CN113706222B - Store site selection method and device - Google Patents
Store site selection method and device Download PDFInfo
- Publication number
- CN113706222B CN113706222B CN202111100921.1A CN202111100921A CN113706222B CN 113706222 B CN113706222 B CN 113706222B CN 202111100921 A CN202111100921 A CN 202111100921A CN 113706222 B CN113706222 B CN 113706222B
- Authority
- CN
- China
- Prior art keywords
- brand
- addressed
- store
- obtaining
- feature
- 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.)
- Active
Links
- 238000010187 selection method Methods 0.000 title description 7
- 238000000034 method Methods 0.000 claims abstract description 62
- 239000013598 vector Substances 0.000 claims description 15
- 238000007621 cluster analysis Methods 0.000 claims description 5
- 238000004590 computer program Methods 0.000 claims description 4
- 238000004422 calculation algorithm Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 7
- 238000004891 communication Methods 0.000 description 4
- 235000021152 breakfast Nutrition 0.000 description 3
- 235000005911 diet Nutrition 0.000 description 3
- 230000037213 diet Effects 0.000 description 3
- 241000287828 Gallus gallus Species 0.000 description 2
- 241000209094 Oryza Species 0.000 description 2
- 235000007164 Oryza sativa Nutrition 0.000 description 2
- 230000006399 behavior Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 235000021186 dishes Nutrition 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 235000009566 rice Nutrition 0.000 description 2
- 235000004347 Perilla Nutrition 0.000 description 1
- 244000124853 Perilla frutescens Species 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 235000021110 pickles Nutrition 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 235000013311 vegetables Nutrition 0.000 description 1
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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/29—Geographical information databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/906—Clustering; Classification
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Finance (AREA)
- Theoretical Computer Science (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Accounting & Taxation (AREA)
- Entrepreneurship & Innovation (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Game Theory and Decision Science (AREA)
- Economics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Remote Sensing (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The application discloses a store location method and device, wherein the store location method comprises the following steps: obtaining brand group images of brands to which the stores to be addressed belong; recalling basic crowd data for selecting the store to be addressed according to the brand group images and the characteristic labels to which the users belong; clustering the basic crowd data to obtain a basic crowd data clustering result; and determining the address information selected for the store to be addressed according to the basic crowd data clustering result. The method recalls basic crowd data of the brand of the store to be addressed based on the brand group image of the store to be addressed and the characteristic label of the user, ensures basic crowd facing the store to be addressed, and further determines address information selected for the store to be addressed through a clustering result of the basic crowd data.
Description
Technical Field
The application relates to the field of data analysis, in particular to a store site selection method and device; the application also relates to an electronic device and a computer storage medium.
Background
With the expansion of the industrial scale of brands, store site selection becomes an indispensable link in the process of brand establishment of business targets and business strategies.
At present, store location is mainly performed by collecting and researching passenger flow data of different sections, but the location mode is often high in cost and limited by human resources, the collected and researched passenger flow data are not comprehensive, and high-quality and accurate store addresses cannot be provided for merchants.
Disclosure of Invention
The application provides a store location method and device to solve the technical problems. The application also provides electronic equipment and a computer storage medium.
The method for shop site selection provided by the application comprises the following steps: obtaining brand group images of brands to which the stores to be addressed belong; recalling basic crowd data for selecting the store to be addressed according to the brand group images and the characteristic labels to which the users belong; clustering the basic crowd data to obtain a basic crowd data clustering result; and determining the address information selected for the store to be addressed according to the basic crowd data clustering result.
Optionally, the obtaining the brand group image of the brand to which the to-be-addressed store belongs includes: obtaining consumer feature labels of other selected stores of the brands to which the to-be-addressed stores belong; determining the similarity between the consumer feature tag and a preset brand feature tag; and taking the brand feature labels with the similarity larger than a preset similarity threshold value as preselected feature labels, and obtaining brand group images composed of the preselected feature labels.
Optionally, the obtaining the consumer feature tag of other selected stores of the brand to which the to-be-addressed store belongs includes: obtaining historical consumption data of consumers of other selected stores sent by the address server; obtaining the consumer feature tag according to the consumer historical consumption data; or, obtaining the historical consumption data of the consumers of the selected store, which is sent by the servers of the other selected stores; and obtaining the characteristic label of the consumer according to the historical consumer consumption data.
Optionally, the obtaining the brand group image of the brand to which the to-be-addressed store belongs includes: obtaining brand information of the store to be addressed, which is sent by an address selection client; and obtaining brand group images of brands of the to-be-addressed stores according to the brand information of the to-be-addressed stores.
Optionally, the recalling the basic crowd data for selecting the to-be-addressed store according to the brand group image and the feature tag to which the user belongs includes: obtaining a feature tag to which the user belongs; sequentially calculating the similarity between the feature labels to which the users belong and the brand group images; and obtaining a preset number of users as the basic crowd data according to the similarity.
Optionally, the sequentially calculating the similarity between the feature tag to which the user belongs and the brand group image includes: obtaining a user feature vector according to the user feature tag; according to the brand feature labels, brand feature vectors are obtained; and calculating cosine similarity between the user feature vector and the brand feature, and obtaining similarity between the feature label of the user and the brand group image.
Optionally, the clustering processing is performed on the basic crowd data to obtain a basic crowd data clustering result, including: obtaining a basic crowd distribution area map and position information of users in the basic crowd data; and carrying out grid division on the basic crowd distribution area map by adopting grids with preset sizes, determining the density of the users in each grid by combining the position information of the users in the basic crowd data, and taking the density of the users in each grid as the clustering result of the basic crowd data.
