CN113379462A - Site selection method, device, equipment and storage medium - Google Patents
Site selection method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN113379462A CN113379462A CN202110728631.5A CN202110728631A CN113379462A CN 113379462 A CN113379462 A CN 113379462A CN 202110728631 A CN202110728631 A CN 202110728631A CN 113379462 A CN113379462 A CN 113379462A
- Authority
- CN
- China
- Prior art keywords
- candidate
- site selection
- grid
- index
- target
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000003860 storage Methods 0.000 title claims abstract description 17
- 238000010187 selection method Methods 0.000 title claims abstract description 13
- 238000000034 method Methods 0.000 claims description 40
- 238000012549 training Methods 0.000 claims description 26
- 238000004590 computer program Methods 0.000 claims description 11
- 239000000126 substance Substances 0.000 claims description 2
- 238000011156 evaluation Methods 0.000 claims 1
- 238000010586 diagram Methods 0.000 description 13
- 238000004891 communication Methods 0.000 description 9
- 230000008569 process Effects 0.000 description 7
- 238000012545 processing Methods 0.000 description 6
- 230000007246 mechanism Effects 0.000 description 5
- 230000006870 function Effects 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000006399 behavior Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0204—Market segmentation
- G06Q30/0205—Location or geographical consideration
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/02—Banking, e.g. interest calculation or account maintenance
Landscapes
- Business, Economics & Management (AREA)
- Finance (AREA)
- Engineering & Computer Science (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Economics (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
- Game Theory and Decision Science (AREA)
- Technology Law (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The disclosure provides a site selection method, a site selection device, site selection equipment and a storage medium, relates to the technical field of computers, particularly relates to the technical field of block chains, and can be used for cloud computing and cloud services. The specific implementation scheme is as follows: determining candidate grids in the target area and feature data of the candidate grids according to the target area information and the grid constraint information of the task demander; determining an index value of a site selection index of a candidate grid according to the feature data of the candidate grid; and selecting a target grid from the candidate grids according to the index value of the site selection index of the candidate grid. The embodiment of the disclosure can improve the site selection efficiency of the network points.
Description
Technical Field
The disclosure relates to the technical field of computers, in particular to the technical field of block chains, can be used for cloud computing and cloud services, and specifically relates to a site selection method, a site selection device, site selection equipment and a storage medium for a network node.
Background
The service network points are used as the frontier position of the service and play an important role in market share. Taking banking business as an example, banking outlets not only concern the reputation and profits of banks, but also concern the vital interests of customers.
How to select the position suitable for setting the network points, namely how to select the site of the network points, is very important.
Disclosure of Invention
The present disclosure provides a method, apparatus, device and storage medium for site selection of a network point.
According to an aspect of the present disclosure, there is provided a method for site selection of a mesh point, including:
determining candidate grids in the target area and feature data of the candidate grids according to the target area information and the grid constraint information of the task demander;
determining an index value of a site selection index of a candidate grid according to the feature data of the candidate grid;
and selecting a target grid from the candidate grids according to the index value of the site selection index of the candidate grid.
According to another aspect of the present disclosure, there is provided a mesh point addressing apparatus, including:
the candidate grid module is used for determining candidate grids in the target area and the feature data of the candidate grids according to the target area information and the grid constraint information of the task demand side;
the index dereferencing module is used for determining the index dereferencing of the site selection indexes of the mesh points of the candidate mesh according to the feature data of the candidate mesh;
and the grid selection module is used for selecting a target grid from the candidate grids according to the index value of the site selection index of the candidate grid.
According to still another aspect of the present disclosure, there is provided an electronic device including:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform a mesh point addressing method provided by any embodiment of the disclosure.
According to yet another aspect of the present disclosure, there is provided a non-transitory computer readable storage medium having stored thereon computer instructions for causing a computer to execute a site selection method provided by any of the embodiments of the present disclosure.
According to yet another aspect of the present disclosure, there is provided a computer program product comprising a computer program which, when executed by a processor, implements the mesh point addressing method provided by any of the embodiments of the present disclosure.
According to the technology disclosed by the invention, the site selection efficiency of the network points can be improved.
It should be understood that the statements in this section do not necessarily identify key or critical features of the embodiments of the present disclosure, nor do they limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description.
Drawings
The drawings are included to provide a better understanding of the present solution and are not to be construed as limiting the present disclosure. Wherein:
fig. 1 is a schematic diagram of a mesh point addressing method provided in accordance with an embodiment of the present disclosure;
fig. 2 is a schematic diagram of another site selection method provided in accordance with an embodiment of the present disclosure;
fig. 3 is a schematic diagram of another site selection method provided in accordance with an embodiment of the present disclosure;
fig. 4 is a schematic diagram of another site selection method provided in accordance with an embodiment of the present disclosure;
fig. 5 is a schematic diagram of a network site addressing apparatus according to an embodiment of the present disclosure;
fig. 6 is a block diagram of an electronic device for implementing a website addressing method of an embodiment of the present disclosure.
