Method and device for determining user authentication mode

Abstract

The present invention proposes a method and device for determining a user authentication method, which relate to the technical field of financial data processing. The method comprises: obtaining historical face recognition data of a bank; determining the corresponding relationship between a face matching threshold and a risk indicator based on the historical face recognition data of the bank; determining the corresponding relationship between a matching gap value and a risk indicator based on the failure data in the historical face recognition data of the bank; when the face data input by the user on the bank terminal is obtained, calculating the matching value of the face data; wherein, if the matching value between the face data and the face data of the user pre-stored in the bank is less than the face matching threshold of the user, determining that the face authentication has failed, and taking the difference between the face matching threshold and the matching value as the matching gap value corresponding to the authentication failure; determining the user authentication method after the authentication has failed; wherein, the bank terminal performs identity authentication on the user based on the user authentication method after the authentication has failed.

Description

Technical Field

[0001] The present invention relates to the technical field of financial data processing, and in particular to a method and device for determining a user authentication mode. Background Art

[0002] This section is intended to provide a background or context to the embodiments of the invention that are recited in the claims. No statement herein is admitted to be prior art by virtue of its inclusion in this section.

[0003] Currently, when customers conduct banking transactions, they often need to verify their identities through certain identity verification methods to reduce risks. In existing transaction scenarios, facial recognition is a commonly used identity verification method. However, if a facial recognition mismatch occurs, manual intervention is usually required, which is inefficient and creates a poor customer experience. Furthermore, in high-risk scenarios, the high level of uncertainty increases the risk of customer transactions. Therefore, facial recognition failures may prevent transactions from proceeding smoothly.

[0004] In summary, there is an urgent need for a technical solution that can overcome the above-mentioned defects and determine the user authentication method after face recognition fails. Summary of the Invention

[0005] In order to solve the problems existing in the prior art, the present invention proposes a method and device for determining the user authentication method, which can determine the customer's authentication method after face recognition fails, allowing the customer's transaction to proceed smoothly and effectively control transaction risks.

[0006] In a first aspect of an embodiment of the present invention, a method for determining a user authentication mode is provided, comprising:

[0007] Obtain historical facial recognition data from banks;

[0008] Determine the correspondence between face matching thresholds and risk indicators based on the bank's historical face recognition data;

[0009] Based on the bank's historical facial recognition failure data, determine the corresponding relationship between the matching gap value and the risk indicator;

[0010] When the facial data entered by the user on the bank terminal is obtained, the matching value of the facial data is calculated; if the matching value between the facial data and the facial data pre-stored by the user at the bank is less than the user's facial matching threshold, the facial authentication is determined to have failed, and the difference between the facial matching threshold and the matching value is used as the matching gap value corresponding to the authentication failure;

[0011] Based on the matching gap value corresponding to this authentication failure, the matching value between the facial data and the facial data of the user pre-stored in the bank, the correspondence between the matching gap value and the risk index, and the correspondence between the facial matching threshold and the risk index, the user authentication method after this authentication failure is determined; among which, the bank terminal authenticates the user based on the user authentication method after this authentication failure.

[0012] In a second aspect of an embodiment of the present invention, a device for determining a user authentication method is provided, including:

[0013] Acquisition module, used to obtain the bank's historical face recognition data;

[0014] A historical data processing module is used to determine the correspondence between face matching thresholds and risk indicators based on the bank's historical face recognition data;

[0015] A failure data processing module is used to determine the corresponding relationship between the matching gap value and the risk indicator based on the failure data in the bank's historical face recognition data;

[0016] A matching value calculation module is configured to calculate a matching value for facial data input by a user on a bank terminal upon obtaining the facial data input by the user on the bank terminal. If the matching value between the facial data and the facial data pre-stored by the user at the bank is less than the facial matching threshold for the user, the facial authentication is determined to have failed, and the difference between the facial matching threshold and the matching value is used as the matching gap value corresponding to the authentication failure.

[0017] The user authentication method determination module is used to determine the user authentication method after the current authentication failure based on the matching gap value corresponding to the current authentication failure, the matching value between the facial data and the user's facial data pre-stored in the bank, the correspondence between the matching gap value and the risk index, and the correspondence between the facial matching threshold and the risk index; wherein, the bank terminal performs identity authentication on the user based on the user authentication method after the current authentication failure.

[0018] In a third aspect of an embodiment of the present invention, a computer device is proposed, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements a method for determining a user authentication method when executing the computer program.

[0019] In a fourth aspect of an embodiment of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, a method for determining a user authentication method is implemented.

