Equipment quantity prediction method and device, storage medium and electronic equipment

Abstract

The embodiment of the invention provides an equipment quantity prediction method and device, a storage medium and electronic equipment, and is applied to the technical field of equipment management, and the method comprises the steps: determining a to-be-predicted bank outlet, and determining various types of equipment, needing to be predicted, of the bank outlet based on the configuration information of the bank outlet; for each type of equipment, acquiring prediction data of the type of equipment at a bank outlet based on various parameter indexes screened for the type of equipment in advance; and inputting the prediction data of each type of equipment into a pre-trained multivariate regression analysis model to enable the multivariate regression analysis model to process each piece of prediction data, and outputting the equipment prediction quantity of each type of equipment. The multiple regression analysis model is used for predicting the number of various devices, prediction does not need to be conducted depending on artificial experience, the parameter indexes of various devices are used for obtaining prediction data in the prediction process, obtaining of useless data is reduced, and the prediction accuracy of the number of various devices is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of equipment management, and in particular to an equipment quantity prediction method and device, a storage medium and an electronic device. Background Art

[0002] Bank branches are service places set up by banks in different regions to provide customers with various financial services. Some bank branches involve different business structures, and different bank branches handle businesses with different focuses.

[0003] When setting up a bank branch, in order to ensure that the bank branch can provide normal business services to customers, the number of various types of equipment in the bank branch will be predicted based on manual experience, and then the equipment of the bank branch will be configured. This prediction method is easily affected by subjective factors, resulting in inaccurate or unreasonable predicted equipment quantities. Summary of the invention

[0004] In view of this, the embodiments of the present application provide a method and apparatus for predicting the number of equipment, a storage medium and an electronic device. By applying the solution provided by the present application, there is no need to rely on manual experience to predict the number of equipment of various types of equipment in bank branches. A multivariate regression analysis model is used to predict the number of equipment of various types of equipment in bank branches. The prediction results are more credible, and the prediction process fully considers the indicators of different dimensions of various types of equipment, thereby improving the accuracy of the prediction results.

[0005] To achieve the above objectives, the present application provides the following technical solutions:

[0006] A method for predicting the number of devices, comprising:

[0007] Determine a bank branch to be predicted, and determine various types of equipment that need to be predicted for the bank branch based on the configuration information of the bank branch;

[0008] For each type of equipment, based on various parameter indicators pre-screened for the type of equipment, the forecast data of the type of equipment is collected at the bank outlets;

[0009] The prediction data of each type of equipment is input into a pre-trained multiple regression analysis model, so that the multiple regression analysis model processes each prediction data and outputs the predicted number of equipment for each type of equipment.

[0010] Optionally, in the above method, based on various parameter indicators pre-screened for such equipment, collecting prediction data of such equipment at the bank outlets includes:

[0011] For each parameter index of such equipment, collect the index data of the bank branch in the parameter index;

[0012] The collected indicator data are determined as the predicted data for this type of equipment.

[0013] The above method optionally includes the following steps:

[0014] For each type of equipment, collect the index characteristic data of the equipment, wherein the index characteristic data includes the data of various preset initial indicators of the equipment;

[0015] Performing clustering processing on the indicator characteristic data to obtain a clustering result;

[0016] Based on the clustering result, various parameter indicators of the equipment of this type are selected from various initial indicators.

[0017] The above method, optionally, the process of training the multivariate regression analysis model includes:

[0018] Based on the various parameter indicators of each type of equipment, an analysis sub-model for each type of equipment is constructed;

[0019] Construct a multivariate regression analysis model using analytical sub-models for each type of equipment;

[0020] Collect model training data;

[0021] The multivariate regression analysis model is trained using the model training data until each analysis sub-model in the multivariate regression analysis model meets a preset training completion condition, and the training of the multivariate regression analysis model is terminated to obtain a trained multivariate regression analysis model.

[0022] The above method may optionally further include:

[0023] Generate an equipment forecast report for the bank branch based on the forecasted number of equipment for each type of equipment;

[0024] Sending the equipment prediction report to a preset audit system, so that the audit system generates the equipment configuration cost of the bank branch based on the equipment prediction report;

[0025] Acquiring value assessment data of the bank branch, and generating a configuration budget of the bank branch based on the value assessment data;

[0026] Based on the configuration budget and the equipment configuration cost, an equipment configuration analysis report for the bank branch is generated.

[0027] A device for predicting the number of equipment, comprising:

[0028] A determination unit, used to determine a bank branch to be predicted, and based on the configuration information of the bank branch, determine various types of equipment that need to be predicted for the bank branch;

[0029] A collection unit, for collecting, for each type of equipment, forecast data of the type of equipment at the bank outlet based on various parameter indicators pre-screened for the type of equipment;

[0030] The prediction unit is used to input the prediction data of each type of equipment into a pre-trained multiple regression analysis model, so that the multiple regression analysis model processes each prediction data and outputs the predicted number of equipment for each type of equipment.

[0031] In the above device, optionally, the collection unit performs a process of collecting prediction data of the type of equipment at the bank branch based on various parameter indicators pre-screened for the type of equipment, including:

[0032] For each parameter index of such equipment, collect the index data of the bank branch in the parameter index;

[0033] The collected indicator data are determined as the predicted data for this type of equipment.

[0034] The above device may optionally further include a screening unit, wherein the screening unit is used to screen various parameter indicators of each type of equipment, including:

[0035] For each type of equipment, collect the index characteristic data of the equipment, wherein the index characteristic data includes the data of various preset initial indicators of the equipment;

[0036] Performing clustering processing on the indicator characteristic data to obtain a clustering result;

[0037] Based on the clustering result, various parameter indicators of the equipment of this type are selected from various initial indicators.

[0038] The above device may optionally further include a model training unit, wherein the process of the model training unit training the multivariate regression analysis model includes:

[0039] Based on the various parameter indicators of each type of equipment, an analysis sub-model for each type of equipment is constructed;

[0040] Construct a multivariate regression analysis model using analytical sub-models for each type of equipment;

[0041] Collect model training data;

[0042] The multivariate regression analysis model is trained using the model training data until each analysis sub-model in the multivariate regression analysis model meets a preset training completion condition, and the training of the multivariate regression analysis model is terminated to obtain a trained multivariate regression analysis model.

[0043] The above-mentioned device may optionally further include a report generating unit, which is used to generate an equipment forecast report for the bank branch based on the predicted equipment quantity of each type of equipment; send the equipment forecast report to a preset audit system, so that the audit system generates the equipment configuration cost of the bank branch based on the equipment forecast report; obtain the value assessment data of the bank branch, and generate the configuration budget of the bank branch based on the value assessment data; generate an equipment configuration analysis report for the bank branch based on the configuration budget and the equipment configuration cost.

[0044] A storage medium includes stored instructions, wherein when the instructions are executed, the device where the storage medium is located is controlled to execute the device quantity prediction method as described above.

[0045] An electronic device includes a memory and one or more instructions, wherein the one or more instructions are stored in the memory and are configured to be executed by one or more processors to perform the device quantity prediction method as described above.

[0046] Compared with the existing technology, this application has the following advantages:

[0047] The embodiment of the present application provides a method and device for predicting the number of equipment, a storage medium and an electronic device, including: determining a bank branch to be predicted, and determining various types of equipment that the bank branch needs to predict based on the configuration information of the bank branch; for each type of equipment, based on various parameter indicators pre-screened for the type of equipment, collecting prediction data of the type of equipment at the bank branch; inputting the prediction data of each type of equipment into a pre-trained multivariate regression analysis model, so that the multivariate regression analysis model processes each prediction data and outputs the predicted number of equipment for each type of equipment. The multivariate regression analysis model is used to predict the number of equipment of each type of equipment, without relying on manual experience for prediction, and the prediction process uses the parameter indicators of each type of equipment to obtain prediction data, reduce the acquisition of useless data, improve the accuracy of the prediction of the number of each type of equipment, and obtain a more reasonable prediction number of each type of equipment, so that subsequent equipment can be fully used, reduce the idle rate of equipment, and improve the utilization rate of equipment, thereby improving the business processing rate of bank branches. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0049] Figure 1A flowchart of a method for predicting the number of devices provided in an embodiment of the present application;

[0050] Figure 2 A flowchart of a training multivariate regression analysis model provided in an embodiment of the present application;

[0051] Figure 3 A flowchart of generating a device configuration analysis report for a bank branch provided in an embodiment of the present application;

[0052] Figure 4 A schematic diagram of the structure of a device quantity prediction device provided in an embodiment of the present application;

[0053] Figure 5 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0054] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0055] In this application, the terms "comprises", "comprising" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprising a ..." does not exclude the presence of other identical elements in the process, method, article or device comprising the element.

