is the combination of the business channel and the business type corresponding to that element. Based on the number of rows and columns of the business risk matrix corresponding to this customer type, zeros are padded to obtain a square matrix, which is then used as the business risk square matrix corresponding to this customer type.

10. The apparatus as claimed in claim 7, characterized in that, The various other banking systems are specifically used for: Each other bank system obtains the related customers corresponding to the customer, the correlation coefficient between the customer and the corresponding related customers, and the related customers corresponding to the transferred customer, as well as the correlation coefficient between the transferred customer and the corresponding related customers, which are pre-stored in the other bank system; The other banking system uses the hash value of the identity information of the relevant customer corresponding to the customer as the fingerprint of the relevant customer of the other banking system, based on the selected hash function, and uses the hash value of the identity information of the relevant customer corresponding to the transferred customer as the fingerprint of the relevant customer of the other banking system. For each related customer fingerprint of this customer in other banking systems, the correlation coefficient between this customer and the related customer fingerprint is determined as the correlation coefficient between this customer and the related customer corresponding to the related customer fingerprint. For each related customer fingerprint in other banking systems corresponding to the transferred customer, the correlation coefficient between the transferred customer and the related customer fingerprint is determined as the correlation coefficient between the transferred customer and the related customer corresponding to the fingerprint.

11. The apparatus as claimed in claim 7, characterized in that, The First Bank system is specifically used for: Based on the updated correlation coefficients between the current customer and the receiving customer, determine the security matrix corresponding to this transfer transaction; Based on the security matrix corresponding to this transfer transaction, determine the security square matrix corresponding to this transfer transaction; The feature value of the security matrix corresponding to this transfer transaction will be used as the security feature value corresponding to this transfer transaction. Based on the security feature value corresponding to this transfer transaction, risk control measures will be implemented for this transfer transaction.

12. The apparatus as claimed in claim 11, characterized in that, The First Bank system is specifically used for: Retrieve historical transfer data; For each historical transfer data, if the absolute value of the difference between the correlation coefficient of the updated customer and the transfer-in customer and the correlation coefficient of the two customers corresponding to the historical transfer data is less than the correlation threshold, then the historical transfer data is used as the historical transfer data corresponding to the current transfer transaction. For each business channel and each risk type, select the historical transfer data corresponding to that business channel and risk type from the historical transfer data corresponding to this transfer transaction; The proportion of historical transfer data that does not involve risk in the corresponding business channel and risk type is used as the safety factor for the corresponding business channel and risk type. Determine the security matrix corresponding to this transfer transaction. In this security matrix, the rows correspond to the business channels and the columns correspond to the risk types. The value of each element of the security matrix is ​​equal to the security coefficient corresponding to the business channel and the risk type of the element.

13. 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, it implements the method of any one of claims 1 to 6.

14. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the method of any one of claims 1 to 6.

15. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the method of any one of claims 1 to 6.

Images