[0020] In a fifth aspect of an embodiment of the present invention, a computer program product is proposed. The computer program product includes a computer program. When the computer program is executed by a processor, a method for determining a user authentication method is implemented.

[0021] The present invention can further analyze the failure of face recognition, effectively control risks and determine the user's authentication method, ensure the smooth progress of customer transactions, protect the customer's property safety, improve the operating efficiency of bank branches, and reduce the operating risks of bank branches. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the description of the embodiments. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0023] Figure 1 The figure is a flow chart of a method for determining a user authentication method according to an embodiment of the present invention.

[0024] Figure 2 4 is a flow chart of determining the corresponding relationship between a face matching threshold and a risk indicator according to an embodiment of the present invention.

[0025] Figure 3 The figure is a flow chart of determining the corresponding relationship between the matching gap value and the risk indicator according to an embodiment of the present invention.

[0026] Figure 4 The figure is a flowchart of determining a user authentication method after a current authentication fails according to an embodiment of the present invention.

[0027] Figure 5 FIG. 4 is a schematic diagram of an apparatus architecture for determining a user authentication method according to an embodiment of the present invention.

[0028] Figure 6 It is a schematic diagram of the structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0029] The principles and spirit of the present invention will be described below with reference to several exemplary embodiments. It should be understood that these embodiments are provided solely to enable those skilled in the art to better understand and implement the present invention, and are not intended to limit the scope of the present invention in any way. Rather, these embodiments are provided to make this disclosure more thorough and complete, and to fully convey the scope of the present disclosure to those skilled in the art.

[0030] Those skilled in the art will appreciate that the embodiments of the present invention may be implemented as a system, apparatus, device, method, or computer program product. Therefore, the present disclosure may be implemented in the following forms: entirely in hardware, entirely in software (including firmware, resident software, microcode, etc.), or in a combination of hardware and software.

[0031] According to an embodiment of the present invention, a method and device for determining a user authentication mode are proposed, which relate to the technical field of financial data processing.

[0032] The principles and spirit of the present invention are explained in detail below with reference to several representative embodiments of the present invention.

[0033] Figure 1 FIG. 1 is a flow chart of a method for determining a user authentication method according to an embodiment of the present invention. Figure 1 As shown, the method includes:

[0034] S1, obtain the bank’s historical face recognition data;

[0035] S2, based on the bank’s historical face recognition data, determines the correspondence between face matching thresholds and risk indicators;

[0036] S3, based on the failure data in the bank's historical face recognition data, determine the corresponding relationship between the matching gap value and the risk indicator;

[0037] S4. When the facial data input by the user on the bank terminal is obtained, a matching value of the facial data is calculated. If the matching value between the facial data and the facial data pre-stored by the user at the bank is less than the facial matching threshold of the user, the facial authentication is determined to have failed, and the difference between the facial matching threshold and the matching value is used as the matching gap value corresponding to the authentication failure.

[0038] S5. Determine the user authentication method after the authentication failure based on the matching gap value corresponding to the authentication failure, the matching value between the facial data and the facial data of the user pre-stored in the bank, the correspondence between the matching gap value and the risk index, and the correspondence between the facial matching threshold and the risk index; wherein, the bank terminal performs identity authentication on the user based on the user authentication method after the authentication failure.

[0039] In order to explain the above method for determining the user authentication mode more clearly, each step is described in detail below.

[0040] In S1, the bank's historical face recognition data is obtained.

[0041] In S2, reference Figure 2 , based on the bank's historical face recognition data, determine the correspondence between face matching thresholds and risk indicators, including:

[0042] S21, setting multiple face matching discrete values;

[0043] S22, for each face matching discrete value, determining the proportion of risky face recognition data in the bank's historical face recognition data when the face matching threshold is set to the face matching discrete value, and using the proportion as a risk indicator corresponding to the face matching discrete value;

[0044] S23, constructing a first discrete function, wherein the independent variable of the first discrete function is the plurality of face matching discrete values, and the function value of the first discrete function corresponding to each face matching discrete value is equal to the risk indicator corresponding to the face matching discrete value;

[0045] S24, performing continuous processing on the first discrete function, and using the obtained continuous function as the correspondence between the face matching threshold and the risk index.

[0046] In S3, reference Figure 3 , based on the bank’s historical face recognition failure data, determine the corresponding relationship between the matching gap value and the risk indicator, including:

[0047] S31, for each failed data in the bank's historical face recognition data, the difference between the face matching threshold corresponding to the failed data and the corresponding face matching value is used as the matching gap value corresponding to the failed data;

[0048] S32, dividing the failed data of the bank's historical face recognition data according to the matching gap value, and determining the failed data corresponding to each matching gap value;

[0049] For example, the matching gap value corresponding to failed data A is 10%, the matching gap value corresponding to failed data B is 20%, and the matching gap value corresponding to failed data C is 10%. The failed data corresponding to the matching gap value of 10% are: failed data A and C, and the failed data corresponding to the matching gap value of 20% is failed data B.