Detailed Description
Exemplary embodiments of the present disclosure are described below with reference to the accompanying drawings, in which various details of the embodiments of the disclosure are included to assist understanding, and which are to be considered as merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
The scheme provided by the embodiment of the disclosure is described in detail below with reference to the accompanying drawings.
Fig. 1 is a schematic diagram of a site selection method of a network node according to an embodiment of the present disclosure, which is applicable to a situation where the network node is selected according to a requirement of a task demander. The method can be executed by a network site selection device, which can be realized by hardware and/or software and can be configured in electronic equipment. Referring to fig. 1, the method specifically includes the following steps:
s110, determining candidate grids in a target area and feature data of the candidate grids according to target area information and grid constraint information of a task demand side;
s120, determining an index value of a site selection index of a candidate grid according to the feature data of the candidate grid;
s130, selecting a target grid from the candidate grids according to the index value of the site selection index of the candidate grids.
The task requiring party refers to a service party with site selection requirements, such as banking service or communication operation service, and the service type is not specifically limited in the embodiment of the present application. The target area is an area where a new network point needs to be set, and the target area information may be an identifier of the target area, a city type to which the target area belongs, and the like. The mesh constraint information may include shape information of the mesh and size information of the mesh, the shape information may be a circle or a rectangle, and the size information of the mesh may be a fixed size, or may be a size range, for example, may be 1km × 1km, 2km × 2km, or may be between 1km and 2 km. In addition, the grids with different shapes can have different size information forms, and taking a circle as an example, the size information of the grids can comprise the coordinates and the radius of a central point; taking a rectangle as an example, the size information of the mesh may be coordinates of four vertices.
In the embodiments of the present disclosure, the target area may be divided into a plurality of candidate grids according to the target area information and the grid constraint information. The feature data of the candidate grid refers to whether influence factors of a new grid point are set in the candidate grid or not, and can be obtained by counting user identity information, user behavior data, attribute information of actual grid points and the like in the candidate grid. The site selection indexes of the candidate grids are used for measuring the possibility of setting the grid points in the candidate grids, the values of the site selection indexes of partial grid points can be in positive correlation with the setting probability of the grid points of the candidate grids, and the values of the site selection indexes of partial grid points can be in negative correlation with the setting probability of the grid points. The service types are different, and the dimensionality of the characteristic data and the dimensionality of the site selection index of the network points can be different.
Specifically, for each candidate grid, feature data of the candidate grid can be determined, and an index value of at least one site selection index of the candidate grid is obtained according to the feature data of the candidate grid; determining the site selection score of the candidate grid according to the index value of each site selection index; and sorting the candidate grids according to the site selection scores of the candidate grids, and selecting a target grid from the candidate grids according to a sorting result. Taking the example that N new mesh points need to be set in the target area, the first N candidate meshes with relatively large mesh point address scores can be selected from the candidate meshes as the target meshes according to the sorting result. The target grids are provided for the task demand party, and a decision mechanism of the task demand party can set a new site by referring to the target grid information, so that intelligent site selection of the site is realized by taking the candidate grids as a unit, and site selection efficiency of the site can be improved.
According to the technical scheme provided by the embodiment of the disclosure, the target area is divided into a plurality of candidate grids, and the target area is intelligently site-selected by taking the candidate grids as units, so that site selection efficiency of the site can be improved.
Fig. 2 is a schematic diagram of another dot addressing method provided in accordance with an embodiment of the present disclosure. The present embodiment is an alternative proposed on the basis of the above-described embodiments. Referring to fig. 2, the method for site selection of a mesh point provided in this embodiment includes:
s210, determining candidate grids in a target area and feature data of the candidate grids according to target area information and grid constraint information of a task demand side;
s220, determining the type of a target city to which the target area belongs according to the target area information;
s230, selecting a target site selection model from candidate site selection models according to the target city type;
s240, determining index values of site selection indexes of the candidate grids according to the feature data of the candidate grids based on the target site selection model;
and S250, selecting a target grid from the candidate grids according to the index value of the site selection index of the candidate grids.
In the embodiment of the disclosure, at least two candidate city types can be obtained by city classification according to the city scale, the city economy type and the like. For example, the candidate city type may be strong first line, second line, third line, other, etc., and the candidate city type may also be manufacturing/industrial cities, financial cities, coastal cities, inland cities, etc.
In the embodiment of the present disclosure, the candidate city type may be associated with a candidate site addressing model, that is, model training may be performed for different candidate city types, so as to obtain an associated candidate site addressing model. By training the candidate site siting models for different candidate city types respectively, the matching degree between the candidate site siting models and the corresponding candidate city types can be improved, and site siting accuracy of the sites in different types of cities is improved.
Specifically, a target city to which the target area belongs can be determined according to the target area information and the membership between the area and the city, a target city type to which the target city belongs is determined from candidate city types, and a candidate site siting model associated with the target city type is used as a target site siting model; dividing the target area into a plurality of candidate grids according to the grid constraint information, and determining the feature data of the candidate grids; for each candidate grid, taking the feature data of the candidate grid as the input of a target site selection model, and determining the index value of a site selection index of the candidate grid according to the output information of the target site selection model; and selecting a target grid from the candidate grids according to the index value of the site selection index of each candidate grid.
It should be noted that each site selection index may be associated with different site selection models, that is, a site selection model is associated with not only a city type but also a site selection index. Aiming at different city types or different site selection indexes, the site selection models can be respectively associated, and the accuracy of index value of the site selection indexes can be improved, so that the accuracy of the target grid is improved.
In an optional implementation, before selecting a target site model from the candidate site models, the method further includes: selecting a sample city according to the candidate city type; determining a sample grid in the sample city according to the grid constraint information and the actual network point position in the sample city; and performing model training according to the characteristic data of the sample grids and the label values of the site selection indexes of the sample grids to obtain the candidate site selection model.
In the model training stage, the sample city is other cities which belong to the candidate city type and are provided with the actual network points of the task demander. Specifically, the task demander may provide candidate area information and grid constraint information, determine a target city type according to the candidate area information, and select a sample city from other cities that belong to the target city type and are provided with actual network points of the task demander. Taking the target city as a coastal city A and taking the task demander as a bank of a certain share as an example, a coastal city B, a coastal city C and a coastal city D provided with the share bank network can be selected as sample cities.
And the actual network point position in the sample city can be taken as the center, the sample city is divided into sample grids according to the grid constraint information, the characteristic data of the sample grids is determined, and the label value of the network point site selection index of the sample grids is determined according to the attribute information of the actual network point in the sample grids. Model training can be respectively carried out aiming at each site selection index to obtain a candidate site selection model related to a candidate city type and the site selection index. It should be noted that the mesh constraint information used in the process of generating the candidate mesh is the same as that used in the process of generating the sample mesh. By taking the actual site position in the sample city as the center, dividing the sample city into sample grids according to grid constraint information, determining the label value of the site selection index of the sample grid according to the attribute information of the actual site in the sample grid, and performing model training according to the characteristic data of the sample grid and the label value of the site selection index of the site to obtain a candidate site selection model, a foundation is laid for intelligent site selection, and the site selection efficiency of the site is improved; in addition, different candidate site selection models can be trained respectively by aiming at each candidate city type or each site selection index, and the accuracy of index value of the site selection index can be improved.
According to the technical scheme provided by the embodiment of the disclosure, the site selection of the mesh point is automatically carried out by taking the candidate mesh as a unit as a target area, so that the site selection efficiency of the mesh point can be improved; by aiming at each candidate city type or each site selection index, different candidate site selection models can be trained, and the accuracy of index value of the site selection index can be improved, so that the site selection accuracy of the site is improved.
Fig. 3 is a schematic diagram of another network site selection method provided in an embodiment of the present disclosure. The present embodiment is an alternative proposed on the basis of the above-described embodiments. Referring to fig. 3, the method for site selection of a mesh point provided in this embodiment includes:
s310, determining candidate grids in the target area and feature data of the candidate grids according to the target area information and the grid constraint information of the task demand side;
s320, determining an index value of a site selection index of a candidate grid according to the feature data of the candidate grid;
s330, respectively obtaining the weight of at least two site selection indexes;
s340, determining a site selection score of the candidate grid according to the index value of the site selection index of the candidate grid and the weight of the site selection index;
and S350, selecting a target grid from the candidate grids according to the site selection scores of the candidate grids.
In the embodiment of the disclosure, the decision mechanism of the task demand party can respectively give different weights to different site selection indexes according to the business targets of the decision mechanism, and the greater the weight is, the greater the importance of the site selection indexes in the site selection process of the network points is.
Specifically, the index values of the site selection indexes of the candidate grids can be weighted according to the weights of the site selection indexes of the network points to obtain the site selection scores of the candidate grids, and the higher the site selection score of the network points is, the higher the matching degree of the candidate grids and the service target is. The candidate grids with relatively high site selection scores of the network points are used as target grids and provided to a decision mechanism of a service party for network point setting reference, so that the network point setting efficiency can be improved. Moreover, the weight of the site selection index of the network point can be set by a decision mechanism of the task demand party according to the business target of the task demand party, so that the individual demand of the task demand party can be met, and the flexibility of site selection of the network point is improved.
According to the technical scheme of the embodiment of the disclosure, the weight is set for the site selection index of the network point according to the business target of the task demand side, so that not only can the flexibility of grid site selection be improved, but also the matching degree of the target grid and the business target can be improved, and the accuracy of the target grid is improved.
The feature data and site selection index in the embodiments of the present disclosure are described below.
In an alternative embodiment, the feature data comprises at least one of a group feature, a regional feature, or a peer feature; the group characteristics comprise at least one of income level proportion of each level, age proportion of each level and number of permanent population, and the condition of a bank card of a task demand party; the regional characteristics are the number of bus stations; the said isotechnical features are the actual network position and the bank type of the actual network.
In the embodiment of the present disclosure, the feature data of the candidate grid and the feature data of the sample grid may be the same, and the mesh point location index of the candidate grid and the mesh point location index of the sample grid may be the same. For convenience of description, the candidate mesh and the sample mesh are not distinguished, and are collectively referred to as a mesh. Moreover, the business type of the task demander can be a bank, namely address selection can be carried out on a bank outlet.
The group characteristics are obtained by counting user identity information and user behavior data in the grid, and the regional characteristics refer to the environmental factor characteristics related to the service type of a task demand party in the grid and are unrelated to the user; the peer characteristics refer to the service characteristics of the task demand party in the grid, the service characteristics of other service parties, and the other service parties and the task demand party belong to the same service type. The data source of the feature data is not specifically limited in the embodiments of the present disclosure, and the feature data may be from different feature data sources, different feature data sources may provide different feature data, and different feature data sources may also provide the same feature data. For feature data of a certain dimension, if at least two feature data sources provide the feature data, a feature data source can be selected for the feature data. For example, the feature data source may be a map-like application, a bank card management organization, and the like.
In this disclosure, the group characteristics may include a situation of card holding by a bank of a task demander in the grid, and taking the task demander as a bank of a certain share system as an example, the group characteristics may include a situation of card holding distribution by the bank of the share system in the grid. The population characteristics may further include at least one of a per-level income level ratio, a per-level age ratio, and a number of regular population. Specifically, the income level can be divided into different levels, and income level proportions of different levels in the grid are respectively counted; the ages can be divided into different levels, and the age proportions of the different levels in the grid are counted respectively; the sum of income level proportion of each level in the grid and the sum of age proportion of each level in the grid are both 1.
In the embodiment of the present disclosure, the regional characteristic may be the number of bus stations in the grid. The same industry characteristics can be the actual network position and the bank type of the actual network, the bank type can be a state bank, a share bank, a city business, a village and town bank, a rural credit society and the like, and for example, the actual network distribution of various banks in the grid can be respectively counted. The accuracy of site selection of the network points is improved by fusing the influence of the characteristic data of the group characteristics, the regional characteristics and the homophyly characteristics on the site selection of the network points.
In an alternative embodiment, the population characteristics further include at least one of a per-level consumption level ratio, a per-occupation ratio, a number of working population, a financial interest preference, or a vehicle type; the regional characteristics further include at least one of a number of subway stations, a number of schools, a number of parking spaces, or a traffic congestion index.
The vehicle type can be a common vehicle or an advanced vehicle, and the dimensionality of the feature data can be further enriched by introducing the consumption level proportion of each level, each occupation proportion, the number of working population, the financial interest preference, whether the vehicle or the vehicle type exists or not and the like into the group features, so that the accuracy of site selection and selection of the website is further improved.
In an optional embodiment, the site selection index is at least one of a total number of customers, a number of new customers for a financial transaction, a number of new customers for a credit card transaction, a number of new customers for a debit card transaction, a total number of daily average deposits, or a number of daily average added deposits.
The site selection index of the mesh point can be determined according to the attribute information of the actual mesh point in the mesh. The site selection index of the network point can also comprise the number of customers of the middle-high grade, and the division rule of the customer grade is not particularly limited.
The target grid can be selected from the candidate grids by determining the index value of each site index of the candidate grid and according to the index value of each site index, so that the target grid can take the index value of each site index into consideration, and the accuracy of the target grid is improved.
In an optional implementation, after selecting the target mesh from the candidate meshes, the method further includes: and feeding back the target grid and the index value of the site selection index of the mesh point of the target grid to a task demander.
The target grid is provided for the task demander, and index values of site selection indexes of all network points of the target grid are also provided to be used as decision basis for the task demander to determine whether to set a new network point in the target grid, so that the convenience of the task demander can be improved, and the site selection efficiency of the network points is improved.
It should be noted that different site selection indexes may also be associated with feature data of different dimensions, and the association relationship between the site selection index and the feature data dimension may be determined in the training process of the site selection model.
Fig. 4 is a schematic diagram of another network site selection method provided in accordance with an embodiment of the present disclosure. The present embodiment is an alternative proposed on the basis of the above-described embodiments. Referring to fig. 4, the method for site selection of a mesh point provided in this embodiment includes:
s410, a task requiring party initiates a model training request;
the task demander can determine grid constraint information such as grid shape, grid size and the like and generate a model training request carrying the grid constraint information.
S420, responding to the model training request, and performing model training to obtain a candidate site addressing model;
and (3) carrying out model training and prediction on the same city, for example, training at least two manufacturing cities as sample cities to obtain a candidate site selection model, and carrying out site selection prediction on other manufacturing cities as target cities. The city type associated with the candidate site siting model may be referred to as a candidate city type. The method can train aiming at different site selection indexes to obtain a plurality of candidate site selection models, namely the candidate site selection models are associated with not only candidate cities but also site selection indexes.
In the training process of the candidate site selection model, taking the actual site position in the sample city as the center, dividing the sample city into different sample grids by adopting grid constraint information, and determining the characteristic data of the sample grids, wherein the characteristic data can comprise group characteristics, regional characteristics and homopolar characteristics; and determining the label value of a site selection index of the sample grid according to the attribute information of the actual sites in the sample city, wherein the site selection index can be the total number of customers, the number of new day customers of financial services, the number of new day customers of credit card services, the number of new day customers of debit card services, the number of middle and high-end customers, the total number of daily average deposits or the number of daily average added deposits and the like.
It should be noted that, in the training process of the candidate site selection model, at least two feature combinations can be determined for any site selection index, and feature dimensions in different feature combinations are different. For example, the group characteristics in the first characteristic combination comprise income level ratios of different levels, age ratios of different levels, the number of standing people, the bank card holding condition of the mission demander and consumption level ratios of different levels, and the group characteristics in the second characteristic combination comprise income level ratios of different levels, age ratios of different levels, the number of standing people, the bank card holding condition of the mission demander, occupation ratios and financial interest preference. And training the feature combinations respectively to obtain different candidate site selection models of the site selection indexes, evaluating the different candidate site selection models respectively to select candidate site selection models to be used of the site selection indexes, and obtaining feature combinations related to the candidate site selection models to be used.
S430, a task demand side initiates a site selection request carrying target area information;
the task demand party can determine target area information and generate a site selection request carrying the target area information.
S440, determining candidate grids in the target area and feature data of the candidate grids according to the target area information and the grid constraint information;
for the type of the target city, the feature combinations to be used by the site selection indexes of all the network points can be different, and the feature data of the candidate grid can be determined for the site selection indexes of any network point according to the feature combinations to be used by the site selection indexes of the network points.
S450, determining the type of a target city to which the target area belongs according to the target area information;
s460, determining index values of site selection indexes of the candidate grids according to the feature data of the candidate grids based on the target site selection models associated with the target city types;
for the type of the target city, the candidate site selection models to be used by each site selection index can be different, and the candidate site selection model to be used by each site selection index can be used as the target site selection model of the site selection index.
S470, selecting a target grid from the candidate grids according to the index value of the site selection index of the candidate grids.
According to the technical scheme of the embodiment of the disclosure, the site selection efficiency of the mesh point can be improved by taking the candidate mesh as a unit and taking the feature data of the candidate mesh as a target area for automatic mesh point site selection; and the candidate site selection model is obtained by respectively training aiming at different candidate city types and different site selection indexes, so that the site selection accuracy of the sites can be improved.
Fig. 5 is a schematic diagram of a site selection device according to an embodiment of the present disclosure, which is applicable to a site selection situation according to a requirement of a task demander. Referring to fig. 5, the site selection apparatus 500 specifically includes the following components:
a candidate grid module 501, configured to determine candidate grids in a target area and feature data of the candidate grids according to target area information and grid constraint information of a task demander;
an index dereferencing module 502, configured to determine an index dereferencing of a site selection index of a candidate grid according to the feature data of the candidate grid;
a grid selecting module 503, configured to select a target grid from the candidate grids according to an index value of the site selection index of the candidate grid.
In an optional implementation manner, the index value module 502 includes:
the city type unit is used for determining the target city type of the target area according to the target area information;
the site selection model unit is used for selecting a target site selection model from candidate site selection models according to the target city type;
and the index dereferencing unit is used for determining the index dereferencing of the site selection indexes of the candidate grids according to the feature data of the candidate grids based on the target site selection model.
In an alternative embodiment, the site selection apparatus 500 further comprises a model training module, said model training module comprises:
the sample city unit is used for selecting a sample city according to the candidate city type;
the sample grid unit is used for determining a sample grid in the sample city according to the grid constraint information and the actual network point position in the sample city;
and the model training unit is used for carrying out model training according to the characteristic data of the sample grids and the label values of the site selection indexes of the mesh points of the sample grids to obtain the candidate mesh point site selection model.
In an alternative embodiment, the grid selection module 503 comprises:
the index weight unit is used for respectively obtaining the weights of at least two site selection indexes;
a site selection scoring unit for determining a site selection score of the candidate grid according to an index value of a site selection index of the candidate grid and a weight of the site selection index;
and the target grid unit is used for selecting a target grid from the candidate grids according to the site selection scores of the candidate grids.
In an alternative embodiment, the feature data comprises at least one of a group feature, a regional feature, or a peer feature; the group characteristics comprise at least one of income level proportion of each level, age proportion of each level and number of permanent population, and the condition of a bank card of a task demand party; the regional characteristics are the number of bus stations; the said isotechnical features are the actual network position and the bank type of the actual network.
In an alternative embodiment, the population characteristics further include at least one of a per-level consumption level ratio, a per-occupation ratio, a number of working population, a financial interest preference, or a vehicle type; the regional characteristics further include at least one of a number of subway stations, a number of schools, a number of parking spaces, or a traffic congestion index.
In an optional embodiment, the site selection index is at least one of a total number of customers, a number of new customers for a financial transaction, a number of new customers for a credit card transaction, a number of new customers for a debit card transaction, a total number of daily average deposits, or a number of daily average added deposits.
According to the technical scheme of the embodiment, the site selection efficiency of the mesh points can be improved by taking the candidate meshes as units to carry out automatic mesh point site selection; and the candidate site selection model is obtained by respectively training aiming at different candidate city types and different site selection indexes, so that the site selection accuracy of the sites can be improved.
In the technical scheme of the disclosure, the acquisition, storage, application and the like of the personal information of the related user all accord with the regulations of related laws and regulations, and do not violate the good customs of the public order.
The present disclosure also provides an electronic device, a readable storage medium, and a computer program product according to embodiments of the present disclosure.
FIG. 6 illustrates a schematic block diagram of an example electronic device 600 that can be used to implement embodiments of the present disclosure. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the disclosure described and/or claimed herein.
As shown in fig. 6, the apparatus 600 includes a computing unit 601, which can perform various appropriate actions and processes according to a computer program stored in a Read Only Memory (ROM) 602 or a computer program loaded from a storage unit 608 into a Random Access Memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the device 600 can also be stored. The calculation unit 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input/output (I/O) interface 605 is also connected to bus 604.
A number of components in the device 600 are connected to the I/O interface 605, including: an input unit 606 such as a keyboard, a mouse, or the like; an output unit 607 such as various types of displays, speakers, and the like; a storage unit 608, such as a magnetic disk, optical disk, or the like; and a communication unit 609 such as a network card, modem, wireless communication transceiver, etc. The communication unit 609 allows the device 600 to exchange information/data with other devices via a computer network such as the internet and/or various telecommunication networks.
The computing unit 601 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of the computing unit 601 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various dedicated Artificial Intelligence (AI) computing chips, various computing units that perform machine learning model algorithms, a digital information processor (DSP), and any suitable processor, controller, microcontroller, and so forth. The calculation unit 601 performs the various methods and processes described above, such as the site selection method. For example, in some embodiments, the mesh point addressing method may be implemented as a computer software program tangibly embodied in a machine-readable medium, such as storage unit 608. In some embodiments, part or all of the computer program may be loaded and/or installed onto the device 600 via the ROM 602 and/or the communication unit 609. When the computer program is loaded into RAM 603 and executed by the computing unit 601, one or more steps of the above described mesh point addressing method may be performed. Alternatively, in other embodiments, the computing unit 601 may be configured to perform the mesh point addressing method in any other suitable manner (e.g., by means of firmware).
Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuitry, Field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Products (ASSPs), system on a chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.
Program code for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the program codes, when executed by the processor or controller, cause the functions/operations specified in the flowchart and/or block diagram to be performed. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.
In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic, speech, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), Wide Area Networks (WANs), blockchain networks, and the internet.
The computer system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs executing on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also called a cloud computing server or a cloud host, and is a host product in a cloud computing service system, so that the defects of high management difficulty and weak service expansibility in the traditional physical host and VPS service are overcome.
It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present disclosure may be executed in parallel or sequentially or in different orders, and are not limited herein as long as the desired results of the technical solutions disclosed in the present disclosure can be achieved.
The above detailed description should not be construed as limiting the scope of the disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made in accordance with design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present disclosure should be included in the scope of protection of the present disclosure.
Claims (17)
1. A site selection method for a network point comprises the following steps:
determining candidate grids in the target area and feature data of the candidate grids according to the target area information and the grid constraint information of the task demander;
determining an index value of a site selection index of a candidate grid according to the feature data of the candidate grid;
and selecting a target grid from the candidate grids according to the index value of the site selection index of the candidate grid.
2. The method according to claim 1, wherein the determining an index value of a mesh point addressing index of a candidate mesh according to the feature data of the candidate mesh comprises:
determining the type of a target city to which the target area belongs according to the target area information;
selecting a target site selection model from candidate site selection models according to the target city type;
and determining an index value of a site selection index of the candidate grid according to the feature data of the candidate grid based on the target site selection model.
3. The method of claim 2, further comprising, prior to selecting a target site model from the candidate site models:
selecting a sample city according to the candidate city type;
determining a sample grid in the sample city according to the grid constraint information and the actual network point position in the sample city;
and performing model training according to the characteristic data of the sample grids and the label values of the site selection indexes of the sample grids to obtain the candidate site selection model.
4. The method of claim 1, wherein the selecting a target grid from the candidate grids according to an index value of a site selection index of the candidate grids comprises:
respectively obtaining the weights of at least two site selection indexes;
determining a site selection score of the candidate grid according to the index value of the site selection index of the candidate grid and the weight of the site selection index;
and selecting a target grid from the candidate grids according to the site selection scores of the candidate grids.
5. The method of any of claims 1-4, wherein the feature data includes at least one of a group feature, a regional feature, or a peer feature; the group characteristics comprise at least one of income level proportion of each level, age proportion of each level and number of permanent population, and the condition of a bank card of a task demand party; the regional characteristics are the number of bus stations; the said isotechnical features are the actual network position and the bank type of the actual network.
6. The method of claim 5, wherein the population characteristics further comprise at least one of a per-level consumption level proportion, a per-occupation proportion, a number of working demographics, a financial interest preference, or a vehicle type; the regional characteristics further include at least one of a number of subway stations, a number of schools, a number of parking spaces, or a traffic congestion index.
7. The method of any one of claims 1-4, wherein the site selection index is at least one of a total number of customers, a daily new number of customers of a financial transaction, a daily new number of customers of a credit card transaction, a daily new number of customers of a debit card transaction, a daily average total deposit, or a daily average added deposit.
8. A site selection apparatus, comprising:
the candidate grid module is used for determining candidate grids in the target area and the feature data of the candidate grids according to the target area information and the grid constraint information of the task demand side;
the index dereferencing module is used for determining the index dereferencing of the site selection indexes of the mesh points of the candidate mesh according to the feature data of the candidate mesh;
and the grid selection module is used for selecting a target grid from the candidate grids according to the index value of the site selection index of the candidate grid.
9. The apparatus of claim 8, wherein the indicator evaluation module comprises:
the city type unit is used for determining the target city type of the target area according to the target area information;
the site selection model unit is used for selecting a target site selection model from candidate site selection models according to the target city type;
and the index dereferencing unit is used for determining the index dereferencing of the site selection indexes of the candidate grids according to the feature data of the candidate grids based on the target site selection model.
10. The apparatus of claim 9, further comprising a model training module comprising:
the sample city unit is used for selecting a sample city according to the candidate city type;
the sample grid unit is used for determining a sample grid in the sample city according to the grid constraint information and the actual network point position in the sample city;
and the model training unit is used for carrying out model training according to the characteristic data of the sample grids and the label values of the site selection indexes of the mesh points of the sample grids to obtain the candidate mesh point site selection model.
11. The apparatus of claim 8, wherein the grid selection module comprises:
the index weight unit is used for respectively obtaining the weights of at least two site selection indexes;
a site selection scoring unit for determining a site selection score of the candidate grid according to an index value of a site selection index of the candidate grid and a weight of the site selection index;
and the target grid unit is used for selecting a target grid from the candidate grids according to the site selection scores of the candidate grids.
12. The apparatus of any of claims 8-11, wherein the feature data comprises at least one of a group feature, a regional feature, or a peer feature; the group characteristics comprise at least one of income level proportion of each level, age proportion of each level and number of permanent population, and the condition of a bank card of a task demand party; the regional characteristics are the number of bus stations; the said isotechnical features are the actual network position and the bank type of the actual network.
13. The apparatus of claim 12, wherein the population characteristics further comprise at least one of a per-level consumption level proportion, a per-occupation proportion, a number of working demographics, a financial interest preference, or a vehicle type; the regional characteristics further include at least one of a number of subway stations, a number of schools, a number of parking spaces, or a traffic congestion index.
14. The apparatus according to any one of claims 8-11, wherein the site selection index is at least one of a total number of customers, a daily new number of customers of a financial transaction, a daily new number of customers of a credit card transaction, a daily new number of customers of a debit card transaction, a daily average total deposit, or a daily average added deposit.
15. An electronic device, comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-7.
16. A non-transitory computer readable storage medium having stored thereon computer instructions for causing the computer to perform the method of any one of claims 1-7.
17. A computer program product comprising a computer program which, when executed by a processor, implements the method according to any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110728631.5A CN113379462A (en) | 2021-06-29 | 2021-06-29 | Site selection method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110728631.5A CN113379462A (en) | 2021-06-29 | 2021-06-29 | Site selection method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113379462A true CN113379462A (en) | 2021-09-10 |
Family
ID=77579898
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110728631.5A Pending CN113379462A (en) | 2021-06-29 | 2021-06-29 | Site selection method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113379462A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2016152044A (en) * | 2015-02-16 | 2016-08-22 | バイドゥ オンライン ネットワーク テクノロジー （ベイジン） カンパニー リミテッド | Method and device for determining target position |
| CN106952105A (en) * | 2017-04-26 | 2017-07-14 | 浙江大学 | A kind of retail shop based on transfer learning optimizes site selecting method |
| CN109657883A (en) * | 2019-01-28 | 2019-04-19 | 重庆邮电大学 | A kind of bank branches recommended method based on multi-source data driving |
| CN110378737A (en) * | 2019-07-23 | 2019-10-25 | 中国工商银行股份有限公司 | A kind of distribution appraisal procedure and device |
| CN111428861A (en) * | 2020-03-16 | 2020-07-17 | 东南大学 | Manufacturing enterprise overseas investment site selection decision method based on multi-scale multi-dimensional proximity |
| CN112541786A (en) * | 2020-12-11 | 2021-03-23 | 中信银行股份有限公司 | Site selection method and device for network points, electronic equipment and storage medium |
| CN112884224A (en) * | 2021-02-20 | 2021-06-01 | 杭州比智科技有限公司 | Method and device for selecting address of entity object, computing equipment and computer storage medium |
-
2021
- 2021-06-29 CN CN202110728631.5A patent/CN113379462A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2016152044A (en) * | 2015-02-16 | 2016-08-22 | バイドゥ オンライン ネットワーク テクノロジー （ベイジン） カンパニー リミテッド | Method and device for determining target position |
| CN106952105A (en) * | 2017-04-26 | 2017-07-14 | 浙江大学 | A kind of retail shop based on transfer learning optimizes site selecting method |
| CN109657883A (en) * | 2019-01-28 | 2019-04-19 | 重庆邮电大学 | A kind of bank branches recommended method based on multi-source data driving |
| CN110378737A (en) * | 2019-07-23 | 2019-10-25 | 中国工商银行股份有限公司 | A kind of distribution appraisal procedure and device |
| CN111428861A (en) * | 2020-03-16 | 2020-07-17 | 东南大学 | Manufacturing enterprise overseas investment site selection decision method based on multi-scale multi-dimensional proximity |
| CN112541786A (en) * | 2020-12-11 | 2021-03-23 | 中信银行股份有限公司 | Site selection method and device for network points, electronic equipment and storage medium |
| CN112884224A (en) * | 2021-02-20 | 2021-06-01 | 杭州比智科技有限公司 | Method and device for selecting address of entity object, computing equipment and computer storage medium |
Non-Patent Citations (2)
| Title |
|---|
| LU FANG等: "Review of board-level solder joint reliability under environmental stress", 《2016 PROGNOSTICS AND SYSTEM HEALTH MANAGEMENT CONFERENCE》, 19 January 2017 (2017-01-19) * |
| 王刚: "邮储银行ATM网点选址分析与规划", 《金融科技时代》, no. 8, pages 30 - 33 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111639253B (en) | Data weight judging method, device, equipment and storage medium | |
| CN107133289A (en) | A kind of method and apparatus of determination commercial circle | |
| CN114580916A (en) | Enterprise risk assessment method and device, electronic equipment and storage medium | |
| CN108415960A (en) | A kind of implementation method and device of geo-location service, electronic equipment | |
| CN110659961A (en) | Method and device for identifying off-line commercial tenant | |
| CN112053097A (en) | Loan collection method and device, electronic equipment and storage medium | |
| CN106294676B (en) | A kind of data retrieval method of ecommerce government system | |
| CN113706291A (en) | Fraud risk prediction method, device, equipment and storage medium | |
| CN115545712A (en) | Fraud prediction method, device, equipment and storage medium for transaction behaviors | |
| CN114549058A (en) | Address selection method and device, electronic equipment and readable storage medium | |
| CN113469461A (en) | Method and device for generating information | |
| CN106886934A (en) | Method, system and apparatus for determining merchant categories | |
| CN109767333A (en) | Select based method, device, electronic equipment and computer readable storage medium | |
| CN113379464B (en) | Block chain-based site selection method, device, equipment and storage medium | |
| EP4012642A2 (en) | Blockchain-based outlet site selection method and apparatus, device and storage medium | |
| CN113379462A (en) | Site selection method, device, equipment and storage medium | |
| CN114490406A (en) | Test coverage item management method, device, equipment and medium | |
| CN114298825A (en) | Method and device for extremely evaluating repayment volume | |
| CN113705201A (en) | Text-based event probability prediction evaluation algorithm, electronic device and storage medium | |
| CN113407587A (en) | Data processing method, device and equipment for online analysis processing engine | |
| CN113435748A (en) | Dot state determination method and apparatus, electronic device and storage medium | |
| CN109872024A (en) | Credit evaluation index processing method and device | |
| CN114547448B (en) | Data processing method, model training method, device, equipment, storage medium and program | |
| CN114926002A (en) | Customer intimacy degree determination method, apparatus, device, medium, and program product | |
| CN114493844A (en) | Information processing method and device and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |