A Site Selection Method, Device, Equipment and Storage Medium for Bank Branches

Abstract

The embodiments of the present application disclose a method, apparatus, device, and storage medium for selecting a bank branch location, including: obtaining POI features of the bank branch to be screened; obtaining user features of the bank branch to be screened based on the POI features; constructing sample data based on the POI features and the user features, wherein the sample data includes a first number of initial features; constructing an initial bank branch evaluation model based on the sample data, and determining a first score and a first weight; then training the initial bank branch evaluation model to obtain a trained bank branch evaluation model, and determining a second score based on the bank branch evaluation model; generating a second weight based on the first score, the second score, and the first weight; and finally, selecting a second number of target features from the first number of initial features based on the second weight. The method of the embodiments of the present application has a small amount of computation and a high accuracy when selecting a bank branch location, and is more effective than existing bank branch location selection methods.

Description

Technical Field

[0001] The present application relates to the field of computers, and in particular to a method, apparatus, device and storage medium for selecting a location for a bank branch. Background Art

[0002] Artificial intelligence (AI) technology is a comprehensive discipline encompassing a wide range of fields, encompassing both hardware and software technologies. Foundational AI technologies generally include sensors, specialized AI chips, cloud computing, distributed storage, big data processing, operating / interaction systems, and mechatronics. AI software technologies primarily encompass computer vision, speech processing, natural language processing, and machine learning / deep learning.

[0003] During the model building process, the increasing number of information dimensions significantly aids in fitting or distinguishing targets. However, this also requires extensive feature screening to avoid problems such as the curse of dimensionality and high model complexity. Therefore, effectively selecting a subset of features with superior model performance from a massive feature set becomes crucial. Feature screening is a crucial step in data processing. By examining the correlation between features and targets or the distribution of feature attributes, it filters out useless features, thereby preventing the curse of dimensionality and simplifying the model. This is a method for improving model generalization.

[0004] Common methods for selecting bank branch locations include the Pearson correlation coefficient, chi-square test, mutual information test, and recursive feature elimination. These methods fail to consider the performance gains from feature combinations and are computationally intensive. For example, in the financial industry, bank branch location selection typically involves manual field surveys of commercial districts and residential areas, gathering data on the district's value, foot traffic, and spending. This data is then combined with subjective judgment to select retail branch locations. However, this approach requires significant computational effort and fails to consider the customer evaluation gains resulting from combining various data points. Summary of the Invention

[0005] The embodiments of the present application provide a method, apparatus, device, and storage medium for selecting a bank branch site, which can achieve more accurate and low-cost screening of target features from features.

[0006] The present application provides a method for selecting a location for a bank branch, including:

[0007] Constructing sample data according to the poi feature and the user feature, wherein the sample data includes a first number of initial features;

[0008] Constructing an initial bank branch evaluation model based on the sample data, and determining a first score and a first weight, wherein the first score is used to characterize the performance of the initial bank branch evaluation model, and the first weight corresponds one-to-one to the initial features;

[0009] Training the initial bank branch evaluation model to obtain a trained bank branch evaluation model, and determining a second score based on the bank branch evaluation model, wherein the second score is used to represent an evaluation of a model effect of the bank branch evaluation model;

[0010] generating a second weight according to the first score, the second score, and the first weight, wherein the second weight corresponds one-to-one to the initial feature;

[0011] According to the second weight, a second number of target features are screened out from the first number of initial features.

[0012] In the above embodiment, the step of constructing an initial bank branch evaluation model based on the sample data and determining a first score and a first weight includes:

[0013] Selecting a third number of training features from the first number of initial features based on a random walk algorithm, and obtaining a selection probability corresponding to each of the initial features;

[0014] determining the first weight according to the third number and the first number;

[0015] The third number of training features is evaluated using a cross-validation method to obtain the first score.

[0016] In the above embodiment, generating the second weight according to the first score, the second score, and the first weight includes:

[0017] Calculate and generate an updated weight according to the first number, the third number, and the first weight;

[0018] The second weight is generated by calculation according to the updated weight, the first score, and the second score.

[0019] In the above embodiment, the selecting the second number of target features from the first number of initial features according to the second weight includes:

[0020] Arranging the first number of initial features in descending order according to the second weight to obtain an initial feature sequence;

[0021] A first second number of initial features are selected from the initial feature sequence as the target features.

[0022] The present application also provides a device, including:

[0023] A feature acquisition unit, configured to acquire the POI features of the bank outlets to be screened, and acquire user features of the bank outlets to be screened based on the POI features;

[0024] A sample data unit, configured to construct sample data according to the poi feature and the user feature, wherein the sample data includes a first number of initial features;

[0025] an initialization unit, configured to construct an initial bank branch evaluation model based on the sample data, and determine a first score and a first weight, wherein the first score is used to characterize the performance of the initial bank branch evaluation model, and the first weight corresponds one-to-one to the initial feature;

[0026] a training unit, configured to train the initial bank branch evaluation model to obtain a trained bank branch evaluation model, and determine a second score based on the bank branch evaluation model, wherein the second score is used to represent an evaluation of a model effect of the bank branch evaluation model;

[0027] a weighting unit, configured to generate a second weight according to the first score, the second score, and the first weight, wherein the second weight corresponds one-to-one to the initial feature;

[0028] A screening unit is used to screen out a second number of the target features from the first number of the initial features according to the second weight.

[0029] In the above embodiment, the initial unit includes:

[0030] a random walk subunit, configured to select a third number of training features from the first number of initial features based on a random walk algorithm, and obtain a selection probability corresponding to each of the initial features;

[0031] a first weight subunit, configured to determine the first weight according to the third quantity and the first quantity;

[0032] The cross-validation subunit is configured to evaluate the third number of training features using a cross-validation method to obtain the first score.

[0033] In the above embodiment, the weighting unit includes:

[0034] an update weight subunit, configured to calculate and generate an update weight according to the first quantity, the third quantity, and the first weight;

[0035] The second weight subunit is configured to calculate and generate the second weight according to the updated weight, the first score, and the second score.

[0036] In the above embodiment, the screening unit includes:

[0037] an initial feature sequence subunit, configured to arrange the first number of initial features in descending order according to the second weight to obtain an initial feature sequence;

[0038] The target feature subunit is used to select the first second number of initial features from the initial feature sequence as the target features.

[0039] An embodiment of the present application also provides a device, including a processor and a memory, wherein the memory stores multiple instructions; the processor loads instructions from the memory to execute the steps in the method.

[0040] An embodiment of the present application further provides a storage medium, wherein the storage medium stores a plurality of instructions, wherein the instructions are suitable for loading by a processor to execute the steps in the method.

[0041] The embodiment of the present application can obtain the POI features of the bank branch to be screened; based on the POI features, obtain the user features of the bank branch to be screened; based on the POI features and the user features, construct sample data, the sample data including a first number of initial features; construct an initial bank branch evaluation model based on the sample data, and determine a first score and a first weight; then train the initial bank branch evaluation model to obtain a trained bank branch evaluation model, and determine a second score based on the bank branch evaluation model; generate a second weight based on the first score, the second score and the first weight; finally, based on the second weight, screen out a second number of target features from the first number of the initial features. The technical solution provided by the embodiment of the present application has a small amount of calculation and a high accuracy when screening target features. Compared with the existing bank branch site selection method, it has a good screening effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0043] Figure 1 This is a scenario diagram of the bank branch site selection method provided in an embodiment of the present application;

[0044] Figure 2This is a flow chart of a method for selecting a bank branch location provided in an embodiment of the present application;

[0045] Figure 3 This is a structural diagram of a bank branch site selection device provided in an embodiment of the present application;

[0046] Figure 4 It is a structural diagram of the device provided in the embodiment of the present application;

[0047] Figure 5 It is a structural diagram of the storage medium provided in an embodiment of the present application. DETAILED DESCRIPTION

[0048] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without making creative efforts are within the scope of protection of this application.

[0049] The terms "first," "second," and "third" in this application are used only for descriptive purposes and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first," "second," or "third" may explicitly or implicitly include at least one of such features. In the description of this application, "multiple" means at least two, for example, two, three, etc., unless otherwise specifically defined. All directional indications in the embodiments of this application (such as up, down, left, right, front, back...) are only used to explain the relative positional relationship, movement, etc. between the components under a specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indications also change accordingly. In addition, the terms "including" and "having," as well as any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or device that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units that are not listed, or may optionally include other steps or units that are inherent to these processes, methods, products, or devices.

[0050] References herein to "embodiments" mean that a particular feature, structure, or characteristic described in connection with the embodiments may be included in at least one embodiment of the present application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it constitute an independent or alternative embodiment that is mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0051] The embodiments of the present application provide a method, apparatus, device and storage medium for selecting a bank branch site.

[0052] The bank branch location selection device may be integrated into a device, such as a terminal, a server, or the like. The terminal may be a mobile phone, a tablet computer, a smart Bluetooth device, a laptop computer, or a personal computer (PC); the server may be a single server or a server cluster consisting of multiple servers.

[0053] In some embodiments, the bank branch site selection device may also be integrated into multiple devices. For example, the bank branch site selection device may be integrated into multiple servers, and the bank branch site selection method of the present application may be implemented by multiple servers.

[0054] In some embodiments, the server may also be implemented in the form of a terminal.

[0055] The methods provided in the embodiments of this application can be applied in financial institution scenarios. For example, they can be used to help banks screen for target characteristics, such as locations suitable for bank branches. The methods provided in the embodiments of this application can also be applied in other scenarios, such as corporate interviews. Specifically, they can be used to help companies screen for target characteristics to evaluate job applicants' business capabilities. For ease of description, the following uses the target characteristics of locations suitable for bank branches as an example.

[0056] refer to Figure 1 , Figure 1 The present invention illustrates an application scenario of a bank branch site selection method provided by a specific implementation of an embodiment of the present application. Assuming that a bank needs to screen target features to evaluate whether address A is suitable as a new bank branch address in order to evaluate whether a certain location is suitable as a bank branch address, the following steps are performed by a terminal:

[0057] According to the poi feature and the user feature, sample data is constructed, and the sample data includes a first number of initial features. In this embodiment, the sample data may include data between the bank and the address A, or may not include data between the bank and the address A.

[0058] An initial bank branch evaluation model is constructed based on the sample data, and a first score and a first weight are determined. The first score is used to characterize the performance of the initial bank branch evaluation model, and the first weight corresponds one-to-one to the initial feature.

[0059] The initial bank branch evaluation model is trained using the sample data until a preset number of iterations is reached, thereby obtaining a trained bank branch evaluation model.

[0060] A second score is determined based on the trained bank branch evaluation model, where the second score is used to represent an evaluation of the model effect of the bank branch evaluation model.

[0061] A second weight is generated according to the first score, the second score, and the first weight, where the second weight corresponds to the initial feature in a one-to-one manner.

[0062] According to the second weight, a second number of target features are screened out from the first number of initial features.

[0063] In this embodiment, the bank may proceed to the following steps based on the obtained target characteristics:

[0064] Obtain target features corresponding to the target address. In this embodiment, the target address is address A, and the target features include address A's POI features and user features.

[0065] The target features are spliced together to obtain the target feature text information of the target address. In this embodiment, all the target features are spliced together to form a complete target feature text information.

[0066] Performing semantic extraction on the target feature text information to obtain a target feature vector. In this embodiment, the target feature vector corresponding to the target feature text information is obtained by performing semantic extraction on the target feature text information.

[0067] Perform customer feature detection on the target feature vector to obtain a customer type corresponding to the target address, where the customer type includes a loan approval type and a loan rejection type. In this embodiment, the customer feature detection process is a binary classification application scenario, and the obtained customer type is one of the two classification results: a loan approval type and a loan rejection type.

[0068] The embodiment of the present application can obtain the POI features of the bank branch to be screened; based on the POI features, obtain the user features of the bank branch to be screened; based on the POI features and the user features, construct sample data, the sample data including a first number of initial features; construct an initial bank branch evaluation model based on the sample data, and determine a first score and a first weight; then train the initial bank branch evaluation model to obtain a trained bank branch evaluation model, and determine a second score based on the bank branch evaluation model; generate a second weight based on the first score, the second score and the first weight; finally, based on the second weight, screen out a second number of target features from the first number of the initial features. The technical solution provided by the embodiment of the present application has a small amount of calculation and a high accuracy when screening target features. Compared with the existing bank branch site selection method, it has a good screening effect.

[0069] It should be noted that the serial numbers of the following embodiments are not intended to limit the preferred order of the embodiments.

[0070] In this embodiment, a method for selecting a bank branch location involving artificial intelligence is provided. Figure 2 As shown, the specific process of the bank branch site selection method includes steps 110 to 160:

[0071] 110. Obtain POI features of the bank outlets to be screened, and obtain user features of the bank outlets to be screened based on the POI features.

[0072] The POI features can include the name, longitude and latitude coordinates, and related attributes of the bank branch to be screened. For example, the name of the bank branch to be screened can be "Community Branch A," and the longitude and latitude coordinates can be 102 degrees east longitude and 30 degrees north latitude. Related attributes can include the detailed address of the bank branch to be screened, and the area type being residential.

[0073] Optionally, user features can be constructed based on POI features and LBS information. For example, based on location-based service LBS information, the user features of customers in the POI area, such as age, education, income, position, address, and family members, can be obtained through the GPS positioning system combined with the above-mentioned POI features.

[0074] It is understandable that in the specific implementation of this application, data related to user characteristics, user information, etc. is involved. When the above embodiments of this application are applied to specific products or technologies, user permission or consent is required, and the collection, use and processing of relevant data must comply with relevant laws, regulations and standards of relevant countries and regions.

[0075] 120. Construct sample data based on the poi features and the user features, where the sample data includes a first number of initial features.

[0076] In some embodiments of the present application, the sample data may be data composed of POI features and user features, and the bank may obtain the sample data through methods such as review, system retrieval, or querying third-party service software. The sample data is composed of data of a first number of initial features, which are used to characterize the relationship between the POI features and the user features. Specifically, the initial feature may be at least one user feature of the user corresponding to a certain POI feature, for example, the age, income, and daily cash flow of user A in community A. It is also clear that the target feature is the one selected from the initial features.

[0077] 130. Construct an initial bank branch evaluation model based on the sample data, and determine a first score and a first weight, wherein the first score is used to characterize the performance of the initial bank branch evaluation model, and the first weight corresponds one-to-one to the initial feature.

[0078] In some embodiments of the present application, the initial bank branch evaluation model may be any neural network model, and the first score is used to estimate the model effect of the initial bank branch evaluation model. Furthermore, the first weight is estimated by the bank based on the sample data.

[0079] Optionally, constructing an initial bank branch evaluation model based on the sample data and determining a first score and a first weight comprises the following steps:

[0080] A third number of training features is selected from the first number of initial features based on a random walk algorithm, and a selection probability corresponding to each of the initial features is obtained.

[0081] The basic idea of a random walk algorithm is to traverse a graph starting from one or a series of vertices. At any vertex, the traverser will walk to its neighboring vertices with probability 1-a, and then randomly jump to any other vertex in the graph with probability a, where a is the jump probability. After each walk, a probability distribution is generated, describing the probability of each vertex being visited. This probability distribution is then used as input for the next walk, and the process is iterated repeatedly. When certain preconditions are met, the probability distribution converges. Once converged, a stable probability distribution is obtained.

[0082] Based on the random walk algorithm, a third number of training features are selected from the first number of initial features, and the probability of being accessed corresponding to each of the initial features is obtained, where the probability of being accessed is the selection probability.

[0083] The first weight is determined according to the third number and the first number.

[0084] In some embodiments of the present application, the first weight is obtained by the following calculation method:

[0085] W=m / n

[0086] Wherein, W is the first weight, j is the number of iterations in the random walk process, n is the first number, and m is the third number.

[0087] The third number of training features is evaluated using a cross-validation method to obtain the first score.

[0088] The cross-validation method uses a set of data to divide into groups, with one set serving as the training set and the other as the validation set (or test set). The classifier is trained using the training set, and the resulting model is then tested using the validation set, which serves as a performance metric for evaluating the classifier. The purpose of cross-validation is to obtain a reliable and stable model, test its effectiveness, and prevent overfitting.

[0089] Through the cross-validation method, the third number of training features are evaluated and processed, and the third number of training features are divided into a training feature training set, and the other part is divided into a training feature verification set. The initial bank branch evaluation model is trained with the training feature training set, and then the training feature verification set is used to test the obtained bank branch evaluation model, which is used as the first score for evaluating the initial bank branch evaluation model.

[0090] 140. Train the initial bank branch evaluation model to obtain a trained bank branch evaluation model, and determine a second score based on the bank branch evaluation model, where the second score is used to represent an evaluation of a model effect of the bank branch evaluation model.

[0091] In some embodiments of the present application, other cross-validation methods may be used to evaluate the trained bank branch evaluation model to obtain the second score.

[0092] 150. Generate a second weight based on the first score, the second score, and the first weight, where the second weight corresponds one-to-one to the initial feature.

[0093] Optionally, generating a second weight according to the first score, the second score, and the first weight comprises the following steps:

[0094] An updated weight is generated by calculation according to the first number, the third number, and the first weight.

[0095] In some embodiments of the present application, the update weight is obtained by the following calculation method:

[0096] w' j =w j -(sum(W)-m) / (nm)

[0097] Among them, w' j is the updated weight, j is the number of iterations, n is the first number, m is the third number, sum(W) is the sum of the updated weights obtained during the iteration, and w j is the first weight.

[0098] The second weight is generated by calculation according to the updated weight, the first score, and the second score.

[0099] In some embodiments of the present application, the second weight is obtained by the following calculation method:

[0100]

[0101] Among them, w k is the second weight, pre_score is the first score, and score is the second score.

[0102] 160. Filter out a second number of target features from the first number of initial features according to the second weight.

[0103] Continuing with the previous example, the target feature is used to characterize whether a location is suitable as a bank branch.

[0104] Optionally, the step of selecting the second number of target features from the first number of initial features according to the second weight includes steps 161 to 162 as follows:

[0105] 161. Arrange the first number of initial features in descending order according to the second weight to obtain an initial feature sequence.

[0106] 162. Filter out the first second number of initial features from the initial feature sequence as the target features.

[0107] In some embodiments of the present application, assuming that q is the second number, the target features finally screened out meet the following conditions:

[0108] In the initial feature sequence, the first q initial features whose total weight ratio is greater than ε are the target features, where ε is 80%.

[0109] The embodiment of the present application can obtain the POI features of the bank branch to be screened; based on the POI features, obtain the user features of the bank branch to be screened; based on the POI features and the user features, construct sample data, the sample data including a first number of initial features; construct an initial bank branch evaluation model based on the sample data, and determine a first score and a first weight; then train the initial bank branch evaluation model to obtain a trained bank branch evaluation model, and determine a second score based on the bank branch evaluation model; generate a second weight based on the first score, the second score and the first weight; finally, based on the second weight, screen out a second number of target features from the first number of the initial features. The technical solution provided by the embodiment of the present application has a small amount of calculation and a high accuracy when screening target features. Compared with the existing bank branch site selection method, it has a good screening effect.

[0110] To better implement the above method, the present application also provides a bank branch site selection device. The bank branch site selection device can be integrated into a device, such as a terminal, a server, or the like. The terminal can be a mobile phone, a tablet computer, a smart Bluetooth device, a laptop computer, a personal computer, or the like; the server can be a single server or a server cluster consisting of multiple servers.

[0111] For example, Figure 3 As shown, the bank branch site selection device may include:

[0112] The feature acquisition unit 301 is used to acquire the POI features of the bank outlets to be screened, and acquire the user features of the bank outlets to be screened based on the POI features;

[0113] The sample data unit 302 is used to construct sample data according to the POI feature and the user feature, wherein the sample data includes a first number of initial features;

[0114] An initialization unit 303 is configured to construct an initial bank branch evaluation model based on the sample data and determine a first score and a first weight, wherein the first score is used to characterize the performance of the initial bank branch evaluation model, and the first weight corresponds to the initial feature in a one-to-one manner;

[0115] A training unit 304 is configured to train the initial bank branch evaluation model to obtain a trained bank branch evaluation model, and determine a second score based on the bank branch evaluation model;

[0116] A weighting unit 305 is configured to generate a second weight according to the first score, the second score, and the first weight, wherein the second weight corresponds to the initial feature in a one-to-one manner;

[0117] The screening unit 306 is configured to screen out a second number of target features from the first number of initial features according to the second weight.

[0118] In some embodiments of the present application, the initialization unit 303 includes:

[0119] a random walk subunit, configured to select a third number of training features from the first number of initial features based on a random walk algorithm, and obtain a selection probability corresponding to each of the initial features;

[0120] a first weight subunit, configured to determine the first weight according to the third quantity and the first quantity;

[0121] The cross-validation subunit is configured to evaluate the third number of training features using a cross-validation method to obtain the first score.

[0122] In some embodiments of the present application, the weighting unit 305 includes:

[0123] an update weight subunit, configured to calculate and generate an update weight according to the first quantity, the third quantity, and the first weight;

[0124] The second weight subunit is configured to calculate and generate the second weight according to the updated weight, the first score, and the second score.

[0125] In some embodiments of the present application, the screening unit 306 includes:

[0126] an initial feature sequence subunit, configured to arrange the first number of initial features in descending order according to the second weight to obtain an initial feature sequence;

[0127] The target feature subunit is used to select the first second number of initial features from the initial feature sequence as the target features.

[0128] During specific implementation, the above modules can be implemented as independent entities, or can be arbitrarily combined and implemented as the same or several entities. The specific implementation of the above modules can be found in the previous method embodiments and will not be repeated here.

[0129] The embodiment of the present application provides a bank branch site selection device, which, based on the aforementioned method embodiment, obtains the POI features of the bank branch to be screened; obtains the user features of the bank branch to be screened based on the POI features; constructs sample data based on the POI features and the user features, the sample data including a first number of initial features; constructs an initial bank branch evaluation model based on the sample data, and determines a first score and a first weight; then trains the initial bank branch evaluation model to obtain a trained bank branch evaluation model, and determines a second score based on the bank branch evaluation model; generates a second weight based on the first score, the second score, and the first weight; and finally, based on the second weight, screens out a second number of target features from the first number of the initial features. The technical solution provided by the embodiment of the present application has a small amount of calculation and a high accuracy when screening target features, and has a good screening effect compared to existing bank branch site selection methods.

[0130] The present application also provides a device, which may be a terminal, a server, or the like. The terminal may be a mobile phone, a tablet computer, a smart Bluetooth device, a laptop computer, a personal computer, or the like; the server may be a single server or a server cluster consisting of multiple servers, or the like.

[0131] In some embodiments, the bank branch site selection device may also be integrated into multiple devices. For example, the bank branch site selection device may be integrated into multiple servers, and the bank branch site selection method of the present application may be implemented by multiple servers.

[0132] For example, Figure 4 , which shows a schematic diagram of the structure of the device involved in the embodiment of the present application, specifically:

[0133] The device may include one or more processing core processors 401, one or more storage media memories 402, a power supply 403, an input module 404, and a communication module 405. Those skilled in the art will appreciate that Figure 4 The device structure shown in the figure does not constitute a limitation of the device, and may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently.

[0134] Processor 401 is the control center of the device, connecting all components of the device using various interfaces and circuits. It executes software programs and / or modules stored in memory 402 and accesses data stored in memory 402 to perform various device functions and process data. In some embodiments, processor 401 may include one or more processing cores. In some embodiments, processor 401 may integrate an application processor and a modem processor. The application processor primarily handles the operating system, user interface, and application programs, while the modem processor primarily handles wireless communications. It is understood that the modem processor may not be integrated into processor 401.

[0135] The memory 402 can be used to store software programs and modules. The processor 401 executes various functional applications and data processing by running the software programs and modules stored in the memory 402. The memory 402 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area may store data created according to the use of the device, etc. In addition, the memory 402 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage device. Accordingly, the memory 402 may also include a memory controller to provide the processor 401 with access to the memory 402.

[0136] The device also includes a power supply 403 for supplying power to various components. In some embodiments, the power supply 403 can be logically connected to the processor 401 via a power management system, thereby enabling the power management system to manage charging, discharging, and power consumption. The power supply 403 can also include one or more DC or AC power supplies, a recharging system, a power failure detection circuit, a power converter or inverter, a power status indicator, and other arbitrary components.

[0137] The device may further include an input module 404, which may be configured to receive input digital or character information and generate keyboard, mouse, joystick, optical or trackball signal input related to user settings and function control.

[0138] The device may also include a communication module 405. In some embodiments, the communication module 405 may include a wireless module. The device may perform short-range wireless transmission via the wireless module of the communication module 405, thereby providing the user with wireless broadband Internet access. For example, the communication module 405 may be used to help the user send and receive emails, browse web pages, and access streaming media.

[0139] Although not shown, the device may further include a display unit, etc., which will not be described in detail here. Specifically, in this embodiment, the processor 401 in the device will load the executable files corresponding to one or more application processes into the memory 402 according to the following instructions, and the processor 401 will run the application stored in the memory 402 to implement various functions as follows:

[0140] Constructing sample data according to the poi feature and the user feature, wherein the sample data includes a first number of initial features;

[0141] Constructing an initial bank branch evaluation model based on the sample data, and determining a first score and a first weight, wherein the first score is used to characterize the performance of the initial bank branch evaluation model, and the first weight corresponds one-to-one to the initial features;

[0142] Training the initial bank branch evaluation model to obtain a trained bank branch evaluation model, and determining a second score based on the bank branch evaluation model, wherein the second score is used to represent an evaluation of a model effect of the bank branch evaluation model;

[0143] generating a second weight according to the first score, the second score, and the first weight, wherein the second weight corresponds one-to-one to the initial feature;

[0144] According to the second weight, a second number of target features are screened out from the first number of initial features.

[0145] The specific implementation of the above operations can be found in the previous embodiments and will not be repeated here.

[0146] Those skilled in the art will appreciate that all or part of the steps in the various methods of the above embodiments may be accomplished through instructions, or through instruction-controlled related hardware. The instructions may be stored in a storage medium and loaded and executed by a processor.

[0147] To this end, an embodiment of the present application provides a storage medium storing a plurality of instructions that can be loaded by a processor to execute the steps of any of the bank branch location selection methods provided in the embodiments of the present application. For example, the instructions can execute the following steps:

[0148] Constructing sample data according to the poi feature and the user feature, wherein the sample data includes a first number of initial features;

[0149] Constructing an initial bank branch evaluation model based on the sample data, and determining a first score and a first weight, wherein the first score is used to characterize the performance of the initial bank branch evaluation model, and the first weight corresponds one-to-one to the initial features;

[0150] Training the initial bank branch evaluation model to obtain a trained bank branch evaluation model, and determining a second score based on the bank branch evaluation model, wherein the second score is used to represent an evaluation of a model effect of the bank branch evaluation model;

[0151] generating a second weight according to the first score, the second score, and the first weight, wherein the second weight corresponds one-to-one to the initial feature;

[0152] According to the second weight, a second number of target features are screened out from the first number of initial features.

[0153] The specific implementation of the above operations can be found in the previous embodiments and will not be repeated here.

[0154] The storage medium may include a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0155] Since the instructions stored in the storage medium can execute the steps in any of the bank branch site selection methods provided in the embodiments of the present application, the beneficial effects that can be achieved by any of the bank branch site selection methods provided in the embodiments of the present application can be achieved. Please refer to the previous embodiments for details and will not be repeated here.

[0156] See Figure 5 , Figure 5 Schematic diagram of the structure of the storage medium of an embodiment of the present invention. The storage medium of an embodiment of the present invention stores program instructions 51 that can implement all the above methods, wherein the program instructions 51 can be stored in the above storage medium in the form of a software product, including a number of instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) or a processor to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, or a computer device such as a computer, a server, a mobile phone, or a tablet.

[0157] Those skilled in the art will clearly understand that for the sake of convenience and brevity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0158] The above is a detailed introduction to the site selection method, device, equipment and storage medium for a bank branch provided in the embodiment of the present application. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method and core idea of the present application; at the same time, for technical personnel in this field, based on the ideas of the present application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A method for selecting a location for a bank branch, characterized in that: include: Obtaining the POI features of the bank outlets to be screened, and obtaining the user features of the bank outlets to be screened based on the POI features; Constructing sample data according to the poi feature and the user feature, wherein the sample data includes a first number of initial features; Constructing an initial bank branch evaluation model based on the sample data and determining a first score and a first weight, including: screening a third number of training features from the first number of initial features based on a random walk algorithm, and obtaining a selection probability corresponding to each of the initial features; calculating a ratio of the third number to the first number to determine the first weight; and evaluating the third number of training features using a cross-validation method to obtain the first score; the first score is used to characterize the performance of the initial bank branch evaluation model, and the first weight corresponds one-to-one to the initial feature; Training the initial bank branch evaluation model to obtain a trained bank branch evaluation model, and determining a second score based on the bank branch evaluation model, wherein the second score is used to represent an evaluation of a model effect of the bank branch evaluation model; Generating a second weight based on the first score, the second score, and the first weight includes: calculating and generating an updated weight based on the first quantity, the third quantity, and the first weight; and calculating and generating the second weight based on the updated weight, the first score, and the second score, wherein the second weight corresponds one-to-one to the initial feature. A second number of target features is selected from the first number of initial features according to the second weight.

2. The method according to claim 1, wherein The calculating and generating an updated weight according to the first quantity, the third quantity, and the first weight includes: According to the formula w' j =w j -(sum(W)-m) / (nm) calculates the updated weight w' j , where w j is the first weight, j is the number of iterations, n is the first quantity, m is the third quantity, and sum(W) is the sum of the updated weights obtained during the iteration process.

3. The method according to claim 1, wherein The calculating and generating the second weight according to the updated weight, the first score, and the second score includes: According to the formula Calculate the second weight w k , where w' j To update the weight, pre_score is the first score and score is the second score.

4. The method according to claim 1, wherein The step of selecting a second number of target features from the first number of initial features according to the second weights includes: Arranging the first number of initial features in descending order according to the second weight to obtain an initial feature sequence; A first second number of initial features are selected from the initial feature sequence as the target features.

5. A bank branch site selection device, characterized in that: The device is used to execute the bank branch site selection method according to any one of claims 1 to 4, comprising: A feature acquisition unit, configured to acquire the POI features of the bank outlets to be screened, and acquire user features of the bank outlets to be screened based on the POI features; A sample data unit, configured to construct sample data according to the poi feature and the user feature, wherein the sample data includes a first number of initial features; an initialization unit, configured to construct an initial bank branch evaluation model based on the sample data, and determine a first score and a first weight, wherein the first score is used to characterize the performance of the initial bank branch evaluation model, and the first weight corresponds one-to-one to the initial feature; a training unit, configured to train the initial bank branch evaluation model to obtain a trained bank branch evaluation model, and determine a second score based on the bank branch evaluation model; a weighting unit, configured to generate a second weight according to the first score, the second score, and the first weight, wherein the second weight corresponds one-to-one to the initial feature; A screening unit is used to screen out a second number of target features from the first number of initial features according to the second weight.

6. A computer device, characterized in that: The system comprises a processor and a memory, wherein the memory stores a plurality of instructions; the processor loads instructions from the memory to execute the steps in the method for selecting a location of a bank branch as claimed in any one of claims 1 to 4.

7. A computer storage medium, characterized in that The storage medium stores a plurality of instructions, and the instructions are suitable for being loaded by a processor to execute the steps in the method for selecting a location of a bank branch according to any one of claims 1 to 4.

Images