[0050] S33, for each matching gap value, determining a risk indicator corresponding to the matching gap value based on the failure data corresponding to the matching gap value;

[0051] S34, constructing a second discrete function, wherein the independent variable of the second discrete function is the matching gap value corresponding to the failure data, and the function value of the second discrete function corresponding to each independent variable is equal to the risk indicator corresponding to the independent variable;

[0052] For example, the independent variables are matching gap value 10% and matching gap value 20%, and the corresponding function values ​​are the risk indicators corresponding to matching gap value 10% and matching gap value 20%.

[0053] S35 , performing a continuous process on the second discrete function, and using the obtained continuous function as the corresponding relationship between the matching gap value and the risk indicator.

[0054] In S4, when the facial data entered by the user on the bank terminal is obtained, the matching value of the facial data is calculated; if the matching value between the facial data and the facial data pre-stored in the bank by the user is less than the facial matching threshold of the user, it is determined that the facial authentication has failed, and the difference between the facial matching threshold and the matching value is used as the matching gap value corresponding to the authentication failure.

[0055] In S5, reference Figure 4 Based on the matching gap value corresponding to the current authentication failure, the matching value between the facial data and the user's pre-stored facial data in the bank, the corresponding relationship between the matching gap value and the risk index, and the corresponding relationship between the facial matching threshold and the risk index, the user authentication method after the current authentication failure is determined, including:

[0056] S51, determining the risk indicator corresponding to the current authentication failure based on the matching gap value corresponding to the current authentication failure and the corresponding relationship between the matching gap value and the risk indicator;

[0057] S52, determining a risk index corresponding to the user based on a matching value between the facial data and the user's facial data pre-stored in the bank and a correspondence between a facial matching threshold and a risk index;

[0058] S53, when the risk index corresponding to the current authentication failure is greater than the risk index corresponding to the user, determine the user authentication method after the current authentication failure based on the risk index of each transaction scenario corresponding to each candidate user authentication method.

[0059] Furthermore, the method further comprises:

[0060] When the risk index corresponding to the current authentication failure is less than or equal to the risk index corresponding to the user, after the current authentication fails, the user authentication mode after the current authentication failure is determined to be empty.

[0061] Specifically, (S53) when the risk index corresponding to the current authentication failure is greater than the risk index corresponding to the user, determining the user authentication method after the current authentication failure based on the risk index of each transaction scenario corresponding to each candidate user authentication method includes:

[0062] S531, for each candidate user authentication method, determining a risk length corresponding to the candidate user authentication method based on risk indicators of each transaction scenario corresponding to the candidate user authentication method;

[0063] For example, the risk length corresponding to the candidate user authentication method is determined as the square root of the sum of the squares of the risk indicators of the candidate user authentication method corresponding to each transaction scenario.

[0064] S532, determining a priority coefficient corresponding to each candidate user authentication method based on the risk length corresponding to each candidate user authentication method;

[0065] S533: Determine the user authentication method after the current authentication fails based on the priority coefficients corresponding to the candidate user authentication methods.

[0066] In one embodiment, (S532) determining the priority coefficient corresponding to each candidate user authentication method according to the risk length corresponding to each candidate user authentication method includes:

[0067] The priority coefficients corresponding to the selected user authentication methods are determined according to the following formula:

[0068]

[0069] Among them, y i and x i They are the priority coefficient and risk length corresponding to the i-th selected user authentication method, x j is the risk length corresponding to the jth selected user authentication method, and g is a monotonically decreasing function with a value range greater than 0.

[0070] In one embodiment, (S533) determining the user authentication method to be used after the current authentication fails based on the priority coefficients corresponding to the candidate user authentication methods includes:

[0071] S533-1, sorting the candidate user authentication methods;

[0072] S533-2, taking the sum of the priority coefficients of all candidate user authentication methods preceding each candidate user authentication method in the ranking as the cumulative coefficient sum corresponding to the candidate user authentication method;

[0073] S533-3, select a function f with a range greater than 0, and determine the domain B of the function f, m = min (B), and

[0074] For example, choose Gaussian probability density function as f.

[0075] S533-4, for each candidate user authentication method, determine the left endpoint value l of the function f corresponding to the candidate user authentication method based on the cumulative coefficient and u corresponding to the candidate user authentication method, where: S is the sum of the priority coefficients corresponding to all candidate user authentication methods;

[0076] S533-5, based on Generate a random number r;

[0077] S533-6, selecting the maximum left endpoint value that is less than r from the left endpoint values ​​of the function f corresponding to all candidate user authentication methods;

[0078] S533-7, using the candidate user authentication method corresponding to the function f whose left endpoint value is equal to the maximum left endpoint value as the user authentication method after the current authentication fails.

[0079] In one embodiment, the method further includes determining a user authentication method to be selected according to the following method:

[0080] S01, obtaining the user authentication method corresponding to the user;

[0081] S02, obtaining user authentication data of the user category to which the user belongs;

[0082] S03, for each user authentication method corresponding to the user, using the user authentication data of the user authentication method in the user authentication data of the user category to which the user belongs as the user authentication data corresponding to the user authentication method;

[0083] S04, selecting user authentication data corresponding to each transaction scenario from the user authentication data corresponding to each user authentication method, and determining the selected user authentication data as the user authentication data corresponding to the transaction scenario for the user authentication method;

[0084] S05, determining a risk indicator of the user authentication method corresponding to each transaction scenario based on the user authentication data corresponding to the user authentication method;

[0085] S06, determining a partial order of user authentication methods corresponding to the user, wherein the partial order is used to determine whether a first user authentication method is superior to a second user authentication method among any two user authentication methods corresponding to the user; if, for each transaction scenario, the risk indicator of the first user authentication method corresponding to the transaction scenario is greater than or equal to the risk indicator of the second user authentication method corresponding to the transaction scenario, then the first user authentication method is determined to be superior to the second user authentication method;

[0086] S07: Determine, based on the partial order of the user authentication methods corresponding to the user, a minimum authentication method among the user authentication methods corresponding to the user, wherein, for each minimum authentication method, no other user authentication method other than the minimum authentication method exists among the user authentication methods corresponding to the user, satisfying that the minimum authentication method is greater than the other user authentication methods;

[0087] S08: Determine a user authentication method to be selected based on the minimum authentication method among the user authentication methods corresponding to the user.

[0088] Specifically, (S07) determining the minimum authentication method among the user authentication methods corresponding to the user according to the partial order of the user authentication methods corresponding to the user, including:

[0089] Initialize the to-be-determined authentication method set and the comparison authentication method set to all user authentication methods corresponding to the user;

[0090] Select a transaction scenario;

[0091] The following three steps are executed repeatedly until the set of authentication methods to be determined is empty:

[0092] Selecting the authentication method a with the lowest risk indicator for the selected transaction scenario from the set of authentication methods to be determined, and comparing the authentication method a with each authentication method b in the set of comparison authentication methods other than the authentication method a according to the partial order of the user authentication methods corresponding to the user;

[0093] If authentication method a is superior to authentication method b, then authentication method a is deleted from the set of authentication methods to be determined; if authentication method b is superior to authentication method a, then authentication method b is deleted from the set of authentication methods to be determined, and authentication method b is determined as the relative authentication method of authentication method a;

[0094] If authentication method a is confirmed to be no greater than any authentication method in the comparison authentication method set except authentication method a based on the partial order of the user authentication methods corresponding to the user, then authentication method a is regarded as the minimum authentication method, and authentication method a is deleted from the authentication method set to be determined, and all relative authentication methods of authentication method a are deleted from the comparison authentication method set.

[0095] It should be noted that user authentication methods with different parameters are considered to be different user authentication methods, for example, face recognition with different parameters can be considered to be different user authentication methods. The above embodiment has less redundant calculations and low computational complexity.

[0096] Specifically, (S08) determining a user authentication method to be selected based on the minimum authentication method among the user authentication methods corresponding to the user, including:

[0097] If the face recognition corresponding to the authentication failure is a minimum authentication method among the user authentication methods corresponding to the user, then all the minimum authentication methods among the user authentication methods corresponding to the user are used as candidate user authentication methods;

[0098] If the face recognition corresponding to this authentication failure is not the minimum authentication method among the user authentication methods corresponding to the user, then the minimum authentication method whose face recognition corresponding to this authentication failure is greater than is selected from all the minimum authentication methods corresponding to the user, and the selected minimum authentication method is used as the candidate user authentication method.

[0099] It should be noted that although the operations of the method of the present invention are described in a specific order in the above embodiments and drawings, this does not require or imply that these operations must be performed in this specific order, or that all illustrated operations must be performed to achieve the desired results. 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.

[0100] After introducing the method of the exemplary embodiment of the present invention, next, reference is made to Figure 5 An apparatus for determining a user authentication method according to an exemplary embodiment of the present invention is introduced.