Optionally, the determining, according to the base crowd data clustering result, address information selected for the to-be-addressed store includes: and confirming the density center of the grid with the density of the user arranged at the top as the address information selected for the to-be-addressed store.
Optionally, the clustering processing is performed on the basic crowd data to obtain a basic crowd data clustering result, including: and carrying out cluster analysis on the users distributed at different positions in sequence according to the preset cluster radius, and determining the number of other users in the cluster radius of each user.
Optionally, the determining, according to the base crowd data clustering result, address information selected for the to-be-addressed store includes: and determining the address information of the user, the number of which is arranged first in the cluster radius of each user, as the address information selected for the store to be addressed.
Optionally, the obtaining the consumer feature tag of other selected stores of the brand to which the to-be-addressed store belongs includes: obtaining the service type of the store to be addressed; consumer feature tags are obtained that are the same as the service type and that belong to other addressed stores of the brand.
The application provides a shop addressing device simultaneously, include: the group image obtaining unit is used for obtaining brand group images of brands to which the store to be addressed belongs; the crowd recall unit is used for recalling basic crowd data for selecting the store to be addressed according to the brand group images and the characteristic labels to which the users belong; the crowd clustering unit is used for carrying out clustering processing on the basic crowd data to obtain a basic crowd data clustering result; and the address determining unit is used for determining the address information selected for the store to be addressed according to the basic crowd data clustering result.
Optionally, the obtaining the brand group image of the brand to which the to-be-addressed store belongs includes: obtaining consumer feature labels of other selected stores of the brands to which the to-be-addressed stores belong; determining the similarity between the consumer feature tag and a preset brand feature tag; and taking the brand feature labels with the similarity larger than a preset similarity threshold value as preselected feature labels, and obtaining brand group images composed of the preselected feature labels.
Optionally, the obtaining the consumer feature tag of other selected stores of the brand to which the to-be-addressed store belongs includes: obtaining historical consumption data of consumers of other selected stores sent by the address server; obtaining the consumer feature tag according to the consumer historical consumption data; or, obtaining the historical consumption data of the consumers of the selected store, which is sent by the servers of the other selected stores; and obtaining the characteristic label of the consumer according to the historical consumer consumption data.
Optionally, the obtaining the brand group image of the brand to which the to-be-addressed store belongs includes: obtaining brand information of the store to be addressed, which is sent by an address selection client; and obtaining brand group images of brands of the to-be-addressed stores according to the brand information of the to-be-addressed stores.
Optionally, the recalling the basic crowd data for selecting the to-be-addressed store according to the brand group image and the feature tag to which the user belongs includes: obtaining a feature tag to which the user belongs; sequentially calculating the similarity between the feature labels to which the users belong and the brand group images; and obtaining a preset number of users as the basic crowd data according to the similarity.
Optionally, the sequentially calculating the similarity between the feature tag to which the user belongs and the brand group image includes: obtaining a user feature vector according to the user feature tag; according to the brand feature labels, brand feature vectors are obtained; and calculating cosine similarity between the user feature vector and the brand feature, and obtaining similarity between the feature label of the user and the brand group image.
Optionally, the clustering processing is performed on the basic crowd data to obtain a basic crowd data clustering result, including: obtaining a basic crowd distribution area map and position information of users in the basic crowd data; and carrying out grid division on the basic crowd distribution area map by adopting grids with preset sizes, determining the density of the users in each grid by combining the position information of the users in the basic crowd data, and taking the density of the users in each grid as the clustering result of the basic crowd data.
Optionally, the determining, according to the base crowd data clustering result, address information selected for the to-be-addressed store includes: and confirming the density center of the grid with the density of the user arranged at the top as the address information selected for the to-be-addressed store.
Optionally, the clustering processing is performed on the basic crowd data to obtain a basic crowd data clustering result, including: and carrying out cluster analysis on the users distributed at different positions in sequence according to the preset cluster radius, and determining the number of other users in the cluster radius of each user.
Optionally, the determining, according to the base crowd data clustering result, address information selected for the to-be-addressed store includes: and determining the address information of the user, the number of which is arranged first in the cluster radius of each user, as the address information selected for the store to be addressed.
Optionally, the obtaining the consumer feature tag of other selected stores of the brand to which the to-be-addressed store belongs includes: obtaining the service type of the store to be addressed; consumer feature tags are obtained that are the same as the service type and that belong to other addressed stores of the brand.
The application also provides a store location method, which comprises the following steps: obtaining address information selected for a store to be addressed; displaying the address information selected for the store to be addressed; the address information selected for the store to be addressed is determined based on the clustering result of the basic crowd data after the basic crowd data is clustered; the basic crowd data are obtained according to brand group images of brands to which the stores to be addressed belong and the feature tags recalled by users.
The application provides a shop addressing device simultaneously, include: an obtaining unit for obtaining address information selected for a store to be addressed; the display unit is used for displaying the address information selected for the store to be addressed; the address information selected for the store to be addressed is determined based on the clustering result of the basic crowd data after the basic crowd data is clustered; the basic crowd data are obtained according to brand group images of brands to which the stores to be addressed belong and the feature tags recalled by users.
The application provides an electronic equipment simultaneously, includes: a processor; and a memory for storing a program of methods, which when read and executed by the processor, performs any of the methods described above.
The present application also provides a computer storage medium storing a computer program which when executed implements any of the methods described above.
