Method and device for controlling internal risks of banks

Abstract

The present invention proposes a method and device for controlling internal risks of a bank, which relates to the field of computer data processing technology. The method includes: when a customer handles business at a branch and requires staff review and authorization, determining the relevant indicators of the customer and the staff; based on the relevant indicators of the customer and the staff, a first correspondence between the biometric recognition threshold and the risk coefficient under various pre-stored relevant indicator conditions, and a second correspondence between the biometric recognition threshold and the risk coefficient, correcting the staff's biometric recognition threshold, wherein the biometric recognition threshold is used to control the internal risks of business handling.

Description

Technical Field

[0001] The present invention relates to the technical field of computer data processing, and in particular to a method and device for controlling internal risks of a bank. 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] In banking business scenarios, bank staff are sometimes required to review and authorize before the customer's business can be processed. However, the staff's review and authorization may introduce internal risks, which may cause losses to the customer's property. Therefore, banks need to control internal risks when staff review and authorize.

[0004] Therefore, there is an urgent need for a technical solution that can overcome the above-mentioned defects and effectively control the internal risks of banks. 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 controlling internal risks of a bank.

[0006] In a first aspect of an embodiment of the present invention, a method for controlling internal bank risks is provided, comprising:

[0007] When a customer conducts business at an outlet and requires staff review and authorization, determine the relevant indicators for the customer and the staff;

[0008] Based on the relevant indicators of the customer and the staff member, the first correspondence between the biometric threshold and the risk coefficient under the pre-stored conditions of various relevant indicators, and the second correspondence between the biometric threshold and the risk coefficient, the biometric threshold of the staff member is corrected, wherein the biometric threshold is used to control the internal risks of business handling.

[0009] In a second aspect of an embodiment of the present invention, a device for controlling internal risks of a bank is provided, comprising:

[0010] When a customer conducts business at an outlet and requires staff review and authorization, determine the relevant indicators for the customer and the staff;

[0011] Based on the relevant indicators of the customer and the staff member, the first correspondence between the biometric threshold and the risk coefficient under the pre-stored conditions of various relevant indicators, and the second correspondence between the biometric threshold and the risk coefficient, the biometric threshold of the staff member is corrected, wherein the biometric threshold is used to control the internal risks of business handling.

[0012] 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 controlling internal risks of a bank when executing the computer program.

[0013] 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 controlling internal risks of a bank is implemented.

[0014] 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 controlling internal risks of a bank is implemented.

[0015] The method and device for controlling internal bank risks proposed in the present invention determine the relevant indicators of customers and staff; based on the relevant indicators of customers and staff, the first corresponding relationship between the biometric threshold and the risk coefficient under the pre-stored conditions of each relevant indicator, and the second corresponding relationship between the biometric threshold and the risk coefficient, the biometric threshold of the staff is corrected, so that when the customer needs the authorization of the staff to handle business at the branch, the internal risk of the bank is effectively controlled, the smooth handling of the customer's business is guaranteed, the safety of the customer's property is protected, and strong technical support is provided for the bank's digital risk control. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] 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.

[0017] Figure 1 The figure is a flow chart of a method for controlling internal bank risks according to an embodiment of the present invention.

[0018] Figure 2 It is a flowchart of determining relevant indicators of customers and staff members according to an embodiment of the present invention.

[0019] Figure 3 It is a flowchart of determining a first correspondence relationship and a second correspondence relationship according to an embodiment of the present invention.

[0020] Figure 4 4 is a flow chart of modifying a worker's biometric identification threshold according to an embodiment of the present invention.

[0021] Figure 5FIG. 1 is a schematic diagram of the architecture of a bank internal risk control device according to an embodiment of the present invention.

[0022] Figure 6 FIG. 1 is a schematic diagram of the architecture of a bank internal risk control device according to another embodiment of the present invention.

[0023] Figure 7 It is a schematic diagram of the structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0024] 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.

[0025] 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.

[0026] According to an embodiment of the present invention, a method and device for controlling internal risks of a bank are proposed, which relate to the technical field of computer data processing.

[0027] The principles and spirit of the present invention are explained in detail below with reference to several representative embodiments of the present invention.

[0028] Figure 1 This is a flow chart of a method for controlling internal bank risks according to an embodiment of the present invention. Figure 1 As shown, the method includes:

[0029] S1: When a customer conducts business at a branch and requires staff approval, determine the relevant indicators of the customer and the staff;

[0030] S2, based on the relevant indicators of the customer and the staff member, the first correspondence between the biometric threshold and the risk factor under the pre-stored conditions of each relevant indicator, and the second correspondence between the biometric threshold and the risk factor, wherein the biometric threshold is used to control the internal risks of business handling.

[0031] In order to explain the above-mentioned internal risk control methods of banks more clearly, each step is explained in detail below.

[0032] In S1, ref. Figure 2, determine the relevant indicators for the customer and the staff member, including:

[0033] S11, obtaining an internal correlation graph, wherein each node of the internal correlation graph is a customer or staff member of the bank, each edge of the internal correlation graph corresponds to a correlation index, and the correlation index represents the degree of correlation between the two nodes corresponding to the edge, and the value of the correlation index is between 0 and 1;

[0034] Among them, the internal correlation graph is constructed by the bank server.

[0035] S12: Determine the correlation index between the customer and the staff member based on the internal correlation graph.

[0036] In one embodiment, (S12) determining the correlation index between the client and the staff member based on the internal correlation graph includes:

[0037] S121, based on the internal correlation graph, initialize the potential correlation index corresponding to each node that has a direct edge connection with the customer to the correlation index corresponding to the edge between the customer and the node in the internal correlation graph, and initialize the potential correlation index corresponding to each node that has no direct edge connection with the customer to 0;

[0038] S122, taking a set consisting of all other nodes in the internal correlation graph except the customer as a set of nodes to be determined;

[0039] S123, looping through the following steps (S123-1 to S123-5) until the relevant indicators between the customer and the staff member are determined:

[0040] S123-1, extracting the node S with the largest potential correlation index from the set of nodes to be determined;

[0041] S123-2, determining whether the node S is the staff member;

[0042] S123-3, if the node S is the staff member, determining the correlation index between the customer and the staff member as the potential correlation index corresponding to the node S, and stopping the execution of the loop;

[0043] S123-4, for each node T that has a direct edge connection to node S, update the potential correlation index corresponding to node T to the maximum value of f(S)×r(S,T) and f(T), where f(T) is the potential correlation index corresponding to node T before the update, f(S) is the potential correlation index corresponding to node S, and r(S,T) is the correlation index corresponding to the edge between nodes S and T in the internal correlation graph;

[0044] S123-5, delete the node S from the set of nodes to be determined.

[0045] Specifically, (S12) determining the correlation indicators between the customer and the staff member based on the internal correlation graph, including:

[0046] The correlation distance value corresponding to each edge of the internal correlation graph is determined according to the following formula:

[0047] d = -lg(r), where d is the relevant distance value corresponding to the edge, and r is the relevant index corresponding to the edge;

[0048] Based on the internal correlation graph and the correlation distance value, determine the minimum correlation distance d between the customer and the staff member m ;

[0049] Based on the minimum relevant distance d between the customer and the staff m , determine the relevant index s between the customer and the staff, where,

[0050] In one embodiment, reference Figure 3 The method further includes determining a first correspondence between the biometric identification threshold and the risk coefficient and a second correspondence between the biometric identification threshold and the risk coefficient under each relevant indicator condition according to the following method:

[0051] S301, obtaining the bank's historical audit data;

[0052] S302, for each piece of historical audit data, the relevant indicators of the client and the corresponding staff member corresponding to the historical audit data are used as the relevant indicators corresponding to the historical audit data;

[0053] S303, for each relevant indicator, taking the corresponding relevant indicator equal to the historical audit data of the relevant indicator as the historical audit data of the relevant indicator;

[0054] S304, for each bank branch, selecting the historical audit data corresponding to the relevant indicator of the bank branch from the historical audit data of each relevant indicator;

[0055] S305, determining a first bank branch and a second bank branch corresponding to the relevant indicator based on historical audit data of each bank branch corresponding to the relevant indicator;

[0056] S306, based on the historical audit data of the first bank branch corresponding to the relevant indicator and the relevant indicator, determine the first corresponding relationship between the biometric identification threshold and the risk coefficient under the relevant indicator condition, and based on the historical audit data of the second bank branch corresponding to the relevant indicator and the relevant indicator, determine the second corresponding relationship between the biometric identification threshold and the risk coefficient under the relevant indicator condition.

[0057] It should be noted that the method for determining the relevant indicators of the customer and the staff member in S1 can be referred to to determine the relevant indicators of the customer and the corresponding staff member corresponding to each historical audit data in S302.

[0058] Specifically, (S305) determining the first bank branch and the second bank branch corresponding to the relevant indicator based on the historical audit data of each bank branch corresponding to the relevant indicator includes at least the following two methods.

[0059] First method:

[0060] S305-11, based on the historical audit data of each bank branch for the relevant indicator, determine the audit risk coefficient of the bank branch for the relevant indicator;

[0061] For example, the proportion of audit data involving risks in the historical audit data of the bank branch corresponding to the relevant indicator is used as the audit risk coefficient of the bank branch corresponding to the relevant indicator.

[0062] S305-12, determining the transaction risk coefficient of each bank branch based on the transaction data of each bank branch;

[0063] The transaction data of each bank branch refers to the transaction data of each bank branch involving audited transactions.

[0064] S305-13, determining a partial order of bank branches, wherein the partial order is used to determine whether a first bank branch is superior to a second bank branch among any two bank branches; if the audit risk coefficient of the first bank branch corresponding to the relevant indicator is less than or equal to the audit risk coefficient of the second bank branch corresponding to the relevant indicator, and the transaction risk coefficient of the first bank branch is less than or equal to the transaction risk coefficient of the second bank branch, then the first bank branch is determined to be superior to the second bank branch in the partial order;

[0065] S305-14, determining the first bank branch and the second bank branch corresponding to the relevant indicator according to the partial order of the bank branches.

