Banking outlet personnel configuration method and device and electronic equipment

Abstract

The invention discloses a bank outlet personnel configuration method and device and electronic equipment. Relates to the field of big data, and the method comprises the steps: determining a to-be-predicted time period of a target website, obtaining the number of business handling people of each business point of the target website in M historical time periods, and obtaining M target arrays; model parameters of the initial prediction model are adjusted through the sample data set and a preset optimization algorithm, a target prediction model is obtained, and the preset optimization algorithm is a spider bee optimization algorithm combined with a preset disturbance strategy; inputting the M target arrays into a target prediction model, and according to the target prediction model, determining a predicted customer number of each service point of the target network point in the to-be-predicted time period; and determining the personnel configuration number of the target website according to the predicted customer number of each service point. Through the method and the device, the problem of relatively low accuracy of determining the network personnel deployment mode through the artificially predicted passenger flow number in the related technology is solved.

Description

Technical Field

[0001] The present application relates to the field of big data, and more specifically, to a method, device and electronic device for configuring bank branch personnel. Background Art

[0002] As the business volume in bank branches gradually increases, the amount of business that staff in bank branches need to handle has also increased significantly. In order to reduce the business workload of staff, it is usually necessary to allocate the number and positions of branch employees according to the number of people who go to the branch to handle business on that day, so as to avoid the situation where the number of customers is far greater than the number of staff, resulting in low efficiency of staff in handling business and long waiting time for customers.

[0003] In order to accurately configure branch staff, it is necessary to accurately predict the number of customers in the future. Currently, branch staff mainly rely on their own experience and intuition to manually predict the number of customers in each time period in the future.

[0004] However, this process is not only cumbersome, time-consuming and labor-intensive, but also prone to human error. Staff need to analyze historical data, holiday schedules, weather conditions, special events and other factors one by one, and then make passenger flow forecasts based on them. However, due to the different analytical capabilities and sensitivity to data of each person, this manual-dependent approach often cannot guarantee the accuracy and consistency of the forecast results, which in turn leads to inaccurate staffing within the outlets.

[0005] Currently, no effective solution has been proposed to address the problem of low accuracy in determining the method of staff deployment at outlets based on manually predicted passenger flow numbers in related technologies. Summary of the invention

[0006] The main purpose of the present application is to provide a bank branch staff configuration method, device and electronic equipment to solve the problem of low accuracy in determining branch staff deployment methods based on manually predicted passenger flow numbers in related technologies.

[0007] In order to achieve the above-mentioned purpose, according to one aspect of the present application, a method for configuring bank branch personnel is provided. The method includes: determining the time period to be predicted of the target branch, and obtaining the number of business operators of each business point of the target branch in M ​​historical time periods, and obtaining M target arrays, wherein each target array contains P values, each value corresponds to the number of business operators of a business point, the time period to be predicted has the same attributes as the historical time period, and M and P are positive integers; adjusting the model parameters of the initial prediction model through a sample data set and a preset optimization algorithm to obtain a target prediction model, wherein the sample data set is composed of multiple groups of sample data, each group of sample data includes the number of business operators of each business point of the target branch in multiple sample historical time periods, and the number of business operators of each business point of the target branch in the sample target time period, and the preset optimization algorithm is a spider bee optimization algorithm combined with a preset disturbance strategy; inputting the M target arrays into the target prediction model, and determining the predicted number of customers of each business point of the target branch in the time period to be predicted according to the target prediction model; determining the number of personnel configurations of the target branch according to the predicted number of customers of each business point.

[0008] Optionally, the model parameters of the initial prediction model are adjusted by the sample data set and the preset optimization algorithm to obtain the target prediction model, including: setting the initial parameters of the preset optimization algorithm, and generating initial values ​​of each target individual to obtain n initial value sets, wherein the initial parameters include: the total number of iterations of the preset optimization algorithm, the number of population individuals n of the spider bee optimization algorithm, each initial value set contains a plurality of initial values ​​that are the same as the number of model parameters, the initial values ​​are used to determine the model parameters, and n is a positive integer; determining the initial value set with the highest prediction accuracy from the n initial value sets by the spider bee optimization algorithm to obtain a first initial value set; based on The first initial value set is perturbed according to a preset perturbation strategy to obtain a second initial value set; the prediction accuracy of the first initial value set and the second initial value set is determined, and the initial value set with the highest prediction accuracy is determined as the candidate initial value set, and it is judged whether the current number of iterations is equal to the total number of iterations; when the current number of iterations is not equal to the total number of iterations, the step of generating the initial value of each target individual is re-executed according to the candidate initial value set until the current number of iterations is equal to the total number of iterations; when the current number of iterations is equal to the total number of iterations, the candidate initial value set is determined as the model parameters of the initial prediction model to obtain the target prediction model.

[0009] Optionally, determining the initial value set with the highest prediction accuracy from n initial value sets by the spider bee optimization algorithm to obtain the first initial value set includes: generating a first random number and a second random number, and determining a calculation formula for optimizing each initial value set according to the size relationship between the first random number and the second random number, and updating the n initial value sets according to the calculation formula to obtain n updated initial value sets; judging whether there is a previous iteration cycle in the current iteration cycle; in the absence of a previous iteration cycle, substituting the n updated initial value sets as model parameters into the initial prediction model respectively to obtain n first initial prediction models, and using the sample data set to determine the prediction accuracy of each first initial prediction model to obtain n prediction accuracy rates. , and determine the updated initial value set in the first initial prediction model with the highest accuracy as the first initial value set; in the case of the existence of the previous iteration cycle, obtain the candidate initial value set obtained in the previous iteration cycle, and substitute the n updated initial value sets as model parameters into the initial prediction model respectively, to obtain n second initial prediction models, and use the sample data set to determine the prediction accuracy of each second initial prediction model, to obtain n prediction accuracy rates, and determine the maximum prediction accuracy rate from the n prediction accuracy rates; compare the maximum prediction accuracy rate with the prediction accuracy rate of the third initial prediction model, and determine the initial value set in the model with higher prediction accuracy rate as the first initial value set, wherein the model parameters in the third initial prediction model are the candidate initial values.

[0010] Optionally, updating n initial value sets according to a calculation formula to obtain n updated initial value sets includes: optimizing the n initial value sets according to the calculation formula to obtain n optimized initial value sets; perturbing each optimized initial value set respectively through the Cauchy perturbation strategy to obtain n perturbed initial value sets; inputting the n optimized initial value sets and the n perturbed initial value sets as model parameters into the initial prediction model respectively to obtain multiple fourth initial prediction models, and calculating the prediction accuracy of each fourth initial prediction model; sorting the prediction accuracy from large to small, and determining the initial value sets in the fourth initial prediction model corresponding to the prediction accuracy in the top n places as the n updated initial value sets.

[0011] Optionally, perturbing the first initial value set according to a preset perturbation strategy to obtain the second initial value set includes: perturbing the first initial value set according to a Gaussian perturbation strategy to obtain the second initial value set.

[0012] Optionally, determining the prediction accuracy of the first initial value set and the second initial value set, and determining the initial value set with the highest prediction accuracy as the candidate initial value set includes: inputting the first initial value set as a model parameter into the initial prediction model to obtain a fifth initial prediction model, and determining the accuracy of the fifth initial prediction model through a sample data set to obtain a first accuracy rate; inputting the second initial value set as a model parameter into the initial prediction model to obtain a sixth initial prediction model, and determining the accuracy of the sixth initial prediction model through a sample data set to obtain a second accuracy rate; comparing the first accuracy rate and the second accuracy rate, and obtaining the initial value set corresponding to the larger accuracy of the first accuracy rate and the second accuracy rate to obtain a candidate initial value set.

[0013] Optionally, determining the number of staff to be deployed at a target outlet based on the predicted number of customers at each business point includes: obtaining the basic number of customers and the basic number of staff to be deployed at each business point; calculating the difference between the predicted number of customers and the basic number of customers at each business point to obtain P differences; and adjusting the basic number of staff to be deployed at each business point based on the P differences to obtain the number of staff to be deployed at the target outlet.

[0014] In order to achieve the above-mentioned purpose, according to another aspect of the present application, a device for configuring bank branch personnel is provided. The device includes: an acquisition unit, which is used to determine the time period to be predicted of the target branch, and obtain the number of business operators of each business point of the target branch in M ​​historical time periods, and obtain M target arrays, wherein each target array contains P values, each value corresponds to the number of business operators of a business point, the time period to be predicted has the same attributes as the historical time period, and M and P are positive integers; an adjustment unit, which is used to adjust the model parameters of the initial prediction model through a sample data set and a preset optimization algorithm to obtain a target prediction model, wherein the sample data set is composed of multiple groups of sample data, each group of sample data includes the number of business operators of each business point of the target branch in multiple sample historical time periods, and the number of business operators of each business point of the target branch in the sample target time period, and the preset optimization algorithm is a spider bee optimization algorithm combined with a preset disturbance strategy; a prediction unit, which is used to input the M target arrays into the target prediction model, and determine the predicted number of customers of each business point of the target branch in the time period to be predicted according to the target prediction model; a determination unit, which is used to determine the number of personnel configured for the target branch according to the predicted number of customers of each business point.

[0015] In an embodiment of the present application, a time period to be predicted of a target outlet is determined, and the number of business transactions of each business point of the target outlet in M ​​historical time periods is obtained to obtain M target arrays, wherein each target array contains P values, each value corresponds to the number of business transactions of a business point, the time period to be predicted has the same attributes as the historical time period, and M and P are positive integers; the model parameters of the initial prediction model are adjusted through a sample data set and a preset optimization algorithm to obtain a target prediction model, wherein the sample data set is composed of multiple groups of sample data, each group of sample data includes the number of business transactions of each business point of the target outlet in multiple sample historical time periods, and the number of business transactions of each business point of the target outlet in the sample target time period, and the preset optimization algorithm is a spider bee optimization algorithm combined with a preset disturbance strategy; the M target arrays are input into the target prediction In the model, the predicted number of customers of each business point of the target outlet in the time period to be predicted is determined according to the target prediction model; the number of staff configuration of the target outlet is determined according to the predicted number of customers of each business point, by setting an initial prediction model, and adjusting the model parameters of the initial prediction model through a sample data set and a preset optimization algorithm, a more accurate target prediction model is obtained, and the target prediction model is used to predict the number of business transactions in the time period to be predicted based on the number of business transactions of the target outlet in the historical period, so that staff are allocated to different business points according to the prediction results, thereby achieving the purpose of improving the prediction accuracy of the number of business transactions, thereby achieving the technical effect of improving the accuracy of staff configuration, and then solving the problem of low accuracy in determining the outlet personnel deployment method by manually predicting the number of passenger flow in related technologies. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The drawings constituting a part of the present application are used to provide a further understanding of the present application. The illustrative embodiments and descriptions of the present application are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0017] Figure 1 A hardware structure block diagram of a computer terminal for implementing a method for configuring bank branch personnel is shown;

[0018] Figure 2 It is a flow chart of the method for configuring bank branch personnel provided in Example 1 of the present application;

[0019] Figure 3 It is a schematic diagram of a bank branch staff configuration device provided according to Example 2 of the present application;

[0020] Figure 4 It is a structural block diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0021] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0022] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0023] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0024] It should be noted that the bank branch personnel configuration method, device and electronic equipment determined in the present disclosure can be used in the big data field, and can also be used in any field other than the big data field. The application field of the bank branch personnel configuration method, device and electronic equipment determined in the present disclosure is not limited.

[0025] It should be noted that the collected information, user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) used in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of relevant data are in compliance with the relevant laws, regulations and standards of the relevant regions, necessary confidentiality measures are taken, and public order and good customs are not violated. Corresponding operation entrances are provided for users to choose to authorize use or refuse use. If the user chooses to refuse, the expert decision-making process is entered. For example, an interface is set between this system and relevant users or institutions. Before obtaining relevant information, it is necessary to send an acquisition request to the aforementioned user or institution through the interface, and obtain relevant information after receiving the consent information fed back by the aforementioned user or institution.

[0026] The embodiments or examples of the present disclosure are not exhaustive, but are only illustrative of some embodiments or examples, and are not intended to be specific limitations on the scope of protection of the present disclosure. In the absence of contradiction, each step in a certain embodiment or example can be implemented as an independent example, and the steps can be combined arbitrarily. For example, the scheme after removing some steps in a certain embodiment or example can also be implemented as an independent example, and the order of the steps in a certain embodiment or example can be arbitrarily exchanged. In addition, the optional methods or optional examples in a certain embodiment or example can be combined arbitrarily; in addition, the various embodiments or examples can be combined arbitrarily, for example, some or all steps of different embodiments or examples can be combined arbitrarily, and a certain embodiment or example can be combined arbitrarily with the optional methods or optional examples of other embodiments or examples.

[0027] For the convenience of description, some nouns or terms involved in the embodiments of the present application are explained below:

[0028] Gaussian perturbation and Cauchy perturbation are two random perturbation methods in the mathematical field, which are widely used in optimization algorithms and signal processing. They introduce randomness into existing solutions or signals to increase the exploration ability of the search space, help the algorithm jump out of the local optimal solution, and improve the global search performance. The advantage of Gaussian perturbation is that it has good mathematical properties, it is easy to control the intensity of the perturbation (through variance adjustment), and in many cases it can ensure the stability of the optimization algorithm. The advantage of Cauchy perturbation is that it can more effectively explore the remote areas of the search space, which helps the algorithm jump out of the deep and narrow local optimal solution.

[0029] Deep Extreme Learning Machine (DELM) is a neural network model based on Extreme Learning Machine (ELM), which enhances the model's feature extraction capability and classification performance by introducing a deep structure.

[0030] The spider bee optimization algorithm is an optimization algorithm based on bionics. The spider bee optimization algorithm has good global search capabilities, but it is easy to fall into local optimal solutions.

[0031] Example 1

[0032] According to an embodiment of the present application, a method embodiment for configuring bank branch personnel is also provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0033] The method embodiment provided in the first embodiment of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Figure 1 The hardware structure block diagram of a computer terminal for implementing the configuration method of bank branch personnel is shown. Figure 1 As shown, the computer terminal 10 (or mobile device) may include one or more (102a, 102b, ..., 102n are used to illustrate) processors 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory 104 for storing data, and a transmission device 106 for communication functions. In addition, it may also include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of the BUS bus), a network interface, a power supply and / or a camera. It can be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the above electronic device. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations are shown.

[0034] It should be noted that the one or more processors 102 and / or other data processing circuits described above may generally be referred to herein as "data processing circuits". The data processing circuits may be embodied in whole or in part as software, hardware, firmware, or any other combination thereof. In addition, the data processing circuit may be a single independent processing module, or may be incorporated in whole or in part into any of the other components in the computer terminal 10 (or mobile device). As described in the embodiments of the present application, the data processing circuit acts as a processor control (e.g., selection of a variable resistor terminal path connected to an interface).

[0035] The memory 104 can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the configuration method of bank branch personnel in the embodiment of the present application. The processor 102 executes various functional applications and data processing by running the software programs and modules stored in the memory 104, that is, the configuration method of bank branch personnel described above is realized. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories may be connected to the computer terminal 10 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0036] The transmission device 106 is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of the computer terminal 10. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0037] The display may be, for example, a touch screen liquid crystal display (LCD) that enables a user to interact with a user interface of the computer terminal 10 (or mobile device).

[0038] Under the above operating environment, this application provides Figure 2 The bank branch staffing method shown. Figure 2 1 is a flow chart of a method for configuring bank branch personnel according to Example 1 of the present application. Figure 2 As shown, the method includes:

[0039] Step S201, determine the time period to be predicted of the target outlet, and obtain the number of business transactions of each business point of the target outlet in M ​​historical time periods, and obtain M target arrays, where each target array contains P values, each value corresponds to the number of business transactions of a business point, the time period to be predicted has the same attributes as the historical time period, and M and P are positive integers.

[0040] Specifically, the target branch can be any bank branch. Since the number of customers received by the branch varies in different time periods, when making predictions, it is necessary to be specific to a certain time period on any date. For example, the time on the date can be segmented into 2-hour segments to obtain multiple business processing time periods, and any time period for which customer quantity prediction is required can be determined as the time period to be predicted.

[0041] In order to accurately predict the number of users in the predicted period, it is necessary to obtain the number of business transactions at each business point of the target outlets in M ​​historical periods, thereby obtaining M target arrays, and then predict the number of users in the predicted period based on the number of business transactions in the M target arrays.

[0042] For example, if the time period to be predicted is from 14:00 to 16:00 on date A, the historical time period obtained may be from 14:00 to 16:00 on date BF before date A, and the number of people handling business at each business point in the target outlet, where the business point may be, for example, an ATM, a counter, and a self-service machine, etc., and 5 target arrays may be obtained, each of which has the number of people handling business at the ATM, the counter, and the self-service machine. The above 5 target arrays may be represented by Table 1:

[0043] Table 1

[0044] Date (14:00-16:00) Number of ATMs Number of people at the counter Number of people at self-service machines B 2 10 5 C 3 12 6 D 5 15 8 E 4 12 5 F 2 11 4

[0045] It should be noted that since the number of users going to the target outlets to handle business on different dates is different, when selecting historical time periods, it is necessary to ensure that the attributes of the time period to be predicted are the same as those of the historical time periods, that is, the attributes of the dates to which the time period to be predicted and the historical time period belong need to be the same, for example, the dates need to be both weekdays, or both weekends, etc., so as to ensure the accuracy of predicting the number of users in the time period to be predicted based on the data of the historical time period.

[0046] Step S202, adjusting the model parameters of the initial prediction model through the sample data set and the preset optimization algorithm to obtain the target prediction model, wherein the sample data set is composed of multiple groups of sample data, each group of sample data includes the number of business transactions of each business point of the target outlet under multiple sample historical time periods, and the number of business transactions of each business point of the target outlet under the sample target time period, and the preset optimization algorithm is a spider bee optimization algorithm combined with a preset disturbance strategy.

[0047] It should be noted that the initial prediction model can be a deep extreme learning machine neural network model, and the parameters that need to be set in the model are optimized by a preset optimization algorithm to obtain a prediction model with higher accuracy, wherein the model parameters include at least one of the following: the number of hidden layer nodes, the type of activation function, the kernel function parameter, the output weight, and the learning rate parameter.

[0048] Specifically, when optimizing the parameters of the initial prediction model, it is necessary to set a sample data set and a preset optimization algorithm for optimizing the parameters, so that it is possible to determine whether the accuracy of the model parameters optimized by the preset optimization algorithm meets the requirements based on the sample data set, thereby ensuring the accuracy of the model optimization operation.

[0049] It should be noted that when setting the sample data set, it is necessary to obtain multiple sample data, and divide the multiple sample data into training group and test group according to preset proportions. The model parameters are optimized through the training group, and the model accuracy is determined using the test group, thereby ensuring the accuracy of the model in predicting the number of business transactions.

[0050] It should be noted that when obtaining sample data, each sample data needs to include the number of business transactions in multiple historical time periods with the same attributes, as well as the actual number of business transactions in the sample target time period with the same attributes as the historical time period. Then, the model prediction accuracy can be judged by comparing the model prediction results with the actual number of business transactions, and the model parameters can be determined based on the accuracy.

[0051] Step S203, inputting the M target arrays into the target prediction model, and determining the predicted number of customers of each business point of the target network point in the prediction period according to the target prediction model.

[0052] Specifically, after optimizing the model parameters of the initial prediction model through the sample data set and the preset optimization algorithm, a target prediction model with a more accurate prediction accuracy is obtained. At this time, M target arrays can be input into the target prediction model, and the M target arrays can be analyzed and predicted according to the target prediction model to obtain the predicted number of customers for each business point in the prediction period, and then the staffing required for the target outlets can be determined based on the predicted number of customers.

[0053] Step S204, determining the number of personnel to be deployed at the target outlets according to the predicted number of customers at each business outlet.

[0054] Specifically, when the predicted number of customers for each business point is obtained, the number of personnel assigned to each business point can be determined based on the difference between the predicted number of customers and the basic number of customers, thereby ensuring the accuracy of personnel allocation at each business point.

[0055] The method for configuring bank branch personnel provided in the embodiment of the present application determines the time period to be predicted of the target branch, and obtains the number of business operators of each business point of the target branch in M ​​historical time periods, thereby obtaining M target arrays, wherein each target array contains P numerical values, each numerical value corresponds to the number of business operators of a business point, the time period to be predicted has the same attributes as the historical time period, and M and P are positive integers; the model parameters of the initial prediction model are adjusted through a sample data set and a preset optimization algorithm to obtain a target prediction model, wherein the sample data set is composed of multiple groups of sample data, each group of sample data includes the number of business operators of each business point of the target branch in multiple sample historical time periods, and the number of business operators of each business point of the target branch in the sample target time period, and the preset optimization algorithm is a spider bee optimization algorithm combined with a preset disturbance strategy; the M target arrays are input into the target prediction model, and the predicted number of customers of each business point of the target branch in the time period to be predicted is determined according to the target prediction model; a method for determining the number of personnel to be configured for the target branch is determined according to the predicted number of customers of each business point. By setting an initial prediction model and adjusting the model parameters of the initial prediction model through a sample data set and a preset optimization algorithm, a more accurate target prediction model is obtained, and the target prediction model is used to predict the number of business transactions in the prediction period based on the number of business transactions at the target outlets in the historical period, so that staff are allocated to different business points according to the prediction results, thereby achieving the purpose of improving the prediction accuracy of the number of business transactions, thereby achieving the technical effect of improving the accuracy of staff configuration, and further solving the problem of low accuracy in determining the deployment method of outlet personnel by manually predicting the number of passenger flow in related technologies.

[0056] In order to obtain a target prediction model with a high prediction accuracy, optionally, in the configuration method of bank branch personnel provided in the embodiment of the present application, the model parameters of the initial prediction model are adjusted through the sample data set and the preset optimization algorithm, and the target prediction model is obtained, including: setting the initial parameters of the preset optimization algorithm, and generating initial values ​​of each target individual, and obtaining n initial value sets, wherein the initial parameters include: the total number of iterations of the preset optimization algorithm, the number of population individuals n of the spider bee optimization algorithm, each initial value set contains a plurality of initial values ​​that are the same as the number of model parameters, and the initial values ​​are used to determine the model parameters, and n is a positive integer; the prediction accuracy is determined from the n initial value sets by the spider bee optimization algorithm The initial value set with the highest prediction accuracy is selected to obtain a first initial value set; the first initial value set is perturbed according to a preset perturbation strategy to obtain a second initial value set; the prediction accuracy of the first initial value set and the second initial value set is determined, and the initial value set with the highest prediction accuracy is determined as a candidate initial value set, and it is judged whether the current number of iterations is equal to the total number of iterations; when the current number of iterations is not equal to the total number of iterations, the step of generating initial values ​​for each target individual is re-executed according to the candidate initial value set until the current number of iterations is equal to the total number of iterations; when the current number of iterations is equal to the total number of iterations, the candidate initial value set is determined as the model parameters of the initial prediction model to obtain the target prediction model.

[0057] Specifically, the preset optimization algorithm may be a spider bee optimization algorithm. When optimizing the model parameters of the initial prediction model, it is first necessary to set the initial parameters of the preset optimization algorithm, including the total number of optimization iterations t max , preset the number of target individuals and initial values ​​in the optimization algorithm, thereby obtaining n initial value sets, and selecting the optimal model parameters from the n initial value sets in the first iteration operation, wherein each target individual corresponds to a set of model parameters, and the number of model parameters to be determined is the same as the number of initial values ​​in each target individual. For example, n can be 5, and when the model parameters are 5 parameters, the 5 initial value sets obtained can be: [a1, b1, c1, d1, e1], [a2, b2, c2, d2, e2], [a3, b3, c3, d3, e3], [a4, b4, c4, d4, e4], [a5, b5, c5, d5, e5].

[0058] It should be noted that after obtaining n initial value sets, it is necessary to use a preset optimization algorithm to start iterative optimization of the n initial value sets. First, it is necessary to select the first initial value set that makes the accuracy of the initial prediction model the highest from the n initial value sets through the spider bee optimization algorithm. The method for determining the first initial value set is to input each initial value set as a model parameter into the initial prediction model respectively, and calculate the accuracy of the initial prediction model carrying the parameters through the sample data in the sample data set to obtain the accuracy of each initial value set.

[0059] It should be noted that after obtaining the first initial value set, it is necessary to use a preset perturbation strategy to perform a perturbation operation on the initial values ​​in the first initial value set to obtain a second initial value set, and select the initial value set with the highest accuracy from the first initial value set and the second initial value set to obtain a candidate initial value set, thereby improving the local search capability and ensuring the comprehensiveness of the initial value set selection.

[0060] It should be noted that after obtaining the candidate initial value set, it indicates that the current iteration calculation has been completed. At this time, it is necessary to determine whether the current number of iterations is equal to the total number of iterations t max , and when it is equal to the total number of iterations, the representation completes the optimization operation, determines the current optimal solution, that is, the candidate initial value set as the model parameters of the initial prediction model, and then obtains the target prediction model. When the current number of iterations is not equal to the total number of iterations, the representation still needs to perform the next round of operations. At this time, it is necessary to re-execute the steps of generating the initial values ​​of each target individual, recalculate a new candidate initial value set, and compare the accuracy of the candidate initial value set of this round with the candidate initial value set of the previous round, so as to update the candidate initial value set, and ensure that after each round of iterative calculation, the obtained candidate initial value set is the optimal value under multiple iterative calculations, thereby ensuring the accuracy of the determination of the model parameters.

[0061] This embodiment optimizes n initial value sets by using a preset optimization algorithm and a preset perturbation algorithm, and optimizes the candidate initial value sets obtained in each round of iteration through multiple iterations, thereby ensuring the accuracy of the model parameters of the prediction model.

[0062] In order to ensure the accuracy of the candidate initial values, optionally, in the configuration method for bank branch personnel provided in the embodiment of the present application, the spider bee optimization algorithm is used to determine the initial value set with the highest prediction accuracy from the n initial value sets, and obtaining the first initial value set includes: generating a first random number and a second random number, and determining a calculation formula for optimizing each initial value set according to the size relationship between the first random number and the second random number, and updating the n initial value sets according to the calculation formula to obtain n updated initial value sets; judging whether there is a previous iteration cycle in the current iteration cycle; in the case that there is no previous iteration cycle, respectively substituting the n updated initial value sets as model parameters into the initial prediction model to obtain n first initial prediction models, and using the sample data set to determine each first initial prediction model. The prediction accuracy of the model is obtained, and n prediction accuracy rates are obtained, and the updated initial value set in the first initial prediction model with the highest accuracy is determined as the first initial value set; in the case of the existence of the previous iteration cycle, the candidate initial value set obtained in the previous iteration cycle is obtained, and the n updated initial value sets are respectively substituted into the initial prediction model as model parameters to obtain n second initial prediction models, and the prediction accuracy of each second initial prediction model is determined using the sample data set to obtain n prediction accuracy rates, and the maximum prediction accuracy rate is determined from the n prediction accuracy rates; the maximum prediction accuracy rate is compared with the prediction accuracy rate of the third initial prediction model, and the initial value set in the model with higher prediction accuracy rate is determined as the first initial value set, wherein the model parameters in the third initial prediction model are the candidate initial values.

[0063] Specifically, when determining the first initial value set through the spider bee optimization algorithm, it is necessary to first generate a first random number and a second random number, and determine an optimized calculation formula based on the first random number and the second random number, so as to update the n initial value sets and obtain n updated initial value sets.

[0064] It should be noted that the first random number and the second random number may be p and k, where p is a random number in [0, 1], and k is calculated by the following formula (1):

[0065]

[0066] Among them, t is the current iteration number, t max is the total number of iterations.

[0067] 1. When p is less than k, each initial value set can be updated by the following calculation process:

[0068]

[0069] Among them, r3 and r4 are two random numbers in [0, 1]. is the set of initial values ​​after the i-th update.

[0070] Formula (2) is as follows:

[0071]

[0072] in, and are any two initial value sets among the n initial value sets, is the i-th initial value set currently being optimized, To complete the optimized i-th initial value set, μ1 can be calculated by formula (3):

[0073] μ1=|rn|*r1 (3)

[0074] Where r1 is a random number between 0 and 1, and rn is a random number generated according to a normal distribution.

[0075] Formula (4) is as follows:

[0076]

[0077] Among them, H and L are the lower limit and upper limit of the initial value at each business point, respectively, and r2 is a random number between 0 and 1. is the i-th initial value set currently being optimized, To complete the optimized i-th initial value set, μ2 can be calculated by formula (5):

[0078] μ2=B*cos(2πl) (5)

[0079] Where l is a randomly generated number between 1 and -2, and B can be calculated using formula (6):

[0080]

[0081] 2. When p is greater than or equal to k, each initial value set can be updated by the following calculation process:

[0082]

[0083] Among them, r3 and r4 are two random numbers in [0, 1]. is the set of initial values ​​after the i-th update.

[0084] Formula (7) is as follows:

[0085]

[0086] in, are any initial value sets among the n initial value sets, is the i-th initial value set currently being optimized, To complete the optimized i-th initial value set, r5 is a vector representing a randomly generated value in the interval [0, 1], and C is calculated by formula (8):

[0087]

[0088] Where r6 is a random number in the interval [0, 1], t is the current iteration number, and tmax is the total iteration number.

[0089] Formula (9) is as follows:

[0090]

[0091] in, is the i-th initial value set currently being optimized, To complete the optimized i-th initial value set, vc is a vector generated between k and -k according to the normal distribution, and k can be calculated by formula (1).

[0092] It should be noted that after obtaining n updated initial value sets, it is necessary to select the best updated initial value set from them. At this time, in order to ensure the accuracy of the initial value set, it is necessary to first determine whether the current iteration cycle has a previous iteration cycle.

[0093] In the absence of the previous iteration cycle, this iterative calculation is characterized as the first iterative calculation. At this time, the n updated initial value sets are directly substituted into the initial prediction model as model parameters to obtain n first initial prediction models, and the prediction accuracy of each first initial prediction model is determined using the sample data set to obtain n prediction accuracy rates, and the updated initial value set in the first initial prediction model with the highest accuracy is determined as the first initial value set, thereby selecting the first initial value set with the highest accuracy from multiple initial value sets according to the prediction accuracy rate.

[0094] When there is a previous iteration cycle, since a candidate initial value set with the highest accuracy will be obtained after the calculation of the previous iteration cycle is completed, it is necessary to perform the iterative calculation of this round on the candidate initial value set and the n updated initial value sets together, and determine the initial value set with the highest prediction accuracy as the first initial value set, so as to ensure the accuracy of the first initial value set obtained in each round of calculation.

[0095] It should be noted that after obtaining the first initial value set, the n updated initial value sets can be updated again according to the first initial value set to obtain n second-updated initial value sets, and the updated first initial value set can be determined from the n second-updated initial value sets, thereby improving the prediction accuracy of the first initial value set.

[0096] First, the calculation formula used to update the n updated initial value sets again can be determined as follows:

[0097]

[0098] in, is the initial value set after the i-th secondary update, formula (10) can be shown as follows:

[0099]

[0100] in, is the first initial value set, is the i-th updated initial value set, and l is a randomly generated number between 1 and -2.

[0101] Formula (11) can be expressed as follows:

[0102]

[0103] Among them, r3 is a random number created in the interval [0, 1]; γ is a number generated according to Levy flight; and are three sets randomly selected from the n updated initial value sets; U is a binary vector used to determine when to apply a step size to avoid building two nests at the same location; U is determined according to the following formula (12):

[0104]

[0105] Among them, r4 and r5 are two vectors representing random values ​​in the interval [0, 1].

[0106] After obtaining n updated initial value sets, the n updated initial value sets and the first initial value set can be used as model parameters to calculate the accuracy of each initial prediction model, and the initial value set with the highest accuracy is determined as the updated first initial value set, thereby improving the accuracy of the first initial value set.

[0107] This embodiment calculates the first initial value set and updates the first initial value set according to the candidate initial value set, thereby improving the accuracy of selecting the first initial value set.

[0108] Optionally, in the bank branch personnel configuration method provided in the embodiment of the present application, n initial value sets are updated according to a calculation formula to obtain n updated initial value sets, including: optimizing the n initial value sets according to the calculation formula to obtain n optimized initial value sets; perturbing each optimized initial value set respectively through the Cauchy perturbation strategy to obtain n perturbed initial value sets; inputting the n optimized initial value sets and the n perturbed initial value sets as model parameters into the initial prediction model respectively to obtain multiple fourth initial prediction models, and calculating the prediction accuracy of each fourth initial prediction model; sorting the prediction accuracy from large to small, and determining the initial value sets in the fourth initial prediction model corresponding to the prediction accuracy in the top n places as the n updated initial value sets.

[0109] Specifically, since the Cauchy distribution has a good two-wing probability, it greatly improves the local anti-interference ability and the overall search and optimization ability. Therefore, in order to increase the distribution range of the initial value set, when updating the n initial value sets according to the calculation formula, the n initial value sets can be optimized according to the above spider bee optimization algorithm to obtain n optimized initial value sets, and further use the Cauchy perturbation strategy to perturb each optimized initial value set to obtain n perturbed initial value sets, thereby increasing the number and distribution range of the initial value sets. The Cauchy perturbation algorithm is shown in formula (13):

[0110] p'=p(1+η) (13)

[0111] Where p is the optimized initial value set, p' is the perturbed initial value set, and η represents the random number of the Cauchy distribution, which can be calculated as follows:

[0112] η=tan[(ε-0.5)π] (14)

[0113] Here, ε is a value randomly drawn from a uniform distribution U(0,1).

[0114] After obtaining n optimized initial value sets and n perturbed initial value sets, there are a total of 2n initial value sets. At this time, it is necessary to determine the prediction accuracy of each initial value set respectively, and determine the initial value set with the prediction accuracy in the top 50% as the updated initial value set, that is, obtain n updated initial value sets.

[0115] This embodiment increases the radiation range of the initial value set by applying the Cauchy perturbation method, thereby achieving the technical effect of improving the prediction accuracy of the selected updated initial value set.

[0116] Optionally, in the bank branch personnel configuration method provided in an embodiment of the present application, perturbing the first initial value set according to a preset perturbation strategy to obtain a second initial value set includes: perturbing the first initial value set according to a Gaussian perturbation strategy to obtain a second initial value set.

[0117] Specifically, after obtaining the first initial value set, in order to enhance the local search capability and reduce the iterative search time of the algorithm, the first initial value set can be perturbed by a Gaussian perturbation strategy to obtain a second initial value set, thereby selecting the optimal set from the first initial value set and the second initial value set as the model parameters, thereby achieving the technical effect of improving the model prediction accuracy.

[0118] Among them, the Gaussian perturbation strategy is shown in formula (15):

[0119] q,=q(1+N(0,1)) (15)

[0120] Among them, q is the first initial value set, q , is the second initial value set, N(0, 1) is a random number that obeys Gaussian distribution characteristics.

[0121] This embodiment achieves the technical effect of enhancing the local search capability and reducing the iterative search time of the algorithm by performing a Gaussian perturbation operation on the first initial value set.

[0122] Optionally, in the bank branch personnel configuration method provided in the embodiment of the present application, determining the prediction accuracy of the first initial value set and the second initial value set, and determining the initial value set with the highest prediction accuracy as the candidate initial value set includes: inputting the first initial value set as a model parameter into the initial prediction model to obtain a fifth initial prediction model, and determining the accuracy of the fifth initial prediction model through a sample data set to obtain a first accuracy rate; inputting the second initial value set as a model parameter into the initial prediction model to obtain a sixth initial prediction model, and determining the accuracy of the sixth initial prediction model through a sample data set to obtain a second accuracy rate; comparing the first accuracy rate and the second accuracy rate, and obtaining the initial value set corresponding to the larger accuracy rate of the first accuracy rate and the second accuracy rate to obtain a candidate initial value set.

[0123] Specifically, after obtaining the first initial value set and the second initial value set, it is necessary to substitute the first initial value set and the second initial value set as model parameters into the initial prediction model respectively to obtain the fifth initial prediction model and the sixth initial prediction model, and then according to the prediction accuracy of the two models, select the initial value set with the highest accuracy from the first initial value set and the second initial value set to obtain the candidate initial value set.

[0124] This embodiment achieves the technical effect of ensuring the accuracy of selecting the candidate initial value set by calculating the prediction accuracy of the first initial value set and the second initial value set.

[0125] Optionally, in the bank branch personnel configuration method provided in the embodiment of the present application, determining the number of personnel to be configured for the target branch based on the predicted number of customers of each business branch includes: obtaining the basic number of customers and the basic number of configured persons for each business branch; calculating the difference between the predicted number of customers and the basic number of customers for each business branch to obtain P differences; adjusting the basic number of configured persons for each business branch according to the P differences to obtain the number of personnel to be configured for the target branch.

[0126] Specifically, after obtaining the predicted number of customers, it is first necessary to determine the basic number of customers and the basic number of configurations for each business point, that is, the correspondence between the number of customers and the number of configurations for each business point. For example, when the basic number of customers is 20, the basic number of configurations is 2. After obtaining the basic number of customers and the basic number of configurations, the difference between the basic number of customers and the predicted number of customers can be determined. For example, when the predicted number of customers is 60, the representation difference is 200%. At this time, according to the difference, the basic number of configurations can be changed from 2 to 6, so as to ensure the accuracy of the number of configurations for each business point, and the number of configurations for all business points can be added together to obtain the number of configurations for the target outlets, thereby ensuring the accuracy of the number of configurations for the target outlets.

[0127] This embodiment achieves the technical effect of ensuring the accuracy of the number of people configured at the target outlets by adjusting the benchmark number of people configured according to the predicted number of customers.

[0128] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0129] Example 2

[0130] The embodiment of the present application also provides a bank branch staff configuration device. It should be noted that the bank branch staff configuration device of the embodiment of the present application can be used to execute the bank branch staff configuration method provided by the embodiment of the present application. The bank branch staff configuration device provided by the embodiment of the present application is introduced below.

[0131] According to an embodiment of the present application, a device for implementing the above-mentioned bank branch personnel configuration method is also provided. Figure 3 Schematic diagram of a bank branch staff configuration device provided according to Example 2 of the present application. Figure 3As shown, the device includes: an acquisition unit 31, an adjustment unit 32, a prediction unit 33, and a determination unit 34.

[0132] The acquisition unit 31 is used to determine the time period to be predicted of the target outlet, and obtain the number of business transactions at each business point of the target outlet in M ​​historical time periods, to obtain M target arrays, wherein each target array contains P values, each value corresponds to the number of business transactions at a business point, the time period to be predicted has the same attributes as the historical time period, and M and P are positive integers.

[0133] The adjustment unit 32 is used to adjust the model parameters of the initial prediction model through the sample data set and the preset optimization algorithm to obtain the target prediction model, wherein the sample data set is composed of multiple groups of sample data, each group of sample data includes the number of business transactions of each business point of the target network point under multiple sample historical time periods, and the number of business transactions of each business point of the target network point under the sample target time period, and the preset optimization algorithm is a spider bee optimization algorithm combined with a preset disturbance strategy.

[0134] The prediction unit 33 is used to input the M target arrays into the target prediction model, and determine the predicted number of customers of each business point of the target network point in the prediction period according to the target prediction model.

[0135] The determination unit 34 is used to determine the number of personnel to be deployed at the target outlet according to the predicted number of customers at each business outlet.

[0136] The configuration device for bank branch personnel provided by the embodiment of the present application determines the time period to be predicted of the target branch through the acquisition unit 31, and obtains the number of business operators of each business point of the target branch in M ​​historical time periods, and obtains M target arrays, wherein each target array contains P values, each value corresponds to the number of business operators of a business point, the attributes of the time period to be predicted are the same as those of the historical time period, and M and P are positive integers. The adjustment unit 32 adjusts the model parameters of the initial prediction model through the sample data set and the preset optimization algorithm to obtain the target prediction model, wherein the sample data set is composed of multiple groups of sample data, each group of sample data includes the number of business operators of each business point of the target branch in multiple sample historical time periods, and the number of business operators of each business point of the target branch in the sample target time period, and the preset optimization algorithm is a spider bee optimization algorithm combined with a preset disturbance strategy. The prediction unit 33 inputs the M target arrays into the target prediction model, and determines the predicted number of customers of each business point of the target branch in the time period to be predicted according to the target prediction model. The determination unit 34 determines the number of personnel configurations of the target branch according to the predicted number of customers of each business point. By setting an initial prediction model and adjusting the model parameters of the initial prediction model through a sample data set and a preset optimization algorithm, a more accurate target prediction model is obtained, and the target prediction model is used to predict the number of business transactions in the prediction period based on the number of business transactions at the target outlets in the historical period, so that staff are allocated to different business points according to the prediction results, thereby achieving the purpose of improving the prediction accuracy of the number of business transactions, thereby achieving the technical effect of improving the accuracy of staff configuration, and further solving the problem of low accuracy in determining the deployment method of outlet personnel by manually predicting the number of passenger flow in related technologies.

[0137] Optionally, in the configuration device for bank branch personnel provided in the embodiment of the present application, the adjustment unit 32 includes: a setting module, which is used to set the initial parameters of the preset optimization algorithm, and generate the initial values ​​of each target individual to obtain n initial value sets, wherein the initial parameters include: the total number of iterations of the preset optimization algorithm, the number of population individuals n of the spider bee optimization algorithm, each initial value set contains a plurality of initial values ​​that are the same as the number of model parameters, and the initial values ​​are used to determine the model parameters, and n is a positive integer; a first determination module, which is used to determine the initial value set with the highest prediction accuracy from the n initial value sets through the spider bee optimization algorithm to obtain a first initial value set; a perturbation module, which is used to determine the initial value set with the highest prediction accuracy from the n initial value sets according to the preset perturbation strategy The first initial value set is perturbed to obtain the second initial value set; a second determination module is used to determine the prediction accuracy of the first initial value set and the second initial value set, and determine the initial value set with the highest prediction accuracy as the candidate initial value set, and judge whether the current number of iterations is equal to the total number of iterations; an execution module is used to re-execute the steps of generating the initial values ​​of each target individual according to the candidate initial value set when the current number of iterations is not equal to the total number of iterations, until the current number of iterations is equal to the total number of iterations; a third determination module is used to determine the candidate initial value set as the model parameters of the initial prediction model when the current number of iterations is equal to the total number of iterations, and obtain the target prediction model.

[0138] Optionally, in the configuration device for bank branch personnel provided in the embodiment of the present application, the first determination module includes: a generation submodule, which is used to generate a first random number and a second random number, and determine a calculation formula for optimizing each initial value set based on the size relationship between the first random number and the second random number, and update the n initial value sets according to the calculation formula to obtain n updated initial value sets; a judgment submodule, which is used to judge whether there is a previous iteration cycle in the current iteration cycle; the first determination submodule is used to, in the absence of a previous iteration cycle, substitute the n updated initial value sets as model parameters into the initial prediction model respectively to obtain n first initial prediction models, and use the sample data set to determine the prediction accuracy of each first initial prediction model to obtain n prediction accuracy rates, and The updated initial value set in the first initial prediction model with the highest accuracy is determined as the first initial value set; an acquisition submodule is used to obtain the candidate initial value set obtained in the previous iteration cycle when there is a previous iteration cycle, and substitute the n updated initial value sets as model parameters into the initial prediction model respectively to obtain n second initial prediction models, and use the sample data set to determine the prediction accuracy of each second initial prediction model to obtain n prediction accuracy rates, and determine the maximum prediction accuracy rate from the n prediction accuracy rates; a first comparison submodule is used to compare the maximum prediction accuracy rate with the prediction accuracy rate of the third initial prediction model, and determine the initial value set in the model with higher prediction accuracy rate as the first initial value set, wherein the model parameters in the third initial prediction model are candidate initial values.

[0139] Optionally, in the configuration device for bank branch personnel provided in the embodiment of the present application, the generation submodule includes: an optimization submodule, which is used to optimize n initial value sets according to a calculation formula to obtain n optimized initial value sets; a first perturbation submodule, which is used to perturb each optimized initial value set respectively through a Cauchy perturbation strategy to obtain n perturbed initial value sets; an input submodule, which is used to input the n optimized initial value sets and the n perturbed initial value sets as model parameters into the initial prediction model respectively, to obtain multiple fourth initial prediction models, and calculate the prediction accuracy of each fourth initial prediction model; a sorting submodule, which is used to sort the prediction accuracy from large to small, and determine the initial value sets in the fourth initial prediction model corresponding to the prediction accuracy in the top n places as n updated initial value sets.

[0140] Optionally, in the bank branch personnel configuration device provided in the embodiment of the present application, the perturbation module includes: a second perturbation submodule, used to perturb the first initial value set according to a Gaussian perturbation strategy to obtain a second initial value set.

[0141] Optionally, in the bank branch personnel configuration device provided in the embodiment of the present application, the second determination module includes: a second determination submodule, used to input the first initial value set as a model parameter into the initial prediction model to obtain a fifth initial prediction model, and determine the accuracy of the fifth initial prediction model through a sample data set to obtain a first accuracy rate; a third determination submodule, used to input the second initial value set as a model parameter into the initial prediction model to obtain a sixth initial prediction model, and determine the accuracy of the sixth initial prediction model through a sample data set to obtain a second accuracy rate; a second comparison submodule, used to compare the first accuracy rate and the second accuracy rate, and obtain the initial value set corresponding to the larger accuracy rate between the first accuracy rate and the second accuracy rate to obtain a candidate initial value set.

[0142] Optionally, in the bank branch personnel configuration device provided in the embodiment of the present application, the determination unit 34 includes: an acquisition module, used to obtain the basic customer quantity and basic configuration number of each business point; a calculation module, used to calculate the difference between the predicted customer quantity and the basic customer quantity of each business point, and obtain P differences; an adjustment module, used to adjust the basic configuration number of each business point according to the P differences, and obtain the staff configuration quantity of the target branch.

[0143] It should be noted that the acquisition unit 31, adjustment unit 32, prediction unit 33, and determination unit 34 correspond to steps S201 to S204 in Embodiment 1, and the four modules and corresponding steps implement the same examples and application scenarios, but are not limited to the contents disclosed in Embodiment 1. It should be noted that the modules or units may be hardware components or software components stored in a memory (e.g., memory 104) and processed by one or more processors (e.g., processors 102a, 102b, ..., 102n), and the modules may also be part of a device and run in the computer terminal 10 provided in Embodiment 1.

[0144] Example 3

[0145] An embodiment of the present application may provide an electronic device, Figure 4 is a structural block diagram of an electronic device according to an embodiment of the present application. Figure 4 As shown, the electronic device may include: one or more ( Figure 4 (only one is shown) processor 1002, memory 1004, storage controller, and peripheral interface, wherein the peripheral interface is connected to the radio frequency module, audio module and display.

[0146] Among them, the memory can be used to store software programs and modules, such as program instructions / modules corresponding to the methods and devices in the embodiments of the present application, and the processor executes various functional applications and data processing by running the software programs and modules stored in the memory, that is, realizing the above-mentioned method. The memory may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory may further include a memory remotely arranged relative to the processor, and these remote memories may be connected to the terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0147] The processor can call the information and application stored in the memory through the transmission device to perform the following steps: determine the time period to be predicted of the target outlet, and obtain the number of business transactions of each business point of the target outlet in M ​​historical time periods to obtain M target arrays, wherein each target array contains P values, each value corresponds to the number of business transactions of a business point, the time period to be predicted has the same attributes as the historical time period, and M and P are positive integers; adjust the model parameters of the initial prediction model through a sample data set and a preset optimization algorithm to obtain a target prediction model, wherein the sample data set is composed of multiple groups of sample data, each group of sample data includes the number of business transactions of each business point of the target outlet in multiple sample historical time periods, and the number of business transactions of each business point of the target outlet in the sample target time period, and the preset optimization algorithm is a spider bee optimization algorithm combined with a preset disturbance strategy; input the M target arrays into the target prediction model, and determine the predicted number of customers of each business point of the target outlet in the time period to be predicted according to the target prediction model; determine the number of personnel configurations of the target outlet according to the predicted number of customers of each business point.

[0148] The processor can also call the information and application program stored in the memory through the transmission device to perform the following steps: adjusting the model parameters of the initial prediction model through the sample data set and the preset optimization algorithm to obtain the target prediction model, including: setting the initial parameters of the preset optimization algorithm, and generating the initial values ​​of each target individual to obtain n initial value sets, wherein the initial parameters include: the total number of iterations of the preset optimization algorithm, the number of population individuals n of the spider bee optimization algorithm, each initial value set contains a plurality of initial values ​​that are the same as the number of model parameters, the initial values ​​are used to determine the model parameters, and n is a positive integer; determining the initial value with the highest prediction accuracy from the n initial value sets through the spider bee optimization algorithm An initial value set is obtained to obtain a first initial value set; the first initial value set is perturbed according to a preset perturbation strategy to obtain a second initial value set; the prediction accuracy of the first initial value set and the second initial value set is determined, and the initial value set with the highest prediction accuracy is determined as a candidate initial value set, and it is judged whether the current number of iterations is equal to the total number of iterations; when the current number of iterations is not equal to the total number of iterations, the step of generating the initial value of each target individual is re-executed according to the candidate initial value set until the current number of iterations is equal to the total number of iterations; when the current number of iterations is equal to the total number of iterations, the candidate initial value set is determined as the model parameters of the initial prediction model to obtain the target prediction model.

[0149] The processor can also call the information and application stored in the memory through the transmission device to perform the following steps: determine the initial value set with the highest prediction accuracy from n initial value sets through the spider bee optimization algorithm, and obtain the first initial value set including: generating a first random number and a second random number, and determining a calculation formula for optimizing each initial value set based on the size relationship between the first random number and the second random number, and updating the n initial value sets according to the calculation formula to obtain n updated initial value sets; judging whether there is a previous iteration cycle in the current iteration cycle; in the case that there is no previous iteration cycle, substituting the n updated initial value sets as model parameters into the initial prediction model respectively to obtain n first initial prediction models, and using the sample data set to determine each first initial prediction model prediction accuracy, obtain n prediction accuracy rates, and determine the updated initial value set in the first initial prediction model with the highest accuracy rate as the first initial value set; in the case of the existence of the previous iteration cycle, obtain the candidate initial value set obtained in the previous iteration cycle, and substitute the n updated initial value sets as model parameters into the initial prediction model respectively, to obtain n second initial prediction models, and use the sample data set to determine the prediction accuracy of each second initial prediction model, to obtain n prediction accuracy rates, and determine the maximum prediction accuracy rate from the n prediction accuracy rates; compare the maximum prediction accuracy rate with the prediction accuracy rate of the third initial prediction model, and determine the initial value set in the model with higher prediction accuracy rate as the first initial value set, wherein the model parameters in the third initial prediction model are the candidate initial values.

[0150] The processor can also call the information and application programs stored in the memory through the transmission device to perform the following steps: updating the n initial value sets according to the calculation formula to obtain n updated initial value sets, including: optimizing the n initial value sets according to the calculation formula to obtain n optimized initial value sets; perturbing each optimized initial value set respectively through the Cauchy perturbation strategy to obtain n perturbed initial value sets; inputting the n optimized initial value sets and the n perturbed initial value sets as model parameters into the initial prediction model respectively to obtain multiple fourth initial prediction models, and calculating the prediction accuracy of each fourth initial prediction model; sorting the prediction accuracy from large to small, and determining the initial value set in the fourth initial prediction model corresponding to the prediction accuracy in the top n places as the n updated initial value sets.

[0151] The processor can also call the information and application stored in the memory through the transmission device to perform the following steps: perturbing the first initial value set according to a preset perturbation strategy to obtain a second initial value set, including: perturbing the first initial value set according to a Gaussian perturbation strategy to obtain a second initial value set.

[0152] The processor can also call the information and application stored in the memory through the transmission device to perform the following steps: determine the prediction accuracy of the first initial value set and the second initial value set, and determine the initial value set with the highest prediction accuracy as the candidate initial value set, including: inputting the first initial value set as a model parameter into the initial prediction model to obtain the fifth initial prediction model, and determining the accuracy of the fifth initial prediction model through the sample data set to obtain the first accuracy; inputting the second initial value set as a model parameter into the initial prediction model to obtain the sixth initial prediction model, and determining the accuracy of the sixth initial prediction model through the sample data set to obtain the second accuracy; comparing the first accuracy and the second accuracy, and obtaining the initial value set corresponding to the larger accuracy of the first accuracy and the second accuracy to obtain the candidate initial value set.

[0153] The processor can also call the information and application programs stored in the memory through the transmission device to perform the following steps: determining the number of staffing for the target outlets based on the predicted number of customers for each business point includes: obtaining the basic number of customers and the basic number of staffing for each business point; calculating the difference between the predicted number of customers and the basic number of customers for each business point to obtain P differences; adjusting the basic number of staffing for each business point based on the P differences to obtain the number of staffing for the target outlets.

[0154] It can be understood by those skilled in the art that Figure 4 The structure shown is for illustration only, and the electronic device may also be a smart phone (such as an Android phone, an iOS phone, etc.), a tablet computer, a PDA, a mobile Internet device (Mobile Internet Devices, MID), a PAD, or other terminal devices. Figure 4 The structure of the electronic device is not limited. Figure 4 More or fewer components (such as network interfaces, display devices, etc.) shown in, or having Figure 4 Different configurations shown.

[0155] A person of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing the hardware related to the terminal device through a program, and the program can be stored in a computer-readable storage medium, and the storage medium may include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0156] Example 4

[0157] The embodiment of the present application further provides a storage medium. Optionally, in this embodiment, the storage medium can be used to store the program code executed by the bank branch personnel configuration method provided in the first embodiment.

[0158] Optionally, in this embodiment, the above storage medium may be located in any computer terminal in a computer terminal group in a computer network, or in any mobile terminal in a mobile terminal group.

[0159] The present application also provides a computer program product, which, when executed on a data processing device, is suitable for executing the steps of the method for configuring bank branch personnel.

[0160] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0161] In the above embodiments of the present application, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0162] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0163] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0164] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0165] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or optical disk and other media that can store program codes.

[0166] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A method for configuring bank branch personnel, characterized in that: include: Determine the time period to be predicted of the target outlet, and obtain the number of business transactions of each business point of the target outlet in M ​​historical time periods, to obtain M target arrays, wherein each target array contains P values, each value corresponds to the number of business transactions of a business point, the time period to be predicted has the same attributes as the historical time period, and M and P are positive integers; The model parameters of the initial prediction model are adjusted through a sample data set and a preset optimization algorithm to obtain a target prediction model, wherein the sample data set is composed of multiple groups of sample data, each group of sample data includes the number of business transactions of each business point of the target network point in multiple sample historical periods, and the number of business transactions of each business point of the target network point in the sample target period, and the preset optimization algorithm is a spider bee optimization algorithm combined with a preset disturbance strategy; Inputting the M target arrays into a target prediction model, and determining the predicted number of customers of each business point of the target network point in the period to be predicted according to the target prediction model; The number of staff to be deployed at the target outlets is determined based on the predicted number of customers at each business outlet.

2. The method according to claim 1, characterized in that The model parameters of the initial prediction model are adjusted through the sample data set and the preset optimization algorithm to obtain the target prediction model including: Setting initial parameters of the preset optimization algorithm and generating initial values ​​of each target individual to obtain n initial value sets, wherein the initial parameters include: the total number of iterations of the preset optimization algorithm, the number n of population individuals of the spider bee optimization algorithm, each initial value set contains a plurality of initial values ​​that are the same as the number of the model parameters, and the initial values ​​are used to determine the model parameters, and n is a positive integer; Determine the initial value set with the highest prediction accuracy from the n initial value sets by using the spider bee optimization algorithm to obtain a first initial value set; Perturbing the first initial value set according to the preset perturbation strategy to obtain a second initial value set; Determine the prediction accuracy of the first initial value set and the second initial value set, determine the initial value set with the highest prediction accuracy as a candidate initial value set, and judge whether the current number of iterations is equal to the total number of iterations; In the case where the current number of iterations is not equal to the total number of iterations, re-performing the step of generating the initial value of each target individual according to the candidate initial value set until the current number of iterations is equal to the total number of iterations; When the current number of iterations is equal to the total number of iterations, the candidate initial value set is determined as the model parameters of the initial prediction model to obtain the target prediction model.

3. The method according to claim 2, characterized in that The spider bee optimization algorithm is used to determine the initial value set with the highest prediction accuracy from the n initial value sets, and the first initial value set is obtained, including: Generate a first random number and a second random number, and determine a calculation formula for optimizing each initial value set according to a size relationship between the first random number and the second random number, and update the n initial value sets according to the calculation formula to obtain n updated initial value sets; Determine whether the current iteration cycle has a previous iteration cycle; In the absence of a previous iteration cycle, the n updated initial value sets are substituted as model parameters into the initial prediction model to obtain n first initial prediction models, and the prediction accuracy of each first initial prediction model is determined using the sample data set to obtain n prediction accuracy rates, and the updated initial value set in the first initial prediction model with the highest accuracy rate is determined as the first initial value set; In the case where there is a previous iteration cycle, the candidate initial value set obtained in the previous iteration cycle is obtained, and the n updated initial value sets are respectively substituted into the initial prediction model as model parameters to obtain n second initial prediction models, and the prediction accuracy of each second initial prediction model is determined using the sample data set to obtain n prediction accuracy rates, and the maximum prediction accuracy rate is determined from the n prediction accuracy rates; The maximum prediction accuracy is compared with the prediction accuracy of the third initial prediction model, and the initial value set in the model with higher prediction accuracy is determined as the first initial value set, wherein the model parameters in the third initial prediction model are the candidate initial values.

4. The method according to claim 3, characterized in that The n initial value sets are updated according to the calculation formula to obtain n updated initial value sets including: Optimizing the n initial value sets according to the calculation formula to obtain n optimized initial value sets; The optimized initial value sets are disturbed respectively by the Cauchy perturbation strategy to obtain n perturbed initial value sets; Inputting the n optimized initial value sets and the n disturbed initial value sets as model parameters into the initial prediction model respectively to obtain a plurality of fourth initial prediction models, and calculating the prediction accuracy of each fourth initial prediction model; The prediction accuracy rates are sorted from large to small, and the initial value sets in the fourth initial prediction model corresponding to the prediction accuracy rates in the top n positions are determined as the n updated initial value sets.

5. The method according to claim 2, characterized in that: The first initial value set is perturbed according to the preset perturbation strategy to obtain a second initial value set including: The first initial value set is perturbed according to a Gaussian perturbation strategy to obtain the second initial value set.

6. The method according to claim 2, characterized in that Determining the prediction accuracy of the first initial value set and the second initial value set, and determining the initial value set with the highest prediction accuracy as the candidate initial value set includes: Inputting the first initial value set as the model parameter into the initial prediction model to obtain a fifth initial prediction model, and determining the accuracy of the fifth initial prediction model through the sample data set to obtain a first accuracy rate; Inputting the second initial value set as the model parameter into the initial prediction model to obtain a sixth initial prediction model, and determining the accuracy of the sixth initial prediction model through the sample data set to obtain a second accuracy rate; The first accuracy rate is compared with the second accuracy rate, and an initial value set corresponding to a larger accuracy rate between the first accuracy rate and the second accuracy rate is obtained to obtain the candidate initial value set.

7. The method according to claim 1, characterized in that Determining the number of staffing for the target outlets based on the predicted number of customers at each business outlet includes: Obtain the basic number of customers and basic configuration personnel for each business point; Calculate the difference between the predicted number of customers and the basic number of customers at each business point to obtain P differences; The basic number of personnel configured for each business point is adjusted according to the P differences to obtain the number of personnel configured for the target network point.

8. A bank branch personnel configuration device, characterized in that: include: An acquisition unit is used to determine a time period to be predicted of a target outlet, and to acquire the number of business operators of each business point of the target outlet in M ​​historical time periods, to obtain M target arrays, wherein each target array contains P values, each value corresponds to the number of business operators of a business point, the time period to be predicted has the same attributes as the historical time period, and M and P are positive integers; An adjustment unit, used to adjust the model parameters of the initial prediction model through a sample data set and a preset optimization algorithm to obtain a target prediction model, wherein the sample data set is composed of multiple groups of sample data, each group of sample data includes the number of business transactions of each business point of the target network point under multiple sample historical periods, and the number of business transactions of each business point of the target network point under the sample target period, and the preset optimization algorithm is a spider bee optimization algorithm combined with a preset disturbance strategy; A prediction unit, used for inputting the M target arrays into a target prediction model, and determining the predicted number of customers of each business point of the target network point in the period to be predicted according to the target prediction model; The determination unit is used to determine the number of personnel to be deployed at the target outlets according to the predicted number of customers at each business outlet.

9. A computer program product comprising computer instructions, characterized in that When the computer instructions are executed by the processor, the steps of the bank branch personnel configuration method described in any one of claims 1 to 7 are implemented.

10. An electronic device, characterized in that: include: A memory storing an executable program; A processor is used to run the program, wherein the program, when running, executes the bank branch personnel configuration method described in any one of claims 1 to 7.

Images