Method and apparatus for controlling latency in a banking system

Abstract

The application provides a bank system waiting time control method and device, and relates to the technical field of computer data processing, which comprises the following steps: obtaining customer information and transaction data of bank customers; classifying the bank customers to obtain multiple customer types; clustering each customer type to obtain multiple customer subsets corresponding to the customer type; determining a risk coefficient vector of a customer subset according to transaction data of the customer subset; selecting a reference customer subset corresponding to the customer type from the multiple customer subsets corresponding to the customer type; determining a first corresponding relationship between the waiting time and the risk coefficient of the customer type according to the reference customer subset corresponding to the customer type; determining a second corresponding relationship between the waiting time and the risk coefficient of the customer type according to a non-reference customer subset corresponding to the customer type; and correcting the waiting time threshold of the bank customers in the non-reference customer subset corresponding to the customer type when using the bank system according to the first corresponding relationship and the second corresponding relationship.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of computer data processing, and particularly relates to a waiting time control method and device of a bank system. BACKGROUND

[0002] This section is intended to provide background information to facilitate an understanding of embodiments of the application as set forth in the claims. The description herein does not constitute an admission of prior art.

[0003] In a bank system, a waiting time threshold is usually set, and if the duration of a customer's misoperation (the waiting time of the bank system) exceeds the waiting time threshold, the account logged in by the bank will be logged out or the transaction initiated will be automatically terminated. In this way, the occurrence of risks can be reduced, but the setting of the waiting time threshold is not related to specific customers at present, resulting in that a part of customers have a relatively large risk.

[0004] In view of the above, there is an urgent need for a technical solution which can overcome the above-mentioned defects and can control the waiting time of a bank system. SUMMARY

[0005] To solve the problems in the prior art, the present application provides a waiting time control method and device of a bank system.

[0006] In a first aspect of the embodiments of the present application, a waiting time control method of a bank system is provided, comprising:

[0007] obtaining customer information and transaction data of bank customers;

[0008] classifying the bank customers according to the customer information to obtain a plurality of customer types;

[0009] clustering each customer type according to the transaction data to obtain a plurality of customer subsets corresponding to the customer type;

[0010] for each customer subset, determining a risk coefficient vector of the customer subset according to the transaction data of the customer subset;

[0011] for each customer type, selecting a reference customer subset corresponding to the customer type from the plurality of customer subsets corresponding to the customer type according to the risk coefficient vector;

[0012] for each customer type, determining a first corresponding relationship between the waiting time and the risk coefficient of the customer type according to the reference customer subset corresponding to the customer type;

[0013] For each customer type, a second corresponding relationship between the waiting time and the risk coefficient of the customer type is determined according to the non-reference customer subset corresponding to the customer type; wherein the non-reference customer subset is a customer subset other than the reference customer subset;

[0014] For each customer type, a second corresponding relationship between the waiting time and the risk coefficient of the customer type is determined according to the non-reference customer subset corresponding to the customer type; wherein the non-reference customer subset is a customer subset other than the reference customer subset;

[0015] In a second aspect of the embodiments of the present application, a waiting time control device of a bank system is provided, comprising:

[0016] A data acquisition module is configured to acquire customer information and transaction data of bank customers;

[0017] A customer classification module is configured to classify the bank customers according to the customer information, and obtain a plurality of customer types;

[0018] A customer clustering module is configured to cluster each customer type according to the transaction data, and obtain a plurality of customer subsets corresponding to the customer type;

[0019] A risk coefficient vector determination module is configured to determine, for each customer subset, a risk coefficient vector of the customer subset according to the transaction data of the customer subset;

[0020] A reference customer subset determination module is configured to select, for each customer type, a reference customer subset corresponding to the customer type from the plurality of customer subsets corresponding to the customer type according to the risk coefficient vector;

[0021] A first corresponding relationship determination module is configured to determine, for each customer type, a first corresponding relationship between the waiting time and the risk coefficient of the customer type according to the reference customer subset corresponding to the customer type;

[0022] A second corresponding relationship determination module is configured to determine, for each customer type, a second corresponding relationship between the waiting time and the risk coefficient of the customer type according to the non-reference customer subset corresponding to the customer type; wherein the non-reference customer subset is a customer subset other than the reference customer subset;

[0023] A correction module is configured to correct, for each customer type, a waiting time threshold of bank customers using the bank system in the non-reference customer subset corresponding to the customer type according to the first corresponding relationship between the waiting time and the risk coefficient of the customer type, and the second corresponding relationship between the waiting time and the risk coefficient of the customer type.

[0024] In a third aspect of the embodiments of the present application, a computer device is provided, which comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the waiting time control method of the banking system when executing the computer program.

[0025] In a fourth aspect of the embodiments of the present application, a computer readable storage medium is provided, which stores a computer program, and the computer program implements the waiting time control method of the banking system when executed by a processor.

[0026] In a fifth aspect of the embodiments of the present application, a computer program product is provided, which comprises a computer program, and the computer program implements the waiting time control method of the banking system when executed by a processor.

