Method and device for determining bank auditors

Abstract

The present invention proposes a method and device for determining bank auditors, which relate to the field of data processing technology. The method comprises: obtaining audit data of banks within a predetermined range, determining a user vector and a corresponding business vector corresponding to each auditor; classifying the auditors within the predetermined range based on the user vectors and the business vectors to obtain multiple auditor categories; for each user category, obtaining the audit data of the user category, and determining the risk indicators of each auditor category when auditing the business data of the user category; when a user conducts business at a bank and an auditor is required to conduct an audit, determining the auditor category corresponding to each auditor to be selected; and determining the auditor for this audit based on the risk indicators of each auditor category when auditing the business data of the user category to which the user belongs, as well as the auditor category to which each auditor to be selected belongs.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a method and device for determining bank auditors. 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 actual business operations, banks need to review certain business data to control risks, such as loan operations and account opening operations. However, the current allocation of reviewers lacks a data basis, which may lead to risks.

[0004] In summary, there is an urgent need for a technical solution that can overcome the above-mentioned defects and allocate auditors through data analysis. 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 bank auditors.

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

[0007] Obtain audit data of banks within a predetermined range and determine the user vector and business vector corresponding to each auditor;

[0008] Based on the user vector and the business vector, the auditors within the predetermined range are classified to obtain multiple auditor categories;

[0009] For each user category, obtain the audit data for that user category and determine the risk indicators for each audit staff category when auditing the business data of that user category;

[0010] When a user conducts business at a bank and requires an auditor to conduct an audit, the auditor category corresponding to each auditor to be selected is determined;

[0011] The auditors for this audit are determined based on the risk indicators of each auditor category when auditing the business data of the user category to which the user belongs, and the auditor category to which each auditor to be selected belongs.

[0012] In a second aspect of an embodiment of the present invention, a device for determining a bank auditor is provided, comprising:

[0013] A vector determination module is used to obtain audit data of banks within a predetermined range and determine the user vector and business vector corresponding to each auditor;

[0014] A classification module is used to classify auditors within a predetermined range based on user vectors and business vectors to obtain multiple auditor categories;

[0015] A risk indicator determination module is used to obtain the audit data of each user category and determine the risk indicators of each audit personnel category when auditing the business data of the user category;

[0016] The auditor category determination module is used to determine the auditor category corresponding to each auditor to be selected when a user conducts business in a bank and requires an auditor to conduct an audit;

[0017] The auditor determination module is used to determine the auditor for this audit based on the risk indicators of the business data of the user category to which the user belongs when each auditor category audits the user, and the auditor category to which each auditor to be selected belongs.

[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 bank auditors 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 bank auditor 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, and when the computer program is executed by a processor, a method for determining a bank auditor is implemented.

[0021] The method and device for determining bank auditors proposed in the present invention obtain the audit data of the bank within a predetermined range to determine the user vector and the corresponding business vector corresponding to each auditor; classify the auditors within the predetermined range based on the user vector and the business vector to obtain multiple auditor categories; for each user category, obtain the audit data of the user category, and determine the risk indicators of each auditor category when auditing the business data of the user category; when a user handles business in the bank and an auditor is required to conduct an audit, determine the auditor category corresponding to each auditor to be selected; determine the auditor for this audit based on the risk indicators of each auditor category when auditing the business data of the user category to which the user belongs, and the auditor category to which each auditor to be selected belongs. The overall solution of the present invention can determine the auditor who is more suitable for auditing the user's business handling this time by analyzing the relevant data of the auditor, thereby effectively controlling the bank's business risks, ensuring the safe conduct of bank business, and providing strong technical support for the bank's digital risk control. 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 bank auditors according to an embodiment of the present invention.

[0024] Figure 2 This is a schematic diagram of a specific process of determining the user vector and the business vector corresponding to each reviewer according to an embodiment of the present invention.

[0025] Figure 3 This is a flowchart of classifying reviewers within a predetermined range according to an embodiment of the present invention.

[0026] Figure 4 This is a schematic diagram of a specific process for determining risk indicators when each reviewer category reviews business data of a user category according to an embodiment of the present invention.

[0027] Figure 5 It is a schematic diagram of a specific process of determining the reviewer category corresponding to each reviewer to be selected according to an embodiment of the present invention.

[0028] Figure 6 This is a flowchart of determining the reviewer for this review according to an embodiment of the present invention.

[0029] Figure 7FIG. 4 is a schematic diagram of the apparatus architecture for determining bank auditors according to an embodiment of the present invention.

[0030] Figure 8 It is a schematic diagram of the structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0031] 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.

[0032] 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.

[0033] According to an embodiment of the present invention, a method and device for determining bank auditors are proposed, which relate to the field of data processing technology.

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

[0035] Figure 1 FIG. 1 is a flow chart of a method for determining bank auditors according to an embodiment of the present invention. Figure 1 As shown, the method includes:

[0036] S1, obtaining audit data of banks within a predetermined range and determining the user vector and business vector corresponding to each auditor;

[0037] S2, classifying the reviewers within a predetermined range according to the user vector and the business vector to obtain multiple reviewer categories;

[0038] S3, for each user category, obtaining the audit data of the user category and determining the risk indicators when each audit personnel category audits the business data of the user category;

[0039] S4, when a user conducts business at a bank and requires an auditor to conduct an audit, determining the auditor category corresponding to each auditor to be selected;

[0040] S5, determining the auditors for this audit based on the risk indicators of each auditor category when auditing the business data of the user category to which the user belongs, and the auditor category to which each auditor to be selected belongs.

[0041] The overall solution of the present invention can analyze the relevant data of the auditors to determine the auditors who are more suitable for auditing the user's business processing, thereby effectively controlling the bank's business risks, ensuring the safe conduct of banking business, and providing strong technical support for the bank's digital risk control.

[0042] In order to explain the above method of determining bank auditors more clearly, each step is explained in detail below.

[0043] In S1, ref. Figure 2 , the specific method for obtaining the audit data of banks within a predetermined range and determining the user vector and business vector corresponding to each auditor is as follows:

[0044] S101, for each auditor, extract the audit data corresponding to the auditor from the audit data of banks within a predetermined range, determine the number of users belonging to each user category among all users corresponding to the audit data, and use the number of users as the number of user categories corresponding to the auditor;

[0045] S102, for each reviewer, determining a user vector corresponding to the reviewer, wherein the components of the user vector correspond one-to-one to the user categories, and the component value of each component is equal to the number of user categories corresponding to the reviewer;

[0046] S103, for each auditor, determine the business vector corresponding to the auditor, wherein the components of the business vector correspond one-to-one to the business that the bank needs to audit, and the component value of each component is equal to the business volume of the business corresponding to the component in the audit data corresponding to the auditor.

[0047] In S2, reference Figure 3 ,According to the user vector and business vector, the auditors within the predetermined range are classified, and the specific method for obtaining multiple auditor categories is as follows:

[0048] S201, determining a user distance function for the auditors, and determining a business distance function for the auditors, wherein the user distance function is used to determine the distance between any two auditors as the distance between the user vectors of the two auditors, and the business distance function is used to determine the distance between any two auditors as the distance between the business vectors of the two auditors;

[0049] S202 , performing cluster analysis on the auditors within a predetermined range based on the user distance function and the business distance function of the auditors, and obtaining a plurality of auditor categories.

[0050] In one embodiment, (S202) cluster analysis is performed on the auditors within a predetermined range based on the user distance function and the business distance function of the auditors to obtain multiple categories of auditors, including:

[0051] Based on the user distance function of the auditors, (select a clustering algorithm, such as K-means, or select learning vector quantization based on risk level as the category identifier) cluster analysis of auditors within a predetermined range to obtain multiple subsets of auditors;

[0052] For each obtained subset of auditors, determine the risk level of each auditor in the subset of auditors and the maximum value of the ratio of the number of auditors corresponding to each risk level in the subset of auditors;

[0053] The following steps are executed repeatedly until the maximum value of the ratio of the number of reviewers corresponding to each risk level in all reviewer subsets is greater than or equal to the set consistency threshold:

[0054] Selecting a subset of reviewers, wherein the maximum value of the ratio of the number of reviewers corresponding to each risk level in the subset of reviewers is less than a set consistency threshold;

[0055] Performing cluster analysis on all auditors in the auditor subset according to the business distance function of the auditors, and replacing the auditor subset with multiple new auditor subsets obtained;

[0056] When the maximum value of the ratio of the number of auditors corresponding to each risk level in all auditor subsets is greater than or equal to the set consistency threshold, each auditor subset is regarded as an auditor category.

[0057] In S3, reference Figure 4 For each user category, the specific method for obtaining the audit data of the user category and determining the risk indicators of each audit personnel category when auditing the business data of the user category is as follows:

[0058] S301, for each user category, extracting audit data of each audit staff category for each user category from the audit data of the user category;

[0059] S302, for each reviewer category, dividing the extracted review data of the reviewer category reviewing the user category into multiple review data subsets;

[0060] S303, using the proportion of risk audit data in each audit data subset as a risk indicator sample when the audit personnel of the audit category audits the business data of the user category;

[0061] S304 : Determine the risk indicator when the reviewer class reviews the business data of the user class as the mean value of the risk indicator samples when the reviewer class reviews the business data of the user class.

[0062] In one embodiment, after determining the risk indicator of each reviewer category when reviewing the business data of the user category as the mean of the risk indicator samples of each reviewer category when reviewing the business data of the user category, the risk variance and the number of risk samples of each reviewer category when reviewing the business data of the user category are determined based on the risk indicator samples of each reviewer category when reviewing the business data of the user category (the variance and the number of risk samples are determined based on samples of the same distribution);

[0063] For each reviewer category, the ratio of the square of the risk variance when the reviewer category reviews the business data of the user category to the number of risk samples is used as the upper bound of the risk indicator error when the reviewer category reviews the business data of the user category.

[0064] In S4, ref. Figure 5 When a user conducts business at a bank and requires an auditor to conduct an audit, the specific method for determining the auditor category corresponding to each auditor to be selected is as follows:

[0065] S401: When the candidate auditor does not belong to any auditor category, determine the user vector and business vector corresponding to the candidate auditor based on the audit data corresponding to the candidate auditor, wherein the components of the user vector correspond one-to-one to the user categories, and the value of each component of the user vector is equal to the number of users belonging to the user category corresponding to the component among all users corresponding to the audit data; the components of the business vector correspond one-to-one to the businesses that the bank needs to audit, and the value of each component of the business vector is equal to the business volume of the business corresponding to the component in the audit data corresponding to the auditor;

[0066] S402: Determine a partial order of the auditors based on the user vectors and business vectors corresponding to the auditors within the predetermined range and the user vector and business vector corresponding to the auditor to be selected, wherein the partial order is used to determine whether the first auditor is closer to the second auditor among any two auditors within the predetermined range;

[0067] S403, selecting reference auditors from the auditors within a predetermined range based on the partial order of the auditors, wherein for each reference auditor, there is no other auditor other than the reference auditor among the auditors within the predetermined range such that the other auditor is closer to the reference auditor;

[0068] S404: Determine the auditor category corresponding to the auditor to be selected based on the reference auditors.

[0069] In one embodiment, (S402) determining the partial order of the reviewers based on the user vectors and business vectors corresponding to the reviewers within the predetermined range and the user vectors and business vectors corresponding to the reviewer to be selected includes:

[0070] S4021, for each auditor within the predetermined range, determining the distance between the user vector of the candidate auditor and the user vector of the auditor as the user distance corresponding to the auditor, and determining the distance between the business vector of the candidate auditor and the business vector of the auditor as the business distance corresponding to the auditor;

[0071] S4022, for any two reviewers within the predetermined range, if the user distance of the first reviewer of the two reviewers is less than or equal to the user distance of the second reviewer of the two reviewers, and the business distance of the first reviewer of the two reviewers is less than or equal to the business distance of the second reviewer of the two reviewers, then it is determined that the first reviewer is closer to the second reviewer.

[0072] In S5, reference Figure 6 Based on the risk indicators of each auditor category when reviewing the business data of the user category to which the user belongs, and the auditor category to which each auditor to be selected belongs, the specific method for determining the auditor for this audit is as follows:

[0073] S501, determining the priority probability corresponding to each candidate reviewer based on the risk indicators of each reviewer category when reviewing the business data of the user category to which the user belongs, and the reviewer category to which each candidate reviewer belongs;

[0074] S502: Determine the auditor for this audit based on the priority probabilities corresponding to the auditors to be selected.

[0075] In one embodiment, (S501) determining the priority probability corresponding to each candidate reviewer based on the risk indicators of each reviewer category when reviewing the business data of the user category to which the user belongs, and the reviewer category to which each candidate reviewer belongs, includes:

[0076] The priority probability corresponding to each candidate auditor is determined based on the risk index, the upper bound of the risk index error, and the auditor category to which each candidate auditor belongs when auditing the business data of the user category to which the user belongs, and the auditor category to which each candidate auditor belongs.

[0077] For example, the priority probability corresponding to each reviewer to be selected is determined according to the following formula:

[0078]

[0079] Among them, r i is the priority probability corresponding to the i-th auditor to be selected, s i and t i are the risk index and the upper bound of the risk index error when the audit category of the i-th audit personnel to be selected audits the business data of the user category to which the user belongs. f1 is a real-valued function with a range greater than 0, and is a monotonically decreasing function of the first independent variable and a monotonically decreasing function of the second independent variable. (For example, ) The f1 here is to distinguish it from the continuous function f that follows, so the subscript 1 is added.

[0080] In one embodiment, (S502) determining the auditor for this audit based on the priority probabilities corresponding to the auditors to be selected includes:

[0081] S5021, selecting a continuous function f and determining an integral value c of the continuous function f, wherein the range of f is greater than 0;

[0082] S5022: Divide the domain of the continuous function f into a plurality of mutually non-overlapping intervals, where each interval corresponds to a candidate auditor, and the integral value of the continuous function f in each interval is equal to the product of the priority probability corresponding to the candidate auditor corresponding to the interval and c;

[0083] S5023, function-based Generate a random number and determine the interval in which the random number lies;

[0084] S5024: Determine the auditor for this audit as the auditor to be selected corresponding to the interval in which the random number is located.

[0085] It needs to be explained that the function The integral value of is 1, so the function One is the probability density function, based on the function Generating random numbers means generating random numbers based on the distribution corresponding to the probability density function.

[0086] 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.

[0087] After introducing the method of the exemplary embodiment of the present invention, next, reference is made to Figure 7 An apparatus for determining bank auditors according to an exemplary embodiment of the present invention is introduced.

[0088] The implementation of the device for determining bank auditors can be referenced to the implementation of the aforementioned method, and any repetitive details 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 in hardware, or a combination of software and hardware, is also possible and contemplated.

[0089] Based on the same inventive concept, the present invention also proposes a device for determining bank auditors, such as Figure 7 As shown, the device includes:

[0090] Vector determination module 710, for obtaining audit data of banks within a predetermined range and determining the user vector and business vector corresponding to each auditor;

[0091] A classification module 720 is used to classify reviewers within a predetermined range according to the user vector and the business vector to obtain multiple reviewer categories;

[0092] The risk indicator determination module 730 is used to obtain the audit data of each user category and determine the risk indicators of each audit personnel category when auditing the business data of the user category;

[0093] The reviewer category determination module 740 is used to determine the reviewer category corresponding to each reviewer to be selected when a user conducts business at a bank and requires review by a reviewer;

[0094] The auditor determination module 750 is used to determine the auditor for this audit based on the risk indicators of each auditor category when auditing the business data of the user category to which the user belongs, and the auditor category to which each auditor to be selected belongs.

[0095] In one embodiment, the vector determination module is specifically configured to:

[0096] For each auditor, extract the audit data corresponding to the auditor from the audit data of banks within a predetermined range, determine the number of users belonging to each user category among all users corresponding to the audit data, and use the number of users as the number of user categories corresponding to the auditor;

[0097] For each auditor, determine the user vector corresponding to the auditor, wherein the components of the user vector correspond one-to-one to the user categories, and the component value of each component is equal to the number of user categories corresponding to the auditor;

[0098] For each auditor, the business vector corresponding to the auditor is determined, wherein the components of the business vector correspond one-to-one to the business that the bank needs to audit, and the component value of each component is equal to the business volume of the business corresponding to the component in the audit data corresponding to the auditor.

[0099] In one embodiment, the classification module is specifically configured to:

[0100] Determine a user distance function for the auditors, and determine a business distance function for the auditors, wherein the user distance function is used to determine the distance between any two auditors as the distance between the user vectors of the two auditors, and the business distance function is used to determine the distance between any two auditors as the distance between the business vectors of the two auditors;

[0101] Based on the user distance function and business distance function of the auditors, cluster analysis is performed on the auditors within a predetermined range to obtain multiple auditor categories.

[0102] In one embodiment, the risk indicator determination module is specifically configured to:

[0103] For each user category, the audit data of each audit staff category auditing the user category is extracted from the audit data of the user category;

[0104] For each reviewer category, the extracted review data of the reviewer category reviewing the user category is divided into multiple review data subsets;

[0105] The proportion of risk audit data in each audit data subset is used as a risk indicator sample when the auditor category audits the business data of the user category;

[0106] The risk indicator when the reviewer category reviews the business data of the user category is determined as the mean of the risk indicator samples when the reviewer category reviews the business data of the user category.

[0107] In one embodiment, the reviewer category determination module is specifically configured to:

[0108] When the candidate auditor does not belong to any auditor category, a user vector and a corresponding business vector corresponding to the candidate auditor are determined based on the audit data corresponding to the candidate auditor, wherein the components of the user vector correspond one-to-one to the user categories, and the component value of each component of the user vector is equal to the number of users belonging to the user category corresponding to the component among all users corresponding to the audit data; the components of the business vector correspond one-to-one to the businesses that the bank needs to audit, and the component value of each component of the business vector is equal to the business volume of the business corresponding to the component in the audit data corresponding to the auditor;

[0109] Determining a partial order of the auditors based on the user vectors and business vectors corresponding to the auditors within the predetermined range and the user vector and business vector corresponding to the auditor to be selected, wherein the partial order is used to determine whether the first auditor is closer to the second auditor among any two auditors within the predetermined range;

[0110] Selecting reference auditors from among the auditors within a predetermined range according to the partial order of the auditors, wherein, for each reference auditor, there is no other auditor other than the reference auditor among the auditors within the predetermined range such that the other auditor is closer to the reference auditor;

[0111] Based on the reference auditors, determine the auditor category corresponding to the auditor to be selected.

[0112] In one embodiment, the reviewer category determination module is specifically configured to:

[0113] For each auditor within the predetermined range, the distance between the user vector of the candidate auditor and the user vector of the auditor is determined as the user distance corresponding to the auditor, and the distance between the business vector of the candidate auditor and the business vector of the auditor is determined as the business distance corresponding to the auditor;

[0114] For any two reviewers within the predetermined range, if the user distance of the first reviewer of the two reviewers is less than or equal to the user distance of the second reviewer of the two reviewers, and the business distance of the first reviewer of the two reviewers is less than or equal to the business distance of the second reviewer of the two reviewers, then the first reviewer is determined to be closer to the second reviewer.

[0115] In one embodiment, the auditor determines that the module is specifically configured to:

[0116] Determine the priority probability corresponding to each candidate auditor based on the risk indicators of each auditor category when auditing the business data of the user category to which the user belongs, and the auditor category to which each candidate auditor belongs;

[0117] The auditors for this audit are determined based on the priority probabilities corresponding to the auditors to be selected.

[0118] In one embodiment, the auditor determines that the module is specifically configured to:

[0119] Select a continuous function f and determine the integral value c of the continuous function f, where the range of f is greater than 0;

[0120] The domain of the continuous function f is divided into multiple non-intersecting intervals, each of which corresponds to a candidate auditor. The integral value of the continuous function f in each interval is equal to the product of the priority probability corresponding to the candidate auditor corresponding to the interval and c;

[0121] Function-based Generate a random number and determine the interval in which the random number lies;

[0122] The auditor for this audit is determined to be the auditor to be selected corresponding to the interval in which the random number is located.

[0123] It should be noted that while the above detailed description mentions several modules of the apparatus for determining bank auditors, 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.

[0124] Based on the above invention concept, Figure 8 As shown, the present invention also proposes a computer device 800, including a memory 810, a processor 820 and a computer program 830 stored in the memory 810 and executable on the processor 820, wherein the processor 820 implements the aforementioned method for determining bank auditors when executing the computer program 830.

[0125] 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 bank auditors is implemented.

[0126] 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 bank auditor is implemented.

[0127] The method and device for determining bank auditors proposed in the present invention obtain the audit data of the bank within a predetermined range to determine the user vector and the corresponding business vector corresponding to each auditor; classify the auditors within the predetermined range based on the user vector and the business vector to obtain multiple auditor categories; for each user category, obtain the audit data of the user category, and determine the risk indicators of each auditor category when auditing the business data of the user category; when a user handles business in the bank and an auditor is required to conduct an audit, determine the auditor category corresponding to each auditor to be selected; determine the auditor for this audit based on the risk indicators of each auditor category when auditing the business data of the user category to which the user belongs, and the auditor category to which each auditor to be selected belongs. The overall solution of the present invention can determine the auditor who is more suitable for auditing the user's business handling this time by analyzing the relevant data of the auditor, thereby effectively controlling the bank's business risks, ensuring the safe conduct of bank business, and providing strong technical support for the bank's digital risk control.

[0128] 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.

[0129] 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.

[0130] 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.

[0131] 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.

[0132] 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 bank auditors, characterized in that: include: Obtain audit data of banks within a predetermined range and determine the user vector and business vector corresponding to each auditor; Based on the user vector and the business vector, the auditors within the predetermined range are classified to obtain multiple auditor categories; For each user category, obtain the audit data for that user category and determine the risk indicators for each audit staff category when auditing the business data of that user category; When a user conducts business at a bank and requires an auditor to conduct an audit, the auditor category corresponding to each auditor to be selected is determined; Determine the auditor for this audit based on the risk indicators of each auditor category when auditing the business data of the user category to which the user belongs, and the auditor category to which each of the audit candidates belongs; For each user category, the audit data for that user category is obtained, and the risk indicators for each audit personnel category when auditing the business data of that user category are determined, including: For each user category, the audit data of each audit staff category auditing the user category is extracted from the audit data of the user category; For each reviewer category, the extracted review data of the reviewer category reviewing the user category is divided into multiple review data subsets; The proportion of risk audit data in each audit data subset is used as a risk indicator sample when the auditor category audits the business data of the user category; The risk indicator when the reviewer category reviews the business data of the user category is determined as the mean of the risk indicator sample when the reviewer category reviews the business data of the user category; Among them, when a user conducts business at a bank and requires an auditor to conduct an audit, the auditor category corresponding to each auditor to be selected is determined, including: When the candidate auditor does not belong to any auditor category, a user vector and a corresponding business vector corresponding to the candidate auditor are determined based on the audit data corresponding to the candidate auditor, wherein the components of the user vector correspond one-to-one to the user categories, and the component value of each component of the user vector is equal to the number of users belonging to the user category corresponding to the component among all users corresponding to the audit data; the components of the business vector correspond one-to-one to the businesses that the bank needs to audit, and the component value of each component of the business vector is equal to the business volume of the business corresponding to the component in the audit data corresponding to the auditor; Determining a partial order of the auditors based on the user vectors and business vectors corresponding to the auditors within the predetermined range and the user vector and business vector corresponding to the auditor to be selected, wherein the partial order is used to determine whether the first auditor is closer to the second auditor among any two auditors within the predetermined range; Selecting reference auditors from among the auditors within a predetermined range according to the partial order of the auditors, wherein, for each reference auditor, there is no other auditor other than the reference auditor among the auditors within the predetermined range such that the other auditor is closer to the reference auditor; Based on the reference auditors, determine the auditor category corresponding to the auditor to be selected.

2. The method according to claim 1, wherein Obtain audit data for banks within a predetermined range and determine the user vector and business vector corresponding to each auditor, including: For each auditor, extract the audit data corresponding to the auditor from the audit data of banks within a predetermined range, determine the number of users belonging to each user category among all users corresponding to the audit data, and use the number of users as the number of user categories corresponding to the auditor; For each auditor, determine the user vector corresponding to the auditor, wherein the components of the user vector correspond one-to-one to the user categories, and the component value of each component is equal to the number of user categories corresponding to the auditor; For each auditor, the business vector corresponding to the auditor is determined, wherein the components of the business vector correspond one-to-one to the business that the bank needs to audit, and the component value of each component is equal to the business volume of the business corresponding to the component in the audit data corresponding to the auditor.

3. The method according to claim 1, wherein Based on the user vector and business vector, the auditors within the predetermined range are classified to obtain multiple auditor categories, including: Determine a user distance function for the auditors, and determine a business distance function for the auditors, wherein the user distance function is used to determine the distance between any two auditors as the distance between the user vectors of the two auditors, and the business distance function is used to determine the distance between any two auditors as the distance between the business vectors of the two auditors; Based on the user distance function and business distance function of the auditors, cluster analysis is performed on the auditors within a predetermined range to obtain multiple auditor categories.

4. The method according to claim 1, wherein Determining the partial order of the auditors based on the user vectors and business vectors corresponding to the auditors within the predetermined range and the user vectors and business vectors corresponding to the auditor to be selected includes: For each auditor within the predetermined range, the distance between the user vector of the candidate auditor and the user vector of the auditor is determined as the user distance corresponding to the auditor, and the distance between the business vector of the candidate auditor and the business vector of the auditor is determined as the business distance corresponding to the auditor; For any two reviewers within the predetermined range, if the user distance of the first reviewer of the two reviewers is less than or equal to the user distance of the second reviewer of the two reviewers, and the business distance of the first reviewer of the two reviewers is less than or equal to the business distance of the second reviewer of the two reviewers, then the first reviewer is determined to be closer to the second reviewer.

5. The method according to claim 1, wherein The auditors for this audit are determined based on the risk indicators of the business data of the user category to which the user belongs when each auditor category reviews the user, as well as the auditor categories to which each auditor to be selected belongs, including: Determine the priority probability corresponding to each candidate auditor based on the risk indicators of each auditor category when auditing the business data of the user category to which the user belongs, and the auditor category to which each candidate auditor belongs; The auditors for this audit are determined based on the priority probabilities corresponding to the auditors to be selected.

6. The method according to claim 5, wherein The auditors for this audit are determined based on the priority probabilities of the auditors to be selected, including: Select a continuous function f and determine the integral value c of the continuous function f, where the range of f is greater than 0; The domain of the continuous function f is divided into multiple non-intersecting intervals, each of which corresponds to a candidate auditor. The integral value of the continuous function f in each interval is equal to the product of the priority probability corresponding to the candidate auditor corresponding to the interval and c; Function-based Generate a random number and determine the interval in which the random number lies; The auditor for this audit is determined to be the auditor to be selected corresponding to the interval in which the random number is located.

7. A device for determining bank auditors, characterized in that: include: A vector determination module is used to obtain audit data of banks within a predetermined range and determine the user vector and business vector corresponding to each auditor; A classification module is used to classify auditors within a predetermined range based on user vectors and business vectors to obtain multiple auditor categories; A risk indicator determination module is used to obtain the audit data of each user category and determine the risk indicators of each audit personnel category when auditing the business data of the user category; The auditor category determination module is used to determine the auditor category corresponding to each auditor to be selected when a user conducts business in a bank and requires an auditor to conduct an audit; The auditor determination module is used to determine the auditor for this audit based on the risk indicators of the business data of the user category to which the user belongs when each auditor category is audited, as well as the auditor category to which each candidate auditor belongs; The risk indicator determination module is specifically used to: For each user category, the audit data of each audit staff category auditing the user category is extracted from the audit data of the user category; For each reviewer category, the extracted review data of the reviewer category reviewing the user category is divided into multiple review data subsets; The proportion of risk audit data in each audit data subset is used as a risk indicator sample when the auditor category audits the business data of the user category; The risk indicator when the reviewer category reviews the business data of the user category is determined as the mean of the risk indicator sample when the reviewer category reviews the business data of the user category; Among them, the auditor category determination module is specifically used to: When the candidate auditor does not belong to any auditor category, a user vector and a corresponding business vector corresponding to the candidate auditor are determined based on the audit data corresponding to the candidate auditor, wherein the components of the user vector correspond one-to-one to the user categories, and the component value of each component of the user vector is equal to the number of users belonging to the user category corresponding to the component among all users corresponding to the audit data; the components of the business vector correspond one-to-one to the businesses that the bank needs to audit, and the component value of each component of the business vector is equal to the business volume of the business corresponding to the component in the audit data corresponding to the auditor; Determining a partial order of the auditors based on the user vectors and business vectors corresponding to the auditors within the predetermined range and the user vector and business vector corresponding to the auditor to be selected, wherein the partial order is used to determine whether the first auditor is closer to the second auditor among any two auditors within the predetermined range; Selecting reference auditors from among the auditors within a predetermined range according to the partial order of the auditors, wherein, for each reference auditor, there is no other auditor other than the reference auditor among the auditors within the predetermined range such that the other auditor is closer to the reference auditor; Based on the reference auditors, determine the auditor category corresponding to the auditor to be selected.

8. The device according to claim 7, wherein The vector determination module is specifically used for: For each auditor, extract the audit data corresponding to the auditor from the audit data of banks within a predetermined range, determine the number of users belonging to each user category among all users corresponding to the audit data, and use the number of users as the number of user categories corresponding to the auditor; For each auditor, determine the user vector corresponding to the auditor, wherein the components of the user vector correspond one-to-one to the user categories, and the component value of each component is equal to the number of user categories corresponding to the auditor; For each auditor, the business vector corresponding to the auditor is determined, wherein the components of the business vector correspond one-to-one to the business that the bank needs to audit, and the component value of each component is equal to the business volume of the business corresponding to the component in the audit data corresponding to the auditor.

9. The device according to claim 7, wherein The classification module is specifically used for: Determine a user distance function for the auditors, and determine a business distance function for the auditors, wherein the user distance function is used to determine the distance between any two auditors as the distance between the user vectors of the two auditors, and the business distance function is used to determine the distance between any two auditors as the distance between the business vectors of the two auditors; Based on the user distance function and business distance function of the auditors, cluster analysis is performed on the auditors within a predetermined range to obtain multiple auditor categories.

10. The device according to claim 7, wherein The auditor category determination module is specifically used to: For each auditor within the predetermined range, the distance between the user vector of the candidate auditor and the user vector of the auditor is determined as the user distance corresponding to the auditor, and the distance between the business vector of the candidate auditor and the business vector of the auditor is determined as the business distance corresponding to the auditor; For any two reviewers within the predetermined range, if the user distance of the first reviewer of the two reviewers is less than or equal to the user distance of the second reviewer of the two reviewers, and the business distance of the first reviewer of the two reviewers is less than or equal to the business distance of the second reviewer of the two reviewers, then the first reviewer is determined to be closer to the second reviewer.

11. The device according to claim 7, wherein The auditors determined that the module was specifically used to: Determine the priority probability corresponding to each candidate auditor based on the risk indicators of each auditor category when auditing the business data of the user category to which the user belongs, and the auditor category to which each candidate auditor belongs; The auditors for this audit are determined based on the priority probabilities corresponding to the auditors to be selected.

12. The device according to claim 11, wherein The auditors determined that the module was specifically used to: Select a continuous function f and determine the integral value c of the continuous function f, where the range of f is greater than 0; The domain of the continuous function f is divided into multiple non-intersecting intervals, each of which corresponds to a candidate auditor. The integral value of the continuous function f in each interval is equal to the product of the priority probability corresponding to the candidate auditor corresponding to the interval and c; Function-based Generate a random number and determine the interval in which the random number lies; The auditor for this audit is determined to be the auditor to be selected corresponding to the interval in which the random number is located.

13. 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 6 is implemented.

14. 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 6 is implemented.

15. 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 6 is implemented.

Images