Compared with the prior art, the application has the following advantages:
the store location method provided by the application comprises the following steps: obtaining brand group images of brands to which the stores to be addressed belong; recalling basic crowd data for selecting the store to be addressed according to the brand group images and the characteristic labels to which the users belong; clustering the basic crowd data to obtain a basic crowd data clustering result; and determining the address information selected for the store to be addressed according to the basic crowd data clustering result. The method recalls basic crowd data of the brand of the store to be addressed based on the brand group image of the store to be addressed and the characteristic label of the user, ensures basic crowd facing the store to be addressed, and further determines address information selected for the store to be addressed through a clustering result of the basic crowd data.
Drawings
Fig. 1 is a schematic view of a shop locating method according to a first embodiment of the present application;
FIG. 2 is a flowchart of a method for shop addressing according to a first embodiment of the present application;
FIG. 3 is a schematic structural diagram of a store location device according to a second embodiment of the present disclosure;
FIG. 4 is a flowchart of a method for shop addressing according to a third embodiment of the present application;
FIG. 5 is a schematic structural diagram of a store location device according to a fourth embodiment of the present disclosure;
fig. 6 is a schematic structural diagram of an electronic device according to a fifth embodiment of the present application.
Detailed Description
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present application. This application, however, may be embodied in many other forms than described herein and similarly generalized by those skilled in the art without departing from the spirit of the application and, therefore, the application is not to be limited to the specific embodiments disclosed below.
In an embodiment of the application, a store location method, a store location device, electronic equipment and a computer storage medium are respectively provided.
In order to facilitate understanding of the store location method provided by the application, the embodiment first describes the store location method with reference to a specific usage scenario.
Please refer to fig. 1, which is a schematic diagram of a scenario of a store location method according to a first embodiment of the present application, wherein fig. 1 includes: a terminal device 101 and a server 102.
The terminal device 101 refers to a terminal device for displaying store address information selected for a store to be addressed. When a store owner or other staff member of a certain brand of store needs to address a new store, brand information of the store to be addressed may be input in the terminal device 101. After receiving the brand information, the terminal device 101 sends the brand information to the server 102.
In the embodiment of the present application, the server 102 refers to an address selection server. After receiving the brand information sent by the terminal device, the server 102 retrieves the brand group image of the brand in the address server to be addressed to the store. In the embodiment of the application, the brand group image refers to an image which is composed of user characteristic labels and can reflect the audience user characteristics of the brand.
After the server 102 retrieves the brand group image, the base crowd data for selecting the address for the to-be-addressed store is recalled from the users according to the brand group image and the feature labels of all users stored in the server 102, wherein the base crowd data at least comprises the position data of the users.
Then, the server 102 performs clustering processing on the basic crowd data to obtain a basic crowd data clustering result. And finally, determining the address information selected for the to-be-addressed store according to the basic crowd data clustering result, and sending the address information to the terminal equipment 101 for display.
It should be noted that, the application is not limited to the specific application scenario of the store selection method provided in the above scenario embodiment, and the store selection method may also be applied to other scenarios. For example: the server 102 may be a brand-specific server that stores therein user data (e.g., historical consumption data) for other, addressed stores of the brand, as well as data (e.g., historical consumption data) for online consumers (i.e., users) of the brand. The application of the store selection method described in the above embodiment of the scenario of the present application is only for facilitating understanding of the present application, and is not intended to limit the application scenario of the store selection method provided in the present application.
The above is a scene embodiment provided for the store location method, and in order to more clearly understand the implementation process of the above scheme of the present application, the first embodiment of the present application further describes the store location method.
Referring to fig. 2, a flowchart of a method for shop location according to a first embodiment of the present application is shown. The method comprises the following steps: step S201 to step S204.
Step S201, a brand group image of the brand to which the store to be addressed belongs is obtained.
The store to be addressed refers to a certain commercial store which is not addressed but has the address requirement. For example: a chain of stores may wish to deploy a new store at a selected address, which may be the store to be addressed.
The brands to which the stores to be addressed belong can be understood as the types of services or sold contents in the stores, in addition to the brands of the contents sold or served in the stores. For example: assuming that the to-be-addressed store is a Chinese restaurant and the store does not have a particular brand, the brand to which the to-be-addressed store belongs may also be the type of store (i.e., chinese restaurant); also for example: assuming that the store to be addressed is a restaurant, in which the dishes provided to the user are mainly "braised chicken rice" and the store also has no specific brand, the brand to which the store to be addressed belongs may be the type of dishes of this store to be addressed (i.e., braised chicken rice).
The brand group image can be understood as a brand portrait of a brand, i.e. a portrait which can embody brand service features, service contents and service audiences. The brand group image is composed of different labels. Specifically, in the case where a brand to which a target store belongs is directly available, the above step S201 is implemented by the following steps S201-1 to S201-3:
step S201-1, obtaining consumer feature labels of other selected stores of the brands to which the to-be-addressed stores belong.
The consumer feature tag refers to a multi-dimensional feature tag. The feature tags may describe information in multiple dimensions of consumer behavior, preferences, geographic location, and the like.
The other selected store refers to a store that has selected a business address and started to business. In practical application, the historical consumption data generated by the consumer on-line or off-line is stored in the addressed stores, so that the feature labels with multiple dimensions can be directly obtained. For example: the geographic position feature tag of the consumer can be obtained through address information filled in the process that the user purchases the selected store commodity on the e-commerce platform; the consumer's preference profile tag, etc., may be obtained from historical consumption data generated by the consumer eating in the addressed store.
