CN109325628B

CN109325628B - Method and device for predicting business window number of bank outlets and electronic equipment

Info

Publication number: CN109325628B
Application number: CN201811162959.XA
Authority: CN
Inventors: 朱江波
Original assignee: Bank of China Ltd
Current assignee: Bank of China Ltd
Priority date: 2018-09-30
Filing date: 2018-09-30
Publication date: 2021-08-20
Anticipated expiration: 2038-09-30
Also published as: CN109325628A

Abstract

The application discloses a method, a device and electronic equipment for predicting the number of business windows of a bank outlet, wherein the method comprises the following steps: setting a waiting time threshold; acquiring a waiting client information set of a network point at the time t of each day in a time period; acquiring a longest waiting time set according to all waiting client information sets; each longest waiting time in the longest waiting time set represents the waiting time corresponding to the last waiting client in the waiting client information set at the same time t of each day in a time period or the time spent by all waiting clients in the waiting client information set for handling the business under the condition that a business window is supposed to be opened in a network node; determining a longest waiting time predicted value of a waiting customer information set at the same time t according to the longest waiting time set; and determining the number of the business windows opened by the network points at the moment t according to the maximum value of the number of the business windows of the network points, the waiting time threshold and the longest waiting time predicted value.

Description

Method and device for predicting business window number of bank outlets and electronic equipment

Technical Field

The present application relates to the field of data mining technologies, and in particular, to a method and an apparatus for predicting the number of business windows of a bank outlet, and an electronic device.

Background

At present, the number of business windows is manually adjusted at bank outlets, namely, the number of the windows is manually increased or decreased according to the number of clients waiting for handling business at present. Without human intervention, the following may occur: the existing windows are small in number, so that a customer waits for a long time, or the number of business windows is large due to few customers, so that resource waste is caused, and certain randomness is brought to artificially increasing or reducing the number of windows. If the human intervention fails, the problem of waiting for a long time for a client or wasting network resources still exists.

Disclosure of Invention

The technical scheme can maximize the reasonable utilization of network resources and enable users to wait for less time.

In order to achieve the above object, an embodiment of the present application provides a method for predicting the number of business windows of a bank outlet, including:

setting a waiting time threshold; the waiting time threshold is the maximum value of the time difference between the starting time of entering a banking outlet and the starting time of starting to transact business, which is tolerated by a client;

acquiring a waiting client information set of the network point at the time t of each day in a time period;

acquiring a longest waiting time set according to all waiting client information sets; each longest waiting time in the longest waiting time set represents the waiting time of the last waiting client in the waiting client information set at the same time t of each day in the time period or the time spent by all waiting clients in the waiting client information set for handling the business under the condition that a business window is supposed to be opened in a network node;

determining the longest waiting time predicted value of the waiting customer information set at the same time t according to the longest waiting time set;

and determining the number of the business windows opened by the network point at the moment t according to the maximum value of the number of the business windows of the network point, the waiting time threshold and the longest waiting time predicted value of the waiting customer information set at the same moment t.

Preferably, the step of acquiring the number of business windows opened by the network points at the time t includes:

rounding the quotient of the longest waiting time predicted value of the waiting customer information set at the same time t divided by the waiting time threshold value to obtain a first result;

and comparing the first result with the maximum value of the number of the business windows of the website, and taking the minimum value of the first result and the maximum value as the number of the business windows opened by the website at the moment t.

Preferably, each piece of waiting client information in the waiting client information set includes a client ID and a corresponding serial number, a start time of entering a banking outlet, a transaction type, a transaction start time, and a transaction completion time.

Preferably, each longest latency obtaining step in the longest latency set includes:

acquiring the time spent by each waiting client in the waiting client information set for handling the service according to the client ID and the corresponding service handling starting time and service handling finishing time;

adding the time spent by each waiting client in the waiting client information set for handling the service to obtain a second result;

and subtracting the time spent by the last waiting client in the waiting client information set for handling the service from the second result to obtain the longest waiting time corresponding to the waiting client information set.

and calculating the sum of the time spent by each waiting client in the waiting client information set for handling the business, and obtaining the longest waiting time corresponding to the waiting client information set.

and under the condition that a network node opens a business window, subtracting the business transaction starting time of the first waiting client in the waiting client information set from the business transaction starting time of the last waiting client in the waiting client information set to obtain the longest waiting time corresponding to the waiting client information set.

and under the condition that a network node opens a business window, subtracting the business transaction starting time of the first waiting client in the waiting client information set from the business transaction finishing time of the last waiting client in the waiting client information set to obtain the longest waiting time corresponding to the waiting client information set.