[0056] Terminology explanation:

[0057] Mean Square Error (MSE): MSE represents the average squared error between the predicted value and the actual value. The smaller the value, the better the model.

[0058] Multiple regression analysis model: The main research object of regression analysis is the statistical relationship between objective variables. It is a mathematical method for dealing with the correlation between multiple variables. In regression analysis, one type of variable is regarded as an explanatory variable, that is, an independent variable or a characteristic value. The other type of variable is regarded as an explained variable, that is, a dependent variable. The independent variable can be one or more, but the dependent variable can only be one. When there is only one independent variable, it is called a univariate linear regression, and when there are two or more independent variables, the regression analysis is called a multiple regression analysis.

[0059] As can be seen from the background technology, the number of various devices in bank branches is currently configured based on manual experience. This configuration method is prone to unreasonable configuration of the number of devices, low utilization of the configured devices or workload, which affects the business handling of bank branches.

[0060] In order to solve the above-mentioned problems, the present application provides an equipment quantity prediction scheme, which can be used to predict the number of various types of equipment in bank branches, and set more scientific and reasonable quantities for various types of equipment in bank branches, so that the equipment in the configured bank branches can be reasonably used, reduce the idle rate of equipment, and improve the utilization rate of equipment, thereby improving the business handling efficiency of bank branches.

[0061] The present application can be used in many general or special computing device environments or configurations, such as personal computers, server computers, handheld or portable devices, tablet devices, multi-processor devices, distributed computing environments including any of the above devices or equipment, etc.

[0062] Reference Figure 1 , is a flow chart of a device quantity prediction method provided in an embodiment of the present application, and is specifically described as follows:

[0063] S101. Determine the bank outlets to be predicted, and based on the configuration information of the bank outlets, determine the various types of equipment that need to be predicted for the bank outlets.

[0064] Receive the branch prediction request sent by the staff, parse the branch prediction request, obtain the branch ID and other information in the branch prediction request, and determine the bank branch to be predicted based on the branch ID.

[0065] The configuration information of the bank branch is obtained, wherein the configuration information includes various types of equipment required by the bank branch, and the various types of equipment required by the bank branch are determined as various types of equipment that need to be predicted.

[0066] Preferably, different bank branches require different types of equipment.

[0067] Exemplarily, the types of devices include, but are not limited to, ATM machines, self-service terminals, online banking terminals, counter terminals, video terminals, electronic signature terminals, express lockers, servers, storage devices, routers, customer password keyboards, and other types of devices.

[0068] S102. For each type of equipment, based on various parameter indicators pre-screened for the type of equipment, collect prediction data for the type of equipment at bank outlets.

[0069] It should be noted that the various parameter indicators of different types of equipment are different, and the various parameter indicators of each type of equipment are screened in advance from various initial indicators.

[0070] Exemplarily, each initial indicator covers each dimension considered when predicting the number of devices for each type of equipment. Each initial indicator includes, but is not limited to, the type of bank branch, the number of personnel in various positions at the bank branch, the business scope of the bank branch, the equipment in use at the bank branch, the models of equipment in use at the bank branch, etc.; further, the type of bank branch includes, but is not limited to, savings branches, comprehensive business branches, self-service branches, smart branches, and specialty branches, etc.; the various positions at the bank branch include, but are not limited to, tellers, account managers, lobby managers, etc., among which each type of position can be used as an initial indicator.

[0071] Exemplarily, the process of screening various parameter indicators of each type of equipment is as follows: collecting indicator characteristic data of this type of equipment, the indicator characteristic data including data of various preset initial indicators of this type of equipment; clustering the indicator characteristic data to obtain clustering results; based on the clustering results, selecting various parameter indicators of this type of equipment from various initial indicators.

[0072] It should be noted that when collecting the indicator characteristic data of this type of equipment, the data of various initial indicators of this type of equipment are collected from each established bank branch, and then the collected data are determined as the indicator characteristic data of this type of equipment.

[0073] Exemplarily, the established bank branches are A, B, and C; the initial indicators are a, b, and c; the device type for which indicator characteristic data needs to be collected is H, then the data of the device type H at the initial indicator a, the initial indicator b, and the initial indicator c in bank branch A are collected, and the data of the device type H at the initial indicator a, the initial indicator b, and the initial indicator c in bank branch B are collected, and the data of the device type H at the initial indicator a, the initial indicator b, and the initial indicator c in bank branch C are collected, and then the collected data are determined as the indicator characteristic data of the device type H.

[0074] Preferably, the index characteristic data collected for such equipment may include the data of various initial indicators of each established bank branch. Continuing with the above example, for the index characteristic data of equipment type H, the data of initial indicator a, initial indicator b and initial indicator c of bank branch A, the data of initial indicator a, initial indicator b and initial indicator c of bank branch B, and the data of initial indicator a, initial indicator b and initial indicator c of bank branch C are all determined as the index characteristic data of equipment type H.

[0075] After obtaining the indicator characteristic data of a certain type of equipment, clustering technology is used to perform clustering processing on the indicator characteristic data to obtain clustering results; based on the clustering results, various parameter indicators of the equipment of this type are selected from various initial indicators.

[0076] Taking the fuzzy C-means clustering method as an example, the algorithm transforms the sample space X = {x 1 ,x 2 ,…,x n} is divided into C categories (2≤C≤n), where x i It will not be strictly divided into a certain class. Sample x i The degree of membership of class j is u ij (0≤u ij ≤1), the membership matrix of all samples U={u ij}, the following conditions are met:

[0077]

[0078] The fuzzy C-means algorithm makes the objective function J fcm Minimum, that is Where m (m>1) is the fuzzy weighted index, c j is the center of the jth class in C, is the sample x i To cluster center c j The Euclidean distance.

[0079] By calculating the sample x i To cluster center c j The Euclidean distance is used to continuously cluster the samples, and finally a clustering result is obtained. Preferably, the clustering result includes sample clusters after the samples are clustered. Different sample clusters correspond to different initial indicators, and the initial indicator corresponding to each sample cluster can be determined as a parameter indicator. Exemplarily, after clustering, 5 sample clusters are obtained, and the initial indicator corresponding to each sample cluster is determined as a parameter indicator.

[0080] The above is an example of the present application. The clustering method used in the present application is not limited to the above fuzzy C-means clustering method.

[0081] Preferably, the clustering results include information such as the correlation and impact of each initial indicator with the type of equipment, and the initial indicator with a strong correlation with the type of equipment is determined as a parameter indicator. For example, the initial indicator with a correlation with the type of equipment greater than a preset threshold is determined as a parameter indicator for the type of equipment.

[0082] Preferably, when screening parameter indicators of various types of equipment, based on the use of clustering technology for screening, the parameter indicators of various types of equipment can also be screened in a combined manner with manual assistance, thereby improving the accuracy of screening and increasing the flexibility of screening.

[0083] By screening various parameter indicators for each type of equipment, initial indicators that are not very relevant to each type of equipment can be screened out, thereby avoiding the impact of invalid data on the subsequent predicted number of equipment and improving the subsequent prediction accuracy.

[0084] Furthermore, the process of collecting prediction data for a certain type of equipment is as follows: for each parameter indicator of this type of equipment, the indicator data of the bank branch on the parameter indicator is collected; the collected indicator data are determined as the prediction data for this type of equipment; the bank branch here is the bank branch for which the number of equipment needs to be predicted.

[0085] Preferably, in order to facilitate the subsequent data processing of the multivariate regression analysis model, after the prediction data of a certain type of equipment is collected, the prediction data can be normalized to obtain normalized prediction data, so that the prediction data subsequently input into the multivariate regression analysis model is normalized data.

[0086] S103, inputting the prediction data of each type of equipment into a pre-trained multiple regression analysis model, so that the multiple regression analysis model processes each prediction data and outputs the predicted number of equipment for each type of equipment.

[0087] Reference Figure 2 , which is a flowchart of the training multivariate regression analysis model provided in the embodiment of the present application, and is specifically described as follows:

[0088] S201. Based on various parameter indicators of each type of equipment, construct an analysis sub-model for each type of equipment.

[0089] Preferably, when constructing the analysis sub-model, the function Y=β is used 0 +β 1 X 1 +β 2 X 2 +β 3 X 3 +...+β k X k Construct, where X k Represents the kth parameter index of a certain type of equipment, where β k is the regression coefficient.

[0090] It should be noted that, since the parameter indicators of different types of equipment are different, the analysis sub-models of different types of equipment are also different.

[0091] After constructing the analysis sub-model, the analysis sub-model needs to be trained to optimize the regression coefficients of the analysis sub-model so that each regression coefficient in the analysis sub-model has an optimal value.

[0092] S202. Construct a multivariate regression analysis model using the analysis sub-models of various types of equipment.

[0093] A multivariate regression analysis model is constructed using the analysis sub-models for each type of equipment, so that the multivariate regression analysis model can subsequently predict the number of equipment of various types for bank branches.

[0094] S203: Collect model training data.

[0095] The data of various parameter indicators of various types of equipment in various established bank branches can be used as model training data. Preferably, the model training data includes training data sets and test data sets. Preferably, the ratio between the training data set and the test data set can be 7:3.

[0096] S204, using the model training data to train the multivariate regression analysis model until each analysis sub-model in the multivariate regression analysis model meets the preset training completion condition, and then the training of the multivariate regression analysis model is terminated to obtain a trained multivariate regression analysis model.

[0097] In the process of training the multivariate regression analysis model, the sklearn.linear_model module in the sklearn library in Python can be used to introduce various parameter indicators of the above-mentioned various types of equipment into the multivariate regression analysis model, and each analysis sub-model in the multivariate regression analysis model is trained. In the process of training each analysis sub-model, the regression coefficients in the analysis sub-model are continuously adjusted until the analysis sub-model meets the preset training completion condition. Exemplarily, the analysis sub-model meets the training completion condition: after adjusting the regression coefficients in the analysis sub-model, when the accuracy of the analysis sub-model test reaches a preset value, the analysis sub-model meets the training completion condition; or, after adjusting the regression coefficients in the analysis sub-model, when the convergence value of the analysis sub-model meets the convergence condition, the analysis sub-model meets the training completion condition. Exemplarily, the convergence condition is met when the convergence value is less than a preset threshold.

[0098] It should be noted that the trained multivariate regression analysis model can be used to predict the number of various types of equipment, and the prediction process is based on the data required for prediction based on the various parameter indicators screened for each type of equipment. Therefore, when predicting each type of equipment, multiple aspects can be considered, and the data used for prediction is valid data, which reduces the impact of invalid data on the prediction results and improves the prediction accuracy.

[0099] In the method provided in the embodiment of the present application, the bank branch to be predicted is determined, and based on the configuration information of the bank branch, the various types of equipment that need to be predicted for the bank branch are determined; for each type of equipment, based on the various parameter indicators pre-screened for the type of equipment, the prediction data of the type of equipment is collected at the bank branch; the prediction data of each type of equipment is input into a pre-trained multivariate regression analysis model, so that the multivariate regression analysis model processes each prediction data and outputs the predicted number of equipment for each type of equipment. The use of the multivariate regression analysis model to predict the number of equipment for each type of equipment does not require relying on manual experience for prediction, and the prediction process uses the parameter indicators of each type of equipment to obtain prediction data, reduce the acquisition of useless data, improve the accuracy of the prediction of the number of each type of equipment, and obtain a more reasonable prediction number of each type of equipment, so that subsequent equipment can be fully used, reduce the idle rate of equipment, and improve the utilization rate of equipment, thereby improving the business processing rate of bank branches.

[0100] This application adopts clustering and manual assisted discrimination methods to screen various initial indicators of various types of equipment in bank outlets collected or detected by multiple system tools. The initial indicators include but are not limited to equipment operation indicators, the number of personnel in the using institution, the type of the using institution, and the details of the equipment in use by the using institution, so as to screen out the various parameter indicators with strong correlation for each type of equipment. Further, the parameter indicators can be regarded as characteristic values; the sklearn.linear_model module in the sklearn library in python is used for model training to determine the correlation between different characteristic values ​​and the degree of influence on the overall equipment configuration, and to build a multivariate regression analysis model for different equipment and different types of bank outlets, so as to calculate the equipment configuration calculation model of the bank outlets. Therefore, according to the actual situation of the bank outlets, the number of different types of equipment that need to be configured in different bank outlets is calculated, and the idle equipment is reduced and the equipment utilization rate is improved.