[0066] Specifically, (S305-14) determining the first bank branch and the second bank branch corresponding to the relevant indicator according to the partial order of the bank branches includes:

[0067] The maximum element of the partial order of bank branches is taken as the maximum branch corresponding to the relevant index, and the minimum element of the partial order of bank branches is taken as the minimum branch corresponding to the relevant index;

[0068] The maximum value of the audit risk coefficient of the maximum outlet corresponding to the relevant indicator is used as the maximum audit coefficient threshold, and the maximum value of the transaction risk coefficient of the maximum outlet corresponding to the relevant indicator is used as the maximum transaction coefficient threshold; the minimum value of the audit risk coefficient of the minimum outlet corresponding to the relevant indicator is used as the minimum audit coefficient threshold, and the minimum value of the transaction risk coefficient of the minimum outlet corresponding to the relevant indicator is used as the minimum transaction coefficient threshold;

[0069] When the historical audit data of the maximum branch corresponding to the relevant indicator is greater than or equal to the data volume threshold, the maximum branch corresponding to the relevant indicator is used as the first bank branch corresponding to the relevant indicator; when the historical audit data of the maximum branch corresponding to the relevant indicator is less than the data volume threshold, the bank branch whose corresponding audit risk coefficient is less than or equal to the maximum audit coefficient threshold and whose corresponding transaction risk coefficient is less than or equal to the maximum transaction coefficient threshold is used as the first bank branch corresponding to the relevant indicator;

[0070] When the historical audit data of the minimum branch corresponding to the relevant indicator is greater than or equal to the data volume threshold, the minimum branch corresponding to the relevant indicator will be used as the second bank branch corresponding to the relevant indicator; when the historical audit data of the minimum branch corresponding to the relevant indicator is less than the data volume threshold, the bank branch whose corresponding audit risk coefficient is greater than or equal to the minimum audit coefficient threshold and whose corresponding transaction risk coefficient is greater than or equal to the minimum transaction coefficient threshold will be used as the second bank branch corresponding to the relevant indicator.

[0071] Second method:

[0072] S305-21, based on the historical audit data of each bank branch for the relevant indicator, determine the audit risk coefficient of the bank branch for the relevant indicator;

[0073] For example, the proportion of audit data involving risks in the historical audit data of the bank branch corresponding to the relevant indicator is used as the audit risk coefficient of the bank branch corresponding to the relevant indicator.

[0074] S305-22, the bank branch whose audit risk coefficient corresponding to the relevant indicator is less than the coefficient threshold is used as the first bank branch corresponding to the relevant indicator, and the bank branch whose audit risk coefficient corresponding to the relevant indicator is greater than or equal to the coefficient threshold is used as the second bank branch corresponding to the relevant indicator.

[0075] Specifically, (S306) determining a first correspondence between the biometric identification threshold and the risk factor under the relevant indicator condition based on historical audit data corresponding to the relevant indicator by the first bank branch corresponding to the relevant indicator, and determining a second correspondence between the biometric identification threshold and the risk factor under the relevant indicator condition based on historical audit data corresponding to the relevant indicator by the second bank branch corresponding to the relevant indicator, including:

[0076] S306-1, setting multiple biometric discrete values;

[0077] S306-2. For each biometric discrete value, determine the percentage of risk-related audit data in the historical audit data for the relevant indicator at the first bank branch corresponding to the relevant indicator when the biometric threshold is set to the biometric discrete value, and use the percentage as the first risk coefficient corresponding to the biometric discrete value. Determine the percentage of risk-related audit data in the historical audit data for the relevant indicator at the second bank branch corresponding to the relevant indicator when the biometric threshold is set to the biometric discrete value, and use the percentage as the second risk coefficient corresponding to the biometric discrete value.

[0078] S306-3, constructing a first risk coefficient function and a second risk coefficient function, wherein the independent variables of the first risk coefficient function and the second risk coefficient function are a plurality of predetermined biometric discrete values, wherein the function value of the first risk coefficient function corresponding to each biometric discrete value is equal to the first risk coefficient corresponding to the biometric discrete value, and the function value of the second risk coefficient function corresponding to each biometric discrete value is equal to the second risk coefficient corresponding to the biometric discrete value;

[0079] S306-4, making the first risk coefficient function and the second risk coefficient function continuous, taking the continuous function corresponding to the first risk coefficient function as the first corresponding relationship between the biometric threshold and the risk coefficient under the relevant indicator condition, and taking the continuous function corresponding to the second risk coefficient function as the second corresponding relationship between the biometric threshold and the risk coefficient under the relevant indicator condition.

[0080] In one embodiment, the method further comprises:

[0081] S0110, for each first bank branch corresponding to the relevant indicator, determine a priority coefficient corresponding to the first bank branch based on the audit risk coefficient of the first bank branch corresponding to the relevant indicator (and the transaction risk coefficient of the first bank branch);

[0082] S0120, performing risk control on the real-time audit data of the bank branch based on the priority coefficient corresponding to the first bank branch corresponding to the relevant indicator.