[0101] The implementation of the device for determining the user authentication method can be referred to in the implementation of the above method, and the repeated parts will not be repeated here. The terms "module" or "unit" used below can be a combination of software and / or hardware that implements the predetermined function. Although the devices described in the following embodiments are preferably implemented in software, implementation in hardware, or a combination of software and hardware, is also possible and contemplated.

[0102] Based on the same inventive concept, the present invention also proposes a device for determining a user authentication method, such as Figure 5 As shown, the device includes:

[0103] An acquisition module 510 is used to acquire the bank's historical face recognition data;

[0104] A historical data processing module 520 is used to determine the correspondence between face matching thresholds and risk indicators based on the bank's historical face recognition data;

[0105] The failure data processing module 530 is used to determine the corresponding relationship between the matching gap value and the risk indicator based on the failure data in the bank's historical face recognition data;

[0106] Matching value calculation module 540 is used to calculate the matching value of the facial data when the facial data input by the user on the bank terminal is obtained. If the matching value between the facial data and the facial data pre-stored by the user in the bank is less than the facial matching threshold of the user, the facial authentication is determined to have failed, and the difference between the facial matching threshold and the matching value is used as the matching gap value corresponding to the authentication failure.

[0107] The user authentication method determination module 550 is used to determine the user authentication method after the current authentication failure based on the matching gap value corresponding to the current authentication failure, the matching value between the facial data and the facial data of the user pre-stored in the bank, the correspondence between the matching gap value and the risk index, and the correspondence between the facial matching threshold and the risk index; wherein, the bank terminal performs identity authentication on the user based on the user authentication method after the current authentication failure.

[0108] In one embodiment, the historical data processing module is specifically configured to:

[0109] Set multiple face matching discrete values;

[0110] For each face matching discrete value, determine the proportion of risky face recognition data in the bank's historical face recognition data when the face matching threshold is set to the face matching discrete value, and use the proportion as the risk indicator corresponding to the face matching discrete value;

[0111] Constructing a first discrete function, wherein the independent variable of the first discrete function is the plurality of face matching discrete values, and the function value of the first discrete function corresponding to each face matching discrete value is equal to the risk indicator corresponding to the face matching discrete value;

[0112] The first discrete function is continuousized, and the obtained continuous function is used as the correspondence between the face matching threshold and the risk index.

[0113] In one embodiment, the failure data processing module is specifically configured to:

[0114] For each failed data in the bank's historical face recognition data, the difference between the face matching threshold corresponding to the failed data and the corresponding face matching value is used as the matching gap value corresponding to the failed data;

[0115] Divide the failed data of the bank's historical face recognition data according to the matching gap value, and determine the failed data corresponding to each matching gap value;

[0116] For each matching gap value, determine the risk indicator corresponding to the matching gap value based on the failure data corresponding to the matching gap value;

[0117] Constructing a second discrete function, wherein the independent variable of the second discrete function is the matching gap value corresponding to the failure data, and the function value of the second discrete function corresponding to each independent variable is equal to the risk indicator corresponding to the independent variable;

[0118] The second discrete function is converted into a continuous function, and the obtained continuous function is used as the corresponding relationship between the matching gap value and the risk indicator.

[0119] In one embodiment, the user authentication method determination module is specifically configured to:

[0120] Determine the risk indicator corresponding to this authentication failure based on the matching gap value corresponding to this authentication failure and the corresponding relationship between the matching gap value and the risk indicator;

[0121] Determine the risk index corresponding to the user based on the matching value between the facial data and the user's pre-stored facial data in the bank and the corresponding relationship between the facial matching threshold and the risk index;

[0122] When the risk indicator corresponding to this authentication failure is greater than the risk indicator corresponding to the user, the user authentication method after this authentication failure is determined based on the risk indicators of each transaction scenario corresponding to each candidate user authentication method.

[0123] In one embodiment, the user authentication method determination module is specifically configured to:

[0124] When the risk index corresponding to the current authentication failure is less than or equal to the risk index corresponding to the user, after the current authentication fails, the user authentication mode after the current authentication failure is determined to be empty.

[0125] In one embodiment, the user authentication method determination module is specifically configured to:

[0126] For each candidate user authentication method, determine the risk length corresponding to the candidate user authentication method based on the risk indicators of each transaction scenario corresponding to the candidate user authentication method;

[0127] Determine the priority coefficient corresponding to each candidate user authentication method according to the risk length corresponding to each candidate user authentication method;

[0128] The user authentication method to be used after the current authentication fails is determined based on the priority coefficients corresponding to the candidate user authentication methods.

[0129] In one embodiment, the user authentication method determination module is specifically configured to:

[0130] Sort each candidate user authentication method;

[0131] The sum of the priority coefficients of all candidate user authentication methods preceding each candidate user authentication method in the sorting order is used as the cumulative coefficient sum corresponding to the candidate user authentication method;

[0132] Select a function f with a range greater than 0, and determine the domain B of the function f, m = min(B), and

[0133] For each candidate user authentication method, determine the left endpoint value l of the function f corresponding to the candidate user authentication method based on the cumulative coefficient and u corresponding to the candidate user authentication method, where: S is the sum of the priority coefficients corresponding to all candidate user authentication methods;

[0134] based on Generate a random number r;

[0135] Select the maximum left endpoint value less than r from the left endpoint values ​​of the function f corresponding to all candidate user authentication methods;

[0136] The candidate user authentication method whose left endpoint value of the corresponding function f is equal to the maximum left endpoint value is used as the user authentication method after the current authentication fails.

[0137] It should be noted that although the above detailed description mentions several modules of the apparatus for determining a user authentication method, this division is merely exemplary and not mandatory. In practice, according to embodiments of the present invention, the features and functions of two or more modules described above may be embodied in a single module. Conversely, the features and functions of a single module described above may be further divided and embodied by multiple modules.

[0138] Based on the above invention concept, 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, wherein the processor 620 implements the aforementioned method for determining a user authentication method when executing the computer program 630.

[0139] Based on the aforementioned inventive concept, the present invention proposes a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method for determining a user authentication method is implemented.

[0140] Based on the aforementioned inventive concept, the present invention proposes a computer program product, which includes a computer program. When the computer program is executed by a processor, a method for determining a user authentication method is implemented.

[0141] The present invention proposes a method and device for determining a user authentication method by obtaining historical face recognition data of a bank; determining the corresponding relationship between a face matching threshold and a risk indicator based on the historical face recognition data of the bank; determining the corresponding relationship between a matching gap value and a risk indicator based on the failure data in the historical face recognition data of the bank; when the face data input by the user on the bank terminal is obtained, calculating the matching value of the face data; wherein, if the matching value between the face data and the face data pre-stored in the bank is less than the face matching threshold of the user, it is determined that the face authentication has failed, and the difference between the face matching threshold and the matching value is used as the matching value corresponding to the authentication failure. Gap value; determine the user authentication method after this authentication failure based on the matching gap value corresponding to this authentication failure, the matching value between the facial data and the facial data of the user pre-stored in the bank, the corresponding relationship between the matching gap value and the risk index, and the corresponding relationship between the facial matching threshold and the risk index; wherein, the bank terminal performs identity authentication on the user based on the user authentication method after this authentication failure. The present invention can further analyze the situation of facial recognition failure, effectively control the risk, and determine the user's authentication method at the same time, thereby ensuring the smooth progress of customer transactions, protecting the customer's property safety, improving the operating efficiency of bank branches, and reducing the operating risks of bank branches.

[0142] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, apparatus, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0143] The present invention is described with reference to flowcharts and / or block diagrams of methods and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts 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, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0144] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0145] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0146] Finally, it should be noted that the above-described embodiments are only specific implementation methods of the present invention, which are used to illustrate the technical solutions of the present invention, rather than to limit them. 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 above-described embodiments, those skilled in the art should understand that any person skilled in the art can modify or easily conceive of changes to the technical solutions described in the above-described embodiments within the technical scope disclosed by the present invention, or replace some of the technical features therein with equivalents. Such modifications, changes, or replacements do not deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the scope of protection of the present invention. Therefore, the scope of protection of the present invention shall be subject to the scope of protection of the claims.

Claims

1. A method for determining a user authentication method, characterized in that: include: Obtain historical facial recognition data from banks; Determine the correspondence between face matching thresholds and risk indicators based on the bank's historical face recognition data; Based on the bank's historical facial recognition failure data, determine the corresponding relationship between the matching gap value and the risk indicator; When the facial data entered by the user on the bank terminal is obtained, the matching value of the facial data is calculated; if the matching value between the facial data and the facial data pre-stored by the user at the bank is less than the user's facial matching threshold, the facial authentication is determined to have failed, and the difference between the facial matching threshold and the matching value is used as the matching gap value corresponding to the authentication failure; Determine the user authentication method after the authentication failure based on the matching gap value corresponding to the current authentication failure, the matching value between the facial data and the user's pre-stored facial data at the bank, the corresponding relationship between the matching gap value and the risk indicator, and the corresponding relationship between the facial matching threshold and the risk indicator; wherein the bank terminal authenticates the user based on the user authentication method after the authentication failure; Among them, based on the bank's historical facial recognition data, the corresponding relationship between facial matching thresholds and risk indicators is determined, including: Set multiple face matching discrete values; For each face matching discrete value, determine the proportion of risky face recognition data in the bank's historical face recognition data when the face matching threshold is set to the face matching discrete value, and use the proportion as the risk indicator corresponding to the face matching discrete value; Constructing a first discrete function, wherein the independent variable of the first discrete function is the plurality of face matching discrete values, and the function value of the first discrete function corresponding to each face matching discrete value is equal to the risk indicator corresponding to the face matching discrete value; Continuizing the first discrete function, and using the obtained continuous function as the correspondence between the face matching threshold and the risk index; Among them, based on the failure data in the bank's historical face recognition data, the corresponding relationship between the matching gap value and the risk indicator is determined, including: For each failed data in the bank's historical face recognition data, the difference between the face matching threshold corresponding to the failed data and the corresponding face matching value is used as the matching gap value corresponding to the failed data; Divide the failed data of the bank's historical face recognition data according to the matching gap value, and determine the failed data corresponding to each matching gap value; For each matching gap value, determine the risk indicator corresponding to the matching gap value based on the failure data corresponding to the matching gap value; Constructing a second discrete function, wherein the independent variable of the second discrete function is the matching gap value corresponding to the failure data, and the function value of the second discrete function corresponding to each independent variable is equal to the risk indicator corresponding to the independent variable; The second discrete function is converted into a continuous function, and the obtained continuous function is used as the corresponding relationship between the matching gap value and the risk indicator.

2. The method according to claim 1, wherein Based on the matching gap value corresponding to the current authentication failure, the matching value between the facial data and the user's pre-stored facial data in the bank, the corresponding relationship between the matching gap value and the risk index, and the corresponding relationship between the facial matching threshold and the risk index, the user authentication method after the current authentication failure is determined, including: Determine the risk indicator corresponding to this authentication failure based on the matching gap value corresponding to this authentication failure and the corresponding relationship between the matching gap value and the risk indicator; Determine the risk index corresponding to the user based on the matching value between the facial data and the user's pre-stored facial data in the bank and the corresponding relationship between the facial matching threshold and the risk index; When the risk indicator corresponding to this authentication failure is greater than the risk indicator corresponding to the user, the user authentication method after this authentication failure is determined based on the risk indicators of each transaction scenario corresponding to each candidate user authentication method.

3. The method according to claim 2, wherein The method further comprises: When the risk index corresponding to the current authentication failure is less than or equal to the risk index corresponding to the user, after the current authentication fails, the user authentication mode after the current authentication failure is determined to be empty.

4. The method according to claim 2, wherein When the risk indicator corresponding to the current authentication failure is greater than the risk indicator corresponding to the user, the user authentication method after the current authentication failure is determined based on the risk indicators of each transaction scenario corresponding to each candidate user authentication method, including: For each candidate user authentication method, determine the risk length corresponding to the candidate user authentication method based on the risk indicators of each transaction scenario corresponding to the candidate user authentication method; Determine the priority coefficient corresponding to each candidate user authentication method according to the risk length corresponding to each candidate user authentication method; The user authentication method to be used after the current authentication fails is determined based on the priority coefficients corresponding to the candidate user authentication methods.

5. The method according to claim 4, wherein Based on the priority coefficients corresponding to the candidate user authentication methods, the user authentication method after the current authentication failure is determined, including: Sort each candidate user authentication method; The sum of the priority coefficients of all candidate user authentication methods preceding each candidate user authentication method in the sorting order is used as the cumulative coefficient sum corresponding to the candidate user authentication method; Select a function f with a range greater than 0, and determine the domain B of the function f, m = min(B), and For each candidate user authentication method, determine the left endpoint value l of the function f corresponding to the candidate user authentication method based on the cumulative coefficient and u corresponding to the candidate user authentication method, where: S is the sum of the priority coefficients corresponding to all candidate user authentication methods; based on Generate a random number r; Select the maximum left endpoint value less than r from the left endpoint values ​​of the function f corresponding to all candidate user authentication methods; The candidate user authentication method whose left endpoint value of the corresponding function f is equal to the maximum left endpoint value is used as the user authentication method after the current authentication fails.