[0101] This application uses cluster analysis to screen the parameter indicators of each type of equipment. In the screening process, the scattered and independent initial indicators are analyzed, the correlation between each initial indicator and the equipment is analyzed, and the influence of different initial indicators on the configuration of the equipment is analyzed. The initial indicators with high correlation with the equipment are used as parameter indicators; after obtaining the various parameter indicators of each type of equipment, a multivariate regression analysis model is constructed. Preferably, different user institutions can construct different multivariate regression analysis models, and the user institutions here can be bank branches. By using the solution provided by this application, it is possible to solve the problem of only relying on traditional rough empirical methods to configure equipment, resulting in some user institutions configuring equipment that does not exceed the standard range of the current stage based on empirical measurement, but in actual use, there are problems such as inefficient equipment, idleness, or insufficient number of equipment in marginal areas in special scenarios, and solve the problem of low scientificity and rationality of equipment configuration. This application is different from the previous traditional rough statistical usage ratio to configure equipment. This application uses a more scientific and accurate mathematical model for prediction, which has stronger stability and scientificity.

[0102] Reference Figure 3 , which is a flowchart of generating a device configuration analysis report for a bank branch provided in an embodiment of the present application, and the relevant descriptions are as follows:

[0103] S301. Generate an equipment forecast report for bank branches based on the forecasted number of equipment for each type of equipment.

[0104] The equipment forecast report includes information such as the forecast quantity of each type of equipment, forecast time, and bank branches that need to be forecasted.

[0105] S302: Send the equipment prediction report to a preset audit system, so that the audit system generates the equipment configuration cost of the bank branch based on the equipment prediction report.

[0106] The audit system obtains quotations for each type of equipment, and then determines the predicted cost of each type of equipment based on the predicted quantity and quotation of each type of equipment. The equipment configuration cost of the bank branch is obtained by summing up the various predicted costs.

[0107] S303: Obtain value assessment data of bank outlets, and generate a configuration budget for the bank outlets based on the value assessment data.

[0108] The value assessment data includes the geographical location information of bank branches, the various types of businesses supported, the branch types of bank branches, the estimated business handling volume of the bank branches, etc. The value of the bank branch is assessed based on the value assessment data, and then the configuration budget of the bank branch is set based on the assessed value. Preferably, the higher the assessed value, the higher the configuration budget.

[0109] S304. Generate an equipment configuration analysis report for the bank branch based on the configuration budget and the equipment configuration cost.

[0110] The configuration budget and the equipment configuration cost are compared. When the equipment configuration cost exceeds the configuration budget, an equipment configuration analysis report is generated to indicate that the predicted equipment cost of the bank branch exceeds the budget. Otherwise, an equipment configuration analysis report is generated to indicate that the predicted equipment cost of the bank branch does not exceed the budget.

[0111] Preferably, the equipment configuration analysis report also includes the predicted number of equipment for each type of equipment at the bank branch, the profit return rate analysis of the bank branch after the bank branch is configured based on the predicted number of each equipment, and the like.

[0112] By conducting a value assessment on bank branches, we can obtain the configuration budget of the bank branches, and then determine whether the number of various types of equipment predicted for the bank branches will exceed the budget. We can provide management personnel with an equipment configuration analysis report to help them determine whether the predicted number of various types of equipment predicted for the bank branches meets construction needs, facilitate risk management, and help them make the next decision.

[0113] Although the present invention depicts operations in a particular order, this should not be understood as requiring that the operations be performed in the particular order shown or in a sequential order.Multitasking and parallel processing may be advantageous under certain circumstances.

[0114] It should be understood that the various steps described in the method embodiments of the present disclosure may be performed in different orders and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present disclosure is not limited in this respect.

[0115] and Figure 1 Correspondingly, the present application also provides a device quantity prediction device, which is used to support Figure 1 To implement the method shown, the device is set in a computer or a processor.

[0116] Reference Figure 4 , is a schematic diagram of the structure of a device quantity prediction device provided in an embodiment of the present application, and is specifically described as follows:

[0117] A determination unit 401 is used to determine a bank branch to be predicted, and based on the configuration information of the bank branch, determine various types of equipment that need to be predicted for the bank branch;

[0118] A collection unit 402 is used to collect prediction data of each type of equipment at the bank branch based on various parameter indicators pre-screened for the type of equipment;

[0119] The prediction unit 403 is used to input the prediction data of each type of equipment into the pre-trained multiple regression analysis model, so that the multiple regression analysis model processes each prediction data and outputs the predicted number of equipment for each type of equipment.

[0120] In the device provided in the embodiment of the present application, the bank branch to be predicted is determined, and based on the configuration information of the bank branch, the various types of equipment that need to be predicted in the bank branch are determined; for each type of equipment, based on the various parameter indicators pre-screened for this type of equipment, the prediction data of this type of equipment is collected at the bank branch; the prediction data of each type of equipment is input into a pre-trained multivariate regression analysis model, so that the multivariate regression analysis model processes each prediction data and outputs the predicted number of equipment for each type of equipment. The use of the multivariate regression analysis model to predict the number of equipment of each type of equipment does not require relying on manual experience for prediction, and the prediction process uses the parameter indicators of each type of equipment to obtain prediction data, reduce the acquisition of useless data, improve the accuracy of the prediction of the number of each type of equipment, and obtain a more reasonable predicted number of each type of equipment, so that subsequent equipment can be fully used, reduce the idle rate of equipment, and improve the utilization rate of equipment, thereby improving the business processing rate of bank branches.

[0121] In another embodiment provided by the present application, the collection unit of the device performs a process of collecting prediction data of the device of this type at the bank branch based on various parameter indicators pre-screened for the device of this type, including:

[0122] For each parameter index of such equipment, collect the index data of the bank branch in the parameter index;

[0123] The collected indicator data are determined as the predicted data for this type of equipment.

[0124] In another embodiment provided by the present application, the device further includes a screening unit, wherein the screening unit is used to screen various parameter indicators of each type of equipment, including:

[0125] For each type of equipment, collect the index characteristic data of the equipment, wherein the index characteristic data includes the data of various preset initial indicators of the equipment;

[0126] Performing clustering processing on the indicator characteristic data to obtain a clustering result;

[0127] Based on the clustering result, various parameter indicators of the equipment of this type are selected from various initial indicators.

[0128] In another embodiment provided by the present application, the device further includes a model training unit, and the process of the model training unit training the multivariate regression analysis model includes:

[0129] Based on the various parameter indicators of each type of equipment, an analysis sub-model for each type of equipment is constructed;

[0130] Construct a multivariate regression analysis model using analytical sub-models for each type of equipment;

[0131] Collect model training data;

[0132] The multivariate regression analysis model is trained using the model training data until each analysis sub-model in the multivariate regression analysis model meets a preset training completion condition, and the training of the multivariate regression analysis model is terminated to obtain a trained multivariate regression analysis model.

[0133] In another embodiment provided by the present application, the device also includes a report generation unit, which is used to generate an equipment prediction report for the bank branch based on the predicted equipment quantity of each type of equipment; send the equipment prediction report to a preset audit system, so that the audit system generates the equipment configuration cost of the bank branch based on the equipment prediction report; obtain the value assessment data of the bank branch, and generate the configuration budget of the bank branch based on the value assessment data; generate an equipment configuration analysis report for the bank branch based on the configuration budget and the equipment configuration cost.

[0134] An embodiment of the present invention further provides a storage medium, which includes stored instructions, wherein when the instructions are executed, the device where the storage medium is located is controlled to execute the above-mentioned device quantity prediction method.

[0135] The embodiment of the present invention further provides an electronic device, the structural diagram of which is shown in FIG. Figure 5 As shown, it specifically includes a memory 601 and one or more instructions 602, wherein the one or more instructions 602 are stored in the memory 601 and are configured to be executed by one or more processors 603 to execute the one or more instructions 602 to perform the above-mentioned device quantity prediction method.

[0136] It should be noted that the 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.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data need to comply with relevant laws, regulations and standards in the relevant regions.

[0137] The specific implementation processes and derivative methods of the above-mentioned embodiments are all within the protection scope of the present invention.

[0138] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system or system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment. The system and system embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0139] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0140] The above description of the disclosed embodiments enables one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for predicting the number of devices, characterized in that: include: Determine a bank branch to be predicted, and determine various types of equipment that need to be predicted for the bank branch based on the configuration information of the bank branch; For each type of equipment, based on various parameter indicators pre-screened for the type of equipment, the forecast data of the type of equipment is collected at the bank outlets; The prediction data of each type of equipment is input into a pre-trained multiple regression analysis model, so that the multiple regression analysis model processes each prediction data and outputs the predicted number of equipment for each type of equipment.

2. The method according to claim 1, characterized in that The predictive data of the equipment of this type is collected at the bank outlets based on various parameter indicators pre-screened for the equipment of this type, including: For each parameter index of such equipment, collect the index data of the bank branch in the parameter index; The collected indicator data are determined as the predicted data for this type of equipment.

3. The method according to claim 1, characterized in that The process of screening various parameter indicators for each type of equipment includes: For each type of equipment, collect the index characteristic data of the equipment, wherein the index characteristic data includes the data of various preset initial indicators of the equipment; Performing clustering processing on the indicator characteristic data to obtain a clustering result; Based on the clustering result, various parameter indicators of the equipment of this type are selected from various initial indicators.

4. The method according to claim 2, characterized in that: The process of training a multivariate regression analysis model includes: Based on the various parameter indicators of each type of equipment, an analysis sub-model for each type of equipment is constructed; Construct a multivariate regression analysis model using analytical sub-models for each type of equipment; Collect model training data; The multivariate regression analysis model is trained using the model training data until each analysis sub-model in the multivariate regression analysis model meets a preset training completion condition, and the training of the multivariate regression analysis model is terminated to obtain a trained multivariate regression analysis model.

5. The method according to claim 1, characterized in that Also includes: Generate an equipment forecast report for the bank branch based on the forecasted number of equipment for each type of equipment; Sending the equipment prediction report to a preset audit system, so that the audit system generates the equipment configuration cost of the bank branch based on the equipment prediction report; Acquiring value assessment data of the bank branch, and generating a configuration budget of the bank branch based on the value assessment data; Based on the configuration budget and the equipment configuration cost, an equipment configuration analysis report for the bank branch is generated.

6. A device for predicting the number of equipment, characterized in that: include: A determination unit, used to determine a bank branch to be predicted, and based on the configuration information of the bank branch, determine various types of equipment that need to be predicted for the bank branch; A collection unit, for collecting, for each type of equipment, forecast data of the type of equipment at the bank outlet based on various parameter indicators pre-screened for the type of equipment; The prediction unit is used to input the prediction data of each type of equipment into a pre-trained multiple regression analysis model, so that the multiple regression analysis model processes each prediction data and outputs the predicted number of equipment for each type of equipment.

7. The device according to claim 6, characterized in that The collecting unit collects the prediction data of the equipment of this type at the bank outlet based on various parameter indicators pre-screened for the equipment of this type, including: For each parameter index of such equipment, collect the index data of the bank branch in the parameter index; The collected indicator data are determined as the predicted data for this type of equipment.

8. The device according to claim 6, characterized in that The method further includes a screening unit, wherein the screening unit is used for screening various parameter indicators of each type of equipment, including: For each type of equipment, collect the index characteristic data of the equipment, wherein the index characteristic data includes the data of various preset initial indicators of the equipment; Performing clustering processing on the indicator characteristic data to obtain a clustering result; Based on the clustering result, various parameter indicators of the equipment of this type are selected from various initial indicators.

9. A storage medium, characterized in that: The storage medium includes stored instructions, wherein when the instructions are executed, the device where the storage medium is located is controlled to execute the device quantity prediction method according to any one of claims 1 to 5.

10. An electronic device, characterized in that: The device comprises a memory and one or more instructions, wherein the one or more instructions are stored in the memory and configured to be executed by one or more processors to perform the device quantity prediction method as described in any one of claims 1 to 5.

Images