[0027] The waiting time control method and device of the banking system provided by the present application correct the waiting time threshold of the banking customers when using the banking system through data analysis, so as to obtain a reasonable waiting time threshold, reduce the risk occurrence of the customers when using the banking system, and ensure the safety of the customers in transaction. BRIEF DESCRIPTION OF DRAWINGS

[0028] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0029] Figure 1 is a flowchart of the waiting time control method of the banking system according to an embodiment of the present application.

[0030] Figure 2 is a flowchart of clustering each customer type according to an embodiment of the present application.

[0031] Figure 3 is a flowchart of determining the risk coefficient vector of the customer subset according to an embodiment of the present application.

[0032] Figure 4 is a flowchart of selecting the reference customer subset corresponding to the customer type from the multiple customer subsets corresponding to the customer type according to an embodiment of the present application.

[0033] Figure 5 is a flowchart of determining the first corresponding relationship between the waiting time and the risk coefficient of the customer type according to an embodiment of the present application.

[0034] Figure 6is a flowchart of a process of determining a second corresponding relationship between a waiting time and a risk coefficient of a customer type according to an embodiment of the present application.

[0035] Figure 7 is a flowchart of a process of revising a waiting time threshold of a non-reference customer subset corresponding to a customer type according to an embodiment of the present application.

[0036] Figure 8 is a schematic diagram of an architecture of a waiting time control device of a bank system according to an embodiment of the present application.

[0037] Figure 9 is a schematic diagram of an architecture of a computer device according to an embodiment of the present application. DETAILED DESCRIPTION

[0038] The principles and spirits of the present application will be described below with reference to several exemplary embodiments. It should be understood that these embodiments are given only to enable those skilled in the art to better understand and implement the present application, and do not limit the scope of the present application in any way. On the contrary, these embodiments are provided to make the present disclosure more thorough and complete, and to fully convey the scope of the present disclosure to those skilled in the art.

[0039] Those skilled in the art know that the embodiments of the present application can be implemented as a system, a device, an apparatus, a method or a computer program product. Therefore, the present disclosure can be embodied in the form of a complete hardware, a complete software (including firmware, resident software, microcode, etc.), or a combination of hardware and software.

[0040] According to the embodiments of the present application, a waiting time control method and device of a bank system are provided, which relate to the technical field of computer data processing.

[0041] The principles and spirits of the present application will be described below with reference to several exemplary embodiments. It should be understood that these embodiments are given only to enable those skilled in the art to better understand and implement the present application, and do not limit the scope of the present application in any way. On the contrary, these embodiments are provided to make the present disclosure more thorough and complete, and to fully convey the scope of the present disclosure to those skilled in the art.

[0042] Figure 1 is a flowchart of a waiting time control method of a bank system according to an embodiment of the present application. As shown in Figure 1 , the method comprises:

[0043] S1, obtaining customer information and transaction data of a bank customer;

[0044] S2, classifying the bank customer according to the customer information, and obtaining a plurality of customer types;

[0045] S3, clustering each customer type according to the transaction data, and obtaining a plurality of customer subsets corresponding to the customer type;

[0046] S4, for each customer subset, determining a risk coefficient vector of the customer subset according to transaction data of the customer subset;

[0047] S5, for each customer type, selecting a reference customer subset corresponding to the customer type from a plurality of customer subsets corresponding to the customer type according to the risk coefficient vector;

[0048] S6, for each customer type, determining a first correspondence between the waiting time and the risk coefficient of the customer type according to the reference customer subset corresponding to the customer type;

[0049] S7, for each customer type, determining a second correspondence between the waiting time and the risk coefficient of the customer type according to a non-reference customer subset corresponding to the customer type; wherein the non-reference customer subset is a customer subset other than the reference customer subset;

[0050] S8, for each customer type, correcting a waiting time threshold of the non-reference customer subset corresponding to the customer type when the bank customer uses the bank system according to the first correspondence between the waiting time and the risk coefficient of the customer type and the second correspondence between the waiting time and the risk coefficient of the customer type.

[0051] The waiting time control method of the bank system provided by the application corrects the waiting time threshold of the bank customer when using the bank system through data analysis, so that a reasonable waiting time threshold is obtained, the occurrence of risk of the customer when using the bank system is reduced, and the safety of the customer when conducting transactions is ensured.

[0052] The application can be applied to bank intelligent terminals (self-service terminals, intelligent counters, etc.), and can also be applied to mobile terminals (mobile bank, etc.).

[0053] In order to more clearly explain the above-mentioned waiting time control method of the bank system, the following will be described in detail in combination with each step.

[0054] In S1, customer information and transaction data of the bank customer are obtained.

[0055] In S2, the bank customer is classified according to the customer information, and a plurality of customer types are obtained.

[0056] In S3, referring to Figure 2 , the customer type is clustered according to the transaction data, and a plurality of customer subsets corresponding to the customer type are obtained, including:

[0057] S31, determining a distance function of the bank customer according to the transaction data, wherein the distance function is used to determine the distance between any two bank customers of the customer type;

[0058] S32, clustering the bank customers of the customer type according to the distance function of the bank customers, to obtain a plurality of customer subsets corresponding to the customer type.

[0059] In an embodiment, (S31) determining the distance function of the bank customers according to the transaction data comprises:

[0060] S311, for each bank customer, determining the transaction quantity of each transaction category corresponding to the bank customer according to the transaction data of the bank customer;

[0061] S312, determining the distance function of the customer according to the following formula:

[0062]

[0063] wherein k1 and k2 are any two customers of the customer type, f(k1, k2) is the distance of k1 and k2, is the transaction quantity of the i-th transaction category corresponding to k1, is the transaction quantity of the i-th transaction category corresponding to k2.

[0064] In an embodiment, (S32) clustering the bank customers of the customer type according to the distance function of the bank customers, to obtain a plurality of customer subsets corresponding to the customer type, comprises:

[0065] S321, clustering the customers of the customer type according to the distance function of the customer using a clustering algorithm (such as K-means, or selecting a learning vector quantization with risk level as the category identifier), to obtain a plurality of customer subsets corresponding to the customer type;

[0066] S322, for each customer subset corresponding to the customer type obtained, determining the risk level of each customer in the customer subset, and further calculating the proportion of the number of customers corresponding to each risk level in the customer subset corresponding to the customer type;

[0067] S323, determining whether each customer subset corresponding to the customer type satisfies the following condition t: there exists a risk level such that the proportion of the number of customers corresponding to the risk level in the customer subset is greater than the proportion threshold;

[0068] S324, if there exists a customer subset corresponding to the customer type that does not satisfy the condition t, then the following steps are executed in a loop until all customer subsets corresponding to the customer type satisfy the condition t:

[0069] selecting a customer subset that does not satisfy the condition t from the customer subsets corresponding to the customer type, clustering the customers of the customer subset according to the distance function of the customer using the selected clustering algorithm, to obtain a plurality of new customer subsets corresponding to the customer type;

[0070] delete the customer subset from the customer subset corresponding to the customer type;

[0071] For each new customer subset corresponding to the customer type obtained, determine the proportion of customers in each risk level in the new customer subset.

[0072] In S4, with reference to Figure 3 For each customer subset, determine the risk coefficient vector of the customer subset according to the transaction data of the customer subset, including:

[0073] S41, for each customer subset, determine the risk coefficient sample of each data dimension corresponding to the customer subset according to the transaction data of the customer subset;

[0074] Wherein, the data dimension at least includes: transaction channel, transaction time, transaction category, transaction scene. Determining the risk coefficient of each data dimension corresponding to the customer subset can not only ensure enough data to determine the risk coefficient, but also improve the calculation accuracy of the risk coefficient.

[0075] S42, determine the risk coefficient vector of the customer subset, wherein the components of the risk coefficient vector correspond one-to-one to the data dimensions, and the component value of each component of the risk coefficient vector is equal to the mean of the risk coefficient sample of the data dimension corresponding to the component corresponding to the customer subset.

[0076] In an embodiment, (S41) for each customer subset, determining the risk coefficient sample of each data dimension corresponding to the customer subset according to the transaction data of the customer subset, including:

[0077] S411, set a transaction volume threshold;

[0078] S412, select the transaction data corresponding to each data dimension from the transaction data of the customer subset;

[0079] S413, divide the transaction data corresponding to each data dimension into a transaction data subset corresponding to the data dimension, wherein each transaction data subset contains a transaction quantity greater than the transaction volume threshold;

[0080] S414, set a maximum risk coefficient error, and a maximum probability that the risk coefficient error is greater than the maximum risk coefficient error;

[0081] S415, calculate the product of the square of the maximum risk coefficient error and the maximum probability;

[0082] S416, determine the threshold value corresponding to the data dimension according to the transaction data subset corresponding to the data dimension and the product;

[0083] S417, for each data dimension, determine whether the data dimension satisfies a condition s: a number of transaction data subsets corresponding to the data dimension is greater than or equal to a threshold value corresponding to the data dimension; if the condition s is not satisfied, perform the following steps cyclically until the data dimension satisfies the condition s:

[0084] obtain new transaction data of the customer subset, and select new transaction data corresponding to the data dimension from the new transaction data; divide the new transaction data corresponding to the data dimension into new transaction data subsets corresponding to the data dimension, wherein each new transaction data subset contains a number of transactions greater than a transaction amount threshold;

[0085] S418, for each data dimension, when it is determined that the data dimension satisfies the condition s, take a proportion of risky transactions in each transaction data subset corresponding to the data dimension as a risk coefficient sample of the customer subset corresponding to the data dimension.

[0086] Specifically, (S416) determining the threshold value corresponding to the data dimension according to the transaction data subset corresponding to the data dimension and the product, comprises:

[0087] S416-1, determine a proportion value of risky transactions in each transaction data subset corresponding to the data dimension;

[0088] S416-2, determine the coefficient variance corresponding to the data dimension according to the determined plurality of proportion values;

[0089] S416-3, determine a quotient of a square of the coefficient variance corresponding to the data dimension and the product;

[0090] S416-4, determine the threshold value corresponding to the data dimension as the smallest integer greater than the quotient.

[0091] In S5, refer to Figure 4 For each customer type, select a reference customer subset corresponding to the customer type from a plurality of customer subsets corresponding to the customer type according to the risk coefficient vector, comprising:

[0092] S51, determine a partial order of customer subsets of the customer type according to the risk coefficient vector, wherein the partial order is used to determine whether a customer subset A in any two customer subsets corresponding to the customer type is better than a customer subset B; if each component of the risk coefficient vector of the customer subset A is less than or equal to the corresponding component of the risk coefficient vector of the customer subset B, the customer subset A is better than the customer subset B in the partial order;

[0093] S52, selecting a reference customer subset corresponding to the customer type from the plurality of customer subsets corresponding to the customer type according to the partial order of the customer subsets of the customer type, wherein for each reference customer subset corresponding to the customer type, there is no other customer subset in the plurality of customer subsets corresponding to the customer type except the reference customer subset, such that the other customer subset is superior to the reference customer subset.

[0094] In an embodiment, (S52) selecting a reference customer subset corresponding to the customer type from the plurality of customer subsets corresponding to the customer type according to the partial order of the customer subsets of the customer type comprises:

[0095] S521, initializing the set of customer subsets to be determined and the set of customer subsets to be compared as the plurality of customer subsets corresponding to the customer type;

[0096] S522, for each component of the risk coefficient vector, determining a variance corresponding to the component according to the value of the component of the risk coefficient vector of the plurality of customer subsets corresponding to the customer type, and selecting a component corresponding to the maximum variance from the components of the risk coefficient vector;

[0097] S523, cyclically performing the following three steps until the set of customer subsets to be determined is empty:

[0098] taking a customer subset a corresponding to the minimum value of the selected component of the risk coefficient vector from the set of customer subsets to be determined, and comparing the customer subset a with each customer subset b (except the customer subset a) in the set of customer subsets to be compared according to the partial order of the customer subsets of the customer type;

[0099] if the customer subset b is superior to the customer subset a, deleting the customer subset a from the set of customer subsets to be determined, and if the customer subset a is superior to the customer subset b, deleting the customer subset b from the set of customer subsets to be determined and determining the customer subset b as a secondary customer subset of the customer subset a;

[0100] if it is confirmed that each customer subset in the set of customer subsets to be compared except the customer subset a is not superior to the customer subset a according to the partial order of the customer subsets of the customer type, taking the customer subset a as a reference customer subset corresponding to the customer type, and deleting the customer subset a from the set of customer subsets to be determined and deleting all secondary customer subsets of the customer subset a from the set of customer subsets to be compared.

[0101] The number of customers of a bank is very large, even in the order of hundreds of millions. The number of customer subsets corresponding to the customer type can also be very large. If all customer subsets corresponding to the customer type are compared at this time to select the reference customer subset corresponding to the customer type, the corresponding calculation complexity is O(N2 ), that is, there is a lot of redundant calculation at this time. The embodiment of selecting the reference customer subset corresponding to the customer type from the plurality of customer subsets corresponding to the customer type can effectively reduce the redundant calculation and reduce the complexity of the calculation (less than O(N 2 ).

[0102] In S6, with reference to Figure 5 , for each customer type, a first correspondence between the waiting time and the risk coefficient of the customer type is determined according to the reference customer subset corresponding to the customer type, including:

[0103] S61, a plurality of first discrete values of the waiting time are set;

[0104] S62, the waiting data of the reference customer subset corresponding to the customer type using the bank system is obtained;

[0105] S63, for each first discrete value, a first proportion of the waiting data involving risks in the waiting data of the reference customer subset corresponding to the customer type using the bank system when the waiting time threshold is set to the first discrete value is determined, and the first proportion is taken as the risk coefficient corresponding to the first discrete value;

[0106] S64, a first discrete function is constructed, wherein the independent variable of the first discrete function is the plurality of first discrete values, and the function value of the first discrete function corresponding to each first discrete value is equal to the risk coefficient corresponding to the first discrete value;

[0107] S65, the first discrete function is continuously, a continuous function is obtained, and the continuous function is taken as the first correspondence between the waiting time and the risk coefficient of the customer subset.

[0108] In S7, with reference to Figure 6 , for each customer type, a second correspondence between the waiting time and the risk coefficient of the customer type is determined according to the non-reference customer subset corresponding to the customer type, including:

[0109] S71, a plurality of second discrete values of the waiting time are set;

[0110] S72, the waiting data of the non-reference customer subset corresponding to the customer type using the bank system is obtained;

[0111] S73, for each second discrete value, a second proportion of the waiting data involving risks in the waiting data of the non-reference customer subset corresponding to the customer type using the bank system when the waiting time threshold is set to the second discrete value is determined, and the second proportion is taken as the risk coefficient corresponding to the second discrete value;

[0112] S74, constructing a second discrete function, wherein an independent variable of the second discrete function is the plurality of second discrete values, and a function value of the second discrete function corresponding to each second discrete value is equal to the risk coefficient corresponding to the second discrete value;

[0113] S75, continuously the second discrete function to obtain a continuous function, and taking the continuous function as a second correspondence between the waiting time and the risk coefficient of the customer subset.

[0114] In S8, referring to Figure 7 For each customer type, according to the first correspondence between the waiting time and the risk coefficient of the customer type, and the second correspondence between the waiting time and the risk coefficient of the customer type, the waiting time threshold of the non-reference customer subset corresponding to the customer type is corrected, including:

[0115] S81, for each customer type, obtaining the waiting time threshold corresponding to each bank customer in the non-reference customer subset corresponding to the customer type;

[0116] S82, for each bank customer in the non-reference customer subset corresponding to the customer type, determining the potential risk coefficient corresponding to the bank customer according to the waiting time threshold corresponding to the bank customer and the first correspondence between the waiting time and the risk coefficient of the customer type;

[0117] S83, determining the potential waiting time threshold corresponding to the bank customer according to the potential risk coefficient corresponding to the bank customer and the second correspondence between the waiting time and the risk coefficient of the customer type;

[0118] S84, correcting the waiting time threshold of the bank customer using the bank system according to the potential waiting time threshold corresponding to the customer.

[0119] It should be noted that although the operations of the method of the present application are described in a specific order in the above embodiments and drawings, this does not require or imply that the operations must be performed in this specific order, or that all of the shown operations must be performed to achieve the desired result. Additionally or alternatively, some steps can be omitted, a plurality of steps can be combined into one step, and / or one step can be divided into a plurality of steps.

[0120] After introducing the method of the exemplary embodiments of the present application, next, referring to Figure 8 The waiting time control device of the bank system of the exemplary embodiments of the present application is introduced.

[0121] The implementation of the waiting time control device of the banking system can refer to the implementation of the above method, and the repeated parts will not be described here. The term "module" or "unit" used below can be a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware or a combination of software and hardware is also possible and is contemplated.

[0122] Based on the same inventive concept, the present application also provides a waiting time control device of a banking system, as shown in the figure, the device comprises: Figure 8

[0123] a data acquisition module 810, configured to acquire customer information and transaction data of bank customers;

[0124] a customer classification module 820, configured to classify the bank customers according to the customer information, and obtain a plurality of customer types;

[0125] a customer clustering module 830, configured to cluster each customer type according to the transaction data, and obtain a plurality of customer subsets corresponding to the customer type;

[0126] a risk coefficient vector determination module 840, configured to determine, for each customer subset, a risk coefficient vector of the customer subset according to the transaction data of the customer subset;

[0127] a reference customer subset determination module 850, configured to select, for each customer type, a reference customer subset corresponding to the customer type from the plurality of customer subsets corresponding to the customer type according to the risk coefficient vector;

[0128] a first correspondence determination module 860, configured to determine, for each customer type, a first correspondence between the waiting time and the risk coefficient of the customer type according to the reference customer subset corresponding to the customer type;

[0129] a second correspondence determination module 870, configured to determine, for each customer type, a second correspondence between the waiting time and the risk coefficient of the customer type according to the non-reference customer subset corresponding to the customer type; wherein the non-reference customer subset is a customer subset other than the reference customer subset;

[0130] a correction module 880, configured to correct, for each customer type, the waiting time threshold of the bank customers in the non-reference customer subset corresponding to the customer type when using the banking system according to the first correspondence between the waiting time and the risk coefficient of the customer type and the second correspondence between the waiting time and the risk coefficient of the customer type.

[0131] In an embodiment, the customer clustering module is specifically configured to:

[0132] ​determine a distance function of the bank customers according to the transaction data, wherein the distance function is used to determine a distance between any two bank customers of the customer type;

[0133] cluster the customers of the customer type according to the distance function of the bank customers, to obtain a plurality of customer subsets corresponding to the customer type.

[0134] In an embodiment, the risk coefficient vector determination module is specifically configured to:

[0135] For each customer subset, determine a risk coefficient sample of each data dimension corresponding to the customer subset according to the transaction data of the customer subset;

[0136] determine a risk coefficient vector of the customer subset, wherein components of the risk coefficient vector correspond to the data dimensions one by one, and a component value of each component of the risk coefficient vector is equal to a mean value of the risk coefficient sample of the data dimension corresponding to the component.

[0137] In an embodiment, the reference customer subset determination module is specifically configured to:

[0138] determine a partial order of the customer subsets of the customer type according to the risk coefficient vectors, wherein the partial order is used to determine whether a customer subset A is better than a customer subset B in any two customer subsets of the customer type corresponding to the customer type; if each component of the risk coefficient vector of the customer subset A is less than or equal to the corresponding component of the risk coefficient vector of the customer subset B, then the customer subset A is better than the customer subset B in the partial order;

[0139] select a reference customer subset corresponding to the customer type from the plurality of customer subsets corresponding to the customer type according to the partial order of the customer subsets of the customer type, wherein for each reference customer subset corresponding to the customer type, there is no other customer subset in the plurality of customer subsets corresponding to the customer type except the reference customer subset, so that the other customer subset is better than the reference customer subset.

[0140] In an embodiment, the first corresponding relationship determination module is specifically configured to:

[0141] set a plurality of first discrete values of the waiting time;

[0142] obtain waiting data of the reference customer subset corresponding to the customer type using the bank system;

[0143] For each first discrete value, determine a first proportion of risk-involved waiting data in the waiting data of the reference customer subset corresponding to the customer type using the bank system when the waiting time threshold is set to the first discrete value, and take the first proportion as a risk coefficient corresponding to the first discrete value.

[0144] constructing a first discrete function, wherein an argument of the first discrete function is the plurality of first discrete values, and a function value of the first discrete function corresponding to each first discrete value is equal to a risk coefficient corresponding to the first discrete value;

[0145] continuously differentiating the first discrete function to obtain a continuous function, and taking the continuous function as the first correspondence between the waiting time and the risk coefficient of the customer subset.

[0146] In an embodiment, the second correspondence determining module is specifically configured to:

[0147] setting a plurality of second discrete values of the waiting time;

[0148] obtaining the waiting data of the non-reference customer subset corresponding to the customer type using the banking system;

[0149] for each second discrete value, determining a second proportion of the waiting data involving the risk in the waiting data of the non-reference customer subset corresponding to the customer type using the banking system when the waiting time threshold is set as the second discrete value, and taking the second proportion as a risk coefficient corresponding to the second discrete value;

[0150] constructing a second discrete function, wherein an argument of the second discrete function is the plurality of second discrete values, and a function value of the second discrete function corresponding to each second discrete value is equal to a risk coefficient corresponding to the second discrete value;

[0151] continuously differentiating the second discrete function to obtain a continuous function, and taking the continuous function as the second correspondence between the waiting time and the risk coefficient of the customer subset.

[0152] In an embodiment, the correcting module is specifically configured to:

[0153] for each customer type, obtaining a waiting time threshold corresponding to each bank customer in the non-reference customer subset corresponding to the customer type;

[0154] for each bank customer in the non-reference customer subset corresponding to the customer type, determining a potential risk coefficient corresponding to the bank customer according to the waiting time threshold corresponding to the bank customer and the first correspondence between the waiting time and the risk coefficient of the customer type;

[0155] determining a potential waiting time threshold corresponding to the customer according to the potential risk coefficient corresponding to the bank customer and the second correspondence between the waiting time and the risk coefficient of the customer type;

[0156] correcting the waiting time threshold when the bank customer uses the banking system according to the potential waiting time threshold corresponding to the customer.

[0157] It should be noted that, although several modules of the waiting time control device of the banking system are mentioned in the foregoing detailed description, such a division is merely exemplary and not mandatory. Indeed, according to embodiments of the application, the features and functions of two or more modules described above can be embodied in one module. Conversely, the features and functions of one module described above can be further divided into modules.

[0158] Based on the foregoing inventive concept, the present application proposes a computer device 900, as shown in Figure 9 The processor 920 implements the foregoing waiting time control method of the banking system when executing the computer program 930.

[0159] Based on the foregoing inventive concept, the present application proposes a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement the foregoing waiting time control method of the banking system.

[0160] Based on the foregoing inventive concept, the present application proposes a computer program product, which comprises a computer program, and the computer program is executed by a processor to implement the waiting time control method of the banking system.

[0161] The waiting time control method and device of the banking system according to the present application correct the waiting time threshold of the banking customers when using the banking system through data analysis, so as to obtain a reasonable waiting time threshold, reduce the risk occurrence when the customers use the banking system, and ensure the safety of the customers when conducting transactions.

[0162] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, device, or computer program product. Therefore, the present application can adopt a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can adopt a computer program product implemented on one or more computer usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer usable program code.

[0163] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 one or more flow or blocks Figure 1 means for functionally implementing the steps listed in the flowchart block or blocks.

[0164] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 one or more flow or blocks Figure 1 means for functionally implementing the steps listed in the flowchart block or blocks.

[0165] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 one or more flow or blocks Figure 1 means for functionally implementing the steps listed in the flowchart block or blocks.

[0166] Finally, it should be noted that the above-mentioned embodiments are merely intended to illustrate the technical solutions of the present application, rather than limit the technical solutions of the present application, and the protection scope of the present application is not limited to this. Although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that any modifications or changes to the technical solutions described in the foregoing embodiments, or any equivalent replacements, can be made by those skilled in the art within the technical scope disclosed by the present application, and these modifications or changes, or replacements, do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present application. Therefore, these modifications or changes, or replacements, should be encompassed within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A waiting time control method of a banking system, characterized by, The method comprises the following steps: obtaining customer information and transaction data of bank customers; classifying the bank customers according to the customer information to obtain multiple customer types; clustering each customer type according to the transaction data to obtain multiple customer subsets corresponding to the customer type; for each customer subset, determining a risk coefficient vector of the customer subset according to the transaction data of the customer subset; for each customer type, selecting a reference customer subset corresponding to the customer type from the multiple customer subsets corresponding to the customer type according to the risk coefficient vector; for each customer type, determining a first correspondence between the waiting time and the risk coefficient of the customer type according to the reference customer subset corresponding to the customer type; for each customer type, determining a second correspondence between the waiting time and the risk coefficient of the customer type according to a non-reference customer subset corresponding to the customer type; wherein the non-reference customer subset is a customer subset other than the reference customer subset; for each customer type, correcting a waiting time threshold of the bank customers in the non-reference customer subset corresponding to the customer type when using the bank system according to the first correspondence between the waiting time and the risk coefficient of the customer type and the second correspondence between the waiting time and the risk coefficient of the customer type; wherein for each customer type, the first correspondence between the waiting time and the risk coefficient of the customer type is determined according to the reference customer subset corresponding to the customer type, comprising: setting multiple first discrete values of the waiting time; obtaining waiting data of the reference customer subset corresponding to the customer type when using the bank system; for each first discrete value, determining a first proportion of risk-related waiting data in the waiting data of the reference customer subset corresponding to the customer type when the waiting time threshold is set to the first discrete value, and taking the first proportion as the risk coefficient corresponding to the first discrete value; constructing a first discrete function, wherein the independent variable of the first discrete function is the multiple first discrete values, and the function value of the first discrete function corresponding to each first discrete value is equal to the risk coefficient corresponding to the first discrete value; continuously differentiating the first discrete function to obtain a continuous function, and taking the continuous function as the first correspondence between the waiting time and the risk coefficient of the customer subset; wherein for each customer type, the second correspondence between the waiting time and the risk coefficient of the customer type is determined according to the non-reference customer subset corresponding to the customer type, comprising: setting multiple second discrete values of the waiting time; obtaining waiting data of the non-reference customer subset corresponding to the customer type when using the bank system; for each second discrete value, determining a second proportion of risk-related waiting data in the waiting data of the non-reference customer subset corresponding to the customer type when the waiting time threshold is set to the second discrete value, and taking the second proportion as the risk coefficient corresponding to the second discrete value; constructing a second discrete function, wherein the independent variable of the second discrete function is the multiple second discrete values, and the function value of the second discrete function corresponding to each second discrete value is equal to the risk coefficient corresponding to the second discrete value; The second discrete function is continuous to obtain a continuous function, and the continuous function is taken as a second correspondence between the waiting time and the risk coefficient of the customer subset.

2. The method of claim 1, wherein, According to the transaction data, each customer type is clustered to obtain a plurality of customer subsets corresponding to the customer type, including: According to the transaction data, a distance function of the bank customers is determined, wherein the distance function is used to determine the distance between any two bank customers of the customer type; According to the distance function of the bank customers, the customers of the customer type are clustered to obtain a plurality of customer subsets corresponding to the customer type.

3. The method of claim 1, wherein, For each customer subset, according to the transaction data of the customer subset, a risk coefficient vector of the customer subset is determined, including: For each customer subset, according to the transaction data of the customer subset, a risk coefficient sample corresponding to each data dimension of the customer subset is determined; The risk coefficient vector of the customer subset is determined, wherein the components of the risk coefficient vector correspond to the data dimensions one by one, and the component value of each component of the risk coefficient vector is equal to the mean value of the risk coefficient sample corresponding to the data dimension corresponding to the component.

4. The method of claim 1, wherein, For each customer type, according to the risk coefficient vector, a reference customer subset corresponding to the customer type is selected from the plurality of customer subsets corresponding to the customer type, including: According to the risk coefficient vector, a partial order of the customer subsets of the customer type is determined, wherein the partial order is used to determine whether a customer subset A is better than a customer subset B in any two customer subsets corresponding to the customer type; if each component of the risk coefficient vector of the customer subset A is less than or equal to the corresponding component of the risk coefficient vector of the customer subset B, then the customer subset A is better than the customer subset B in the partial order; According to the partial order of the customer subsets of the customer type, a reference customer subset corresponding to the customer type is selected from the plurality of customer subsets corresponding to the customer type, wherein for each reference customer subset corresponding to the customer type, there is no other customer subset in the plurality of customer subsets corresponding to the customer type except the reference customer subset, so that the other customer subset is better than the reference customer subset.

5. The method of claim 1, wherein, For each customer type, according to the first correspondence between the waiting time and the risk coefficient of the customer type, and the second correspondence between the waiting time and the risk coefficient of the customer type, the waiting time threshold of the bank customers of the non-reference customer subset corresponding to the customer type when using the bank system is corrected, including: For each customer type, the waiting time threshold corresponding to each bank customer in the non-reference customer subset corresponding to the customer type is obtained; For each bank customer in the non-reference customer subset corresponding to the customer type, according to the waiting time threshold corresponding to the bank customer and the first correspondence between the waiting time and the risk coefficient of the customer type, a potential risk coefficient corresponding to the bank customer is determined; According to the potential risk coefficient corresponding to the bank customer and the second correspondence between the waiting time and the risk coefficient of the customer type, a potential waiting time threshold corresponding to the customer is determined; According to the potential waiting time threshold corresponding to the customer, the waiting time threshold of the bank customer when using the bank system is corrected.

6. A waiting time control device of a banking system, characterized by comprising: including: The data acquisition module is configured to acquire customer information and transaction data of the bank customers. The customer classification module is configured to classify the bank customers according to the customer information, and obtain a plurality of customer types. The customer clustering module is configured to cluster each customer type according to the transaction data, and obtain a plurality of customer subsets corresponding to the customer type. The risk coefficient vector determination module is configured to determine, for each customer subset, a risk coefficient vector of the customer subset according to transaction data of the customer subset. The reference customer subset determination module is configured to select, for each customer type, a reference customer subset corresponding to the customer type from a plurality of customer subsets corresponding to the customer type according to the risk coefficient vector. The first correspondence relationship determination module is configured to determine, for each customer type, a first correspondence relationship between the waiting time and the risk coefficient of the customer type according to the reference customer subset corresponding to the customer type. The second correspondence relationship determination module is configured to determine, for each customer type, a second correspondence relationship between the waiting time and the risk coefficient of the customer type according to a non-reference customer subset corresponding to the customer type, wherein the non-reference customer subset is a customer subset other than the reference customer subset. The correction module is configured to correct, for each customer type, a waiting time threshold of a bank customer of a non-reference customer subset corresponding to the customer type when using the bank system according to the first correspondence relationship between the waiting time and the risk coefficient of the customer type and the second correspondence relationship between the waiting time and the risk coefficient of the customer type. The first correspondence relationship determination module is specifically configured to: set a plurality of first discrete values of the waiting time; acquire waiting data of the reference customer subset corresponding to the customer type when using the bank system; for each first discrete value, determine a first proportion of risk-related waiting data in the waiting data of the reference customer subset corresponding to the customer type when using the bank system when the waiting time threshold is set to the first discrete value, and take the first proportion as a risk coefficient corresponding to the first discrete value; construct a first discrete function, wherein the independent variable of the first discrete function is the plurality of first discrete values, and the function value of the first discrete function corresponding to each first discrete value is equal to the risk coefficient corresponding to the first discrete value; continuously obtain a continuous function by continuously connecting the first discrete function, and take the continuous function as the first correspondence relationship between the waiting time and the risk coefficient of the customer subset. The second correspondence relationship determination module is specifically configured to: set a plurality of second discrete values of the waiting time; acquire waiting data of the non-reference customer subset corresponding to the customer type when using the bank system; for each second discrete value, determine a second proportion of risk-related waiting data in the waiting data of the non-reference customer subset corresponding to the customer type when using the bank system when the waiting time threshold is set to the second discrete value, and take the second proportion as a risk coefficient corresponding to the second discrete value; construct a second discrete function, wherein the independent variable of the second discrete function is the plurality of second discrete values, and the function value of the second discrete function corresponding to each second discrete value is equal to the risk coefficient corresponding to the second discrete value. The second discrete function is continuous to obtain a continuous function, and the continuous function is taken as a second correspondence between the waiting time and the risk coefficient of the customer subset.

7. The apparatus of claim 6, wherein, The customer clustering module is specifically configured to: determine a distance function of the bank customers according to the transaction data, wherein the distance function is used to determine the distance between any two bank customers of the customer type; cluster the customers of the customer type according to the distance function of the bank customers to obtain a plurality of customer subsets corresponding to the customer type.

8. The apparatus of claim 6, wherein, The risk coefficient vector determination module is specifically configured to: for each customer subset, determine a risk coefficient sample corresponding to each data dimension of the customer subset according to the transaction data of the customer subset; determine a risk coefficient vector of the customer subset, wherein the components of the risk coefficient vector correspond to the data dimensions one by one, and the component value of each component of the risk coefficient vector is equal to the mean value of the risk coefficient sample corresponding to the data dimension corresponding to the component.

9. The apparatus of claim 6, wherein, The reference customer subset determination module is specifically configured to: determine a partial order of the customer subsets of the customer type according to the risk coefficient vectors, wherein the partial order is used to determine whether a customer subset A is better than a customer subset B in any two customer subsets of the customer type; if each component of the risk coefficient vector of the customer subset A is less than or equal to the corresponding component of the risk coefficient vector of the customer subset B, the customer subset A is better than the customer subset B in the partial order; select a reference customer subset corresponding to the customer type from the plurality of customer subsets corresponding to the customer type according to the partial order of the customer subsets of the customer type, wherein for each reference customer subset corresponding to the customer type, there is no other customer subset in the plurality of customer subsets corresponding to the customer type except the reference customer subset, so that the other customer subset is better than the reference customer subset.

10. The apparatus of claim 6, wherein, The correction module is specifically configured to: for each customer type, obtain a waiting time threshold corresponding to each bank customer in a non-reference customer subset corresponding to the customer type; for each bank customer in the non-reference customer subset corresponding to the customer type, determine a potential risk coefficient corresponding to the bank customer according to the waiting time threshold corresponding to the bank customer and the first correspondence between the waiting time and the risk coefficient of the customer type; determine a potential waiting time threshold corresponding to the customer according to the potential risk coefficient corresponding to the bank customer and the second correspondence between the waiting time and the risk coefficient of the customer type; correct the waiting time threshold when the bank customer uses the bank system according to the potential waiting time threshold corresponding to the customer.

11. A computer device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, The processor executes the computer program to realize the method of any one of claims 1 to 5.

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

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

Images