It may be understood that the consumer feature tag of the other located stores of the brand of the to-be-addressed store may be a tag stored in advance by the address selection server 102 in the above embodiment of the scenario, may be a tag sent by the server of the other stores to the address selection server 102 based on the address selection request of the client 101, or may be a consumer feature tag obtained by the address selection server after receiving the historical consumption data of the consumer and analyzing the historical consumption data. The present application is not limited in this regard.
Step S201-2, determining the similarity between the consumer feature label and a preset brand feature label.
In the first embodiment of the present application, the preset brand feature labels refer to the total number of brand feature labels stored in the server 102, and it can be understood that before the total number of brand feature labels are not matched with the to-be-addressed stores, these labels cannot reflect the brand features of brands to which the to-be-addressed stores belong.
In the embodiment of the application, the brand feature label corresponding to the brand of the store to be addressed is determined by adopting a mode of calculating the similarity between the consumer feature label and the preset brand feature label.
For example, the preset brand feature tag includes: four brand feature labels representing the characteristics of the vegetable system, namely, roux, sichuan pickle, perilla and cantonese. And only the preference feature tag representing the consumer preference of the roulette among the preference feature tags of most consumers obtained according to step S201-1 is considered to be the cuisine feature tag which represents the roulette among the preset brand feature tags.
For another example, the preset brand feature tag includes: while the brand feature tags representing service contents such as clothing shoe bags, diets and entertainment are only preference feature tags representing diets among the majority of consumer consumption content tags obtained according to step S201-1, the feature tag representing service contents such as diets among the preset brand feature tags is considered to be a consumption content feature tag matched with the brand.
After traversing all the preset brand feature labels, selecting all brand feature labels with similarity greater than the preset similarity threshold to form the brand group image together, namely executing the following step S201-3.
Step S201-3, brand feature labels with similarity larger than a preset similarity threshold value are used as pre-selected feature labels, and brand group images formed by the pre-selected feature labels are obtained.
In addition, in the case that the brand of the store to be addressed cannot be directly obtained, the step S201-1 is implemented by the following step S201-4:
step S201-4, obtaining the service type of the to-be-addressed store, and determining the consumer feature labels of other addressed stores which are the same as the service type.
That is, if the brand to which the to-be-addressed store belongs cannot be directly obtained, or in other words, if the to-be-addressed store does not have a brand, the consumer feature tag may be obtained based on the service type of the to-be-addressed store.
For example: assuming that the to-be-addressed store is a breakfast restaurant, i.e., the service type of the to-be-addressed store is: breakfast is provided. The consumer characteristic tag may be determined by selecting historical consumer consumption data for other selected stores that provide breakfast as a service type.
Step S201 of the present application is directed to building brand group images of brands based on brand consumers. In order to bring the address selected for the store to be addressed as close as possible to the audience of the brand, it is also necessary to further mine the potential users of the store to be addressed.
Step S202, recall the basic crowd data for selecting the store to be addressed according to the brand group images and the characteristic labels to which the users belong.
In step S202 of the present application, the user refers to all users for whom the server 102 is able to obtain historical consumption information, including consumers with consumption records and consumers without consumption records in other addressed stores of the brand.
As in step S201-1 of the present application, the feature labels to which the user belongs refer to multidimensional feature labels, and these labels should be capable of describing user feature information. For example: the feature tags may describe information in multiple dimensions of user behavior, preferences, geographic location, and the like. In an optional embodiment of the present application, the feature tag to which the user belongs should at least describe geographical location information of the user, so as to generalize to address information selected by the to-be-addressed store according to the geographical location information of the user.
Specifically, step S202 is implemented by the following steps S202-1 to S202-3.
Step S202-1, obtaining the feature tag of the user.
Step S202-2, sequentially calculating the similarity between the feature labels to which the users belong and the brand group images.
Before calculating the similarity, a user feature vector is formed according to the feature attribute of the feature tag to which the user belongs; and according to the brand feature labels forming the brand group images, forming brand feature vectors.
And obtaining the similarity between the feature labels of the users and the brand group images by calculating the cosine similarity between the user feature vectors and the brand features.
Step S202-3, obtaining a preset number of users as the basic crowd data according to the similarity.
After the similarity is determined, sorting the users according to the similarity, obtaining a preset number of users with the front sorting as basic crowd, and selecting the preset number of users as basic crowd data.
And step S203, clustering the basic crowd data to obtain a basic crowd data clustering result.
In an optional embodiment of the present application, the clustering processing on the basic crowd data includes the following two ways:
The first is a way to center cluster the population.
The method comprises the steps of firstly obtaining a basic crowd distribution area map of a basic crowd based on basic crowd data, wherein the basic crowd distribution area map comprises the positions of all users in the basic crowd in the map.
And then, dividing the basic crowd map by adopting grids with preset sizes, and dividing the basic crowd distribution map into a plurality of grids.
Specifically, the above-mentioned dividing of the basic crowd map by using the grid with the preset size may be implemented by a preset dividing algorithm, for example: geohash5 algorithm. Geohash is an address coding method that can encode two-dimensional spatial longitude and latitude data into a string. In the general application process, the method can understand the earth as a two-dimensional plane and recursively decompose the two-dimensional plane into smaller sub-blocks, wherein each sub-block has the same code in a certain longitude and latitude range, and the method can solve the problem of searching the longitude and latitude of the data.
In particular, in the first embodiment of the present application, the Geohash5 may be used to segment the base crowd distribution map into a grid of 4.9×4.9. And determining the user density in each grid according to the geographical position data of the users in the basic crowd.
The method for carrying out the central clustering on the crowd has high calculation efficiency, and can obtain any geographic position in each grid. In an optional embodiment of the present application, if the area coverage of the crowd-distributed area map is larger (for example, the crowd-distributed area map covers nationally or globally), the central clustering mode is preferentially adopted to obtain the basic crowd data clustering result.
The second is a clustering mode based on crowd density.
That is, according to the preset cluster radius, the users distributed at different positions are subjected to cluster analysis in sequence, and the number of other users in the cluster radius of each user is determined.
In a specific application process, the crowd density-based clustering algorithm may be a dbscan algorithm. dbscan (Density-Based Spatial Clustering of Applications with Noise) is a relatively representative Density-based clustering algorithm. The algorithm defines clusters as the largest set of densely connected points, is able to divide areas with a sufficiently high density into clusters, and can find clusters of arbitrary shape in a spatial database.
In order to facilitate description of the crowd density-based clustering algorithm provided in the first embodiment of the present application, the number of users in the base crowd will be considered as n, and the preset cluster radius is e.
Firstly, extracting position data of a user which is not subjected to clustering processing from the basic crowd data as a position center point, and finding out other users in the clustering radius of the position center point.
If the number of other users of the position center point is larger than a preset number threshold, the corresponding users of the position center point and other users in the clustering radius form a same-category cluster, and meanwhile the density of the number of other users in the clustering radius of the position center point is determined.
If the number of other users of the location center point is smaller than the preset number threshold, the location center point is not suitable for being used as the address selected by the shop to be addressed.
After traversing the position data of all the users which are not subjected to clustering processing, determining the number of other users in the clustering radius corresponding to each user, and taking the user address information with the largest number of other users in the clustering radius as the address information selected by the store with the address.
The preset clustering radius in the crowd density-based clustering mode is an adjustable parameter, and the final clustering result is determined by crowd distribution conditions. In an alternative embodiment of the present application, the scheme is adapted to select a store address in a city.
And step S204, determining the address information selected for the to-be-addressed store according to the basic crowd data clustering result.
In this embodiment of the present application, the step S204 is mainly performed according to the clustering results obtained in the two different clustering manners in the step S203, and further, according to the clustering results, the address information selected for the store to be addressed is determined.
For the first method for central clustering of people, the clustering result is specifically the user density in each grid, and then the grid central position information of the grid with the maximum user density can be selected as the address information selected for the store to be addressed.
And for the second mode of carrying out density clustering on the crowd, if the clustering result is the number of other users in the clustering radius of each user, selecting the address information corresponding to the first-ranked users with the density of the number of other users in the clustering radius as the address information selected for the store to be addressed.
In summary, according to the store location method provided in the first embodiment of the present application, based on the brand group image of the brand and the feature tag of the user of the store to be located, the basic crowd data of the store to be located is recalled, the basic crowd facing the store to be located is ensured, and then the address information selected for the store to be located is determined through the clustering result of the basic crowd data.
The first embodiment of the application provides a store address selecting method, and correspondingly, the second embodiment of the application simultaneously provides a store address selecting device. Since the apparatus embodiments are substantially similar to the method embodiments described above, the description is relatively simple, and reference will be made to the description of the method embodiments described above in part. The device embodiments described below are merely illustrative,
Fig. 3 is a schematic structural diagram of a store location device according to a second embodiment of the present application.
The device comprises:
a group image obtaining unit 301, configured to obtain a brand group image of a brand to which a store to be addressed belongs;
a crowd recall unit 302, configured to recall, according to the brand group image and a feature tag to which the user belongs, basic crowd data for selecting the store to be addressed;
the crowd clustering unit 303 is configured to perform clustering processing on the basic crowd data to obtain a basic crowd data clustering result;
and the address determining unit 304 is configured to determine address information selected for the to-be-addressed store according to the base crowd data clustering result.
Optionally, the obtaining the brand group image of the brand to which the to-be-addressed store belongs includes:
obtaining consumer feature labels of other selected stores of the brands to which the to-be-addressed stores belong;
Determining the similarity between the consumer feature tag and a preset brand feature tag;
and taking the brand feature labels with the similarity larger than a preset similarity threshold value as preselected feature labels, and obtaining brand group images composed of the preselected feature labels.
Optionally, the obtaining the consumer feature tag of other selected stores of the brand to which the to-be-addressed store belongs includes:
obtaining historical consumption data of consumers of other selected stores sent by the address server; obtaining the consumer feature tag according to the consumer historical consumption data;
or,
obtaining historical consumer consumption data of the selected store sent by the server of the other selected stores; and obtaining the characteristic label of the consumer according to the historical consumer consumption data.
Optionally, the recalling the basic crowd data for selecting the to-be-addressed store according to the brand group image and the feature tag to which the user belongs includes:
obtaining a feature tag to which the user belongs;
sequentially calculating the similarity between the feature labels to which the users belong and the brand group images;
and obtaining a preset number of users as the basic crowd data according to the similarity.
Optionally, the sequentially calculating the similarity between the feature tag to which the user belongs and the brand group image includes:
obtaining a user feature vector according to the user feature tag; according to the brand feature labels, brand feature vectors are obtained;
and calculating cosine similarity between the user feature vector and the brand feature, and obtaining similarity between the feature label of the user and the brand group image.