[0083] Furthermore, (S0120) risk control is performed on the real-time audit data of the bank branch based on the priority coefficient corresponding to the first bank branch corresponding to the relevant indicator, including:

[0084] S0121, sorting the first bank branches corresponding to the relevant indicators;

[0085] S0122, based on the priority coefficient corresponding to the first bank branch corresponding to the relevant indicator, determine the priority lower limit value corresponding to each first bank branch according to the following formula:

[0086]

[0087] w k is the priority lower bound value corresponding to the k-th first bank branch, x i and x j are the priority coefficients corresponding to the i-th and j-th first bank branches of the relevant indicator, respectively; g is a real function with a range greater than 0 and a partial derivative less than 0;

[0088] S0123, select a random number generator that conforms to a uniform distribution and has a value range of [0,1];

[0089] S0124, for each real-time audit data of the bank branch, generate a random number according to the selected random number generator, and use the random number as the random number corresponding to the real-time audit data;

[0090] S0125, selecting a maximum priority lower bound value that is smaller than the random number corresponding to the real-time audit data from the priority lower bound values ​​corresponding to the first bank branch;

[0091] S0126: Perform risk control on the real-time audit data of the bank branch according to the audit risk control method of the first bank branch whose corresponding priority lower limit value is equal to the maximum priority lower limit value.

[0092] In one embodiment, the method further comprises:

[0093] S0210, based on the historical audit data of the second bank branch corresponding to the relevant indicator, using risk as a prediction indicator, training a prediction model, and using the obtained prediction model as the audit prediction model corresponding to the bank branch;

[0094] S0220, based on the audit prediction model corresponding to the bank branch, conduct risk prediction on the real-time audit data of the bank branch.

[0095] In S2, reference Figure 4, based on the relevant indicators of the customer and the staff member, the first correspondence between the biometric threshold and the risk factor under the pre-stored relevant indicator conditions, and the second correspondence between the biometric threshold and the risk factor, modifying the staff member's biometric threshold, including:

[0096] S21, obtaining the biometric identification threshold of the staff member stored in the bank server;

[0097] S22, determining a potential risk factor of the staff member based on the staff member's biometric threshold, relevant indicators of the customer and the staff member, and a first correspondence between the biometric threshold and the risk factor under the relevant indicator conditions;

[0098] S23, determining a potential biometric threshold for the staff member based on the staff member's potential risk coefficient and a second corresponding relationship between the biometric threshold and the risk coefficient under the relevant indicator condition;

[0099] S24, modifying the biometric threshold of the staff member according to the potential biometric threshold of the staff member.

[0100] 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.

[0101] After introducing the method of the exemplary embodiment of the present invention, next, reference is made to Figure 5 A device for controlling internal risks of a bank according to an exemplary embodiment of the present invention is introduced.

[0102] The implementation of the bank's internal risk control device can be referenced to the implementation of the aforementioned method, and any repetitions will not be repeated. The terms "module" or "unit" used below may refer to a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, implementation using hardware, or a combination of software and hardware, is also possible and contemplated.

[0103] Based on the same inventive concept, the present invention also proposes a bank internal risk control device, such as Figure 5 As shown, the device includes:

[0104] The relevant index determination module 510 is used to determine the relevant index between the customer and the staff member when the customer handles business at the branch and needs staff member's review and authorization;

[0105] The biometric threshold correction module 520 is used to correct the biometric threshold of the staff member based on the relevant indicators of the customer and the staff member, the first correspondence between the biometric threshold and the risk coefficient under the pre-stored conditions of various relevant indicators, and the second correspondence between the biometric threshold and the risk coefficient, wherein the biometric threshold is used to control the internal risks of business handling.

[0106] In one embodiment, the relevant indicator determination module is specifically configured to:

[0107] Obtain an internal correlation graph, wherein each node of the internal correlation graph is a customer or staff member of the bank, each edge of the internal correlation graph corresponds to a correlation index, and the correlation index represents the degree of correlation between the two nodes corresponding to the edge, and the value of the correlation index is between 0 and 1;

[0108] Based on the internal correlation diagram, the correlation indicators between the customer and the staff member are determined.

[0109] In one embodiment, the relevant indicator determination module is specifically configured to:

[0110] According to the internal correlation graph, the potential correlation index corresponding to each node that has a direct edge connection with the customer is initialized to the correlation index corresponding to the edge corresponding to the customer and the node in the internal correlation graph, and the potential correlation index corresponding to each node that has no direct edge connection with the customer is initialized to 0;

[0111] The set consisting of all other nodes in the internal correlation graph except the customer is used as the set of nodes to be determined;

[0112] Repeat the following steps until the relevant indicators between the customer and the staff member are determined:

[0113] Take out the node S with the largest potential correlation index from the set of nodes to be determined;

[0114] Determine whether the node S is the staff member;

[0115] If the node S is the staff member, the correlation index between the customer and the staff member is determined as the potential correlation index corresponding to the node S, and the execution of the loop is stopped;

[0116] For each node T that has a direct edge connection with node S, update the potential correlation index corresponding to node T to the maximum value of f(S)×r(S,T) and f(T), where f(T) is the potential correlation index corresponding to node T before the update, f(S) is the potential correlation index corresponding to node S, and r(S,T) is the correlation index corresponding to the edge between node S and node T in the internal correlation graph;

[0117] Delete the node S from the set of nodes to be determined.

[0118] In one embodiment, reference Figure 6 , the apparatus further includes: a corresponding relationship determination module 530;

[0119] The corresponding relationship determination module determines the first corresponding relationship between the biometric identification threshold and the risk coefficient and the second corresponding relationship between the biometric identification threshold and the risk coefficient under each relevant indicator condition according to the following method:

[0120] Obtain historical audit data of the bank;

[0121] For each piece of historical audit data, the relevant indicators of the client and the corresponding staff member corresponding to the historical audit data are used as the relevant indicators corresponding to the historical audit data;

[0122] For each relevant indicator, the corresponding relevant indicator equal to the historical audit data of the relevant indicator is used as the historical audit data of the relevant indicator;

[0123] For each bank branch, select the historical audit data of each relevant indicator from the historical audit data of each relevant indicator;

[0124] Determine the first bank branch and the second bank branch corresponding to the relevant indicator based on the historical audit data of each bank branch corresponding to the relevant indicator;

[0125] Based on the historical audit data of the first bank branch corresponding to the relevant indicator, the first corresponding relationship between the biometric threshold and the risk coefficient under the relevant indicator conditions is determined, and based on the historical audit data of the second bank branch corresponding to the relevant indicator, the second corresponding relationship between the biometric threshold and the risk coefficient under the relevant indicator conditions is determined.

[0126] In one embodiment, the correspondence relationship determination module is specifically configured to:

[0127] Determine the audit risk coefficient of each bank branch for the relevant indicator based on the historical audit data of the relevant indicator for that bank branch;

[0128] Determine the transaction risk coefficient of each bank branch based on the transaction data of each bank branch;

[0129] Determining a partial order of bank branches, wherein the partial order is used to determine whether a first bank branch is superior to a second bank branch among any two bank branches; if the audit risk coefficient of the first bank branch corresponding to the relevant indicator is less than or equal to the audit risk coefficient of the second bank branch corresponding to the relevant indicator, and the transaction risk coefficient of the first bank branch is less than or equal to the transaction risk coefficient of the second bank branch, then the first bank branch is determined to be superior to the second bank branch in the partial order;

[0130] According to the partial order of the bank branches, a first bank branch and a second bank branch corresponding to the relevant indicator are determined.

[0131] In one embodiment, the correspondence relationship determination module is specifically configured to:

[0132] Determine the audit risk coefficient of each bank branch for the relevant indicator based on the historical audit data of the relevant indicator for that bank branch;

[0133] The bank branch whose audit risk coefficient corresponding to the relevant indicator is less than the coefficient threshold is used as the first bank branch corresponding to the relevant indicator, and the bank branch whose audit risk coefficient corresponding to the relevant indicator is greater than or equal to the coefficient threshold is used as the second bank branch corresponding to the relevant indicator.

[0134] In one embodiment, the correspondence relationship determination module is specifically configured to:

[0135] Set multiple biometric discrete values;

[0136] For each biometric discrete value, determine the proportion of audit data involving risk in the historical audit data corresponding to the relevant indicator at the first bank branch corresponding to the relevant indicator when the biometric threshold is set to the biometric discrete value, and use this proportion as the first risk coefficient corresponding to the biometric discrete value; determine the proportion of audit data involving risk in the historical audit data corresponding to the relevant indicator at the second bank branch corresponding to the relevant indicator when the biometric threshold is set to the biometric discrete value, and use this proportion as the second risk coefficient corresponding to the biometric discrete value;

[0137] Constructing a first risk coefficient function and a second risk coefficient function, wherein the independent variables of the first risk coefficient function and the second risk coefficient function are a plurality of predetermined biometric discrete values, the function value of the first risk coefficient function corresponding to each biometric discrete value is equal to the first risk coefficient corresponding to the biometric discrete value, and the function value of the second risk coefficient function corresponding to each biometric discrete value is equal to the second risk coefficient corresponding to the biometric discrete value;

[0138] The first risk coefficient function and the second risk coefficient function are made continuous, and the continuous function corresponding to the first risk coefficient function is used as the first corresponding relationship between the biometric threshold and the risk coefficient under the relevant indicator conditions, and the continuous function corresponding to the second risk coefficient function is used as the second corresponding relationship between the biometric threshold and the risk coefficient under the relevant indicator conditions.

[0139] In one embodiment, the biometric threshold correction module is specifically configured to:

[0140] Obtain the biometric threshold of the staff member stored in the bank server;

[0141] Determine the potential risk factor of the staff member based on the biometric threshold of the staff member, relevant indicators of the customer and the staff member, and a first correspondence between the biometric threshold and the risk factor under the relevant indicator conditions;

[0142] Determining a potential biometric threshold for the staff member based on the staff member's potential risk coefficient and a second corresponding relationship between the biometric threshold and the risk coefficient under the relevant indicator conditions;

[0143] Modify the biometric threshold of the staff member based on the potential biometric threshold of the staff member.

