Method and apparatus for determining a biometric threshold by a bank

Abstract

This invention proposes a method and apparatus for banks to determine biometric thresholds, relating to the field of computer data processing technology. The method includes: acquiring biometric failure data from the bank; segmenting the failure data within each biometric failure data set to obtain potential risk words, wherein the failure data is error information determined by the bank server; selecting key risk words from the potential risk words; determining multiple controllable biometric thresholds based on biometric recognition data corresponding to each biometric threshold; for each controllable biometric threshold, determining a keyword matrix corresponding to that controllable biometric threshold based on the key risk words; for each bank service terminal, determining a keyword matrix corresponding to that bank service terminal; determining multiple controllable biometric thresholds corresponding to the bank service terminal; and identifying the biometrics of customers at that bank service terminal based on the multiple controllable biometric thresholds corresponding to that bank service terminal.

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 determine biometric thresholds. 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, banks typically record biometric failure data, but this type of data often contains useful information, such as risk information. However, existing technologies have not proposed any solutions for analyzing transaction risks based on this biometric failure data. Summary of the Invention

[0004] To address the problems existing in the prior art, this invention proposes a method and apparatus for banks to determine biometric thresholds. By analyzing biometric failure data and biometric recognition data, transaction risks are determined, and controllable biometric thresholds are adjusted to ensure transaction security.

[0005] In a first aspect of the present invention, a method for a bank to determine a biometric threshold is proposed, comprising:

[0006] Failed to obtain biometric data from the bank;

[0007] The failure data contained in the various biometric failure data of the bank is segmented into words to obtain potential risk words. Among them, the failure data is the error information determined by the bank's server.

[0008] Select key risk words from potential risk words;

[0009] Based on the biometric recognition data corresponding to each biometric threshold, multiple controllable biometric thresholds are determined.

[0010] For each controllable biometric threshold, a keyword matrix corresponding to that controllable biometric threshold is determined based on key risk words;

[0011] For each bank service terminal, determine the keyword matrix corresponding to that bank service terminal;

[0012] Based on the keyword matrix corresponding to the bank service terminal and the keyword matrix corresponding to each controllable biometric threshold, multiple controllable biometric thresholds corresponding to the bank service terminal are determined.

[0013] Based on multiple controllable biometric thresholds corresponding to the bank service terminal, the biometric characteristics of the customers of the bank service terminal are identified.

[0014] In a second aspect of the present invention, an apparatus for a bank to determine a biometric threshold is provided, comprising:

[0015] The data acquisition module is used to acquire failed biometric data from banks.

[0016] The word segmentation module is used to segment the failure data contained in the bank's various biometric failure data to obtain potential risk words. Here, the failure data is the error information determined by the bank's server.

[0017] The selection module is used to select key risk words from potential risk words;

[0018] The biometric recognition data processing module is used to determine multiple controllable biometric thresholds based on the biometric recognition data corresponding to each biometric threshold.

[0019] The key risk word processing module is used to determine the keyword matrix corresponding to each controllable biometric threshold based on key risk words.

[0020] The keyword matrix determination module is used to determine the keyword matrix corresponding to each bank service terminal.

[0021] The keyword matrix processing module is used to determine multiple controllable biometric thresholds corresponding to the bank service terminal based on the keyword matrix corresponding to the bank service terminal and the keyword matrix corresponding to each controllable biometric threshold.

[0022] The biometric identification module is used to identify the biometric features of customers of the bank service terminal based on multiple controllable biometric thresholds corresponding to the bank service terminal.

[0023] 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 a bank to determine biometric thresholds.

[0024] In a fourth aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing a computer program that, when executed by a processor, implements a method for a bank to determine biometric thresholds.

[0025] In a fifth aspect of the present invention, a computer program product is provided, the computer program product comprising a computer program that, when executed by a processor, implements a method for a bank to determine biometric thresholds.

[0026] This invention proposes a method and apparatus for banks to determine biometric thresholds. The method involves acquiring biometric failure data from banks; segmenting the failure data within each biometric failure data set to obtain potential risk words, where the failure data represents error information determined by the bank server; selecting key risk words from the potential risk words; determining multiple controllable biometric thresholds based on the biometric recognition data corresponding to each biometric threshold; for each controllable biometric threshold, determining a keyword matrix corresponding to that threshold based on the key risk words; determining a keyword matrix corresponding to each bank service terminal; determining multiple controllable biometric thresholds for that bank service terminal based on the keyword matrix and the keyword matrices corresponding to each controllable biometric threshold; and identifying the biometrics of customers at that bank service terminal based on these multiple controllable biometric thresholds. The overall solution of this invention determines transaction risks and controllable biometric thresholds by analyzing biometric failure data and biometric recognition data, thereby ensuring the security of biometric identification and protecting transaction and property security. Attached Figure Description

[0027] 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.

[0028] Figure 1 This is a schematic flowchart of a method for determining biometric thresholds in a bank according to an embodiment of the present invention.

[0029] Figure 2 This is a schematic diagram of the process for determining multiple controllable biometric thresholds according to an embodiment of the present invention.

[0030] Figure 3 This is a schematic diagram of the process for determining the keyword matrix corresponding to the controllable biometric threshold according to an embodiment of the present invention.

[0031] Figure 4 This is a flowchart illustrating the process of determining the keyword matrix corresponding to the bank service terminal according to an embodiment of the present invention.

[0032] Figure 5 This is a schematic diagram of the process for determining multiple controllable biometric thresholds corresponding to the bank service terminal according to an embodiment of the present invention.

[0033] Figure 6 This is a schematic diagram of the device architecture for determining biometric thresholds in a bank, according to an embodiment of the present invention.

[0034] Figure 7 This is a schematic diagram of a computer device structure according to an embodiment of the present invention. Detailed Implementation

[0035] 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.

[0036] 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.

[0037] According to an embodiment of the present invention, a method and apparatus for determining biometric thresholds in banks are proposed, relating to the field of computer data processing technology.

[0038] The principles and spirit of the present invention will be explained in detail below with reference to several representative embodiments.

[0039] Figure 1 This is a schematic flowchart of a method for determining biometric thresholds in a bank, according to an embodiment of the present invention. Figure 1 As shown, the method includes:

[0040] S1, Failed to obtain biometric data from the bank;

[0041] S2, segment the failure data contained in the various biometric failure data of the bank to obtain potential risk words, where the failure data is the error information determined by the bank server;

[0042] S3, Select key risk words from potential risk words;

[0043] S4. Based on the biometric recognition data corresponding to each biometric threshold, determine multiple controllable biometric thresholds.

[0044] S5. For each controllable biometric threshold, determine the keyword matrix corresponding to the controllable biometric threshold based on key risk words.

[0045] S6. For each bank service terminal, determine the keyword matrix corresponding to that bank service terminal;

[0046] S7. Based on the keyword matrix corresponding to the bank service terminal and the keyword matrix corresponding to each controllable biometric threshold, determine multiple controllable biometric thresholds corresponding to the bank service terminal.

[0047] S8 identifies the biometric features of customers of the bank service terminal based on multiple controllable biometric thresholds corresponding to the bank service terminal.

[0048] To provide a clearer explanation of the methods used by banks to determine biometric thresholds, each step will be explained in detail below.

[0049] In S4, refer to Figure 2 Based on the biometric recognition data corresponding to each biometric threshold, multiple controllable biometric thresholds are determined, including:

[0050] S41, For each biometric threshold, determine the failure matrix and risk matrix corresponding to the biometric threshold based on the biometric recognition data corresponding to the biometric threshold;

[0051] S42, based on the failure matrix and risk matrix corresponding to each biometric threshold, determine multiple controllable biometric thresholds.

[0052] In one embodiment, (S41) for each biometric threshold, based on the biometric identification data corresponding to the biometric threshold, a failure matrix and a risk matrix corresponding to the biometric threshold are determined, including:

[0053] Select two dimensions of transaction data;

[0054] Determine the value of each biometric identification data corresponding to the two transaction data dimensions corresponding to the biometric threshold;

[0055] For each combination of the two transaction data dimensions, the combination of values ​​corresponding to the two transaction data dimensions selected from the biometric identification data corresponding to the biometric threshold is the biometric identification data of the combination, and the selected biometric identification data is used as the biometric identification data of the biometric threshold with respect to the combination.

[0056] The proportion of failed identifications in the biometric identification data of the combination with respect to the biometric threshold is taken as the failure proportion of the biometric threshold with respect to the combination, and the proportion of risk identifications in the biometric identification data of the combination with respect to the biometric threshold is taken as the risk proportion of the biometric threshold with respect to the combination.

[0057] Determine the failure matrix and risk matrix corresponding to the biometric threshold, wherein the rows and columns of the failure matrix and the risk matrix correspond to the two transaction data dimensions respectively; determine the value of each element of the failure matrix as the failure ratio of the biometric threshold with respect to the combination of the rows and columns corresponding to that element; determine the value of each element of the risk matrix as the risk ratio of the biometric threshold with respect to the combination of the rows and columns corresponding to that element.

[0058] In one embodiment, two transaction data dimensions are selected, including:

[0059] Customer categories and transaction categories.

[0060] In one embodiment, (S42) multiple controllable biometric thresholds are determined based on the failure matrix and risk matrix corresponding to each biometric threshold, including:

[0061] For each biometric threshold, when the failure matrix corresponding to the biometric threshold is a square matrix, the maximum value of the modulus of the eigenvalues ​​of the failure matrix corresponding to the biometric threshold is taken as the failure modulus of the biometric threshold; otherwise, based on the number of rows and columns of the failure matrix corresponding to the biometric threshold, the failure matrix corresponding to the biometric threshold is padded with 0s, and the maximum value of the modulus of the non-zero eigenvalues ​​of the obtained square matrix is ​​taken as the failure modulus of the biometric threshold.

[0062] When the risk matrix corresponding to the biometric threshold is a square matrix, the maximum value of the modulus of the eigenvalues ​​of the risk matrix corresponding to the biometric threshold is taken as the risk modulus of the biometric threshold. Otherwise, based on the number of rows and columns of the risk matrix corresponding to the biometric threshold, the risk matrix corresponding to the biometric threshold is padded with 0s, and the maximum value of the modulus of the non-zero eigenvalues ​​of the obtained square matrix is ​​taken as the risk modulus of the biometric threshold.

[0063] Based on the failure modulus and risk modulus corresponding to each biometric threshold, multiple controllable biometric thresholds are determined.

[0064] In S5, refer to Figure 3 For each controllable biometric threshold, a keyword matrix corresponding to that threshold is determined based on key risk words, including:

[0065] S51, Obtain the biometric failure data corresponding to the controllable biometric threshold;

[0066] S52, determine the customer category corresponding to each biometric failure data corresponding to the controllable biometric threshold, and the key risk words contained therein;

[0067] S53, Select the biometric failure data corresponding to each customer category from the biometric failure data corresponding to the controllable biometric threshold, and use the selected biometric failure data as the biometric failure data of the customer category with respect to the controllable biometric threshold.

[0068] S54, For each key risk word, the number of biometric recognitions contained in the biometric failure data of the corresponding key risk word in the biometric failure data of the customer category with respect to the controllable biometric threshold is taken as the number of recognitions of the customer category and the key risk word with respect to the controllable biometric threshold.

[0069] S55, determine the keyword matrix corresponding to the controllable biometric threshold, wherein the rows of the keyword matrix correspond to customer categories, the columns correspond to key risk words, and the value of each element of the keyword matrix is ​​equal to the number of customer categories and key risk words identified with respect to the controllable biometric threshold.

[0070] In S6, refer to Figure 4 For each bank service terminal, determine the keyword matrix corresponding to that bank service terminal, including:

[0071] S61, Obtain biometric failure data corresponding to the bank service terminal;

[0072] S62, determine the customer category corresponding to each biometric failure data of the bank service terminal, and the key risk words contained therein;

[0073] S63, Select biometric failure data corresponding to each customer category from the biometric failure data corresponding to the bank service terminal, and use the selected biometric failure data as the biometric failure data of the customer category for the bank service terminal;

[0074] S64, For each key risk word, the number of biometric recognitions contained in the biometric failure data of the corresponding key risk word in the biometric failure data of the customer category with respect to the bank service terminal is taken as the number of recognitions of the customer category and the key risk word with respect to the bank service terminal.

[0075] S65, determine the keyword matrix corresponding to the bank service terminal, wherein the rows of the keyword matrix correspond to customer categories, the columns correspond to key risk words, and the value of each element of the keyword matrix is ​​equal to the number of customer categories and key risk words identified for the bank service terminal.

[0076] In S7, refer to Figure 5Based on the keyword matrix corresponding to the bank service terminal and the keyword matrix corresponding to each controllable biometric threshold, multiple controllable biometric thresholds corresponding to the bank service terminal are determined, including:

[0077] S71, For each controllable biometric threshold, determine the keyword gap matrix corresponding to the controllable biometric threshold based on the keyword matrix corresponding to the controllable biometric threshold and the keyword matrix corresponding to the bank service terminal;

[0078] S72, when the number of rows in the keyword difference matrix corresponding to the controllable biometric threshold is equal to the number of columns, the maximum value of the modulus of the eigenvalues ​​of the keyword difference matrix corresponding to the controllable biometric threshold is taken as the modulus of the keyword difference corresponding to the controllable biometric threshold; otherwise, based on the number of rows and the number of columns, the keyword difference matrix corresponding to the controllable biometric threshold is padded with 0s, and the maximum value of the modulus of the eigenvalues ​​of the obtained matrix is ​​taken as the modulus of the keyword difference corresponding to the controllable biometric threshold.

[0079] S73, based on the keyword difference modulus corresponding to each controllable biometric threshold, determine multiple controllable biometric thresholds corresponding to the bank service terminal.

[0080] In S8, based on multiple controllable biometric thresholds corresponding to the bank service terminal, the biometric characteristics of the customer of the bank service terminal are identified, including:

[0081] When the biometric threshold of a customer stored on the bank server for the bank service terminal is lower than all controllable biometric thresholds corresponding to the bank service terminal, the customer's biometrics are identified based on the minimum value of the controllable biometric thresholds corresponding to the bank service terminal.

[0082] When the biometric threshold of a customer stored on the bank server for a bank service terminal is higher than all controllable biometric thresholds corresponding to that bank service terminal, the customer's biometrics are identified based on the maximum value of the controllable biometric thresholds corresponding to that bank service terminal.

[0083] In one embodiment, (S71) for each controllable biometric threshold, based on the keyword matrix corresponding to the controllable biometric threshold and the keyword matrix corresponding to the bank service terminal, a keyword gap matrix corresponding to the controllable biometric threshold is determined, including:

[0084] Based on the keyword matrix corresponding to the bank service terminal, the keyword matrix corresponding to the controllable biometric threshold is corrected;

[0085] The difference between the keyword matrix corresponding to the bank service terminal and the keyword matrix corresponding to the corrected controllable biometric threshold is taken as the keyword gap matrix corresponding to the controllable biometric threshold.

[0086] (It should be noted that making corrections can resolve calculation problems caused by inconsistent data units.)

[0087] In one embodiment, (S73) based on the keyword difference modulus corresponding to each controllable biometric threshold, multiple controllable biometric thresholds corresponding to the bank service terminal are determined, including:

[0088] Determine whether a controllable biometric threshold exists, satisfying the condition t: the keyword difference modulus corresponding to the controllable biometric threshold is less than the modulus threshold;

[0089] If no controllable biometric threshold satisfies condition t, then the bank service terminal is designated as the current service terminal, and the following four steps are executed repeatedly until a controllable biometric threshold satisfies condition t:

[0090] Obtain biometric failure data from multiple related service terminals of the current service terminal;

[0091] Based on the acquired biometric failure data, update the keyword matrix corresponding to the bank service terminal;

[0092] Based on the updated keyword matrix corresponding to the bank service terminal and the keyword matrix corresponding to each controllable biometric threshold, update the keyword difference modulus corresponding to each controllable biometric threshold; (In actual application scenarios, the method for updating the keyword difference modulus corresponding to each controllable biometric threshold can be found in S71 to S73.)

[0093] Update the current service terminal to these multiple related service terminals;

[0094] When a controllable biometric threshold satisfies condition t, the controllable biometric threshold that satisfies condition t is used as the controllable biometric threshold corresponding to the bank service terminal.