Optionally, the clustering processing is performed on the basic crowd data to obtain a basic crowd data clustering result, including:
obtaining a basic crowd distribution area map and position information of users in the basic crowd data;
and carrying out grid division on the basic crowd distribution area map by adopting grids with preset sizes, determining the density of the users in each grid by combining the position information of the users in the basic crowd data, and taking the density of the users in each grid as the clustering result of the basic crowd data.
Optionally, the determining, according to the base crowd data clustering result, address information selected for the to-be-addressed store includes:
and confirming the density center of the grid with the density of the user arranged at the top as the address information selected for the to-be-addressed store.
Optionally, the clustering processing is performed on the basic crowd data to obtain a basic crowd data clustering result, including:
and carrying out cluster analysis on the users distributed at different positions in sequence according to the preset cluster radius, and determining the number of other users in the cluster radius of each user.
Optionally, the determining, according to the base crowd data clustering result, address information selected for the to-be-addressed store includes:
and determining the address information of the user, the number of which is arranged first in the cluster radius of each user, as the address information selected for the store to be addressed.
Optionally, the obtaining the consumer feature tag of other selected stores of the brand to which the to-be-addressed store belongs includes:
obtaining the service type of the store to be addressed;
consumer feature tags are obtained that are the same as the service type and that belong to other addressed stores of the brand.
The third embodiment of the present application provides another store location method, corresponding to the first and second embodiments described above. Since this method embodiment is substantially similar to the first and second embodiments described above, the description is relatively simple, and reference will be made to the descriptions of the first and second embodiments described above for relevant points. The following description of the third embodiment of the present application is merely illustrative.
The store location method provided by the third embodiment of the application is applied to a client for providing address information for stores to be located. Referring to fig. 4, a flowchart of a method for shop addressing according to a third embodiment of the present application is shown. The method comprises step S401 and step S402.
Step S401, address information which is sent by a server and is selected for a store to be addressed is obtained;
step S402, displaying the address information selected for the store to be addressed;
the address information selected for the store to be addressed is determined based on the clustering result of the basic crowd data after the basic crowd data is clustered; the basic crowd data are obtained according to brand group images of brands to which the stores to be addressed belong and the feature tags recalled by users.
Corresponding to the third embodiment, a fourth embodiment of the present application provides a store location device. Since this embodiment of the device is substantially similar to the third embodiment described above, the description is relatively simple, and reference will be made to the description of the third embodiment described above for relevant points. The following description of the fourth embodiment of the present application is merely illustrative.
Fig. 5 is a schematic structural diagram of a store location device according to a fourth embodiment of the present disclosure.
The device comprises:
an obtaining unit 501 for obtaining address information selected for a store to be addressed;
the display unit 502 is configured to display the address information selected for the store to be addressed;
the address information selected for the store to be addressed is determined based on the clustering result of the basic crowd data after the basic crowd data is clustered; the basic crowd data are recalled and obtained according to brand group images of brands to which the stores to be addressed belong and the feature labels of the users.
The fifth embodiment of the present application further provides an electronic device, where the electronic device may set the user selection device in a program form to execute the method provided by the embodiment of the present invention.
Optionally, an optional hardware structure of the terminal device may be shown in fig. 6, which is a schematic structural diagram of an electronic device provided in the fifth embodiment of the present application, including: at least one processor 601, at least one communication interface 602, at least one memory 603 and at least one communication bus 604;
alternatively, the communication interface 602 may be an interface of a communication module, such as an interface of a GSM module;
the processor 601 may be a central processing unit CPU or a specific integrated circuit ASIC (Application Specific Integrated Circuit) or one or more integrated circuits configured to implement embodiments of the present invention.
The memory 603 may comprise high-speed RAM memory or may further comprise non-volatile memory (non-volatile memory), such as at least one disk memory.
The memory 603 stores a program, and the processor 601 calls the program stored in the memory 603 to execute the method provided by the embodiment of the present invention.
The sixth embodiment of the present application also provides a computer storage medium storing a computer program which when executed implements the method provided in the above-described method embodiments.
It should be noted that, for the detailed description of the storage medium provided in the sixth embodiment of the present application, reference may be made to the related description of the foregoing method embodiment provided in the present application, which is not repeated herein.
While the preferred embodiment has been described, it is not intended to limit the invention thereto, and any person skilled in the art may make variations and modifications without departing from the spirit and scope of the present invention, so that the scope of the present invention shall be defined by the claims of the present application.
In one typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include volatile memory in a computer-readable medium, random Access Memory (RAM) and/or nonvolatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of computer-readable media.
1. Computer readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of storage media for a computer include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium, which can be used to store information that can be accessed by a computing device. Computer readable media, as defined herein, does not include non-transitory computer readable media (transmission media), such as modulated data signals and carrier waves.
2. Those skilled in the art will appreciate that embodiments of the present application may be provided as a system or an electronic device. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
Claims (14)
1. A store location method, comprising:
obtaining a brand group image of a brand to which a store to be addressed belongs, comprising: obtaining consumer feature labels of other selected stores of the brands to which the to-be-addressed stores belong; determining the similarity between the consumer feature tag and a preset brand feature tag; taking brand feature labels with similarity larger than a preset similarity threshold value as preselected feature labels, and obtaining brand group images composed of the preselected feature labels; the preset brand feature tag comprises: brand feature labels representing cuisine features, and/or brand feature labels representing service content;
and recalling the basic crowd data for selecting the store to be addressed according to the brand group images and the characteristic labels to which the users belong, wherein the basic crowd data comprises: obtaining a characteristic tag to which the user belongs, wherein the user refers to all users of which the server can obtain historical consumption information, and the users comprise consumers with consumption records and consumers without consumption records in other selected stores of the brand; sequentially calculating the similarity between the feature labels to which the users belong and the brand group images; sorting the users according to the similarity, and obtaining a preset number of users with front sorting as the basic crowd data;
Clustering the basic crowd data to obtain a basic crowd data clustering result;
and determining the address information selected for the store to be addressed according to the basic crowd data clustering result.