Preferably, each longest latency obtaining step in the longest latency set further includes:

acquiring a gap time; the gap time is the result of adding and summing the difference between the transaction starting time of the next waiting client in all the waiting client information sets and the transaction finishing time of the current waiting client;

and adding the second result to the gap time, and subtracting the time spent by the last waiting client in the waiting client information set for handling the service to obtain the longest waiting time corresponding to the waiting client information set.

and adding the gap time to the sum of the time spent by each waiting client in the waiting client information set for handling the business to obtain the longest waiting time corresponding to the waiting client information set.

the difference of the time t subtracted from the service handling completion time of the client handling the service on each business window opened by the corresponding network point at the same time t is added to obtain a third result;

and subtracting the time spent by the last waiting client in the waiting client information set for handling the service after the second result and the third result are added to the gap time to obtain the longest waiting time corresponding to the waiting client information set.

and adding the gap time and the third result to the sum of the time spent by each waiting client in the waiting client information set for handling the business to obtain the longest waiting time corresponding to the waiting client information set.

when a business window is opened by a network point, the difference of the time t subtracted from the business handling completion time of a client handling business on the business window opened by the network point corresponding to the same time t is obtained to obtain a third result;

and subtracting the transaction starting time of the first waiting client in the waiting client information set from the transaction starting time of the last waiting client in the waiting client information set, and adding the third result to obtain the longest waiting time corresponding to the waiting client information set.

and subtracting the transaction starting time of the first waiting client in the waiting client information set from the transaction finishing time of the last waiting client in the waiting client information set, and adding the third result to obtain the longest waiting time corresponding to the waiting client information set.

Preferably, the longest waiting time prediction value of the waiting customer information set at the same time t is obtained by adding and averaging all the longest waiting times in the longest waiting time set at the time t in a period of time.

Preferably, the step of obtaining the longest waiting time prediction value of the waiting customer information set at the same time t includes:

setting a probability value;

and dividing the number of the longest waiting time predicted values of the waiting client information sets with the longest waiting time larger than or smaller than the same time t by the number of the longest waiting time in the longest waiting time set to be equal to the probability value to determine the longest waiting time predicted value of the waiting client information set with the same time t.

In order to achieve the above object, an embodiment of the present invention provides an apparatus for predicting the number of business windows of a bank outlet, including:

a waiting time threshold setting unit for setting a waiting time threshold; the waiting time threshold is the maximum value of the time difference between the starting time of entering a banking outlet and the starting time of starting to transact business, which is tolerated by a client;

the statistical unit is used for acquiring a waiting client information set of the website at the time t of each day in a time period;

the longest waiting time set acquisition unit is used for acquiring a longest waiting time set according to all waiting client information sets; each longest waiting time in the longest waiting time set represents the waiting time of the last waiting client in the waiting client information set at the same time t of each day in the time period or the time spent by all waiting clients in the waiting client information set for handling the business under the condition that a business window is supposed to be opened in a network node;

the waiting time predicted value obtaining unit is used for determining the longest waiting time predicted value of the waiting client information set at the same time t according to the longest waiting time set;

and the predicting unit is used for determining the number of the business windows opened by the network point at the moment t according to the maximum value of the number of the business windows of the network point, the waiting time threshold and the longest waiting time predicted value of the waiting customer information set at the same moment t.

Preferably, the prediction unit includes:

the first calculation module is used for rounding the quotient of the longest waiting time predicted value of the waiting customer information set at the same time t divided by the waiting time threshold value to obtain a first result;

and the comparison module is used for comparing the first result with the maximum value of the number of the business windows of the website, and the minimum value of the first result and the maximum value is the number of the business windows set by the website at the moment t.

Preferably, each piece of waiting client information of the waiting client information set acquired by the statistical unit includes a client ID and a corresponding serial number, a starting time of entering a bank branch, a transaction type, a transaction starting time, and a transaction completion time.

Preferably, the longest latency set acquiring unit includes:

the second calculation module is used for acquiring the time spent by each waiting client in the waiting client information set for handling the service according to the client ID and the corresponding service handling starting time and service handling finishing time;

the third calculation module is used for adding the time spent by each waiting client in the waiting client information set for handling the business to obtain a second result;

and the fourth calculation module is used for subtracting the time spent by the last waiting client in the waiting client information set for handling the business from the second result to obtain the longest waiting time corresponding to the waiting client information set.

Preferably, the longest latency set acquiring unit includes:

the fifth calculation module is used for acquiring the time spent by each waiting client in the waiting client information set for handling the service according to the client ID and the corresponding service handling starting time and service handling finishing time;

and the sixth calculating module is used for calculating the sum of the time spent by each waiting client in the waiting client information set for handling the business, and obtaining the longest waiting time corresponding to the waiting client information set.

Preferably, the longest waiting time set obtaining unit is further configured to, when a network node opens a business window, subtract the business transaction start time of the first waiting client in the waiting client information set from the business transaction start time of the last waiting client in the waiting client information set to obtain the longest waiting time corresponding to the waiting client information set.

Preferably, the longest waiting time set obtaining unit is further configured to, when a network node opens a business window, subtract a business transaction completion time of a last waiting client in the waiting client information set from a business transaction start time of a first waiting client in the waiting client information set to obtain the longest waiting time corresponding to the waiting client information set.

Preferably, the longest latency set acquiring unit further includes:

a seventh calculation module for obtaining the gap time; the gap time is the result of adding and summing the difference between the transaction starting time of the next waiting client in all the waiting client information sets and the transaction finishing time of the current waiting client;

the fourth calculating module is further configured to add the second result to the gap time and then subtract a time spent by the last waiting client in the waiting client information set to handle the service, so as to obtain a longest waiting time corresponding to the waiting client information set.

Preferably, the longest latency set acquiring unit further includes:

the sixth calculating module is further configured to add the gap time to the sum of the time spent by each waiting client in the waiting client information set to obtain the longest waiting time corresponding to the waiting client information set.

Preferably, the longest latency set acquiring unit further includes:

the eighth calculation module is used for subtracting the difference of the time t from the service handling completion time of the client handling the service on each business window arranged on each corresponding network point at the same time t and adding the differences to obtain a third result;

the fourth calculating module is further configured to subtract the time spent by the last waiting client in the waiting client information set to handle the service after the second result and the third result are added to the gap time, so as to obtain the longest waiting time corresponding to the waiting client information set.

Preferably, the longest latency set acquiring unit further includes:

the sixth calculating module is further configured to add the gap time and the third result to a sum of time spent by each waiting client in the waiting client information set to handle the service, and obtain the longest waiting time corresponding to the waiting client information set.

Preferably, the longest latency set acquiring unit further includes:

the eighth calculation module is used for subtracting the difference of the time t from the service handling completion time of the client handling the service on the business window set by the network point corresponding to the same time t under the condition that the network point sets a business window, and obtaining a third result;

and the fourth calculation module is further configured to subtract the service transaction start time of the first waiting client in the waiting client information set from the service transaction start time of the last waiting client in the waiting client information set and the third result to obtain the longest waiting time corresponding to the waiting client information set.

Preferably, the longest latency set acquiring unit further includes:

and the sixth calculation module is further configured to subtract the transaction completion time of the last waiting client in the waiting client information set by the transaction start time of the first waiting client in the waiting client information set and the third result, and obtain the longest waiting time corresponding to the waiting client information set.

Preferably, the predicted waiting time value obtaining unit is configured to add and average all longest waiting times in a longest waiting time set of a time t within a period of time to obtain the predicted longest waiting time value of the waiting client information set at the same time t.

Preferably, the waiting time prediction value obtaining unit includes:

the probability threshold value setting module is used for setting a probability value;

and a ninth calculating module, configured to divide the number of the longest waiting time prediction values of the waiting client information sets at the longest waiting time set, where the longest waiting time is greater than or less than the same time t, by the number of the longest waiting time in the longest waiting time set, where the number of the longest waiting time in the longest waiting time set is equal to the probability value, to determine the longest waiting time prediction value of the waiting client information set at the same time t.

In order to achieve the above object, an electronic device according to an embodiment of the present invention includes a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor implements the steps of the method for predicting the number of business windows of a bank outlet when executing the computer program.

In order to achieve the above object, the present application provides a readable storage medium, on which a computer program is stored, and the computer program, when executed, implements the steps of the method for predicting the number of business windows of a bank outlet.

Therefore, compared with the prior art, the technical scheme can accurately predict the number of the business windows of the bank outlets which should be set in the corresponding time period, so that the bank can plan the business number of the outlet windows at a certain time in advance, the bank can meet the requirements of customers by using the least outlet resources, certain customer satisfaction can be ensured, and the outlet resources can be saved.

Drawings

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, it is obvious that the drawings in the following description are only some embodiments described in the present application, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.

FIG. 1 is a flowchart of a method for predicting the number of business windows of a bank outlet according to an embodiment of the present disclosure;

FIG. 2 is a functional block diagram of an apparatus for predicting the number of business windows of a bank outlet according to an embodiment of the present disclosure;

FIG. 3 is a functional block diagram of a prediction unit in the device for predicting the business window number of a bank outlet according to the embodiment of the present disclosure;

fig. 4 is a functional block diagram of a longest waiting time set obtaining unit in the device for predicting the business window number of a banking outlet according to the embodiment of the present disclosure;

fig. 5 is a second functional block diagram of a longest waiting time set obtaining unit in the device for predicting the business window number of a bank outlet according to the embodiment of the present application;

fig. 6 is a third functional block diagram of a longest waiting time set obtaining unit in the device for predicting the business window number of a banking outlet according to the embodiment of the present disclosure;

fig. 7 is a fourth functional block diagram of a longest waiting time set obtaining unit in the device for predicting the business window number of a bank outlet according to the embodiment of the present application;

fig. 8 is a fifth functional block diagram of a longest waiting time set obtaining unit in the device for predicting the business window number of a bank outlet according to the embodiment of the present disclosure;

fig. 9 is a sixth functional block diagram of a longest waiting time set obtaining unit in the device for predicting the business window number of a bank outlet according to the embodiment of the present application;

fig. 10 is a schematic view of an electronic device according to an embodiment of the present application.

Detailed Description

The technical solutions in the embodiments of the present disclosure will be described more fully hereinafter with reference to the non-limiting exemplary embodiments shown in the accompanying drawings and detailed in the following description, taken in conjunction with the accompanying drawings, which illustrate, more fully, the exemplary embodiments of the present disclosure and their various features and advantageous details. It should be noted that the features illustrated in the drawings are not necessarily drawn to scale. The present disclosure omits descriptions of well-known materials, components, and process techniques so as not to obscure the example embodiments of the present disclosure. The examples given are intended merely to facilitate an understanding of ways in which the example embodiments of the disclosure may be practiced and to further enable those of skill in the art to practice the example embodiments. Thus, these examples should not be construed as limiting the scope of the embodiments of the disclosure.

Unless otherwise specifically defined, technical or scientific terms used herein shall have the ordinary meaning as understood by those of ordinary skill in the art to which this disclosure belongs. The use of "first," "second," and similar terms in this disclosure is not intended to indicate any order, quantity, or importance, but rather is used to distinguish one element from another. Further, in the various embodiments of the present disclosure, the same or similar reference numerals denote the same or similar components.

The waiting number of the customers and the type of the transaction at a certain time t (for example, 11 am) are roughly determined statistically in a certain period, that is, the waiting time of the customers is roughly determined at a certain time, which can be accurately obtained by the huge customer history data of the bank. When a proper waiting time threshold is set, the minimum value of the number of business windows opened by the bank outlets when the waiting time threshold is met can be obtained. In the technical scheme, the waiting time threshold is the maximum value of the starting time from the starting time of entering the banking outlet to the starting time of starting to transact business, which is tolerated by a client. Once the customer waits at the banking outlet for a time period exceeding the waiting time threshold, emotions are easily generated and even complaint events occur. If the waiting time of the customer at the banking outlet is less than the waiting time threshold, the satisfaction degree of the customer is improved. The planning can make the bank meet the requirements of customers by using the least network resources, thereby not only ensuring certain customer satisfaction, but also saving network resources.

Based on the above description, as shown in fig. 1, a flowchart of a method for predicting the number of business windows of a bank outlet is provided for the embodiments of the present application. The method for predicting the number of business windows of the bank outlets can be applied to a bank background server. In particular, the bank backend server may be a backend business server capable of providing the financial data processing involved in performing transactions. In this embodiment, the server may be an electronic device having data operation, storage function and network interaction function; software may also be provided that runs in the electronic device to support data processing, storage, and network interaction. The number of servers is not particularly limited in the present embodiment. The server may be one server, several servers, or a server cluster formed by several servers. The method comprises the following steps:

step 101): setting a waiting time threshold; wherein the waiting time threshold is the maximum value of the time difference between the starting time of entering the banking outlet and the starting time of starting to process the business, which is tolerated by the customer.

In this embodiment, the waiting time threshold may be set based on experience of business personnel at the banking site, or may be obtained through statistical evaluation of values given by customers in a questionnaire survey. How to set the latency threshold is not described in detail here, which is not the focus of the present solution.

Step 102): and acquiring a waiting customer information set of the network point at the time t of each day in a time period.

In this embodiment, the waiting clients at the same time every day in the past period are counted, and the time t may be 3 pm, assuming that the counted time range is m days. The set of waiting customers at 3 pm on day i of m days is: { C_i1、C_i2、C_i3……C_iN(i)}. Wherein, C_iN(i)And customer transaction information with the serial number N (i) is sequentially queued in the waiting customer set at 3 pm on the ith day of m days. N (i) represents the number of waiting clients corresponding to the same time t each day of m days. In practical applications, the number of waiting clients at the same time t may be the same or different. The transaction information includes: client ID and corresponding serial number, starting time of entering a bank outlet, transaction type, transaction starting time and transaction finishing time.

Step 103): acquiring a longest waiting time set according to all waiting client information sets; each longest waiting time in the longest waiting time set represents the waiting time of the last waiting client in the waiting client information set at the same time t of each day in the time period or the time spent by all waiting clients in the waiting client information set for handling the business under the condition that a business window is supposed to be opened in one network point.

From step 103, the longest latency set is divided into two cases, the first: each longest waiting time in the longest waiting time set represents the waiting time of the last waiting client in the waiting client information set at the same time t of each day in the time period under the condition that a business window is supposed to be opened in a network point.

In this embodiment, assuming that the banking outlet opens only one business window, the waiting time W of the last waiting client in the waiting client set corresponds to 3 pm on the ith day of m days_i,N(i)The formula of (1) is:

W_i,N(i)＝V_i,1+V_i,2+...+V_i,(N(i)-1) (1)

the waiting client set comprises N (i) waiting clients, the time required for the service handling of each waiting client is obtained by subtracting the service handling starting time from the service handling finishing time in the transaction information of the corresponding client of each waiting client, and the waiting time of the last waiting client is the sum of the time required for the service handling of the first N (i) -1 waiting clients.

In this embodiment, there is also a very special case, which is a simple application scenario of opening a business window, and it is not necessary to obtain the waiting time of the last waiting client through the formula (1). Waiting time W of the last waiting client in the waiting client set corresponding to 3 pm on the ith day of m days_i,N(i)Can also be expressed as:

W_i,N(i)＝T_1,N(i)-T_2,1 (2)

in formula 2, T_1,N(i)Indicating the starting time, T, at which the last waiting client in the waiting client set transacts the service_2,1Indicating the starting time of the first waiting client in the waiting client set to handle the service.

In the second case: each longest waiting time in the longest waiting time set represents the time spent by all waiting clients in the waiting client information set for handling business.

In this embodiment, the formula of the longest waiting time for waiting for the customer set at 3 pm on the ith day of m days may be represented as:

V＝V_i,1+V_i,2+...+V_i,(N(i)-1)+V_i,N(i) (3)

in the formula (3), there are n (i) waiting clients in the waiting client set, and the time required for the service transaction of each waiting client is obtained by subtracting the service transaction start time from the service transaction completion time in the transaction information of the corresponding client of each waiting client, and the sum of the time spent by all waiting clients in the waiting client information set is the longest waiting time.

Similarly, there is a very special case, which is a simple application scenario of opening a business window, and there is no need to obtain the waiting time of the last waiting client through the formula (3). The formula for the longest wait time for waiting on the customer set at 3 pm on the ith of m days is:

V＝T_2,N(i)-T_1,1 (4)

in the formula (4), T_2,N(i)Indicating the time of completion of the transaction of the last waiting client in the waiting client set, T_1,1Indicating the starting time of the transaction of the first waiting client in the waiting client set.

In practice, there is a time difference between when the current client has finished transacting business and before the next client begins transacting business in the business window. In order to calculate the waiting time of the last waiting client in the waiting client set more accurately, the time difference between the time when the current client finishes processing the service and the time when the next client starts processing the service in the business window can be determined by subtracting the time when the current client finishes processing the service from the starting time when the next client finishes processing the service, all the time differences in the waiting client set are added, and the result is added into formula (1) or formula (4), so that the estimated longest waiting time is more accurate.

Of course, it is also considered that, at the time t, the business window of the bank outlet is opened and the clients are handling business, which may affect the waiting time of the clients waiting later. Further, the precondition for calculating the longest waiting time is that a network node is assumed to open a business window. Based on this, the time required for the client to handle the business on each business window of the bank outlets set at the time t needs to be calculated. Assuming that 4 business windows are opened currently, the time required for the client to handle the business on each business window is obtained based on the formula (5), 4 time values are finally obtained, the 4 time values are added into the longest waiting time obtained by the previous calculation, and the finally obtained value is more accurate than the longest waiting time value estimated before.

Step 104): and determining the longest waiting time predicted value of the waiting customer information set at the same time t according to the longest waiting time set.

In this embodiment, the longest waiting time prediction value of the waiting client information set at the same time t is obtained by adding and averaging all the longest waiting times in the longest waiting time set at the time t within a time period.

In this embodiment, the obtaining of the longest waiting time prediction value of the waiting client information set at the same time t may further include:

setting a probability value; and dividing the number of the longest waiting time predicted values of the waiting client information sets with the longest waiting time larger than or smaller than the same time t by the number of the longest waiting time in the longest waiting time set to be equal to the probability value to determine the longest waiting time predicted value of the waiting client information set with the same time t.

In practice, there are many ways to determine the longest waiting time prediction value of the waiting client information set at the same time t according to the longest waiting time set, and how to calculate the longest waiting time prediction value is not described in detail here, which is not the focus of the present technical solution.

Step 105): and determining the number of the business windows opened by the network point at the moment t according to the maximum value of the number of the business windows of the network point, the waiting time threshold and the longest waiting time predicted value of the waiting customer information set at the same moment t.

In this embodiment, the step of acquiring the number of business windows opened by the network point at the time t includes:

In summary, as can be seen from fig. 1 and the above embodiments, the technical solution can accurately predict the number of business windows of the bank outlets that should be opened in the corresponding time period, so that the bank can plan the number of business windows at a certain time in advance, and the bank can meet the needs of customers by using the least number of outlet resources, thereby not only ensuring a certain customer satisfaction, but also saving outlet resources.

As shown in fig. 2, a functional block diagram of an apparatus for predicting the number of business windows of a bank outlet is provided for the embodiment of the present application. The method comprises the following steps:

a waiting time threshold setting unit 201 for setting a waiting time threshold; the waiting time threshold is the maximum value of the time difference between the starting time of entering a banking outlet and the starting time of starting to transact business, which is tolerated by a client;

a statistical unit 202, configured to obtain a set of waiting client information of the website at a time t of each day in a time period;

a longest waiting time set obtaining unit 203, configured to obtain a longest waiting time set according to all waiting client information sets; each longest waiting time in the longest waiting time set represents the waiting time of the last waiting client in the waiting client information set at the same time t of each day in the time period or the time spent by all waiting clients in the waiting client information set for handling the business under the condition that a business window is supposed to be opened in a network node;

a waiting time prediction value obtaining unit 204, configured to determine, according to the longest waiting time set, a longest waiting time prediction value of a waiting client information set at the same time t;

and the predicting unit 205 is configured to determine the number of business windows opened by the website at the time t according to the maximum value of the number of business windows of the website, the waiting time threshold, and the longest waiting time prediction value of the waiting customer information set at the same time t.

As shown in fig. 3, a functional block diagram of a prediction unit in the device for predicting the number of business windows of a bank outlet according to the embodiment of the present application is provided. The prediction unit 205 includes:

a first calculating module 2051, configured to round a quotient obtained by dividing a longest waiting time predicted value of the waiting customer information set at the same time t by the waiting time threshold to obtain a first result;

a comparing module 2052, configured to compare the first result with a maximum value of the number of business windows of the website, where the minimum value of the first result and the maximum value is the number of business windows opened by the website at the time t.

In this embodiment, each piece of waiting client information of the waiting client information set acquired by the statistical unit includes a client ID and a corresponding serial number, a start time of entering a bank outlet, a transaction type, a transaction start time, and a transaction completion time.

As shown in fig. 4, it is one of the functional block diagrams of the longest waiting time set obtaining unit in the device for predicting the business window number of a banking outlet according to the embodiment of the present application. The longest latency set acquisition unit 203 includes:

a second calculating module 2031, configured to obtain, according to the client ID and the corresponding service transaction starting time and service transaction completing time, time spent by each waiting client in the waiting client information set to transact the service;

a third calculating module 2032, configured to add the time spent by each waiting client in the waiting client information set to handle the service, so as to obtain a second result;

a fourth calculating module 2033, configured to subtract, from the second result, the time spent by the last waiting client in the waiting client information set to handle the service, to obtain the longest waiting time corresponding to the waiting client information set.

As shown in fig. 5, it is a second functional block diagram of the longest waiting time set obtaining unit in the device for predicting the business window number of a bank outlet according to the embodiment of the present invention. The longest latency set acquisition unit 203 includes:

a fifth calculating module 2031' configured to obtain, according to the client ID and the corresponding service transaction starting time and service transaction completing time, the time spent by each waiting client in the waiting client information set to transact the service;

a sixth calculating module 2032' configured to calculate a sum of time spent by each waiting client in the waiting client information set to handle the service, and obtain the longest waiting time corresponding to the waiting client information set.

In this embodiment, the longest waiting time set obtaining unit is further configured to, when a network node opens a business window, subtract the business transaction start time of the first waiting client in the waiting client information set from the business transaction start time of the last waiting client in the waiting client information set, and obtain the longest waiting time corresponding to the waiting client information set.

In this embodiment, the longest waiting time set obtaining unit is further configured to, when a network node opens a business window, subtract a business transaction completion time of a last waiting client in the waiting client information set from a business transaction start time of a first waiting client in the waiting client information set to obtain the longest waiting time corresponding to the waiting client information set.

On the basis of fig. 4, as shown in fig. 6, the longest latency set obtaining unit 203 further includes:

a seventh calculating module 2034 for obtaining the gap time; the gap time is the result of adding and summing the difference between the transaction starting time of the next waiting client in all the waiting client information sets and the transaction finishing time of the current waiting client;

the fourth calculating module 2033 is further configured to add the second result to the gap time and subtract the time spent by the last waiting client in the waiting client information set to handle the service, so as to obtain the longest waiting time corresponding to the waiting client information set.

On the basis of fig. 5, as shown in fig. 7, the longest latency set obtaining unit further includes:

the sixth calculating module 2032' is further configured to add the gap time to the sum of the time spent by each waiting client in the waiting client information set to obtain the longest waiting time corresponding to the waiting client information set.

On the basis of fig. 6, as shown in fig. 8, the longest latency set obtaining unit 203 further includes:

an eighth calculating module 2035, configured to subtract the difference of the time t from the service transaction completion time of the client handling the service on each business window opened by the corresponding website at the same time t, and add the difference to obtain a third result;

the fourth calculating module 2033 is further configured to add the second result and the third result to the gap time, and then subtract the time spent by the last waiting client in the waiting client information set to handle the service, to obtain the longest waiting time corresponding to the waiting client information set.

In addition to fig. 7, as shown in fig. 9, the longest latency set obtaining unit 203 further includes:

the sixth calculating module 2032' is further configured to add the gap time and the third result to the sum of the time spent by each waiting client in the waiting client information set to obtain the longest waiting time corresponding to the waiting client information set.

On the basis of fig. 6, the longest latency set obtaining unit 203 further includes:

an eighth calculating module 2035, configured to, when a network node sets a business window, subtract a difference between a business transaction completion time of a client handling business and a time t from the business transaction completion time of a client handling business on the business window set by the network node at the same time t, and obtain a third result;

the fourth calculating module 2033 is configured to subtract the service transaction start time of the first waiting client in the waiting client information set from the service transaction start time of the last waiting client in the waiting client information set and add the third result to obtain the longest waiting time corresponding to the waiting client information set.

On the basis of fig. 7, the longest latency set obtaining unit 203 further includes:

the sixth calculating module 2032' is configured to subtract the transaction completion time of the last waiting client in the waiting client information set from the transaction start time of the first waiting client in the waiting client information set and add the third result to obtain the longest waiting time corresponding to the waiting client information set.

In this embodiment, the waiting time prediction value obtaining unit is configured to add and average all longest waiting times in a longest waiting time set of a time t within a period of time to obtain a longest waiting time prediction value of a waiting client information set at the same time t.

In this embodiment, the predicted waiting time value obtaining unit includes:

and the waiting time predicted value calculating module is used for dividing the number of the longest waiting time predicted values of the waiting client information sets with the longest waiting time longer than or shorter than the same time t by the number of the longest waiting time in the longest waiting time set to be equal to the probability value so as to determine the longest waiting time predicted value of the waiting client information set with the same time t.

Fig. 10 is a schematic view of an electronic device according to an embodiment of the present disclosure. The method comprises a memory, a processor and a computer program which is stored on the memory and can run on the processor, wherein the processor realizes the steps of the method for predicting the business window number of the bank outlet when executing the computer program.

The specific functions implemented by the memory and the processor of the method for predicting the number of business windows of the bank outlets provided by the embodiment of the present specification can be explained in comparison with the foregoing embodiment of the present specification, and the number of business windows of the bank outlets predicted by the technical scheme can maximize the reasonable utilization of the outlet resources while allowing the user to wait for a relatively short time, and can achieve the technical effects of the foregoing embodiment, which is not described herein again.

In this embodiment, the memory may include a physical device for storing information, and typically, the information is digitized and then stored in a medium using an electrical, magnetic, or optical method. The memory according to this embodiment may further include: devices that store information using electrical energy, such as RAM, ROM, etc.; devices that store information using magnetic energy, such as hard disks, floppy disks, tapes, core memories, bubble memories, usb disks; devices for storing information optically, such as CDs or DVDs. Of course, there are other ways of memory, such as quantum memory, graphene memory, and so forth.

In this embodiment, the processor may be implemented in any suitable manner. For example, the processor may take the form of, for example, a microprocessor or processor and a computer-readable medium that stores computer-readable program code (e.g., software or firmware) executable by the (micro) processor, logic gates, switches, an Application Specific Integrated Circuit (ASIC), a programmable logic controller, an embedded microcontroller, and so forth.

In this embodiment, an embodiment of the present application further provides a readable storage medium, on which a computer program is stored, where the computer program is executed to implement the steps of the method for predicting the number of business windows of a bank outlet.

Therefore, the technical scheme can accurately predict the number of business windows of the bank outlets which should be set in the corresponding time period, so that the bank can plan the business number of the outlet windows at a certain time in advance, the bank can meet the requirements of customers by using the least outlet resources, certain customer satisfaction can be ensured, and the outlet resources can be saved. In a word, the number of business windows of the bank outlets predicted by the technical scheme can maximize the reasonable utilization of the outlet resources and enable users to wait for less time.

In the 90 s of the 20 th century, improvements in a technology could clearly distinguish between improvements in hardware (e.g., improvements in circuit structures such as diodes, transistors, switches, etc.) and improvements in software (improvements in process flow). However, as technology advances, many of today's process flow improvements have been seen as direct improvements in hardware circuit architecture. Designers almost always obtain the corresponding hardware circuit structure by programming an improved method flow into the hardware circuit. Thus, it cannot be said that an improvement in the process flow cannot be realized by hardware physical modules. For example, a Programmable Logic Device (PLD), such as a Field Programmable Gate Array (FPGA), is an integrated circuit whose Logic functions are determined by programming the Device by a user. A digital system is "integrated" on a PLD by the designer's own programming without requiring the chip manufacturer to design and fabricate application-specific integrated circuit chips. Furthermore, nowadays, instead of manually making an Integrated Circuit chip, such Programming is often implemented by "logic compiler" software, which is similar to a software compiler used in program development and writing, but the original code before compiling is also written by a specific Programming Language, which is called Hardware Description Language (HDL), and HDL is not only one but many, such as abel (advanced Boolean Expression Language), ahdl (alternate Language Description Language), traffic, pl (core unified Programming Language), HDCal, JHDL (Java Hardware Description Language), langue, Lola, HDL, laspam, hardbyscript Description Language (vhr Description Language), and the like, which are currently used by Hardware compiler-software (Hardware Description Language-software). It will also be apparent to those skilled in the art that hardware circuitry that implements the logical method flows can be readily obtained by merely slightly programming the method flows into an integrated circuit using the hardware description languages described above.

Those skilled in the art will also appreciate that, in addition to implementing clients and servers as pure computer readable program code, the same functionality can be implemented by logically programming method steps such that the clients and servers implement logic gates, switches, application specific integrated circuits, programmable logic controllers, embedded microcontrollers and the like. Such clients and servers may thus be considered a hardware component, and the means included therein for performing the various functions may also be considered as structures within the hardware component. Or even means for performing the functions may be regarded as being both a software module for performing the method and a structure within a hardware component.

From the above description of the embodiments, it is clear to those skilled in the art that the present application can be implemented by software plus necessary general hardware platform. Based on such understanding, the technical solutions of the present application may be essentially or partially implemented in the form of a software product, which may be stored in a storage medium, such as a ROM/RAM, a magnetic disk, an optical disk, etc., and includes several instructions for enabling a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method described in the embodiments or some parts of the embodiments of the present application.

The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments can be referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, both for the embodiments of the client and the server, reference may be made to the introduction of embodiments of the method described above.

The application may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The application may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.

Although the present application has been described in terms of embodiments, those of ordinary skill in the art will recognize that there are numerous variations and permutations of the present application without departing from the spirit of the application, and it is intended that the appended claims encompass such variations and permutations without departing from the spirit of the application.

Claims

1. A method for predicting the number of business windows of a bank outlet is characterized by comprising the following steps:

acquiring a waiting client information set of the website at the time t of each day in a time period, wherein each piece of waiting client information of the waiting client information set comprises a client ID and a corresponding serial number, an initial time of entering a bank website, a service handling type, a service handling initial time and a service handling completion time;

determining the number of business windows opened by the network point at the moment t according to the maximum value of the number of business windows of the network point, the waiting time threshold value and the longest waiting time predicted value of the waiting customer information set at the same moment t;

determining the number of business windows opened by the website at the moment t according to the maximum value of the number of business windows of the website, the waiting time threshold and the longest waiting time predicted value of the waiting customer information set at the same moment t, wherein the method comprises the following steps: rounding the quotient of the longest waiting time predicted value of the waiting customer information set at the same time t divided by the waiting time threshold value to obtain a first result; comparing the first result with the maximum value of the number of business windows of the website, and taking the minimum value as the number of business windows set by the website at the moment t;

when the longest waiting time set is obtained according to all waiting client information sets, the waiting time corresponding to the last waiting client in the waiting client information set or the time spent by all waiting clients in the waiting client information set is determined according to the time required by each waiting client for transacting the service and the time difference between the time when the current client transacts the service and the time when each waiting client begins to transact the service in the business window.

2. The method of claim 1, wherein each longest latency acquisition step in the set of longest latencies comprises:

3. The method of claim 1, wherein each longest latency acquisition step in the set of longest latencies comprises:

4. The method of claim 1, wherein each longest latency acquisition step in the set of longest latencies comprises:

5. The method of claim 1, wherein each longest latency acquisition step in the set of longest latencies comprises:

6. The method of claim 2, wherein each longest latency acquisition step in the set of longest latencies further comprises:

7. The method of claim 3, wherein each longest latency acquisition step in the set of longest latencies further comprises:

8. The method of claim 6, wherein each longest latency acquisition step in the set of longest latencies further comprises:

9. The method of claim 7, wherein each longest latency acquisition step in the set of longest latencies further comprises:

10. The method of claim 4, wherein each longest latency acquisition step in the set of longest latencies further comprises:

11. The method of claim 5, wherein each longest latency acquisition step in the set of longest latencies further comprises:

12. The method of claim 1, wherein the longest waiting time prediction value of the waiting customer information sets at the same time t is obtained by averaging all longest waiting times in the longest waiting time set at the time t within a period of time.

13. The method of claim 1, wherein the step of obtaining the longest waiting time prediction value of the waiting customer information sets at the same time t comprises:

setting a probability value;

14. An apparatus for predicting the number of business windows of a banking outlet, comprising:

the system comprises a counting unit, a service processing unit and a service processing unit, wherein the counting unit is used for acquiring a waiting client information set of the website at the time t of each day in a time period, and each piece of waiting client information of the waiting client information set comprises a client ID and a corresponding serial number, an initial time of entering a bank website, a service handling type, a service handling initial time and a service handling completion time;

the prediction unit is used for determining the number of business windows opened by the network point at the moment t according to the maximum value of the number of business windows of the network point, the waiting time threshold and the longest waiting time prediction value of the waiting customer information set at the same moment t;

wherein the prediction unit includes: the first calculation module is used for rounding the quotient of the longest waiting time predicted value of the waiting customer information set at the same time t divided by the waiting time threshold value to obtain a first result; the comparison module is used for comparing the first result with the maximum value of the number of the business windows of the website, and the minimum value of the first result and the maximum value is the number of the business windows set by the website at the moment t;

the longest waiting time set acquiring unit is further configured to determine the waiting time corresponding to the last waiting client in the waiting client information set or the time spent by all waiting clients in the waiting client information set to handle the service according to the time required by each waiting client to handle the service and the time difference between when the current client finishes handling the service and before each waiting client starts handling the service in the business window.

15. The apparatus of claim 14, wherein the longest latency set acquisition unit comprises:

16. The apparatus of claim 14, wherein the longest latency set acquisition unit comprises:

17. The apparatus according to claim 14, wherein the longest waiting time set obtaining unit is further configured to, when a network node opens a business window, subtract the business starting time of the first waiting client in the waiting client information set from the business starting time of the last waiting client in the waiting client information set to obtain the longest waiting time corresponding to the waiting client information set.

18. The apparatus according to claim 14, wherein the longest waiting time set obtaining unit is further configured to, when a network node opens a business window, subtract a business transaction completion time of a last waiting client in the waiting client information set from a business transaction start time of a first waiting client in the waiting client information set to obtain the longest waiting time corresponding to the waiting client information set.

19. The apparatus of claim 15, wherein the longest latency set acquisition unit further comprises:

20. The apparatus of claim 16, wherein the longest latency set acquisition unit further comprises:

21. The apparatus of claim 19, wherein the longest latency set acquisition unit further comprises:

22. The apparatus of claim 20, wherein the longest latency set acquisition unit further comprises:

23. The apparatus of claim 17, wherein the longest latency set acquisition unit further comprises:

24. The apparatus of claim 18, wherein the longest latency set acquisition unit further comprises:

25. The apparatus according to claim 14, wherein the waiting time prediction value obtaining unit obtains the longest waiting time prediction value of the waiting client information set at a time t by averaging all longest waiting times in the longest waiting time set at the same time t.

26. The apparatus of claim 14, wherein the latency prediction value acquisition unit comprises:

27. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor when executing the computer program performs the steps of the method for predicting the number of banking outlet business windows according to any one of claims 1 to 13.

28. A readable storage medium having stored thereon a computer program, wherein the computer program when executed implements the steps of the method of predicting a number of banking outlet business windows of any one of claims 1 to 13.