[0144] It should be noted that while the detailed description above mentions several modules of the bank's internal risk control system, this division is merely exemplary and not mandatory. In practice, depending on the 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.

[0145] Based on the above invention concept, 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, wherein the processor 720 implements the aforementioned method for controlling internal bank risks when executing the computer program 730.

[0146] 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 aforementioned method for controlling internal bank risks is implemented.

[0147] 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 controlling internal risks of a bank is implemented.

[0148] The method and device for controlling internal bank risks proposed in the present invention determine the relevant indicators of customers and staff; based on the relevant indicators of customers and staff, the first corresponding relationship between the biometric threshold and the risk coefficient under the pre-stored conditions of each relevant indicator, and the second corresponding relationship between the biometric threshold and the risk coefficient, the biometric threshold of the staff is corrected, so that when the customer needs the authorization of the staff to handle business at the branch, the internal risk of the bank is effectively controlled, the smooth handling of the customer's business is guaranteed, the safety of the customer's property is protected, and strong technical support is provided for the bank's digital risk control.

[0149] The acquisition, storage, use, and processing of data in this application's technical solution comply with relevant national laws and regulations.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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 controlling internal bank risks, characterized in that: include: When a customer conducts business at an outlet and requires staff review and authorization, determine the relevant indicators for the customer and the staff; Based on the relevant indicators of the customer and the staff member, the first correspondence between the biometric threshold and the risk factor under the pre-stored conditions of the relevant indicators, and the second correspondence between the biometric threshold and the risk factor, the staff member's biometric threshold is modified, wherein the biometric threshold is used to control the internal risk of business processing; Among them, determine the relevant indicators of the customer and the staff, including: Obtain an internal correlation graph, wherein each node of the internal correlation graph is a customer or staff member of the bank, each edge of the internal correlation graph corresponds to a correlation index, and the correlation index represents the degree of correlation between the two nodes corresponding to the edge, and the value of the correlation index is between 0 and 1; Determine the correlation indicators between the client and the staff member based on the internal correlation diagram; According to the internal correlation diagram, the relevant indicators between the customer and the staff member are determined, including: According to the internal correlation graph, the potential correlation index corresponding to each node that has a direct edge connection with the customer is initialized to the correlation index corresponding to the edge corresponding to the customer and the node in the internal correlation graph, and the potential correlation index corresponding to each node that has no direct edge connection with the customer is initialized to 0; The set consisting of all other nodes in the internal correlation graph except the customer is used as the set of nodes to be determined; Repeat the following steps until the relevant indicators between the customer and the staff member are determined: Take out the node S with the largest potential correlation index from the set of nodes to be determined; Determine whether the node S is the staff member; If the node S is the staff member, the correlation index between the customer and the staff member is determined as the potential correlation index corresponding to the node S, and the execution of the loop is stopped; For each node T that has a direct edge connection with node S, update the potential correlation index corresponding to node T to the maximum value of f(S)′r(S,T) and f(T), where f(T) is the potential correlation index corresponding to node T before the update, f(S) is the potential correlation index corresponding to node S, and r(S,T) is the correlation index corresponding to the edge between node S and node T in the internal correlation graph; Delete the node S from the set of nodes to be determined; The method also includes determining a first correspondence between the biometric identification threshold and the risk coefficient and a second correspondence between the biometric identification threshold and the risk coefficient under various relevant indicator conditions according to the following method: Obtain historical audit data of the bank; For each piece of historical audit data, the relevant indicators of the client and the corresponding staff member corresponding to the historical audit data are used as the relevant indicators corresponding to the historical audit data; For each relevant indicator, the corresponding relevant indicator equal to the historical audit data of the relevant indicator is used as the historical audit data of the relevant indicator; For each bank branch, select the historical audit data of each relevant indicator from the historical audit data of each relevant indicator; Determine the first bank branch and the second bank branch corresponding to the relevant indicator based on the historical audit data of each bank branch corresponding to the relevant indicator; Based on the historical audit data of the first bank branch corresponding to the relevant indicator, the first corresponding relationship between the biometric threshold and the risk coefficient under the relevant indicator conditions is determined, and based on the historical audit data of the second bank branch corresponding to the relevant indicator, the second corresponding relationship between the biometric threshold and the risk coefficient under the relevant indicator conditions is determined.

2. The method according to claim 1, wherein Based on the historical audit data of each bank branch corresponding to the relevant indicator, the first bank branch and the second bank branch corresponding to the relevant indicator are determined, including: Determine the audit risk coefficient of each bank branch for the relevant indicator based on the historical audit data of the relevant indicator for that bank branch; Determine the transaction risk coefficient of each bank branch based on the transaction data of each bank branch; Determining a partial order of bank branches, wherein the partial order is used to determine whether a first bank branch is superior to a second bank branch among any two bank branches; if the audit risk coefficient of the first bank branch corresponding to the relevant indicator is less than or equal to the audit risk coefficient of the second bank branch corresponding to the relevant indicator, and the transaction risk coefficient of the first bank branch is less than or equal to the transaction risk coefficient of the second bank branch, then the first bank branch is determined to be superior to the second bank branch in the partial order; According to the partial order of the bank branches, a first bank branch and a second bank branch corresponding to the relevant indicator are determined.

3. The method according to claim 1, wherein Based on the historical audit data of each bank branch corresponding to the relevant indicator, the first bank branch and the second bank branch corresponding to the relevant indicator are determined, including: Determine the audit risk coefficient of each bank branch for the relevant indicator based on the historical audit data of the relevant indicator for that bank branch; The bank branch whose audit risk coefficient corresponding to the relevant indicator is less than the coefficient threshold is used as the first bank branch corresponding to the relevant indicator, and the bank branch whose audit risk coefficient corresponding to the relevant indicator is greater than or equal to the coefficient threshold is used as the second bank branch corresponding to the relevant indicator.

4. The method according to claim 1, wherein Determining a first correspondence between the biometric identification threshold and the risk factor under the relevant indicator conditions based on historical audit data of the first bank branch corresponding to the relevant indicator, and determining a second correspondence between the biometric identification threshold and the risk factor under the relevant indicator conditions based on historical audit data of the second bank branch corresponding to the relevant indicator, including: Set multiple biometric discrete values; For each biometric discrete value, determine the proportion of audit data involving risk in the historical audit data corresponding to the relevant indicator at the first bank branch corresponding to the relevant indicator when the biometric threshold is set to the biometric discrete value, and use this proportion as the first risk coefficient corresponding to the biometric discrete value; determine the proportion of audit data involving risk in the historical audit data corresponding to the relevant indicator at the second bank branch corresponding to the relevant indicator when the biometric threshold is set to the biometric discrete value, and use this proportion as the second risk coefficient corresponding to the biometric discrete value; Constructing a first risk coefficient function and a second risk coefficient function, wherein the independent variables of the first risk coefficient function and the second risk coefficient function are a plurality of predetermined biometric discrete values, the function value of the first risk coefficient function corresponding to each biometric discrete value is equal to the first risk coefficient corresponding to the biometric discrete value, and the function value of the second risk coefficient function corresponding to each biometric discrete value is equal to the second risk coefficient corresponding to the biometric discrete value; The first risk coefficient function and the second risk coefficient function are made continuous, and the continuous function corresponding to the first risk coefficient function is used as the first corresponding relationship between the biometric threshold and the risk coefficient under the relevant indicator conditions, and the continuous function corresponding to the second risk coefficient function is used as the second corresponding relationship between the biometric threshold and the risk coefficient under the relevant indicator conditions.

5. The method according to claim 1, wherein Based on the relevant indicators of the customer and the staff member, the first correspondence between the biometric threshold and the risk factor under the pre-stored conditions of the relevant indicators, and the second correspondence between the biometric threshold and the risk factor, the staff member's biometric threshold is modified, including: Obtain the biometric threshold of the staff member stored in the bank server; Determine the potential risk factor of the staff member based on the biometric threshold of the staff member, relevant indicators of the customer and the staff member, and a first correspondence between the biometric threshold and the risk factor under the relevant indicator conditions; Determining a potential biometric threshold for the staff member based on the staff member's potential risk coefficient and a second corresponding relationship between the biometric threshold and the risk coefficient under the relevant indicator conditions; Modify the biometric threshold of the staff member based on the potential biometric threshold of the staff member.

6. A bank internal risk control device, characterized in that: include: The relevant indicator determination module is used to determine the relevant indicators between a customer and a staff member when a customer conducts business at a branch and requires staff review and authorization; A biometric threshold correction module, configured to correct the biometric threshold of the staff member based on relevant indicators of the customer and the staff member, a first correspondence between the biometric threshold and the risk factor under various pre-stored relevant indicator conditions, and a second correspondence between the biometric threshold and the risk factor, wherein the biometric threshold is used to control internal risks in business processing; Among them, the relevant indicator determination module is specifically used to: Obtain an internal correlation graph, wherein each node of the internal correlation graph is a customer or staff member of the bank, each edge of the internal correlation graph corresponds to a correlation index, and the correlation index represents the degree of correlation between the two nodes corresponding to the edge, and the value of the correlation index is between 0 and 1; Determine the correlation indicators between the client and the staff member based on the internal correlation diagram; Among them, the relevant indicator determination module is specifically used to: According to the internal correlation graph, the potential correlation index corresponding to each node that has a direct edge connection with the customer is initialized to the correlation index corresponding to the edge corresponding to the customer and the node in the internal correlation graph, and the potential correlation index corresponding to each node that has no direct edge connection with the customer is initialized to 0; The set consisting of all other nodes in the internal correlation graph except the customer is used as the set of nodes to be determined; Repeat the following steps until the relevant indicators between the customer and the staff member are determined: Take out the node S with the largest potential correlation index from the set of nodes to be determined; Determine whether the node S is the staff member; If the node S is the staff member, the correlation index between the customer and the staff member is determined as the potential correlation index corresponding to the node S, and the execution of the loop is stopped; For each node T that has a direct edge connection with node S, update the potential correlation index corresponding to node T to the maximum value of f(S)′r(S,T) and f(T), where f(T) is the potential correlation index corresponding to node T before the update, f(S) is the potential correlation index corresponding to node S, and r(S,T) is the correlation index corresponding to the edge between node S and node T in the internal correlation graph; Delete the node S from the set of nodes to be determined; Among them, it also includes: a corresponding relationship determination module; The corresponding relationship determination module determines the first corresponding relationship between the biometric identification threshold and the risk coefficient and the second corresponding relationship between the biometric identification threshold and the risk coefficient under each relevant indicator condition according to the following method: Obtain historical audit data of the bank; For each piece of historical audit data, the relevant indicators of the client and the corresponding staff member corresponding to the historical audit data are used as the relevant indicators corresponding to the historical audit data; For each relevant indicator, the corresponding relevant indicator equal to the historical audit data of the relevant indicator is used as the historical audit data of the relevant indicator; For each bank branch, select the historical audit data of each relevant indicator from the historical audit data of each relevant indicator; Determine the first bank branch and the second bank branch corresponding to the relevant indicator based on the historical audit data of each bank branch corresponding to the relevant indicator; Based on the historical audit data of the first bank branch corresponding to the relevant indicator, the first corresponding relationship between the biometric threshold and the risk coefficient under the relevant indicator conditions is determined, and based on the historical audit data of the second bank branch corresponding to the relevant indicator, the second corresponding relationship between the biometric threshold and the risk coefficient under the relevant indicator conditions is determined.

7. The device according to claim 6, characterized in that The corresponding relationship determination module is specifically used for: Determine the audit risk coefficient of each bank branch for the relevant indicator based on the historical audit data of the relevant indicator for that bank branch; Determine the transaction risk coefficient of each bank branch based on the transaction data of each bank branch; Determining a partial order of bank branches, wherein the partial order is used to determine whether a first bank branch is superior to a second bank branch among any two bank branches; if the audit risk coefficient of the first bank branch corresponding to the relevant indicator is less than or equal to the audit risk coefficient of the second bank branch corresponding to the relevant indicator, and the transaction risk coefficient of the first bank branch is less than or equal to the transaction risk coefficient of the second bank branch, then the first bank branch is determined to be superior to the second bank branch in the partial order; According to the partial order of the bank branches, a first bank branch and a second bank branch corresponding to the relevant indicator are determined.

8. The device according to claim 6, wherein The corresponding relationship determination module is specifically used for: Determine the audit risk coefficient of each bank branch for the relevant indicator based on the historical audit data of the relevant indicator for that bank branch; The bank branch whose audit risk coefficient corresponding to the relevant indicator is less than the coefficient threshold is used as the first bank branch corresponding to the relevant indicator, and the bank branch whose audit risk coefficient corresponding to the relevant indicator is greater than or equal to the coefficient threshold is used as the second bank branch corresponding to the relevant indicator.

9. The device according to claim 6, wherein The corresponding relationship determination module is specifically used for: Set multiple biometric discrete values; For each biometric discrete value, determine the proportion of risk-related audit data in the historical audit data of the first bank branch corresponding to the relevant indicator when the biometric threshold is set to the biometric discrete value, and use the proportion as the first risk coefficient corresponding to the biometric discrete value; Determine the proportion of risk-related audit data in the historical audit data of the second bank branch corresponding to the relevant indicator when the biometric threshold is set to the biometric discrete value, and use the proportion as the second risk coefficient corresponding to the biometric discrete value; Constructing a first risk coefficient function and a second risk coefficient function, wherein the independent variables of the first risk coefficient function and the second risk coefficient function are a plurality of predetermined biometric discrete values, the function value of the first risk coefficient function corresponding to each biometric discrete value is equal to the first risk coefficient corresponding to the biometric discrete value, and the function value of the second risk coefficient function corresponding to each biometric discrete value is equal to the second risk coefficient corresponding to the biometric discrete value; The first risk coefficient function and the second risk coefficient function are made continuous, and the continuous function corresponding to the first risk coefficient function is used as the first corresponding relationship between the biometric threshold and the risk coefficient under the relevant indicator conditions, and the continuous function corresponding to the second risk coefficient function is used as the second corresponding relationship between the biometric threshold and the risk coefficient under the relevant indicator conditions.

10. The device according to claim 6, wherein The biometric threshold correction module is specifically used to: Obtain the biometric threshold of the staff member stored in the bank server; Determine the potential risk factor of the staff member based on the biometric threshold of the staff member, relevant indicators of the customer and the staff member, and a first correspondence between the biometric threshold and the risk factor under the relevant indicator conditions; Determining a potential biometric threshold for the staff member based on the staff member's potential risk coefficient and a second corresponding relationship between the biometric threshold and the risk coefficient under the relevant indicator conditions; Modify the biometric threshold of the staff member based on the potential biometric threshold of the staff member.

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