2. The method of claim 1, wherein the obtaining consumer feature tags for other addressed stores of the brand to which the to-be-addressed store belongs comprises:
obtaining historical consumption data of consumers of other selected stores sent by the address server; obtaining the consumer feature tag according to the consumer historical consumption data;
or,
obtaining historical consumer consumption data of the selected store sent by the server of the other selected stores; and obtaining the characteristic label of the consumer according to the historical consumer consumption data.
3. The method of claim 1, wherein the obtaining a brand group image of a brand to which the to-be-addressed store belongs comprises:
obtaining brand information of the store to be addressed, which is sent by an address selection client;
and obtaining brand group images of brands of the to-be-addressed stores according to the brand information of the to-be-addressed stores.
4. The method of claim 1, wherein the sequentially calculating similarities between the feature labels to which the users belong and the brand group images comprises:
Obtaining a user feature vector according to the user feature tag;
according to the brand feature labels, brand feature vectors are obtained;
and calculating cosine similarity between the user feature vector and the brand feature, and obtaining similarity between the feature label of the user and the brand group image.
5. The method of claim 1, wherein the clustering the base crowd data to obtain a base crowd data clustering result comprises:
obtaining a basic crowd distribution area map and position information of users in the basic crowd data;
and carrying out grid division on the basic crowd distribution area map by adopting grids with preset sizes, determining the density of the users in each grid by combining the position information of the users in the basic crowd data, and taking the density of the users in each grid as the clustering result of the basic crowd data.
6. The method of claim 5, wherein determining address information selected for the to-be-addressed store based on the base crowd data clustering results comprises:
and confirming the position information corresponding to the density center of the grid with the density arranged at the head of the user as the address information selected for the to-be-addressed store.
7. The method of claim 1, wherein the clustering the base crowd data to obtain a base crowd data clustering result comprises:
and carrying out cluster analysis on the users distributed at different positions in sequence according to the preset cluster radius, and determining the number of other users in the cluster radius of each user.
8. The method of claim 7, wherein determining address information selected for the to-be-addressed store based on the base crowd data clustering results comprises:
and determining the address information of the user with the first number of other users in the cluster radius of each user as the address information selected for the store to be addressed.
9. The method of claim 1, wherein the obtaining consumer feature tags for other addressed stores of the brand to which the to-be-addressed store belongs comprises:
obtaining the service type of the store to be addressed;
consumer feature tags are obtained that are the same as the service type and that belong to other addressed stores of the brand.
10. A store location apparatus, comprising:
a group image obtaining unit for obtaining a brand group image of a brand to which a store to be addressed belongs, comprising: obtaining consumer feature labels of other selected stores of the brands to which the to-be-addressed stores belong; determining the similarity between the consumer feature tag and a preset brand feature tag; taking brand feature labels with similarity larger than a preset similarity threshold value as preselected feature labels, and obtaining brand group images composed of the preselected feature labels; the preset brand feature tag comprises: brand feature labels representing cuisine features, and/or brand feature labels representing service content;
The crowd recall unit is used for recalling basic crowd data for selecting the store to be addressed according to the brand group images and the characteristic labels to which the users belong, and comprises the following steps: obtaining a characteristic tag to which the user belongs, wherein the user refers to all users of which the server can obtain historical consumption information, and the users comprise consumers with consumption records and consumers without consumption records in other selected stores of the brand; sequentially calculating the similarity between the feature labels to which the users belong and the brand group images; sorting the users according to the similarity, and obtaining a preset number of users with front sorting as the basic crowd data;
the crowd clustering unit is used for carrying out clustering processing on the basic crowd data to obtain a basic crowd data clustering result;
and the address determining unit is used for determining the address information selected for the store to be addressed according to the basic crowd data clustering result.
11. A store addressing method, wherein the method is applied to a client providing address information for a store to be addressed, and comprises:
obtaining address information which is sent by a server and is selected for a store to be addressed;
Displaying the address information selected for the store to be addressed;
the address information selected for the store to be addressed is determined based on the clustering result of the basic crowd data after the basic crowd data is clustered; the basic crowd data are obtained according to brand group images of brands to which the stores to be addressed belong and feature tags to which the users belong; the basic crowd data is obtained in the following way: obtaining a characteristic tag to which the user belongs, wherein the user refers to all users of which the server can obtain historical consumption information, and the users comprise consumers with consumption records and consumers without consumption records in other selected stores of the brand; sequentially calculating the similarity between the feature labels to which the users belong and the brand group images; sorting the users according to the similarity, and obtaining a preset number of users with front sorting as the basic crowd data; the brand group image is obtained as follows: obtaining consumer feature labels of other selected stores of the brands to which the to-be-addressed stores belong; determining the similarity between the consumer feature tag and a preset brand feature tag; taking brand feature labels with similarity larger than a preset similarity threshold value as preselected feature labels, and obtaining brand group images composed of the preselected feature labels; the preset brand feature tag comprises: brand feature labels representing cuisine features, and/or brand feature labels representing service content.
