CN116433302A

CN116433302A - Store location method and electronic equipment

Info

Publication number: CN116433302A
Application number: CN202111667240.3A
Authority: CN
Inventors: 黄缨宁; 南雨含; 杨磊; 张钰; 王云鹤; 寇祖良
Original assignee: 4Paradigm Beijing Technology Co Ltd
Current assignee: 4Paradigm Beijing Technology Co Ltd
Priority date: 2021-12-31
Filing date: 2021-12-31
Publication date: 2023-07-14

Abstract

The embodiment of the application relates to the technical field of data processing, and discloses a store location method and electronic equipment. The store location method comprises the following steps: receiving at least one existing store address of the target brand, acquiring all store addresses of at least one reference brand in a preset range of each existing store address, further obtaining correlation characteristics of the target brand and the at least one reference brand according to the number of stores of each reference brand and distance information of the store addresses of each reference brand and the at least one existing store address, and determining an address selecting area according to all store addresses of the at least one reference brand in the second area. Further, at least one new store address of the target brand is predicted within the site selection area based on the relevance features. Therefore, the technical scheme not only can realize automatic site selection and greatly save manpower, but also is not influenced by personnel experience, and can ensure the accuracy of the prediction result.

Description

Store location method and electronic equipment

Technical Field

The embodiment of the application relates to the technical field of data processing, in particular to a store location method and electronic equipment.

Background

With the development of retail industry, the site selection of each store of a chain is particularly important as an off-line business layout. Store location requires analysis of factors such as passenger flow volume, busy ratio, user mobility, user purchasing power, and existing stores in the vicinity.

At present, the above information is usually obtained by manual in-situ analysis, and then the analysis decision is performed on the obtained information again by manual.

Disclosure of Invention

The embodiment of the application provides a store location method and electronic equipment, which are used for solving the problem that the existing store location depends on manual work.

In a first aspect, an embodiment of the present application provides a store location method, where the method includes:

receiving at least one existing store address of a target brand, the at least one existing store address being located within a first area;

acquiring the whole department store address of at least one reference brand in the preset range of each existing department store address;

obtaining the correlation characteristics of the target brand and the at least one reference brand according to the number of store positions of each reference brand, the distance information of the store position of each reference brand and the at least one existing store position and the attribute information of each brand;

Determining an address selecting area according to all store addresses of the at least one reference brand in a second area, wherein the second area comprises an area with attribute similarity exceeding a preset value with the first area;

predicting at least one new store address of the target brand within the addressed area based on the relevance feature.

In some possible embodiments, obtaining the correlation feature of the target brand and the at least one reference brand according to the number of shops of each reference brand, the distance information between the shop address of each reference brand and the at least one existing shop address, and the attribute information of each brand, includes:

determining an initial correlation coefficient of the target brand and each reference brand according to the attribute information of the target brand and the attribute information of each reference brand, determining a first weight corresponding to each reference brand according to the number of stores of each reference brand, and determining a second weight corresponding to each reference brand according to the distance information of the store address of each reference brand and the existing store address;

corresponding to each reference brand, obtaining the correlation coefficient of the reference brand and the target brand according to the initial correlation coefficient, the first weight and the second weight corresponding to the reference brand;

The correlation characteristic is obtained according to the correlation coefficient of each reference brand.

In some possible implementations, for each of the reference brands, the distance information of each of the reference brands' store addresses from the at least one existing store address is implemented as any one of:

an average value of distances between each existing store address and each store address of the reference brand within a preset range of the existing store address; or alternatively

An average of distances of each store address of the reference brand from each of the existing store addresses.

In some possible implementations, the predicting at least one new store address of the target brand within the addressed area based on the relevance feature includes:

acquiring a plurality of addresses to be selected;

obtaining the reference characteristic corresponding to each address to be selected according to the position distribution of the addresses to be selected in the address selecting area;

and selecting at least one address to be selected from the addresses to be selected as the new store address according to the matching degree of the reference characteristic and the correlation characteristic.

In some possible embodiments, according to the location distribution of the plurality of addresses to be selected in the address selecting area, obtaining the reference feature corresponding to each address to be selected includes:

And corresponding to any address to be selected, and determining the reference characteristic corresponding to the address to be selected according to the address to be selected and the number and the distance of the reference brand store addresses in the preset range of the address to be selected.

In some possible implementations, the acquiring the full department store address of the at least one reference brand within the preset range of the existing department store addresses includes:

acquiring the total number of all other brands and store addresses of each other brand within the preset range of each existing store address;

and screening out all the store addresses of the at least one reference brand and each reference brand according to the total number of the store addresses of each other brand.

In some possible embodiments, the method further comprises:

receiving turnover corresponding to each existing store in the at least one existing store address;

predicting the turnover corresponding to at least one new store of the target brand according to the correlation characteristics.

In a second aspect, embodiments of the present application further provide a store location device, where the device includes:

a receiving module for receiving at least one existing store address of a target brand, the at least one existing store address being located within a first area;

The acquisition module is used for acquiring the whole department store address of at least one reference brand in the preset range of each existing department store address;

the feature acquisition module is used for acquiring the correlation features of the target brand and the at least one reference brand according to the number of store positions of each reference brand, the distance information of the store position of each reference brand and the at least one existing store position and the attribute information of each brand;

the determining module is used for determining an address selecting area according to all store addresses of the at least one reference brand in a second area, wherein the second area comprises an area with attribute similarity exceeding a preset value with the first area;

and the prediction module is used for predicting at least one new store address of the target brand in the address selecting area according to the correlation characteristic.

In some possible embodiments, the feature obtaining module is further configured to determine an initial correlation coefficient between the target brand and each reference brand according to the attribute information of the target brand and the attribute information of each reference brand, determine a first weight corresponding to each reference brand according to the number of stores of each reference brand, and determine a second weight corresponding to each reference brand according to the distance information between the store address of each reference brand and the existing store address; corresponding to each reference brand, obtaining the correlation coefficient of the reference brand and the target brand according to the initial correlation coefficient, the first weight and the second weight corresponding to the reference brand; and obtaining the correlation characteristic according to the correlation coefficient of each reference brand.

In some possible embodiments, the prediction module is further configured to obtain a plurality of candidate addresses; obtaining the reference characteristic corresponding to each address to be selected according to the position distribution of the addresses to be selected in the address selecting area; and selecting at least one address to be selected from the addresses to be selected as the new store address according to the matching degree of the reference feature and the correlation feature.

In some possible embodiments, the prediction module is further configured to correspond to any one of the candidate addresses, and determine, according to the candidate addresses and the number and the distance of the reference brand store addresses within the preset range, a reference feature corresponding to the candidate addresses.

In some possible embodiments, the obtaining module is further configured to obtain all other brands within the preset range of each existing store address and the total number of store addresses of each other brand; and screening out all the store addresses of the at least one reference brand and the respective reference brands according to the total number of the store addresses of each other brand.

In some possible implementations, the receiving module is further configured to receive a turnover corresponding to each of the at least one existing store address;

and the prediction module is also used for predicting the turnover corresponding to at least one new store of the target brand according to the correlation characteristics.

In a third aspect, embodiments of the present application further provide an electronic device, including: the system comprises a memory and a processor, wherein the memory and the processor are in communication connection, the memory stores computer instructions, and the processor executes the method in the first aspect or any possible implementation manner of the first aspect through executing the computer instructions.

In a fourth aspect, the embodiments further provide a computer-readable storage medium storing computer instructions for causing the computer to perform the method of the first aspect or any of the possible implementation manners of the first aspect.

In the technical scheme, after receiving at least one existing store address of a target brand in a first area, an electronic device obtains all department store addresses of at least one reference brand in a preset range of each existing store address, so as to obtain correlation characteristics of the target brand and the at least one reference brand according to the number of stores of each reference brand and distance information between the store address of each reference brand and the at least one existing store address, and determine an address selecting area according to all store addresses of the at least one reference brand in a second area. Wherein the second region includes a region having the same attribute as the first region. The electronic device then predicts at least one new store address for the target brand within the addressing area based on the relevance feature. As can be seen, in the present technical solution, the correlation characteristic of the existing store address of the target brand and at least one reference brand surrounding the existing store address is used as a parameter, and in the second area including at least one reference brand store address, a new store address of the target brand is predicted based on the relationship between the at least one reference brand store address and the correlation characteristic, so that a method for determining a referenceable address parameter according to the existing store address and further predicting a new store address according to the determined address parameter can be implemented. Therefore, automatic site selection can be realized, a large amount of manpower is saved, the influence of personnel experience is avoided, and the accuracy of a predicted result can be ensured.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the embodiments will be briefly described below, and it will be obvious to those skilled in the art that other drawings can be obtained from these drawings without inventive effort.