6. A device for determining a user authentication method, characterized in that: include: Acquisition module, used to obtain the bank's historical face recognition data; A historical data processing module is used to determine the correspondence between face matching thresholds and risk indicators based on the bank's historical face recognition data; A failure data processing module is used to determine the corresponding relationship between the matching gap value and the risk indicator based on the failure data in the bank's historical face recognition data; A matching value calculation module is configured to calculate a matching value for facial data input by a user on a bank terminal upon obtaining the facial data input by the user on the bank terminal. If the matching value between the facial data and the facial data pre-stored by the user at the bank is less than the facial matching threshold for the user, the facial authentication is determined to have failed, and the difference between the facial matching threshold and the matching value is used as the matching gap value corresponding to the authentication failure. A user authentication method determination module is configured to determine the user authentication method after the current authentication failure based on the matching gap value corresponding to the current authentication failure, the matching value between the facial data and the user's pre-stored facial data in the bank, the corresponding relationship between the matching gap value and the risk indicator, and the corresponding relationship between the facial matching threshold and the risk indicator; wherein the bank terminal authenticates the user based on the user authentication method after the current authentication failure; The historical data processing module is specifically used for: Set multiple face matching discrete values; For each face matching discrete value, determine the proportion of risky face recognition data in the bank's historical face recognition data when the face matching threshold is set to the face matching discrete value, and use the proportion as the risk indicator corresponding to the face matching discrete value; Constructing a first discrete function, wherein the independent variable of the first discrete function is the plurality of face matching discrete values, and the function value of the first discrete function corresponding to each face matching discrete value is equal to the risk indicator corresponding to the face matching discrete value; Continuizing the first discrete function, and using the obtained continuous function as the correspondence between the face matching threshold and the risk index; The failure data processing module is specifically used to: For each failed data in the bank's historical face recognition data, the difference between the face matching threshold corresponding to the failed data and the corresponding face matching value is used as the matching gap value corresponding to the failed data; Divide the failed data of the bank's historical face recognition data according to the matching gap value, and determine the failed data corresponding to each matching gap value; For each matching gap value, determine the risk indicator corresponding to the matching gap value based on the failure data corresponding to the matching gap value; Constructing a second discrete function, wherein the independent variable of the second discrete function is the matching gap value corresponding to the failure data, and the function value of the second discrete function corresponding to each independent variable is equal to the risk indicator corresponding to the independent variable; The second discrete function is converted into a continuous function, and the obtained continuous function is used as the corresponding relationship between the matching gap value and the risk indicator.

7. The device according to claim 6, characterized in that The user authentication method determination module is specifically used to: Determine the risk indicator corresponding to this authentication failure based on the matching gap value corresponding to this authentication failure and the corresponding relationship between the matching gap value and the risk indicator; Determine the risk index corresponding to the user based on the matching value between the facial data and the user's pre-stored facial data in the bank and the corresponding relationship between the facial matching threshold and the risk index; When the risk indicator corresponding to this authentication failure is greater than the risk indicator corresponding to the user, the user authentication method after this authentication failure is determined based on the risk indicators of each transaction scenario corresponding to each candidate user authentication method.

8. The device according to claim 7, wherein The user authentication method determination module is specifically used to: When the risk index corresponding to the current authentication failure is less than or equal to the risk index corresponding to the user, after the current authentication fails, the user authentication mode after the current authentication failure is determined to be empty.

9. The device according to claim 7, wherein The user authentication method determination module is specifically used to: For each candidate user authentication method, determine the risk length corresponding to the candidate user authentication method based on the risk indicators of each transaction scenario corresponding to the candidate user authentication method; Determine the priority coefficient corresponding to each candidate user authentication method according to the risk length corresponding to each candidate user authentication method; The user authentication method to be used after the current authentication fails is determined based on the priority coefficients corresponding to the candidate user authentication methods.

10. The device according to claim 9, wherein The user authentication method determination module is specifically used to: Sort each candidate user authentication method; The sum of the priority coefficients of all candidate user authentication methods preceding each candidate user authentication method in the sorting order is used as the cumulative coefficient sum corresponding to the candidate user authentication method; Select a function f with a range greater than 0, and determine the domain B of the function f, m = min(B), and For each candidate user authentication method, determine the left endpoint value l of the function f corresponding to the candidate user authentication method based on the cumulative coefficient and u corresponding to the candidate user authentication method, where: S is the sum of the priority coefficients corresponding to all candidate user authentication methods; based on Generate a random number r; Select the maximum left endpoint value less than r from the left endpoint values ​​of the function f corresponding to all candidate user authentication methods; The candidate user authentication method whose left endpoint value of the corresponding function f is equal to the maximum left endpoint value is used as the user authentication method after the current authentication fails.

11. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the method according to any one of claims 1 to 5 is implemented.

12. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 5 is implemented.

13. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 5 is implemented.

Images