Methods and devices for identity verification in banking business

By analyzing the discrepancy between the identity verification data from the bank's server and the matching value from the edge computing system, the identity verification method is automatically switched, solving the problem of manual intervention after facial recognition failure and improving the efficiency and security of banking operations.

CN115829588BActive Publication Date: 2026-11-17BANK OF CHINA
View PDF 1 Cites 0 Cited by

Patent Information

Application Number
CN202211431623.5
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2022-11-15
Publication Date
2026-11-17
Estimated Expiration
2042-11-15

AI Technical Summary

Technical Problem

In existing technologies, when facial recognition fails in banking operations, manual intervention is required, which is inefficient, results in a poor customer experience, and poses high transaction risks in high-risk scenarios.

Method used

By analyzing identity verification data through bank servers, a reference customer matrix and matching gap values ​​are determined. When facial recognition fails, the edge computing system switches to other identity verification methods to ensure the smooth progress of identity verification.

Benefits of technology

It has improved the operational efficiency of bank branches, reduced operational risks, achieved digital risk control, and ensured the safety of customers' assets.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN115829588B_ABST
    Figure CN115829588B_ABST
Patent Text Reader

Abstract

This invention proposes a method and apparatus for processing identity verification methods in banking operations, relating to the field of computer data processing technology. The method includes: a bank server determining a reference customer matrix corresponding to each identity verification method based on identity verification data for each method; determining the correspondence between the matching gap value of the edge computing system and the customer matrix based on face recognition failure data; determining the correspondence between the matching gap value of the edge computing system and the identity verification method based on the correspondence between the matching gap value of the edge computing system and the customer matrix, and the reference customer matrix corresponding to each identity verification method; when a customer fails face recognition at a bank branch, the bank branch determines the matching gap value corresponding to this face recognition failure based on the matching value and the matching threshold; and determining the identity verification method corresponding to this face recognition failure, which is used to continue verifying the customer's identity after this face recognition failure.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This invention relates to the field of computer data processing technology, and more particularly to a method and apparatus for identity verification in banking operations. 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] Currently, facial recognition is a commonly used method for customer identity verification when conducting business at banks. However, due to limitations in facial recognition parameter settings for certain individuals, mismatches frequently occur. Addressing this issue often requires manual intervention from staff, which is inefficient and provides a poor customer experience. Furthermore, in high-risk scenarios, the increased uncertainty raises the risk to customer transactions. Therefore, ensuring smooth transactions after facial recognition failure is a pressing issue that needs to be addressed.

[0004] In summary, there is an urgent need for a technical solution that can overcome the above-mentioned shortcomings and verify the customer's identity after facial recognition fails. Summary of the Invention

[0005] To address the problems existing in the prior art, this invention proposes a method and apparatus for identity verification in banking operations.

[0006] In a first aspect of the present invention, a method for processing identity verification in banking operations is proposed, comprising:

[0007] The bank server determines the reference customer matrix corresponding to each identity verification method based on the identity verification data of each identity verification method.

[0008] Based on the face recognition failure data from the edge computing system, the bank server determines the correspondence between the matching gap value of the edge computing system and the customer matrix.

[0009] The bank server determines the correspondence between the matching gap value of the edge computing system and the identity verification method based on the correspondence between the matching gap value of the edge computing system and the customer matrix, and the reference customer matrix corresponding to each identity verification method.

[0010] The bank server sends the mapping relationship between the matching gap value of the edge computing system and the identity verification method to the edge computing system;

[0011] When a customer fails to undergo facial recognition at a bank branch, the bank branch determines the matching gap value corresponding to the failure based on the matching value and the matching threshold.

[0012] Based on the matching gap value corresponding to this facial recognition failure, the bank branch determines the corresponding identity verification method based on the correspondence between the matching gap value of the bank branch's edge computing system and the identity verification method. This identity verification method is used to continue to verify the customer's identity after this facial recognition failure.

[0013] In a second aspect of the present invention, an identity verification processing apparatus for banking services is provided, comprising:

[0014] The bank server is used to determine the reference customer matrix corresponding to each identity verification method based on the identity verification data of each identity verification method.

[0015] The bank server is used to determine the correspondence between the matching gap value of the edge computing system and the customer matrix based on the face recognition failure data of the edge computing system.

[0016] The bank server is used to determine the correspondence between the matching gap value of the edge computing system and the identity verification method based on the correspondence between the matching gap value of the edge computing system and the customer matrix, and the reference customer matrix corresponding to each identity verification method.

[0017] The bank server is used to send the mapping relationship between the matching gap value of the edge computing system and the identity verification method to the edge computing system;

[0018] Bank branches are used to determine the matching gap value corresponding to the failure of facial recognition when a customer fails to perform facial recognition at a bank branch, based on the matching value and the matching threshold.

[0019] The bank branch uses the matching gap value corresponding to the failed facial recognition, the matching gap value of the bank branch's edge computing system, and the correspondence between the two to determine the identity verification method. This identity verification method is used to continue to verify the customer's identity after the failed facial recognition.

[0020] 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 an identity verification method for banking business.

[0021] 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 processing identity verification in banking business.

[0022] 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, it implements an identity verification method for banking business.

[0023] The identity verification method and apparatus for banking services proposed in this invention can analyze identity verification data and, in the event of a failure to effectively analyze a customer's facial recognition, add other identity verification methods to verify the identity, thereby ensuring the safety of customer assets, improving the operational efficiency of bank branches, realizing digital risk control for banks, and effectively reducing the operational risks of bank branches. Attached Figure Description

[0024] 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.

[0025] Figure 1 This is a schematic diagram of a banking business identity verification method processing procedure according to an embodiment of the present invention.

[0026] Figure 2 This is a flowchart illustrating the process of determining the reference customer matrix corresponding to each identity verification method according to an embodiment of the present invention.

[0027] Figure 3 This is a flowchart illustrating the process of determining the correspondence between the matching gap value of the edge computing system and the customer matrix according to an embodiment of the present invention.

[0028] Figure 4 This is a flowchart illustrating the process of determining the correspondence between the matching gap value of the edge computing system and the identity verification method according to an embodiment of the present invention.

[0029] Figure 5 This is a schematic diagram of the identity verification processing device for banking services according to an embodiment of the present invention.

[0030] Figure 6 This is a schematic diagram of a computer device structure according to an embodiment of the present invention. Detailed Implementation

[0031] 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.

[0032] 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.

[0033] According to an embodiment of the present invention, a method and apparatus for processing identity verification in banking business are proposed, relating to the field of computer data processing technology.

[0034] The principles and spirit of the present invention will be explained in detail below with reference to several representative embodiments.

[0035] Figure 1 This is a schematic diagram of a bank identity verification method processing procedure according to an embodiment of the present invention. Figure 1 As shown, the method includes:

[0036] S1, the bank server determines the reference customer matrix corresponding to each identity verification method based on the identity verification data of each identity verification method;

[0037] S2, the bank server determines the correspondence between the matching gap value of the edge computing system and the customer matrix based on the face failure data of the edge computing system;

[0038] S3, the bank server determines the correspondence between the matching gap value of the edge computing system and the identity verification method based on the correspondence between the matching gap value of the edge computing system and the customer matrix, and the reference customer matrix corresponding to each identity verification method.

[0039] S4, the bank server sends the correspondence between the matching gap value of the edge computing system and the identity verification method to the edge computing system;

[0040] S5, when a customer fails to perform facial recognition at a bank branch, the bank branch determines the matching gap value corresponding to the failure based on the matching value and the matching threshold.

[0041] S6. Based on the matching gap value corresponding to the face recognition failure, the matching gap value of the bank branch's edge computing system, and the correspondence between the identity verification method, the bank branch determines the identity verification method corresponding to the face recognition failure. This identity verification method is used to continue to verify the customer's identity after the face recognition failure.

[0042] In one embodiment, reference Figure 2 In S1, the bank server determines the reference customer matrix corresponding to each identity verification method based on the identity verification data of each method, including:

[0043] S11, For each identity verification method, divide the identity verification data of that identity verification method into multiple identity verification data subsets;

[0044] In practical applications, it can be divided according to the period, such as 1 month, 3 months, etc.

[0045] S12, determine the customer matrix and risk matrix corresponding to each subset of identity verification data;

[0046] S13, Based on the risk matrix, determine the controllable audit data subset among the multiple identity verification data subsets;

[0047] S14, use the customer matrix corresponding to each controllable subset of audit data as the reference customer matrix corresponding to this identity verification method.

[0048] In one embodiment, (S11) for each identity verification method, the identity verification data for that method is divided into multiple identity verification data subsets, including:

[0049] S11-1, setting multiple sub-periods;

[0050] S11-2, Based on the identity verification data of this identity verification method in each sub-period, determine the period duration corresponding to this identity verification method;

[0051] S11-3, based on the duration of the period, divide the identity verification data of this identity verification method into multiple identity verification data subsets, wherein the time length corresponding to each identity verification data subset is equal to the duration of the period.

[0052] In one embodiment, (S11-2) based on the identity verification data of the identity verification method in each sub-period, the duration of the period corresponding to the identity verification method is determined, including:

[0053] S11-21, For each sub-period, determine the customer matrix for that sub-period based on the identity verification data of that identity verification method in that sub-period;

[0054] In practical applications, the method for determining the customer matrix for this identity verification method in the sub-period can be found in steps S12-1 to S12-4.

[0055] S11-22, For each subsequent sub-period after this sub-period, calculate the matrix difference between the customer matrix of this identity verification method in this sub-period and the customer matrix in this subsequent sub-period;

[0056] S11-23, Based on the number of rows and columns of the matrix difference, pad the matrix difference with zeros to obtain a square matrix, and use the eigenvalues ​​of the obtained square matrix as the relevant eigenvalues ​​of the sub-period and the subsequent sub-period;

[0057] S11-24, Based on the relevant characteristic values ​​of the sub-period and each subsequent sub-period after the sub-period, determine the relevant sub-period corresponding to the sub-period;

[0058] S11-25, Determine the duration of the period corresponding to the sub-period based on the relevant sub-periods corresponding to the sub-period;

[0059] S11-26, take the minimum duration of each sub-period as the duration of the identity verification method.

[0060] In one embodiment, (S11-24) determining the relevant sub-periods corresponding to the sub-period based on the relevant feature values ​​of the sub-period and each subsequent sub-period after the sub-period includes:

[0061] For each subsequent sub-period after the current sub-period, if the magnitude of the relevant feature value of the current sub-period and the subsequent sub-period is less than the second threshold, then the subsequent sub-period is regarded as the relevant sub-period corresponding to the current sub-period.

[0062] In one embodiment, (S11-25) determining the duration of the period corresponding to the sub-period based on the related sub-periods, including:

[0063] For each relevant sub-period corresponding to the sub-period, if the periods after the sub-period and before the relevant sub-period are all relevant sub-periods corresponding to the sub-period, then the relevant sub-period is regarded as the potential relevant subsequent period corresponding to the sub-period.

[0064] The latest potentially relevant subsequent period among the potentially relevant subsequent periods corresponding to this sub-period is taken as the boundary relevant period corresponding to this sub-period.

[0065] The duration of the sub-period is determined based on the sub-period and the boundary-related period corresponding to the sub-period.

[0066] In one embodiment, (S12) determining the customer matrix and risk matrix corresponding to each subset of identity verification data includes:

[0067] S12-1, Determine the transaction channel and customer category corresponding to each identity verification data in the identity verification data subset;

[0068] S12-2, use the identity verification data as the identity verification data corresponding to the transaction channel and the customer category;

[0069] S12-3, for each transaction channel and each customer category, the number of customers included in the identity verification data corresponding to the transaction channel and the customer category shall be taken as the number of customers corresponding to the transaction channel and the customer category, and the proportion of identity verification data involving risk in the identity verification data corresponding to the transaction channel and the customer category shall be taken as the risk proportion corresponding to the transaction channel and the customer category.

[0070] S12-4, determine the customer matrix and risk matrix corresponding to the subset of identity verification data, wherein the rows of the customer matrix and the risk matrix correspond to transaction channels, and the columns correspond to customer categories; for each element of the customer matrix, determine the corresponding transaction channel and customer category, and use the number of customers corresponding to the transaction channel and customer category as the value of the element; for each element of the risk matrix, determine the corresponding transaction channel and customer category, and use the risk percentage corresponding to the transaction channel and customer category as the value of the element.

[0071] In one embodiment, (S13) based on the risk matrix, the controllable verification data subset among the plurality of identity verification data subsets is determined, including:

[0072] S13-1, For each subset of identity verification data, pad the matrix with zeros according to the number of rows and columns of the risk matrix corresponding to the subset of identity verification data to obtain a square matrix, and use the non-zero eigenvalues ​​of the obtained square matrix as the risk eigenvalues ​​corresponding to the subset of identity verification data.

[0073] S13-2, Based on the risk characteristic value, determine the controllable audit data subset among the multiple identity verification data subsets.

[0074] In one embodiment, (S13-2) based on risk characteristic values, the controllable verification data subset of the plurality of identity verification data subsets is determined, including:

[0075] The subset of identity verification data whose corresponding risk characteristic values ​​are all less than the first threshold is taken as the controllable verification data subset.

[0076] In one embodiment, reference Figure 3 In S2, the bank server determines the correspondence between the matching gap value of the edge computing system and the customer matrix based on the face recognition failure data of the edge computing system, including:

[0077] S21, For each face failure data in the edge computing system, the difference between the face threshold corresponding to the face failure data and the corresponding face matching value is taken as the matching gap value corresponding to the face failure data.

[0078] S22, For each matching gap value, the face failure data whose matching gap value is equal to the matching gap value in the face failure data is taken as the face failure data corresponding to the matching gap value.

[0079] S23, Based on the face failure data corresponding to the matching gap value, determine the customer matrix corresponding to the matching gap value;

[0080] S24. Based on each matching gap value and the customer matrix corresponding to each matching gap value, determine the correspondence between the matching gap value and the customer matrix of the edge computing system.

[0081] In one embodiment, (S23) determining the customer matrix corresponding to the matching gap value based on the face failure data corresponding to the matching gap value includes:

[0082] S23-1, Determine the transaction channel and customer category corresponding to each failed face data for the matching gap value;

[0083] S23-2, use the face failure data as the face failure data corresponding to the transaction channel and the customer category;

[0084] S23-3, For each transaction channel and each customer category, the number of customers included in the face failure data corresponding to that transaction channel and that customer category shall be taken as the number of customers corresponding to that transaction channel and that customer category.

[0085] S23-4, determine the customer matrix corresponding to the matching gap value, where the rows of the customer matrix correspond to transaction channels and the columns correspond to customer categories; for each element of the customer matrix, determine the transaction channel and customer category corresponding to the element, and use the number of customers corresponding to the transaction channel and customer category as the value of the element.

[0086] In one embodiment, reference Figure 4 In S3, the bank server determines the correspondence between the matching gap value of the edge computing system and the identity verification method based on the correspondence between the matching gap value and the customer matrix, and the reference customer matrix corresponding to each identity verification method. This includes:

[0087] S31, the difference matching value contained in the correspondence between the matching gap value of the edge computing system and the customer matrix is ​​used as the candidate difference value;

[0088] S32, For each candidate difference value, the identity verification method corresponding to the candidate difference value is determined based on the customer matrix corresponding to the candidate difference value and the reference customer matrix corresponding to each identity verification method in the correspondence relationship.

[0089] S33. Based on each candidate difference value and the identity verification method corresponding to each candidate difference value, determine the correspondence between the matching gap value and the identity verification method of the edge computing system.

[0090] In one embodiment, (S32) for each candidate difference value, based on the customer matrix corresponding to the candidate difference value in the correspondence and the reference customer matrix corresponding to each identity verification method, the identity verification method corresponding to the candidate difference value is determined, including:

[0091] S32-1, For each identity verification method, determine the matrix difference between the identity verification method and the candidate difference value based on the reference customer matrix corresponding to the identity verification method and the customer matrix corresponding to the candidate difference value.

[0092] S32-2, when the number of rows in the matrix difference corresponding to the candidate difference value of the identity verification method is equal to the number of columns, the eigenvalue of the matrix difference is used as the eigenvalue corresponding to the identity verification method; otherwise, the matrix is ​​padded with zeros according to the number of rows and the number of columns to obtain a square matrix, and the eigenvalue of the obtained square matrix is ​​used as the eigenvalue corresponding to the identity verification method.

[0093] S32-3, Based on the feature values ​​corresponding to each identity verification method, determine the identity verification method corresponding to the candidate difference value.

[0094] In one embodiment, for each identity verification method, based on the reference customer matrix corresponding to the identity verification method and the customer matrix corresponding to the candidate difference value, the matrix difference between the identity verification method and the candidate difference value is determined, including:

[0095] The difference between the reference customer matrix corresponding to the identity verification method and the customer matrix corresponding to the candidate difference value is taken as the matrix difference between the identity verification method and the candidate difference value.

[0096] It should be noted that the time range of the data in each matrix remains consistent when performing the above matrix difference calculation.

[0097] Alternatively, during calculation, a specific position within the matrix can be selected, for example, with 1 row and 1 column. Based on the values ​​of the two matrices at that position, the values ​​of other positions in the matrix can be corrected. Then, calculations can be performed based on the corrected matrices (including directly calculating the matrix difference). This can solve the calculation problems caused by inconsistent time dimensions of the data. In practical applications, other methods can also be used for matrix calculations.

[0098] In one embodiment, (S32-3) determining the identity verification method corresponding to the candidate difference value based on the feature values ​​corresponding to each identity verification method includes:

[0099] The identity verification method whose corresponding feature value modulus is less than the third threshold is taken as the identity verification method corresponding to the candidate difference value.

[0100] In one embodiment, (S32-3) determining the identity verification method corresponding to the candidate difference value based on the feature values ​​corresponding to each identity verification method includes:

[0101] S32-31, when there is no identity verification method, and the modulus of the feature value corresponding to the identity verification method is less than the third threshold, obtain the face failure data of the similar edge computing system of the edge computing system.

[0102] S32-32, based on the face failure data of similar edge computing systems, update the customer matrix corresponding to the candidate difference value;

[0103] S32-33, based on the updated customer matrix corresponding to the candidate difference value and the reference customer matrix corresponding to each identity verification method, determine the identity verification method corresponding to the candidate difference value.

[0104] In one embodiment, the method further includes determining similar edge computing systems to the edge computing system as follows:

[0105] Each edge computing system other than the current edge computing system is selected as a candidate edge system.

[0106] For each candidate edge system, the customers of that candidate edge system are designated as candidate customers.

[0107] The customers of this edge computing system are used as reference customers;

[0108] For each reference customer and each candidate customer, the correlation value between the reference customer and the candidate customer is used as the potential correlation value between the edge computing system and the candidate edge system.

[0109] Based on the potential correlation values ​​between the edge computing system and the candidate edge system, the correlation values ​​between the edge computing system and the candidate edge system are determined.

[0110] Based on the correlation values ​​between the edge computing system and each candidate edge computing system, similar edge computing systems are determined.

[0111] 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.

[0112] After introducing the method of exemplary embodiments of the present invention, the following references are made. Figure 5 An exemplary embodiment of the identity verification processing device for banking business of the present invention will be introduced.

[0113] The implementation of the identity verification processing device for banking operations can refer to the implementation of the above-described method, and repeated details will not be elaborated upon. 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.

[0114] Based on the same inventive concept, this invention also proposes an identity verification processing device for banking services, such as... Figure 5 As shown, the device includes:

[0115] The bank server is used to determine the reference customer matrix corresponding to each identity verification method based on the identity verification data of each identity verification method.

[0116] The bank server is used to determine the correspondence between the matching gap value of the edge computing system and the customer matrix based on the face recognition failure data of the edge computing system.

[0117] The bank server is used to determine the correspondence between the matching gap value of the edge computing system and the identity verification method based on the correspondence between the matching gap value of the edge computing system and the customer matrix, and the reference customer matrix corresponding to each identity verification method.

[0118] The bank server is used to send the mapping relationship between the matching gap value of the edge computing system and the identity verification method to the edge computing system;

[0119] Bank branches are used to determine the matching gap value corresponding to the failure of facial recognition when a customer fails to perform facial recognition at a bank branch, based on the matching value and the matching threshold.

[0120] The bank branch uses the matching gap value corresponding to the failed facial recognition, the matching gap value of the bank branch's edge computing system, and the correspondence between the two to determine the identity verification method. This identity verification method is used to continue to verify the customer's identity after the failed facial recognition.

[0121] In one embodiment, the bank server is specifically used for:

[0122] For each identity verification method, the identity verification data for that method is divided into multiple subsets of identity verification data.

[0123] Determine the customer matrix and risk matrix corresponding to each subset of identity verification data;

[0124] Based on the risk matrix, determine the controllable subset of verification data from the multiple identity verification data subsets;

[0125] The customer matrix corresponding to each controllable subset of audit data is used as the reference customer matrix for that identity verification method.

[0126] In one embodiment, the bank server is specifically used for:

[0127] Determine the transaction channel and customer category corresponding to each piece of identity verification data in this subset of identity verification data;

[0128] Use this identity verification data as the identity verification data corresponding to this transaction channel and this customer category;

[0129] For each transaction channel and each customer category, the number of customers included in the identity verification data corresponding to that transaction channel and that customer category is taken as the number of customers corresponding to that transaction channel and that customer category, and the proportion of identity verification data involving risk in the identity verification data corresponding to that transaction channel and that customer category is taken as the risk proportion corresponding to that transaction channel and that customer category.

[0130] Determine the customer matrix and risk matrix corresponding to the subset of identity verification data, where rows in the customer matrix and risk matrix correspond to transaction channels, and columns correspond to customer categories; for each element in the customer matrix, determine the corresponding transaction channel and customer category, and use the number of customers corresponding to the transaction channel and customer category as the value of the element; for each element in the risk matrix, determine the corresponding transaction channel and customer category, and use the risk percentage corresponding to the transaction channel and customer category as the value of the element.

[0131] In one embodiment, the bank server is specifically used for:

[0132] For each subset of identity verification data, a square matrix is ​​obtained by padding the risk matrix with zeros according to the number of rows and columns of the risk matrix corresponding to the subset of identity verification data. The non-zero eigenvalues ​​of the obtained square matrix are used as the risk eigenvalues ​​corresponding to the subset of identity verification data.

[0133] Based on risk characteristic values, determine the controllable audit data subset from the multiple identity verification data subsets.

[0134] In one embodiment, the bank server is specifically used for:

[0135] For each failed face data in the edge computing system, the difference between the face threshold corresponding to the failed face data and the corresponding face matching value is taken as the matching gap value corresponding to the failed face data.

[0136] For each matching gap value, the face failure data whose matching gap value is equal to that matching gap value is taken as the face failure data corresponding to that matching gap value.

[0137] Based on the face failure data corresponding to the matching gap value, determine the customer matrix corresponding to the matching gap value;

[0138] Based on each matching gap value and the corresponding customer matrix, the correspondence between the matching gap values ​​and the customer matrix of the edge computing system is determined.

[0139] In one embodiment, the bank server is specifically used for:

[0140] Determine the transaction channel and customer category corresponding to each failed face data point for the matching gap value;

[0141] Use this failed face recognition data as the face recognition failure data corresponding to this transaction channel and this customer category;

[0142] For each transaction channel and each customer category, the number of customers included in the face recognition failure data corresponding to that transaction channel and that customer category is taken as the number of customers corresponding to that transaction channel and that customer category.

[0143] Determine the customer matrix corresponding to the matching gap value, where each row of the customer matrix corresponds to a transaction channel and each column corresponds to a customer category; for each element of the customer matrix, determine the corresponding transaction channel and customer category, and use the number of customers corresponding to the transaction channel and customer category as the value of the element.

[0144] In one embodiment, the bank server is specifically used for:

[0145] The difference matching values ​​included in the correspondence between the matching gap value of the edge computing system and the customer matrix are used as candidate difference values;

[0146] For each candidate difference value, the identity verification method corresponding to the candidate difference value is determined based on the customer matrix corresponding to the candidate difference value and the reference customer matrix corresponding to each identity verification method in the correspondence.

[0147] Based on each candidate difference value and the corresponding identity verification method, the correspondence between the matching gap value and the identity verification method of the edge computing system is determined.

[0148] In one embodiment, the bank server is specifically used for:

[0149] For each identity verification method, the matrix difference between the identity verification method and the candidate difference value is determined based on the reference customer matrix corresponding to the identity verification method and the customer matrix corresponding to the candidate difference value.

[0150] When the number of rows in the matrix difference corresponding to the candidate difference value of the identity verification method is equal to the number of columns, the eigenvalue of the matrix difference is used as the eigenvalue corresponding to the identity verification method; otherwise, the matrix is ​​padded with zeros according to the number of rows and columns to obtain a square matrix, and the eigenvalue of the obtained square matrix is ​​used as the eigenvalue corresponding to the identity verification method.

[0151] Based on the feature values ​​corresponding to each identity verification method, determine the identity verification method corresponding to the candidate difference value.

[0152] It should be noted that although several modules of the identity verification processing device for banking business 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 one module. Conversely, the features and functions of one module described above can be further divided and embodied by multiple modules.

[0153] Based on the aforementioned inventive concept, such as Figure 6 As shown, the present invention also proposes a computer device 600, including a memory 610, a processor 620, and a computer program 630 stored in the memory 610 and executable on the processor 620. When the processor 620 executes the computer program 630, it implements the aforementioned identity verification method for banking business.

[0154] 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 identity verification method for banking business.

[0155] Based on the aforementioned inventive concept, this invention proposes a computer program product, which includes a computer program that, when executed by a processor, implements a method for processing identity verification in banking operations.

[0156] The identity verification method and apparatus for banking services proposed in this invention can analyze identity verification data and, in the event of a failure to effectively analyze a customer's facial recognition, add other identity verification methods to verify the identity, thereby ensuring the safety of customer assets, improving the operational efficiency of bank branches, realizing digital risk control for banks, and effectively reducing the operational risks of bank branches.

[0157] The acquisition, storage, use, and processing of data in this application all comply with the relevant provisions of national laws and regulations.

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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 processing identity verification in banking operations, characterized in that, include: The bank server determines the reference customer matrix corresponding to each identity verification method based on the identity verification data of each identity verification method. Based on the face recognition failure data from the edge computing system, the bank server determines the correspondence between the matching gap value of the edge computing system and the customer matrix. The bank server determines the correspondence between the matching gap value of the edge computing system and the identity verification method based on the correspondence between the matching gap value of the edge computing system and the customer matrix, and the reference customer matrix corresponding to each identity verification method. The bank server sends the mapping relationship between the matching gap value of the edge computing system and the identity verification method to the edge computing system; When a customer fails to undergo facial recognition at a bank branch, the bank branch determines the matching gap value corresponding to the failure based on the matching value and the matching threshold. Based on the matching gap value corresponding to this facial recognition failure, the bank branch determines the corresponding identity verification method based on the correspondence between the matching gap value of the bank branch's edge computing system and the identity verification method. This identity verification method is used to continue to verify the customer's identity after this facial recognition failure. The bank server determines a reference customer matrix for each identity verification method based on the identity verification data from each method, including: For each identity verification method, the identity verification data for that method is divided into multiple subsets of identity verification data. Determine the customer matrix and risk matrix corresponding to each subset of identity verification data; Based on the risk matrix, determine the controllable subset of verification data from the multiple identity verification data subsets; Use the customer matrix corresponding to each controllable subset of audit data as the reference customer matrix corresponding to that identity verification method; This includes determining the customer matrix and risk matrix corresponding to each subset of identity verification data, including: Determine the transaction channel and customer category corresponding to each piece of identity verification data in this subset of identity verification data; Use this identity verification data as the identity verification data corresponding to this transaction channel and this customer category; For each transaction channel and each customer category, the number of customers included in the identity verification data corresponding to that transaction channel and that customer category is taken as the number of customers corresponding to that transaction channel and that customer category, and the proportion of identity verification data involving risk in the identity verification data corresponding to that transaction channel and that customer category is taken as the risk proportion corresponding to that transaction channel and that customer category. Determine the customer matrix and risk matrix corresponding to the subset of identity verification data, where rows in the customer matrix and risk matrix correspond to transaction channels, and columns correspond to customer categories; for each element in the customer matrix, determine the corresponding transaction channel and customer category, and use the number of customers corresponding to the transaction channel and customer category as the value of the element; for each element in the risk matrix, determine the corresponding transaction channel and customer category, and use the risk percentage corresponding to the transaction channel and customer category as the value of the element. Based on the risk matrix, the controllable subset of identity verification data is determined, including: For each subset of identity verification data, a square matrix is ​​obtained by padding the risk matrix with zeros according to the number of rows and columns of the risk matrix corresponding to the subset of identity verification data. The non-zero eigenvalues ​​of the obtained square matrix are used as the risk eigenvalues ​​corresponding to the subset of identity verification data. Based on risk characteristic values, determine the controllable verification data subset from the multiple identity verification data subsets; Based on risk characteristic values, the controllable verification data subsets within these multiple identity verification data subsets are determined, including: The subset of identity verification data whose corresponding risk characteristic values ​​are all less than the first threshold is taken as the controllable verification data subset.

2. The method as described in claim 1, characterized in that, Based on the face recognition failure data from the edge computing system, the bank server determines the correspondence between the matching gap value of the edge computing system and the customer matrix, including: For each failed face data in the edge computing system, the difference between the face threshold corresponding to the failed face data and the corresponding face matching value is taken as the matching gap value corresponding to the failed face data. For each matching gap value, the face failure data whose matching gap value is equal to that matching gap value is taken as the face failure data corresponding to that matching gap value. Based on the face failure data corresponding to the matching gap value, determine the customer matrix corresponding to the matching gap value; Based on each matching gap value and the corresponding customer matrix, the correspondence between the matching gap values ​​and the customer matrix of the edge computing system is determined.

3. The method as described in claim 2, characterized in that, Based on the face failure data corresponding to the matching gap value, determine the customer matrix corresponding to the matching gap value, including: Determine the transaction channel and customer category corresponding to each failed face data point for the matching gap value; Use this failed face recognition data as the face recognition failure data corresponding to this transaction channel and this customer category; For each transaction channel and each customer category, the number of customers included in the face recognition failure data corresponding to that transaction channel and that customer category is taken as the number of customers corresponding to that transaction channel and that customer category. Determine the customer matrix corresponding to the matching gap value, where each row of the customer matrix corresponds to a transaction channel and each column corresponds to a customer category; for each element of the customer matrix, determine the corresponding transaction channel and customer category, and use the number of customers corresponding to the transaction channel and customer category as the value of the element.

4. The method as described in claim 1, characterized in that, Based on the correspondence between the matching gap value of the edge computing system and the customer matrix, and the reference customer matrix corresponding to each identity verification method, the bank server determines the correspondence between the matching gap value of the edge computing system and the identity verification method, including: The difference matching values ​​included in the correspondence between the matching gap values ​​of the edge computing system and the customer matrix are used as candidate difference values; For each candidate difference value, the identity verification method corresponding to the candidate difference value is determined based on the customer matrix corresponding to the candidate difference value and the reference customer matrix corresponding to each identity verification method in the correspondence. Based on each candidate difference value and the corresponding identity verification method, the correspondence between the matching gap value and the identity verification method of the edge computing system is determined.

5. The method as described in claim 4, characterized in that, For each candidate difference value, based on the customer matrix corresponding to that candidate difference value in the correspondence and the reference customer matrix corresponding to each identity verification method, the identity verification method corresponding to that candidate difference value is determined, including: For each identity verification method, the matrix difference between the identity verification method and the candidate difference value is determined based on the reference customer matrix corresponding to the identity verification method and the customer matrix corresponding to the candidate difference value. When the number of rows in the matrix difference corresponding to the candidate difference value of the identity verification method is equal to the number of columns, the eigenvalue of the matrix difference is used as the eigenvalue corresponding to the identity verification method; otherwise, the matrix is ​​padded with zeros according to the number of rows and columns to obtain a square matrix, and the eigenvalue of the obtained square matrix is ​​used as the eigenvalue corresponding to the identity verification method. Based on the feature values ​​corresponding to each identity verification method, determine the identity verification method corresponding to the candidate difference value.

6. A device for processing identity verification methods in banking operations, characterized in that, include: The bank server is used to determine the reference customer matrix corresponding to each identity verification method based on the identity verification data of each identity verification method. The bank server is used to determine the correspondence between the matching gap value of the edge computing system and the customer matrix based on the face recognition failure data of the edge computing system. The bank server is used to determine the correspondence between the matching gap value of the edge computing system and the identity verification method based on the correspondence between the matching gap value of the edge computing system and the customer matrix, and the reference customer matrix corresponding to each identity verification method. The bank server is used to send the mapping relationship between the matching gap value of the edge computing system and the identity verification method to the edge computing system; Bank branches are used to determine the matching gap value corresponding to the failure of facial recognition when a customer fails to perform facial recognition at a bank branch, based on the matching value and the matching threshold. The bank branch uses the matching gap value corresponding to the failed face recognition, the matching gap value of the bank branch's edge computing system, and the correspondence between the identity verification method to determine the identity verification method corresponding to the failed face recognition. This identity verification method is used to continue to verify the identity of the customer after the failed face recognition. Specifically, the bank server is used for: For each identity verification method, the identity verification data for that method is divided into multiple subsets of identity verification data. Determine the customer matrix and risk matrix corresponding to each subset of identity verification data; Based on the risk matrix, determine the controllable subset of verification data from the multiple identity verification data subsets; Use the customer matrix corresponding to each controllable subset of audit data as the reference customer matrix corresponding to that identity verification method; Specifically, the bank server is used for: Determine the transaction channel and customer category corresponding to each piece of identity verification data in this subset of identity verification data; Use this identity verification data as the identity verification data corresponding to this transaction channel and this customer category; For each transaction channel and each customer category, the number of customers included in the identity verification data corresponding to that transaction channel and that customer category is taken as the number of customers corresponding to that transaction channel and that customer category, and the proportion of identity verification data involving risk in the identity verification data corresponding to that transaction channel and that customer category is taken as the risk proportion corresponding to that transaction channel and that customer category. Determine the customer matrix and risk matrix corresponding to the subset of identity verification data, where rows in the customer matrix and risk matrix correspond to transaction channels, and columns correspond to customer categories; for each element in the customer matrix, determine the corresponding transaction channel and customer category, and use the number of customers corresponding to the transaction channel and customer category as the value of the element; for each element in the risk matrix, determine the corresponding transaction channel and customer category, and use the risk percentage corresponding to the transaction channel and customer category as the value of the element. Specifically, the bank server is used for: For each subset of identity verification data, a square matrix is ​​obtained by padding the risk matrix with zeros according to the number of rows and columns of the risk matrix corresponding to the subset of identity verification data. The non-zero eigenvalues ​​of the obtained square matrix are used as the risk eigenvalues ​​corresponding to the subset of identity verification data. Based on risk characteristic values, determine the controllable verification data subset from the multiple identity verification data subsets; Specifically, the bank server is used for: The subset of identity verification data whose corresponding risk characteristic values ​​are all less than the first threshold is taken as the controllable verification data subset.

7. The apparatus as claimed in claim 6, characterized in that, The bank server is specifically used for: For each failed face data in the edge computing system, the difference between the face threshold corresponding to the failed face data and the corresponding face matching value is taken as the matching gap value corresponding to the failed face data. For each matching gap value, the face failure data whose matching gap value is equal to that matching gap value is taken as the face failure data corresponding to that matching gap value. Based on the face failure data corresponding to the matching gap value, determine the customer matrix corresponding to the matching gap value; Based on each matching gap value and the corresponding customer matrix, the correspondence between the matching gap values ​​and the customer matrix of the edge computing system is determined.

8. The apparatus as claimed in claim 7, characterized in that, The bank server is specifically used for: Determine the transaction channel and customer category corresponding to each failed face data point for the matching gap value; Use this failed face recognition data as the face recognition failure data corresponding to this transaction channel and this customer category; For each transaction channel and each customer category, the number of customers included in the face recognition failure data corresponding to that transaction channel and that customer category is taken as the number of customers corresponding to that transaction channel and that customer category. Determine the customer matrix corresponding to the matching gap value, where each row of the customer matrix corresponds to a transaction channel and each column corresponds to a customer category; for each element of the customer matrix, determine the corresponding transaction channel and customer category, and use the number of customers corresponding to the transaction channel and customer category as the value of the element.

9. The apparatus as claimed in claim 6, characterized in that, The bank server is specifically used for: The difference matching values ​​included in the correspondence between the matching gap values ​​of the edge computing system and the customer matrix are used as candidate difference values; For each candidate difference value, the identity verification method corresponding to the candidate difference value is determined based on the customer matrix corresponding to the candidate difference value and the reference customer matrix corresponding to each identity verification method in the correspondence. Based on each candidate difference value and the corresponding identity verification method, the correspondence between the matching gap value and the identity verification method of the edge computing system is determined.

10. The apparatus as claimed in claim 9, characterized in that, The bank server is specifically used for: For each identity verification method, the matrix difference between the identity verification method and the candidate difference value is determined based on the reference customer matrix corresponding to the identity verification method and the customer matrix corresponding to the candidate difference value. When the number of rows in the matrix difference corresponding to the candidate difference value of the identity verification method is equal to the number of columns, the eigenvalue of the matrix difference is used as the eigenvalue corresponding to the identity verification method; otherwise, the matrix is ​​padded with zeros according to the number of rows and columns to obtain a square matrix, and the eigenvalue of the obtained square matrix is ​​used as the eigenvalue corresponding to the identity verification method. Based on the feature values ​​corresponding to each identity verification method, determine the identity verification method corresponding to the candidate difference value.

11. 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 5.

12. 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 5.

13. 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 5.

Citation Information

Patent Citations

  • Customer identity auditing method and system

    CN114840835A