FIG. 1 is a method flow diagram of a store location method 100 provided in an embodiment of the present application;

FIG. 2 is a schematic diagram of an exemplary map-based store location relationship provided by an embodiment of the present application;

FIG. 3 is a schematic diagram of an exemplary map-based region relationship provided by an embodiment of the present application;

FIG. 4A is a schematic diagram of an exemplary composition of a store addressing device 40 provided in an embodiment of the present application;

fig. 4B is an exemplary structural schematic diagram of the electronic device 41 provided in the embodiment of the present application.

Detailed Description

The terminology used in the examples below in this application is for the purpose of describing alternative embodiments and is not intended to be limiting of the application. As used in the specification and the appended claims, the singular forms "a," "an," "the," and "the" are intended to include the plural forms as well. It should also be understood that, although the terms first, second, etc. may be used in the following embodiments to describe some type of object, the object is not limited to these terms. These terms are used to distinguish between specific objects of that class of objects. For example, the terms first, second, etc. may be used in the following embodiments to describe a region, but a region should not be limited to these terms. Other classes of objects that may be described in the following embodiments using the terms first, second, etc. are not described here again.

The embodiment of the application relates to a machine learning technology and provides a store location method. The store location method related to the embodiment of the application can be applied to the location of off-line stores, and the stores can be brands including tea A, duck B, hot pot C and the like by way of example. It should be understood that the english letters "a", "B" and "C" described above are references to some brand names and do not indicate brands named a tea, B duck, C chafing dish. The brand names referred to below in this specification using english alphabets are not repeated.

According to the store location method, based on existing stores of a target brand, correlation characteristics of each existing store and at least one reference brand store around the existing stores are obtained, and further, in a to-be-located area containing at least one reference brand store, the correlation characteristics are used as parameters, and new store addresses of the target brand are predicted by combining with at least one reference brand store in the to-be-located area, so that automatic location is achieved.

The store location method provided by the embodiment of the application can be executed by one electronic device or a computer cluster. The computer cluster comprises at least two electronic devices supporting the store location method of the embodiment of the application, and any electronic device can realize the store location function described by the embodiment of the application through a deployment algorithm model.

Any of the electronic devices to which embodiments of the present application relate may be electronic devices such as cell phones, tablet computers, wearable devices (e.g., smartwatches, smartbracelets, etc.), notebook computers, desktop computers, and vehicle-mounted devices. The electronic device is pre-installed with a map application. It will be appreciated that embodiments of the present application do not impose any limitation on the specific type of electronic device.

The technical solutions of the embodiments of the present application and technical effects produced by the technical solutions of the present application are described below by describing several exemplary embodiments.

Referring to fig. 1, fig. 1 is a flowchart of a method of shop location method 100 (hereinafter referred to as method 100) according to an embodiment of the present application, where the method 100 is applied to an electronic device as described above. The method 100 comprises the steps of:

step S101, at least one existing store address of a target brand is received, the at least one existing store address being located in a first area.

The target brand is a brand of a new store address to be determined, and the target brand can be a brand of any commodity. The first area may include at least one administrative area, such as "Beijing, chaoyang area", or at least one city, such as "Suzhou, city".

Alternatively, the first area may be a pre-selected area, where the similarity of the attribute with the area to which the new store address to be determined belongs exceeds a preset value. Optionally, the attributes of the area described in the embodiments of the present application include: people flow in an area, consumption level related to the area, traffic conditions of the area, etc. It should be understood that the preset value of the similarity here may be set according to the need.

Alternatively, the at least one existing store address may be all the existing stores of the target brand contained in the first area, or may be addresses of a preset number of existing stores of the target brand in the first area, for example, 10.

In a possible implementation manner, the store address may be implemented as latitude and longitude data of a location where an existing store is located. In another possible implementation, the store address may be implemented as a set of area information, street information, cell information, building number information, etc. of the location of the existing store.

By way of example, a user may want to set a new store of brand a in an area where a new store address is to be determined (e.g., a beijing ocean lake area), then a first area (e.g., a beijing ocean area) having similar area attributes to the new store address may be determined, and in turn, area information, street information, cell information, and building number information of an existing store of brand a of the first area (e.g., a beijing ocean area) may be input to the electronic device.

In another possible implementation, the electronic device further receives a turnover corresponding to each of at least one existing store address of the target brand. Alternatively, the turnover corresponding to each existing store may be a turnover within a preset period of time of the existing store, for example, a turnover of the last year.

Step S102, obtaining the whole department store address of at least one reference brand in the preset range of each existing department store address.

Wherein the preset range may be 1 meter to 1500 meters. Alternatively, the reference brand may be any brand within a preset range, or a brand within a preset range satisfying a certain condition.

In some embodiments, after receiving the at least one existing store address, the electronic device may determine a location of each existing store address in the map in conjunction with the map application, and further, obtain, centering on each existing store address, all store addresses of non-target brands (also referred to as other brands) within a preset range of the electronic device as all store addresses of the at least one reference brand.

In other embodiments, after receiving the at least one existing store address, the electronic device, in conjunction with the map application, respectively centers on each existing store address, obtains all other brands within a preset range and total number of each other brand of store address, and further screens out (e.g. in order from large to small) at least one reference brand and all store addresses of each reference brand according to the total number of each other brand of store address. For example, a preset range of existing store addresses includes other brands: brand B, brand C, brand D, brand E, brand F and Brand G, wherein the total number of Brand B's stores is, for example, 6, brand C's stores is, for example, 5, brand D's stores is, for example, 5, brand E's stores is, for example, 4, brand F's stores is, for example, 3, and Brand G's stores is, for example, 1. Then, the electronic device may screen out brand B, brand C, brand D, brand E, and brand F as reference brands.

By way of example, referring to the exemplary map-based store locations illustrated in fig. 2, fig. 2 is an interface, for example, of a map application running in an electronic device, illustrating two existing store addresses for brand a: address 21 and address 22. The electronic device determines the circular areas illustrated in fig. 2, for example, with the address 21 and the address 22 as the centers, and with the radius of 1 km, and further obtains the addresses of all the stores of other brands in each circular area, for example, to obtain a brand B illustrated in fig. 2. It should be appreciated that the circular area of FIG. 2 may also include full department store addresses for Brand C, brand D, brand E, and Brand F (not shown).

It should be understood that fig. 2 is only a schematic depiction and is not limiting of embodiments of the present application. In practical implementation, the number of existing store addresses of brand a, the number of reference brands, and the number of stores of each reference brand may be different from those shown in fig. 2, and will not be described here again.

Step S103, according to the number of stores of each reference brand, the distance information of the store address of each reference brand and at least one existing store address and the attribute information of each brand, the correlation characteristics of the target brand and at least one reference brand are obtained.

Wherein, because each reference brand corresponds to at least one store address, for each reference brand, in some embodiments, distance information of the store address of the reference brand from at least one existing store address may be implemented as: average value of distance between each existing store address and each store address of the reference brand in preset range of the existing store addresses. In some embodiments, the distance information of the reference brand of store address from at least one existing store address may be implemented as: average value of distances of each store address of the reference brand from each existing store address.

For example, referring again to FIG. 2, brand B is taken as an example. In the map illustrated in fig. 2, 3 stores of brand B are included in the preset range of store addresses 21 of brand a, and 2 stores of brand B are included in the preset range of store addresses 22 of brand a. In one implementation, the existing store distance information for brand B and brand a may be an average of a first average of distances between store address 21 and 3 store addresses of brand B within its preset range and a second average of distances between store address 22 and 2 store addresses of brand B within its preset range. In another implementation, the 5 brands B are the average of the sum of the distances between store address 21 and store address 22. The determination methods of the distance information of brand C, brand D, brand E, and brand F and brand a in fig. 2 are similar to those described in this example, and will not be repeated here.

The correlation feature related to the embodiment of the application can represent the forward influence degree of the reference brand on the target brand, and the larger the feature value of the correlation feature is, the larger the forward influence degree of the corresponding reference brand on the target brand can be indicated, and the smaller the feature value of the correlation feature is, the smaller the forward influence degree of the corresponding reference brand on the target brand can be indicated. Where positive influence means that there is a beneficial influence on the development of the target brand.

Optionally, after obtaining at least one existing store address of the target brand and the store address of the corresponding reference brand, the electronic device may determine an initial correlation coefficient of the target brand and each reference brand according to the attribute information of the target brand and the attribute information of each reference brand. And determining the first weight corresponding to each reference brand according to the number of stores of each reference brand. And determining the second weight corresponding to each reference brand according to the distance information between the store address of each reference brand and the existing store address. And corresponding to each reference brand, obtaining the correlation coefficient of the reference brand and the target brand according to the initial correlation coefficient, the first weight and the second weight corresponding to the reference brand. And obtaining the correlation characteristic according to the correlation coefficient of each reference brand.

Alternatively, each brand has various attributes based on its product, and this embodiment of the present application is referred to as attribute information of the brand. The attribute information of the brand may include, for example, industry information described by the brand, functionality of the brand product, and the like. The electronic device may set an initial correlation coefficient for the target brand and the reference brand based on the influence between the different brand attribute information, the initial correlation coefficient also indicating a degree of positive influence of the reference brand on the target brand.

For example, target brand a is a tea, and involves the catering industry, and in a practical scenario, if a user does not have a dinner drink shop in a region, a brand shop such as shoe brand B and cosmetic brand C in the region is more beneficial to the development of the a tea, and accordingly, the initial correlation coefficients of the brand B and the brand C and the target brand are larger, for example, each is 0.9. On the contrary, the brand D 'O drink' which is the catering brand has a competitive relationship with the A tea, so that the smaller the forward influence degree of the brand D 'O drink' on the A tea is, the smaller the initial correlation coefficient between the brand D 'O drink' and the A tea is, for example, 0.1.

Alternatively, the first weight and the second weight may be values greater than or equal to 1. The first weight may indicate a contribution of a number of stores of the reference brand to the corresponding initial relevance coefficient, the greater the number of stores of the reference brand, the greater the contribution, and the greater the first weight. The second weight may indicate a contribution of distance information of the reference brand's store address from the existing store address to the corresponding initial correlation coefficient, the smaller the distance of the reference brand's store address from the existing store address, the greater the contribution, and the greater the second weight.

Alternatively, the correlation coefficient of any reference brand with the target brand may be implemented, for example, as: the initial correlation coefficient of the reference brand and the target brand is multiplied by the first weight of the reference brand and the second weight of the reference brand. The data set consisting of the correlation coefficients of the target brand and each reference brand is the correlation feature corresponding to the target brand.

Step S104, determining the addressing area according to all store addresses of at least one reference brand in the second area.

The second area may be an area indicated by the user in advance, and the second area includes an area having the same attribute as the first area. Optionally, if the area to be determined of the new store address is preset, the second area includes the area to be determined of the new store address. For example, the area where the new store address is predetermined to be determined is a beijing city lake area, and then the second area includes the beijing city lake area.

Alternatively, the second area may include the first area, and the second area is, for example, beijing. The second area may not include the first area, and the second area is, for example, a beijing city lake area.

In connection with step S102, after determining at least one reference brand, the electronic device may invoke the map application to obtain the all department store addresses of the at least one reference brand in the second area, and further, use the area composed of all the department store addresses as the addressing area of the target brand.

For example, referring to fig. 3, after determining brand B, brand C, brand D, brand E, and brand F, the electronic device obtains all the store addresses of brand B, brand C, brand D, brand E, and brand F within the range of the area 31, and further, based on the corresponding full-department store addresses within the range of the area 31, forms an area 32, where the area 32 is the site area of brand a.

It should be noted that, although the operation content of step S103 is executed before the operation content of step S104 in the method 100, in practical implementation, the execution order of the operation content of step S103 and the operation content of step S104 is not limited, and the operation content of step S103 and the operation content of step S104 may be executed at the same time, or the operation content of step S104 may be executed before the operation content of step S103.

Step S105, at least one new store address of the target brand is predicted in the addressing area according to the correlation characteristics.

The electronic device can acquire a plurality of addresses to be selected, and further acquire the reference characteristic corresponding to each address to be selected according to the position distribution of the addresses to be selected in the address selecting area. And then, selecting at least one candidate address from the candidate addresses as a new store address according to the matching degree of the reference characteristic and the correlation characteristic.

In some embodiments, the address to be selected may be preset by a user, for example, the user sets a new store in the vicinity of subway station X and subway station Y in the beijing ocean lake area in advance, where the addresses of subway station X and subway station Y are the addresses to be selected.

In other embodiments, the electronic device may use the center of at least one reference brand-dense area corresponding to a larger correlation coefficient in the addressing area as the candidate address. For example, the correlation coefficient corresponding to the brand D is the largest, the correlation coefficient corresponding to the brand E is the next largest, the electronic device determines the area where the brand D is denser in the address selection area, and the center of the corresponding area is used as the address to be selected, and determines the area where the brand E is denser in the address selection area, and the center of the corresponding area is also used as the address to be selected. It should be appreciated that in practical implementations, the number of addresses to be selected may be determined as desired.

Furthermore, the electronic device may obtain, based on the distance information between each candidate address and its surrounding reference brands and the number of the reference brands, a reference feature corresponding to each candidate address, where the reference feature characterizes the correlation between the target brand and the surrounding reference brands when the target brand is at the candidate address. The process of obtaining the reference feature corresponding to each candidate address is similar to the process of obtaining the correlation coefficient in step S103, and will not be described in detail here.

The degree of matching of the reference feature with the correlation feature may be implemented, for example, as: the similarity of the reference feature to the correlation feature may be expressed, for example, in terms of euclidean distance. The selecting at least one candidate address from the candidate addresses as the new store addresses according to the matching degree of the reference feature and the correlation feature may be implemented, for example, by sequentially determining at least one new store address with the corresponding candidate address as the target brand according to the order of the similarity from high to low. The number of new store addresses can be flexibly set according to the requirements, and is not limited herein.

In other embodiments, if the electronic device further receives the sales corresponding to each existing store of the target brand, the electronic device may further predict the sales of the corresponding new store according to the similarity between the reference feature and the correlation feature of the new store.

For example, the average sales of all sales of at least one existing store of the target brand may be obtained, and then, after predicting the similarity between the reference feature and the correlation feature of the new store, a difference value obtained by subtracting 1 from the similarity may be obtained, and then, on the basis of the average sales, a proportion corresponding to the difference value may be increased, and a proportion corresponding to the difference value may be decreased, which may be used as the predicted sales range of the new store.

For example, the average turnover for 10 existing stores of brand A is 10000 yuan. In the process of predicting a new store of brand A, the electronic equipment obtains that the similarity between the reference characteristic and the correlation characteristic of the new store is 97%, and the corresponding difference between the similarity and the correlation characteristic is 3%. Furthermore, the electronic device obtains 9700 according to algorithm 10000 (1-3%), and obtains 13000 according to algorithm 10000 (1+3%). Then, it is determined that the business balance of the new store ranges from 9700 yuan to 13000 yuan.

The above embodiments describe each implementation of the store location method provided in the embodiments of the present application from the angles of obtaining the existing store address of the target brand, obtaining the reference brand, obtaining the correlation characteristics of the target brand and the reference brand, and predicting the actions executed by the electronic device such as the new store address according to the correlation characteristics, and the learning algorithm processing. It should be understood that the embodiments of the present application may implement the above functions in the form of hardware or a combination of hardware and computer software, corresponding to the processing steps of obtaining the existing store address of the target brand, obtaining the reference brand store, obtaining the correlation characteristics of the target brand and the reference brand, and predicting the new store address according to the correlation characteristics. Whether a function is implemented as hardware or computer software driven hardware depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.

For example, if the above implementation steps are implemented by software modules, the corresponding functions are implemented. As shown in fig. 4A, the store addressing device 40 may include a receiving module 401, an obtaining module 402, a feature obtaining module 403, a determining module 404, and a predicting module 405. The store addressing device 40 may be used to perform some or all of the operations of the method 100 described above.

For example: a receiving module 401, configured to receive at least one existing store address of a target brand, where the at least one existing store address is located in a first area. An acquiring module 402, configured to acquire a full department store address of at least one reference brand within a preset range of each of the existing department store addresses. The feature obtaining module 403 is configured to obtain a correlation feature between the target brand and the at least one reference brand according to the number of stores of each reference brand, the distance information between the store address of each reference brand and the at least one existing store address, and attribute information of each brand. A determining module 404, configured to determine an address selecting area according to all store addresses of the at least one reference brand in a second area, where the second area includes an area with a similarity with the attribute of the first area exceeding a preset value. A prediction module 405, configured to predict at least one new store address of the target brand in the location area according to the relevance feature.

As can be seen, the store address selecting device 40 provided in the embodiment of the present application predicts a new store address of a target brand based on the relationship between at least one reference brand store address and the correlation characteristic in the second area including at least one reference brand store address, using the correlation characteristic of the existing store address of the target brand and at least one reference brand around the existing store address as a parameter, thereby implementing a method for determining a referenceable address parameter according to the existing store address and predicting the new store address according to the determined address parameter. Therefore, automatic site selection can be realized, a large amount of manpower is saved, the influence of personnel experience is avoided, and the accuracy of a predicted result can be ensured.

Optionally, the feature obtaining module 403 is further configured to determine an initial correlation coefficient between the target brand and each reference brand according to the attribute information of the target brand and the attribute information of each reference brand, determine a first weight corresponding to each reference brand according to the number of stores of each reference brand, and determine a second weight corresponding to each reference brand according to the distance information between the store address of each reference brand and the existing store address; corresponding to each reference brand, obtaining the correlation coefficient of the reference brand and the target brand according to the initial correlation coefficient, the first weight and the second weight corresponding to the reference brand; and obtaining the correlation characteristic according to the correlation coefficient of each reference brand.

Optionally, for each of the reference brands, the distance information of the store address of each of the reference brands from the at least one existing store address is implemented as any one of the following:

Optionally, the prediction module 405 is further configured to obtain a plurality of addresses to be selected; obtaining the reference characteristic corresponding to each address to be selected according to the position distribution of the addresses to be selected in the address selecting area; and selecting at least one address to be selected from the addresses to be selected as the new store address according to the matching degree of the reference feature and the correlation feature.

Optionally, the prediction module 405 is further configured to determine, according to the number and the distance of the candidate addresses and the reference brand store addresses within the preset range, a reference feature corresponding to the candidate addresses, where the candidate addresses correspond to any candidate address.

Optionally, the obtaining module 402 is further configured to obtain all other brands within the preset range of each existing store address and a total number of store addresses of each other brand; and screening out all the store addresses of the at least one reference brand and the respective reference brands according to the total number of the store addresses of each other brand.

Optionally, the receiving module 401 is further configured to receive a turnover corresponding to each of the at least one existing store address; the prediction module 405 is further configured to predict a turnover corresponding to at least one new store of the target brand according to the relevance feature.

It will be appreciated that the above division of the modules/units is merely a division of logic functions, and in actual implementation, the functions of the above modules may be integrated into a hardware entity implementation, for example, the functions of the acquisition module 402, the feature acquisition module 403, the determination module 404, and the prediction module 405 may be integrated into a processor implementation, the functions of the receiving module 401 may be integrated into a transceiver implementation, and programs and instructions implementing the functions of the above modules may be maintained in a memory. For example, fig. 4B provides an electronic device 41, the electronic device 41 comprising a processor 411, a transceiver 412, and a memory 413. The transceiver 412 is used to perform the method 100 for obtaining address information and turnover of the existing store of the target brand. The memory 413 may be used to store programs/codes preloaded by the store addressing device 40, or may be used to store codes executed by the processor 401. The processor 411, when executing the code stored in the memory 413, causes the electronic device 41 to perform some or all of the operations of the store addressing method in the method 100 described above.

The specific implementation is described in detail in the embodiments illustrated in method 100 above and not described in detail herein.

In a specific implementation, corresponding to the foregoing electronic device, the embodiment of the application further provides a computer storage medium, where the computer storage medium provided in the electronic device may store a program, and when the program is executed, may implement some or all of the steps in each embodiment of the store location method including the method 100. The storage medium may be a magnetic disk, an optical disk, a read-only memory (ROM), a random-access memory (random access memory, RAM), or the like.

One or more of the above modules or units may be implemented in software, hardware, or a combination of both. When any of the above modules or units are implemented in software, the software exists in the form of computer program instructions and is stored in a memory, a processor can be used to execute the program instructions and implement the above method flows. The processor may include, but is not limited to, at least one of: a central processing unit (central processing unit, CPU), microprocessor, digital Signal Processor (DSP), microcontroller (microcontroller unit, MCU), or artificial intelligence processor, each of which may include one or more cores for executing software instructions to perform operations or processes. The processor may be built into a SoC (system on a chip) or an application specific integrated circuit (application specific integrated circuit, ASIC) or may be a separate semiconductor chip. The processor may further include necessary hardware accelerators, such as field programmable gate arrays (field programmable gate array, FPGAs), PLDs (programmable logic devices), or logic circuits implementing dedicated logic operations, in addition to the cores for executing software instructions for operation or processing.

When the above modules or units are implemented in hardware, the hardware may be any one or any combination of a CPU, microprocessor, DSP, MCU, artificial intelligence processor, ASIC, soC, FPGA, PLD, dedicated digital circuitry, hardware accelerator, or non-integrated discrete device that may run the necessary software or that is independent of the software to perform the above method flows.

Further, a bus interface may be included in FIG. 4B, which may include any number of interconnected buses and bridges, with the various circuits of the memory, specifically represented by one or more of the processors and the memory, being linked together. The bus interface may also link together various other circuits such as peripheral devices, voltage regulators, power management circuits, etc., which are well known in the art and, therefore, will not be described further herein. The bus interface provides an interface. The transceiver provides a means for communicating with various other apparatus over a transmission medium. The processor is responsible for managing the bus architecture and general processing, and the memory may store data used by the processor in performing operations.

When the above modules or units are implemented in software, they may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loaded and executed on a computer, produces a flow or function in accordance with embodiments of the present invention, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable apparatus. The computer instructions may be stored in or transmitted from one computer-readable storage medium to another, for example, by wired (e.g., coaxial cable, optical fiber, digital Subscriber Line (DSL)), or wireless (e.g., infrared, wireless, microwave, etc.). The computer readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. that contains an integration of one or more available media. The usable medium may be a magnetic medium (e.g., floppy Disk, hard Disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid State Disk (SSD)), etc.

It should be understood that, in various embodiments of the present application, the size of the sequence number of each process does not mean that the execution sequence of each process should be determined by its functions and internal logic, and should not constitute any limitation on the implementation process of the embodiments.

All parts of the specification are described in a progressive manner, and all parts of the embodiments which are the same and similar to each other are referred to each other, and each embodiment is mainly described as being different from other embodiments. In particular, for apparatus and system embodiments, the description is relatively simple, as it is substantially similar to method embodiments, with reference to the description of the method embodiments section.

While alternative embodiments of the present application have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. It is therefore intended that the following claims be interpreted as including the preferred embodiments and all such alterations and modifications as fall within the scope of the application.

The foregoing embodiments have been provided for the purpose of illustrating the general principles of the present invention, and are not meant to limit the scope of the invention, but to limit the scope of the invention.

Claims

1. A store location method, the method comprising:

2. The store location method according to claim 1, wherein obtaining the correlation feature of the target brand and the at least one reference brand based on the number of stores of each reference brand and the distance information between each reference brand's store address and the at least one existing store address and the attribute information of each brand, comprises:

3. The store addressing method according to claim 1 or 2, characterized in that, for each of the reference brands, the distance information of each of the reference brands' store addresses from the at least one existing store address is implemented as any one of the following:

4. The store addressing method of claim 1, wherein said predicting at least one new store address of said target brand within said addressing area based on said correlation characteristics comprises:

acquiring a plurality of addresses to be selected;

5. The store addressing method of claim 4, wherein obtaining a reference feature corresponding to each of the candidate addresses according to a position distribution of the plurality of candidate addresses in the addressing area comprises:

6. The store addressing method of claim 1, wherein said obtaining full department store addresses of at least one reference brand within a predetermined range of said existing store addresses comprises:

7. The store location method of claim 1, further comprising:

8. A store location apparatus, the apparatus comprising:

9. An electronic device, the electronic device comprising: a memory and a processor in communication with each other, the memory having stored therein computer instructions, the processor performing the method of any of claims 1-7 by executing the computer instructions.

10. A computer readable storage medium having stored thereon computer instructions for causing the computer to perform the method of any one of claims 1-7.