[0095] In one embodiment, the method further includes determining the relevant service terminal for each bank service terminal according to the following method:

[0096] For each other service terminal besides the bank service terminal, the intersection of the account set of the bank service terminal and the account set of the other service terminal is taken as the common account set corresponding to the other service terminal; the difference between the account set of the bank service terminal and the account set of the other service terminal is taken as the unique account set corresponding to the bank service terminal; and the difference between the account set of the other service terminal and the account set of the bank service terminal is taken as the unique account set corresponding to the other service terminal.

[0097] The relevant indicators of each account in the unique account set corresponding to the bank service terminal and each account in the unique account set corresponding to the other service terminal are used as the relevant indicators of the bank service terminal and the other service terminal.

[0098] Based on the number of accounts included in the shared account set corresponding to the other service terminal, and all relevant indicators corresponding to the bank service terminal and the other service terminal, determine the relevant indicators of the bank service terminal and the other service terminal;

[0099] Based on the relevant indicators of this bank's service terminal and other service terminals, the relevant service terminals of this bank's service terminal are determined.

[0100] In one embodiment, the method further includes:

[0101] For each biometric failure data point of the bank, the key risk words corresponding to the biometric failure data point are determined based on the potential risk words obtained by segmenting the failure data contained in the biometric failure data point.

[0102] Based on the key risk words corresponding to each biometric failure data, the bank's biometric failure data is classified to obtain multiple failure data sets;

[0103] For each set of failed data, a prediction model is trained using risk as the category identifier to obtain a risk model.

[0104] Based on the obtained risk model, risk control is carried out on the bank's real-time biometric identification.

[0105] In one embodiment, the method further includes:

[0106] Select biometric failure data from the bank's biometric failure data where the corresponding biometric matching value is less than the matching threshold;

[0107] For each selected biometric failure data, the difference between the matching threshold corresponding to the biometric failure data and the corresponding biometric matching value is taken as the matching difference value corresponding to the biometric failure data.

[0108] For each matching difference, the biometric failure data whose matching difference is equal to that matching difference is selected as the biometric failure data corresponding to that matching difference;

[0109] Based on the biometric failure data corresponding to the matching difference, determine the biometric failure modulus corresponding to the matching difference; (In practical applications, the method for determining the biometric failure modulus corresponding to the matching difference can be found in S41 and S42 regarding the risk matrix and risk modulus.)

[0110] Risk control is achieved for real-time biometric identification of banks based on the biometric failure modulus corresponding to each matching difference.

[0111] In one embodiment, risk control is performed on the bank's real-time biometric identification based on the biometric failure modulus corresponding to each matching difference, including:

[0112] For each biometric failure data, if there is a biometric success data after the biometric failure data, and the customer corresponding to the biometric success data and the customer corresponding to the biometric failure data are the same customer, and the time difference between the time corresponding to the biometric success data and the time corresponding to the biometric failure data is less than a time threshold, then the biometric failure data is determined as controllable failure data.

[0113] Determine the module length threshold based on the biological failure module length corresponding to the controllable failure data;

[0114] For each real-time biometric identification by the bank, when the biometric matching value corresponding to the real-time biometric identification is less than the corresponding matching threshold, the difference between the corresponding matching threshold and the corresponding biometric matching value is taken as the real-time matching difference.

[0115] The biological failure modulus corresponding to the real-time matching difference is taken as the real-time failure modulus.

[0116] Risk control is implemented for this real-time biometric identification based on the module length threshold and the real-time failure module length.

[0117] In one embodiment, risk control is performed on the real-time biometric identification based on the modulus threshold and the real-time failure modulus, including:

[0118] When the real-time failure magnitude exceeds the magnitude threshold, real-time risk control is performed on the real-time biometric identification.

[0119] 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.

[0120] After introducing the method of exemplary embodiments of the present invention, the following references are made. Figure 6 An apparatus for determining biometric thresholds in a bank according to an exemplary embodiment of the present invention will be described.

[0121] The implementation of the device for determining biometric thresholds in banks can refer to the implementation of the methods described above, and will not be repeated here. 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.

[0122] Based on the same inventive concept, this invention also proposes a device for banks to determine biometric thresholds, such as... Figure 6 As shown, the device includes:

[0123] Data acquisition module 110 is used to acquire failed biometric data from banks;

[0124] The word segmentation module 120 is used to segment the failure data contained in the various biometric failure data of the bank to obtain potential risk words. The failure data is the error information determined by the bank's server.

[0125] Module 130 is used to select key risk words from potential risk words;

[0126] The biometric recognition data processing module 140 is used to determine multiple controllable biometric thresholds based on the biometric recognition data corresponding to each biometric threshold.

[0127] The key risk word processing module 150 is used to determine the keyword matrix corresponding to each controllable biometric threshold based on the key risk words.

[0128] Keyword matrix determination module 160 is used to determine the keyword matrix corresponding to each bank service terminal.

[0129] The keyword matrix processing module 170 is used to determine multiple controllable biometric thresholds corresponding to the bank service terminal based on the keyword matrix corresponding to the bank service terminal and the keyword matrix corresponding to each controllable biometric threshold.

[0130] The biometric identification module 180 is used to identify the biometric features of customers of the bank service terminal based on multiple controllable biometric thresholds corresponding to the bank service terminal.

[0131] In one embodiment, the biometric identification data processing module is specifically used for:

[0132] For each biometric threshold, the failure matrix and risk matrix corresponding to that biometric threshold are determined based on the biometric identification data corresponding to that biometric threshold.

[0133] Based on the failure matrix and risk matrix corresponding to each biometric threshold, multiple controllable biometric thresholds are determined.

[0134] In one embodiment, the biometric identification data processing module is specifically used for:

[0135] Select two dimensions of transaction data;

[0136] Determine the value of each biometric identification data corresponding to the two transaction data dimensions corresponding to the biometric threshold;

[0137] For each combination of the two transaction data dimensions, the combination of values ​​corresponding to the two transaction data dimensions selected from the biometric identification data corresponding to the biometric threshold is the biometric identification data of the combination, and the selected biometric identification data is used as the biometric identification data of the biometric threshold with respect to the combination.

[0138] The proportion of failed identifications in the biometric identification data of the combination with respect to the biometric threshold is taken as the failure proportion of the biometric threshold with respect to the combination, and the proportion of risk identifications in the biometric identification data of the combination with respect to the biometric threshold is taken as the risk proportion of the biometric threshold with respect to the combination.

[0139] Determine the failure matrix and risk matrix corresponding to the biometric threshold, wherein the rows and columns of the failure matrix and the risk matrix correspond to the two transaction data dimensions respectively; determine the value of each element of the failure matrix as the failure ratio of the biometric threshold with respect to the combination of the rows and columns corresponding to that element; determine the value of each element of the risk matrix as the risk ratio of the biometric threshold with respect to the combination of the rows and columns corresponding to that element.

[0140] In one embodiment, the biometric identification data processing module is specifically used for:

[0141] For each biometric threshold, when the failure matrix corresponding to the biometric threshold is a square matrix, the maximum value of the modulus of the eigenvalues ​​of the failure matrix corresponding to the biometric threshold is taken as the failure modulus of the biometric threshold; otherwise, based on the number of rows and columns of the failure matrix corresponding to the biometric threshold, the failure matrix corresponding to the biometric threshold is padded with 0s, and the maximum value of the modulus of the non-zero eigenvalues ​​of the obtained square matrix is ​​taken as the failure modulus of the biometric threshold.

[0142] When the risk matrix corresponding to the biometric threshold is a square matrix, the maximum value of the modulus of the eigenvalues ​​of the risk matrix corresponding to the biometric threshold is taken as the risk modulus of the biometric threshold. Otherwise, based on the number of rows and columns of the risk matrix corresponding to the biometric threshold, the risk matrix corresponding to the biometric threshold is padded with 0s, and the maximum value of the modulus of the non-zero eigenvalues ​​of the obtained square matrix is ​​taken as the risk modulus of the biometric threshold.

[0143] Based on the failure modulus and risk modulus corresponding to each biometric threshold, multiple controllable biometric thresholds are determined.

[0144] In one embodiment, the key risk word processing module is specifically used for:

[0145] Obtain the biometric failure data corresponding to the controllable biometric threshold;

[0146] Determine the customer category corresponding to each biometric failure data corresponding to the controllable biometric threshold, and the key risk words contained therein;

[0147] Select the biometric failure data corresponding to each customer category from the biometric failure data corresponding to the controllable biometric threshold, and use the selected biometric failure data as the biometric failure data of that customer category with respect to the controllable biometric threshold;

[0148] For each key risk word, the number of biometric recognitions contained in the biometric failure data of the corresponding key risk word in the biometric failure data of the customer category with respect to the controllable biometric threshold is taken as the number of recognitions of the customer category and the key risk word with respect to the controllable biometric threshold.

[0149] Determine the keyword matrix corresponding to the controllable biometric threshold, wherein the rows of the keyword matrix correspond to customer categories, the columns correspond to key risk words, and the value of each element of the keyword matrix is ​​equal to the number of customer categories and key risk words identified with respect to the controllable biometric threshold.

[0150] In one embodiment, the keyword matrix determination module is specifically used for:

[0151] Obtain the biometric failure data corresponding to the bank's service terminal;

[0152] Determine the customer category corresponding to each failed biometric data point for the bank's service terminal, as well as the key risk terms it contains;

[0153] Select biometric failure data corresponding to each customer category from the biometric failure data corresponding to the bank service terminal, and use the selected biometric failure data as the biometric failure data of that customer category for that bank service terminal;

[0154] For each key risk word, the number of biometric recognitions contained in the biometric failure data of the corresponding key risk word in the biometric failure data of the bank service terminal for that customer category is taken as the number of recognitions of that customer category and that key risk word for that bank service terminal.

[0155] Determine the keyword matrix corresponding to the bank service terminal, where the rows of the keyword matrix correspond to customer categories and the columns correspond to key risk words. The value of each element of the keyword matrix is ​​equal to the number of customer categories and key risk words identified for that element with respect to the bank service terminal.

[0156] In one embodiment, the keyword matrix processing module is specifically used for:

[0157] For each controllable biometric threshold, the keyword gap matrix corresponding to the controllable biometric threshold is determined based on the keyword matrix corresponding to the controllable biometric threshold and the keyword matrix corresponding to the bank service terminal.

[0158] When the number of rows in the keyword gap matrix corresponding to the controllable biometric threshold is equal to the number of columns, the maximum value of the modulus of the eigenvalues ​​of the keyword gap matrix corresponding to the controllable biometric threshold is taken as the modulus of the keyword gap corresponding to the controllable biometric threshold; otherwise, based on the number of rows and the number of columns, the keyword gap matrix corresponding to the controllable biometric threshold is padded with 0s, and the maximum value of the modulus of the eigenvalues ​​of the obtained matrix is ​​taken as the modulus of the keyword gap corresponding to the controllable biometric threshold.

[0159] Based on the keyword difference modulus corresponding to each controllable biometric threshold, multiple controllable biometric thresholds corresponding to the bank service terminal are determined.

[0160] In one embodiment, the biometric identification module is specifically used for:

[0161] When the biometric threshold of a customer stored on the bank server for the bank service terminal is lower than all controllable biometric thresholds corresponding to the bank service terminal, the customer's biometrics are identified based on the minimum value of the controllable biometric thresholds corresponding to the bank service terminal.

[0162] When the biometric threshold of a customer stored on the bank server for a bank service terminal is higher than all controllable biometric thresholds corresponding to that bank service terminal, the customer's biometrics are identified based on the maximum value of the controllable biometric thresholds corresponding to that bank service terminal.

[0163] It should be noted that although several modules of the bank's biometric threshold determination device have been mentioned in the detailed description above, this division is merely exemplary and not mandatory. In fact, according to embodiments of the 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.

[0164] 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 determining biometric thresholds in banks.

[0165] 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 determining biometric thresholds in banks.

[0166] Based on the aforementioned inventive concept, the present invention proposes a computer program product, which includes a computer program that, when executed by a processor, implements a method for banks to determine biometric thresholds.

[0167] This invention proposes a method and apparatus for banks to determine biometric thresholds. The method involves acquiring biometric failure data from banks; segmenting the failure data within each biometric failure data set to obtain potential risk words, where the failure data represents error information determined by the bank server; selecting key risk words from the potential risk words; determining multiple controllable biometric thresholds based on the biometric recognition data corresponding to each biometric threshold; for each controllable biometric threshold, determining a keyword matrix corresponding to that threshold based on the key risk words; determining a keyword matrix corresponding to each bank service terminal; determining multiple controllable biometric thresholds for that bank service terminal based on the keyword matrix and the keyword matrices corresponding to each controllable biometric threshold; and identifying the biometrics of customers at that bank service terminal based on these multiple controllable biometric thresholds. The overall solution of this invention determines transaction risks and controllable biometric thresholds by analyzing biometric failure data and biometric recognition data, thereby ensuring the security of biometric identification and protecting transaction and property security.

[0168] The acquisition, storage, use, and processing of data in this application all comply with the relevant provisions of national laws and regulations.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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 of determining a biometric threshold by a bank, characterized by, include: Failed to obtain biometric data from the bank; The failure data contained in the various biometric failure data of the bank is segmented into words to obtain potential risk words. Among them, the failure data is the error information determined by the bank's server. Select key risk words from potential risk words; Based on the biometric recognition data corresponding to each biometric threshold, multiple controllable biometric thresholds are determined. For each controllable biometric threshold, a keyword matrix corresponding to that controllable biometric threshold is determined based on key risk words; For each bank service terminal, determine the keyword matrix corresponding to that bank service terminal; Based on the keyword matrix corresponding to the bank service terminal and the keyword matrix corresponding to each controllable biometric threshold, multiple controllable biometric thresholds corresponding to the bank service terminal are determined. Based on multiple controllable biometric thresholds corresponding to the bank service terminal, the biometric characteristics of the customers of the bank service terminal are identified. Among them, based on the biometric recognition data corresponding to each biometric threshold, multiple controllable biometric thresholds are determined, including: For each biometric threshold, the failure matrix and risk matrix corresponding to that biometric threshold are determined based on the biometric identification data corresponding to that biometric threshold. Based on the failure matrix and risk matrix corresponding to each biometric threshold, multiple controllable biometric thresholds are determined.

2. The method of claim 1, wherein, For each biometric threshold, based on the biometric recognition data corresponding to that threshold, a failure matrix and a risk matrix are determined, including: Select two dimensions of transaction data; Determine the value of each biometric identification data corresponding to the two transaction data dimensions corresponding to the biometric threshold; For each combination of the two transaction data dimensions, the combination of values ​​corresponding to the two transaction data dimensions selected from the biometric identification data corresponding to the biometric threshold is the biometric identification data of the combination, and the selected biometric identification data is used as the biometric identification data of the biometric threshold with respect to the combination. The proportion of failed identifications in the biometric identification data of the combination with respect to the biometric threshold is taken as the failure proportion of the biometric threshold with respect to the combination, and the proportion of risk identifications in the biometric identification data of the combination with respect to the biometric threshold is taken as the risk proportion of the biometric threshold with respect to the combination. Determine the failure matrix and risk matrix corresponding to the biometric threshold, wherein the rows and columns of the failure matrix and the risk matrix correspond to the two transaction data dimensions respectively; determine the value of each element of the failure matrix as the failure ratio of the biometric threshold with respect to the combination of the rows and columns corresponding to that element; determine the value of each element of the risk matrix as the risk ratio of the biometric threshold with respect to the combination of the rows and columns corresponding to that element.

3. The method of claim 1, wherein, Based on the failure matrix and risk matrix corresponding to each biometric threshold, multiple controllable biometric thresholds are determined, including: For each biometric threshold, when the failure matrix corresponding to the biometric threshold is a square matrix, the maximum value of the modulus of the eigenvalues ​​of the failure matrix corresponding to the biometric threshold is taken as the failure modulus of the biometric threshold; otherwise, based on the number of rows and columns of the failure matrix corresponding to the biometric threshold, the failure matrix corresponding to the biometric threshold is padded with 0s, and the maximum value of the modulus of the non-zero eigenvalues ​​of the obtained square matrix is ​​taken as the failure modulus of the biometric threshold. When the risk matrix corresponding to the biometric threshold is a square matrix, the maximum value of the modulus of the eigenvalues ​​of the risk matrix corresponding to the biometric threshold is taken as the risk modulus of the biometric threshold. Otherwise, based on the number of rows and columns of the risk matrix corresponding to the biometric threshold, the risk matrix corresponding to the biometric threshold is padded with 0s, and the maximum value of the modulus of the non-zero eigenvalues ​​of the obtained square matrix is ​​taken as the risk modulus of the biometric threshold. Based on the failure modulus and risk modulus corresponding to each biometric threshold, multiple controllable biometric thresholds are determined.

4. The method of claim 1, wherein, For each controllable biometric threshold, a keyword matrix corresponding to that threshold is determined based on key risk terms, including: Obtain the biometric failure data corresponding to the controllable biometric threshold; Determine the customer category corresponding to each biometric failure data corresponding to the controllable biometric threshold, and the key risk words contained therein; Select the biometric failure data corresponding to each customer category from the biometric failure data corresponding to the controllable biometric threshold, and use the selected biometric failure data as the biometric failure data of that customer category with respect to the controllable biometric threshold. For each key risk word, the number of biometric recognitions contained in the biometric failure data of the corresponding key risk word in the biometric failure data of the customer category with respect to the controllable biometric threshold is taken as the number of recognitions of the customer category and the key risk word with respect to the controllable biometric threshold. Determine the keyword matrix corresponding to the controllable biometric threshold, wherein the rows of the keyword matrix correspond to customer categories, the columns correspond to key risk words, and the value of each element of the keyword matrix is ​​equal to the number of customer categories and key risk words identified with respect to the controllable biometric threshold.

5. The method of claim 1, wherein, For each bank service terminal, determine the keyword matrix corresponding to that bank service terminal, including: Obtain the biometric failure data corresponding to the bank's service terminal; Determine the customer category corresponding to each failed biometric data point for the bank's service terminal, as well as the key risk terms it contains; Select biometric failure data corresponding to each customer category from the biometric failure data corresponding to the bank service terminal, and use the selected biometric failure data as the biometric failure data of that customer category for that bank service terminal; For each key risk word, the number of biometric recognitions contained in the biometric failure data of the corresponding key risk word in the biometric failure data of the bank service terminal for that customer category is taken as the number of recognitions of that customer category and that key risk word for that bank service terminal. Determine the keyword matrix corresponding to the bank service terminal, where the rows of the keyword matrix correspond to customer categories and the columns correspond to key risk words. The value of each element of the keyword matrix is ​​equal to the number of customer categories and key risk words identified for that element with respect to the bank service terminal.

6. The method of claim 1, wherein, Based on the keyword matrix corresponding to the bank service terminal and the keyword matrix corresponding to each controllable biometric threshold, multiple controllable biometric thresholds corresponding to the bank service terminal are determined, including: For each controllable biometric threshold, the keyword gap matrix corresponding to the controllable biometric threshold is determined based on the keyword matrix corresponding to the controllable biometric threshold and the keyword matrix corresponding to the bank service terminal. When the number of rows in the keyword gap matrix corresponding to the controllable biometric threshold is equal to the number of columns, the maximum value of the modulus of the eigenvalues ​​of the keyword gap matrix corresponding to the controllable biometric threshold is taken as the modulus of the keyword gap corresponding to the controllable biometric threshold; otherwise, based on the number of rows and the number of columns, the keyword gap matrix corresponding to the controllable biometric threshold is padded with 0s, and the maximum value of the modulus of the eigenvalues ​​of the obtained matrix is ​​taken as the modulus of the keyword gap corresponding to the controllable biometric threshold. Based on the keyword difference modulus corresponding to each controllable biometric threshold, multiple controllable biometric thresholds corresponding to the bank service terminal are determined.

7. The method of claim 1, wherein, Based on multiple controllable biometric thresholds corresponding to the bank service terminal, the biometric characteristics of the customer of the bank service terminal are identified, including: When the biometric threshold of a customer stored on the bank server for the bank service terminal is lower than all controllable biometric thresholds corresponding to the bank service terminal, the customer's biometrics are identified based on the minimum value of the controllable biometric thresholds corresponding to the bank service terminal. When the biometric threshold of a customer stored on the bank server for a bank service terminal is higher than all controllable biometric thresholds corresponding to that bank service terminal, the customer's biometrics are identified based on the maximum value of the controllable biometric thresholds corresponding to that bank service terminal.

8. An apparatus for a bank to determine a biometric threshold, the apparatus comprising: include: The data acquisition module is used to acquire failed biometric data from banks. The word segmentation module is used to segment the failure data contained in the bank's various biometric failure data to obtain potential risk words. Here, the failure data is the error information determined by the bank's server. The selection module is used to select key risk words from potential risk words; The biometric recognition data processing module is used to determine multiple controllable biometric thresholds based on the biometric recognition data corresponding to each biometric threshold. The key risk word processing module is used to determine the keyword matrix corresponding to each controllable biometric threshold based on key risk words. The keyword matrix determination module is used to determine the keyword matrix corresponding to each bank service terminal. The keyword matrix processing module is used to determine multiple controllable biometric thresholds corresponding to the bank service terminal based on the keyword matrix corresponding to the bank service terminal and the keyword matrix corresponding to each controllable biometric threshold. The biometric identification module is used to identify the biometric features of customers of the bank service terminal based on multiple controllable biometric thresholds corresponding to the bank service terminal. Specifically, the biometric data processing module is used for: For each biometric threshold, the failure matrix and risk matrix corresponding to that biometric threshold are determined based on the biometric identification data corresponding to that biometric threshold. Based on the failure matrix and risk matrix corresponding to each biometric threshold, multiple controllable biometric thresholds are determined.

9. The apparatus of claim 8, wherein, The biometric data processing module is specifically used for: Select two dimensions of transaction data; Determine the value of each biometric identification data corresponding to the two transaction data dimensions corresponding to the biometric threshold; For each combination of the two transaction data dimensions, the combination of values ​​corresponding to the two transaction data dimensions selected from the biometric identification data corresponding to the biometric threshold is the biometric identification data of the combination, and the selected biometric identification data is used as the biometric identification data of the biometric threshold with respect to the combination. The proportion of failed identifications in the biometric identification data of the combination with respect to the biometric threshold is taken as the failure proportion of the biometric threshold with respect to the combination, and the proportion of risk identifications in the biometric identification data of the combination with respect to the biometric threshold is taken as the risk proportion of the biometric threshold with respect to the combination. Determine the failure matrix and risk matrix corresponding to the biometric threshold, wherein the rows and columns of the failure matrix and the risk matrix correspond to the two transaction data dimensions respectively; determine the value of each element of the failure matrix as the failure ratio of the biometric threshold with respect to the combination of the rows and columns corresponding to that element; determine the value of each element of the risk matrix as the risk ratio of the biometric threshold with respect to the combination of the rows and columns corresponding to that element.

10. The apparatus of claim 8, wherein, The biometric data processing module is specifically used for: For each biometric threshold, when the failure matrix corresponding to the biometric threshold is a square matrix, the maximum value of the modulus of the eigenvalues ​​of the failure matrix corresponding to the biometric threshold is taken as the failure modulus of the biometric threshold; otherwise, based on the number of rows and columns of the failure matrix corresponding to the biometric threshold, the failure matrix corresponding to the biometric threshold is padded with 0s, and the maximum value of the modulus of the non-zero eigenvalues ​​of the obtained square matrix is ​​taken as the failure modulus of the biometric threshold. When the risk matrix corresponding to the biometric threshold is a square matrix, the maximum value of the modulus of the eigenvalues ​​of the risk matrix corresponding to the biometric threshold is taken as the risk modulus of the biometric threshold. Otherwise, based on the number of rows and columns of the risk matrix corresponding to the biometric threshold, the risk matrix corresponding to the biometric threshold is padded with 0s, and the maximum value of the modulus of the non-zero eigenvalues ​​of the obtained square matrix is ​​taken as the risk modulus of the biometric threshold. Based on the failure modulus and risk modulus corresponding to each biometric threshold, multiple controllable biometric thresholds are determined.

11. The apparatus of claim 8, wherein, The key risk term processing module is specifically used for: Obtain the biometric failure data corresponding to the controllable biometric threshold; Determine the customer category corresponding to each biometric failure data corresponding to the controllable biometric threshold, and the key risk words contained therein; Select the biometric failure data corresponding to each customer category from the biometric failure data corresponding to the controllable biometric threshold, and use the selected biometric failure data as the biometric failure data of that customer category with respect to the controllable biometric threshold. For each key risk word, the number of biometric recognitions contained in the biometric failure data of the corresponding key risk word in the biometric failure data of the customer category with respect to the controllable biometric threshold is taken as the number of recognitions of the customer category and the key risk word with respect to the controllable biometric threshold. Determine the keyword matrix corresponding to the controllable biometric threshold, wherein the rows of the keyword matrix correspond to customer categories, the columns correspond to key risk words, and the value of each element of the keyword matrix is ​​equal to the number of customer categories and key risk words identified with respect to the controllable biometric threshold.

12. The apparatus of claim 8, wherein, The keyword matrix determination module is specifically used for: Obtain the biometric failure data corresponding to the bank's service terminal; Determine the customer category corresponding to each failed biometric data point for the bank's service terminal, as well as the key risk terms it contains; Select biometric failure data corresponding to each customer category from the biometric failure data corresponding to the bank service terminal, and use the selected biometric failure data as the biometric failure data of that customer category for that bank service terminal; For each key risk word, the number of biometric recognitions contained in the biometric failure data of the corresponding key risk word in the biometric failure data of the bank service terminal for that customer category is taken as the number of recognitions of that customer category and that key risk word for that bank service terminal. Determine the keyword matrix corresponding to the bank service terminal, where the rows of the keyword matrix correspond to customer categories and the columns correspond to key risk words. The value of each element of the keyword matrix is ​​equal to the number of customer categories and key risk words identified for that element with respect to the bank service terminal.

13. The apparatus of claim 8, wherein, The keyword matrix processing module is specifically used for: For each controllable biometric threshold, the keyword gap matrix corresponding to the controllable biometric threshold is determined based on the keyword matrix corresponding to the controllable biometric threshold and the keyword matrix corresponding to the bank service terminal. When the number of rows in the keyword gap matrix corresponding to the controllable biometric threshold is equal to the number of columns, the maximum value of the modulus of the eigenvalues ​​of the keyword gap matrix corresponding to the controllable biometric threshold is taken as the modulus of the keyword gap corresponding to the controllable biometric threshold. Otherwise, based on the number of rows and columns, the keyword difference matrix corresponding to the controllable biometric threshold is padded with 0s, and the maximum value of the modulus of the obtained matrix is ​​taken as the modulus of the keyword difference corresponding to the controllable biometric threshold. Based on the keyword difference modulus corresponding to each controllable biometric threshold, multiple controllable biometric thresholds corresponding to the bank service terminal are determined.

14. The apparatus of claim 8, wherein, The biometric recognition module is specifically used for: When the biometric threshold of a customer stored on the bank server for the bank service terminal is lower than all controllable biometric thresholds corresponding to the bank service terminal, the customer's biometrics are identified based on the minimum value of the controllable biometric thresholds corresponding to the bank service terminal. When the biometric threshold of a customer stored on the bank server for a bank service terminal is higher than all controllable biometric thresholds corresponding to that bank service terminal, the customer's biometrics are identified based on the maximum value of the controllable biometric thresholds corresponding to that bank service terminal.

15. A computer device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the method of any one of claims 1 to 7.

16. 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 7.

17. A computer program product, characterised 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 7.

Images