12. A store location apparatus, comprising:
an obtaining unit for obtaining address information selected for a store to be addressed;
the display unit is used for displaying the address information selected for the store to be addressed;
the address information selected for the store to be addressed is determined based on the clustering result of the basic crowd data after the basic crowd data is clustered; the basic crowd data are obtained according to brand group images of brands to which the stores to be addressed belong and feature tags to which the users belong; the basic crowd data is obtained in the following way: obtaining a characteristic tag to which the user belongs, wherein the user refers to all users of which the server can obtain historical consumption information, and the users comprise consumers with consumption records and consumers without consumption records in other selected stores of the brand; sequentially calculating the similarity between the feature labels to which the users belong and the brand group images; sorting the users according to the similarity, and obtaining a preset number of users with front sorting as the basic crowd data; the brand group image is obtained as follows: obtaining consumer feature labels of other selected stores of the brands to which the to-be-addressed stores belong; determining the similarity between the consumer feature tag and a preset brand feature tag; taking brand feature labels with similarity larger than a preset similarity threshold value as preselected feature labels, and obtaining brand group images composed of the preselected feature labels; the preset brand feature tag comprises: brand feature labels representing cuisine features, and/or brand feature labels representing service content.
13. An electronic device, comprising:
a processor;
a memory for storing a program of methods, which when read and executed by the processor performs the method of any one of claims 1-9, 11.
14. A computer storage medium, characterized in that it stores a computer program, which when executed implements the method of any one of claims 1-9, 11.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111100921.1A CN113706222B (en) | 2021-09-18 | 2021-09-18 | Store site selection method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111100921.1A CN113706222B (en) | 2021-09-18 | 2021-09-18 | Store site selection method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113706222A CN113706222A (en) | 2021-11-26 |
| CN113706222B true CN113706222B (en) | 2023-12-22 |
Family
ID=78661274
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111100921.1A Active CN113706222B (en) | 2021-09-18 | 2021-09-18 | Store site selection method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113706222B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TWI831113B (en) * | 2022-01-13 | 2024-02-01 | 東方線上股份有限公司 | Method and system for selecting selling location |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109377328A (en) * | 2018-12-19 | 2019-02-22 | 口口相传(北京)网络技术有限公司 | The recommended method and device in businessman shops geographical location |
| CN111626777A (en) * | 2020-05-25 | 2020-09-04 | 泰康保险集团股份有限公司 | Site selection method, site selection decision system, storage medium and electronic equipment |
| CN112215658A (en) * | 2020-10-15 | 2021-01-12 | 平安国际智慧城市科技股份有限公司 | Big data-based addressing method and device, computer equipment and storage medium |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120221366A1 (en) * | 2011-02-25 | 2012-08-30 | Bowman Charles V | Site Selection Data Analysis and System |
-
2021
- 2021-09-18 CN CN202111100921.1A patent/CN113706222B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109377328A (en) * | 2018-12-19 | 2019-02-22 | 口口相传(北京)网络技术有限公司 | The recommended method and device in businessman shops geographical location |
| CN111626777A (en) * | 2020-05-25 | 2020-09-04 | 泰康保险集团股份有限公司 | Site selection method, site selection decision system, storage medium and electronic equipment |
| CN112215658A (en) * | 2020-10-15 | 2021-01-12 | 平安国际智慧城市科技股份有限公司 | Big data-based addressing method and device, computer equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113706222A (en) | 2021-11-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11238065B1 (en) | Systems and methods for generating and implementing knowledge graphs for knowledge representation and analysis | |
| CN104731917B (en) | A kind of recommendation method and device | |
| CN107944481B (en) | Method and apparatus for generating information | |
| US11204896B2 (en) | Scalable space-time density data fusion | |
| JP7210086B2 (en) | AREA DIVISION METHOD AND DEVICE, ELECTRONIC DEVICE AND PROGRAM | |
| US11100073B2 (en) | Method and system for data assignment in a distributed system | |
| CN108009205B (en) | Search result caching method based on position, search method, client and system | |
| US20150371430A1 (en) | Identifying Imagery Views Using Geolocated Text | |
| CN111274341A (en) | Site selection method and device for network points | |
| CN104320848B (en) | The system and method for indoor positioning is realized based on cloud computing | |
| CN113706222B (en) | Store site selection method and device | |
| CN103870526A (en) | Commodity information inquiry method, terminal and server | |
| CN109145225B (en) | Data processing method and device | |
| CN102880716B (en) | The active being identified the inter-related task of entity is paid | |
| CN108076439B (en) | Method and device for pushing messages based on wireless access point | |
| CN111125557A (en) | Resource screening method and device, computer equipment and storage medium | |
| CN110969466A (en) | Method and device for determining advertisement delivery area | |
| CN112100511B (en) | Preference degree data obtaining method and device and electronic equipment | |
| Deng et al. | Gridwave: A grid-based clustering algorithm for market transaction data based on spatial-temporal density-waves and synchronization | |
| CN112395486B (en) | Broadband service recommendation method, system, server and storage medium | |
| CN113362090A (en) | User behavior data processing method and device | |
| CN112507242B (en) | Service intention identification method and device and electronic equipment | |
| CN115525841A (en) | Method for acquiring point of interest information, electronic device and storage medium | |
| CN111915679B (en) | Method, device and equipment for determining target point based on floor | |
| Priya et al. | Distributed processing of location based spatial query through vantage point transformation |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |