Store site selection processing method, apparatus, and related product

Abstract

Embodiments of the present application provide a store site selection processing method and device and related products, the method comprising: for each geographical grid for store site selection, obtaining site selection reference data of the geographical grid; the site selection reference data comprises: the number of self-owned stores located in the geographical grid, the number of related stores located in the geographical grid, the business volume of a specific self-owned business handled in the geographical grid, the business volume of a non-specific self-owned business handled in the geographical grid, the business penetration rate of the non-specific self-owned business handled in the geographical grid, and the passenger flow data in the geographical grid; determining the site selection weight of the geographical grid according to the site selection reference data, and screening target grids in each geographical grid according to the site selection weight of each geographical grid; clustering each target grid according to the geographical position of each target grid, and determining a recommended store site selection area according to each grid cluster combination obtained by clustering.

Description

Technical Field

[0001] This invention relates to the field of computer technology, and in particular to a method, apparatus and related products for store site selection. Background Technology

[0002] Store location selection refers to choosing a suitable geographical location for a new store when opening it. Related technologies typically involve manual methods, examining factors such as pedestrian traffic and the distribution of existing stores in different locations, and then determining the store location based on these findings. However, relying on manual methods to determine store locations depends on human experience, resulting in poor accuracy. Summary of the Invention

[0003] The purpose of this invention is to provide a store location selection processing method, apparatus, and related products that can improve the accuracy of determining store locations.

[0004] To solve the above-mentioned technical problems, the embodiments of the present invention are implemented as follows: In a first aspect, embodiments of the present invention provide a store location selection processing method, including: For each geographic grid used for store site selection, obtain site selection reference data for the geographic grid; the site selection reference data includes: the number of owned stores located in the geographic grid, the number of related stores located in the geographic grid, the business volume of specific owned businesses handled in the geographic grid, the business volume of non-specific owned businesses handled in the geographic grid, the business penetration rate of the non-specific owned businesses handled in the geographic grid, and the pedestrian traffic data in the geographic grid; Based on the location reference data, the location weight of the geographic grid is determined, and the target grid is obtained by filtering among the geographic grids according to the location weight of each geographic grid. Based on the geographical location of each target grid, the target grids are clustered, and based on the clustering combinations of the grids obtained, a recommended store location area is determined; the store location area is used for visualization display.

[0005] Secondly, embodiments of the present invention provide a store location selection processing device, comprising: The data acquisition unit is used to acquire site selection reference data for each geographic grid used for store site selection; the site selection reference data includes: the number of owned stores located in the geographic grid, the number of related stores located in the geographic grid, the business volume of specific owned businesses handled in the geographic grid, the business volume of non-specific owned businesses handled in the geographic grid, the business penetration rate of the non-specific owned businesses handled in the geographic grid, and the pedestrian traffic data in the geographic grid. The grid filtering unit is used to determine the location weight of the geographic grid based on the location reference data, and to filter the target grid from each geographic grid according to the location weight of each geographic grid. The region determination unit is used to cluster each of the target grids according to their geographical locations, and to determine the recommended store location area based on the clustering combination of the grids obtained from the clustering; the store location area is used for visualization display.

[0006] Thirdly, embodiments of the present invention provide an electronic device, including a processor, a communication interface, a memory, and a communication bus; wherein the processor, the communication interface, and the memory communicate with each other via the bus; the memory is used to store computer programs; and the processor is used to execute the programs stored in the memory to implement the steps of the method described in the first aspect.

[0007] Fourthly, embodiments of the present invention provide a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the method described in the first aspect.

[0008] Fifthly, embodiments of the present invention provide a computer program product, including a computer program that, when executed by a processor, implements the steps of the method described in the first aspect.

[0009] In this embodiment, the location weight of each geographic grid is determined based on the location reference data of each grid. Target grids are then selected from among the grids based on their location weights. These target grids are then clustered according to their geographical location. Based on the clustering combinations of these grids, recommended store location areas are determined and visualized. This achieves automated determination and recommendation of store location areas. Users can further determine the store location within the recommended areas based on their needs. Compared to related technologies that rely on manual experience to determine store locations, this significantly improves the accuracy of store location determination. Attached Figure Description

[0010] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0011] Figure 1 A schematic flowchart illustrating a store site selection processing method provided in an embodiment of this disclosure; Figure 2 A schematic diagram of the structure of a store location processing device provided in an embodiment of this disclosure; Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0012] To enable those skilled in the art to better understand the technical solutions of this invention, the technical solutions of the embodiments of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this invention, and not all embodiments. Based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of this invention.

[0013] The purpose of this invention is to provide a store location selection method, apparatus, and related products that can improve the accuracy of determining store locations. This method can be applied on the server side and executed by the server.

[0014] Figure 1 This is a flowchart illustrating a store site selection method provided in an embodiment of this disclosure, as shown below. Figure 1 Instructions, the process includes: Step S102: For each geographic grid used for store location selection, obtain location reference data for the geographic grid. The location reference data includes: the number of owned stores located in the geographic grid, the number of related stores located in the geographic grid, the business volume of specific owned businesses handled in the geographic grid, the business volume of non-specific owned businesses handled in the geographic grid, the business penetration rate of non-specific owned businesses handled in the geographic grid, and the pedestrian traffic data in the geographic grid. Step S104: Determine the location weight of the geographic grid based on the location reference data, and select the target grid from each geographic grid according to the location weight of each geographic grid. Step S106: Based on the geographical location of each target grid, cluster each target grid, and determine the recommended store location area based on the clustering combination of each grid; the store location area is used for visualization display.

[0015] In this embodiment, the location weight of each geographic grid is determined based on the location reference data of each grid. Target grids are then selected from among the grids based on their location weights. These target grids are then clustered according to their geographical location. Based on the clustering combinations of these grids, recommended store location areas are determined and visualized. This achieves automated determination and recommendation of store location areas. Users can further determine the store location within the recommended areas based on their needs. Compared to related technologies that rely on manual experience to determine store locations, this significantly improves the accuracy of store location determination.

[0016] In this embodiment, multiple geographic grids for store site selection are predetermined. The area size of each geographic grid can be the same or different. In one example, the predetermined geographical area of ​​the county or city for store site selection can be divided into geographic grids of a certain size, such as 50 meters * 50 meters, thereby obtaining multiple geographic grids for store site selection.

[0017] In step S102 above, location reference data for each geographic grid used for store location selection is obtained. For each geographic grid, the location reference data includes: the number of owned stores located in the geographic grid, the number of related stores located in the geographic grid, the business volume of specific owned businesses handled in the geographic grid, the business volume of non-specific owned businesses handled in the geographic grid, the business penetration rate of non-specific owned businesses handled in the geographic grid, and the pedestrian traffic data in the geographic grid.

[0018] In this context, "owned stores" refer to stores belonging to the same brand as the store being selected. "Related stores" refer to stores belonging to different brands within the same industry as the store being selected. For example, in this embodiment, when selecting stores for telecommunications operator A, the owned stores are those of telecommunications operator A, while the related stores are those of other telecommunications operators, such as telecommunications operators B and C. Similarly, in this embodiment, when selecting stores for restaurant brand 1, the owned stores are those of restaurant brand 1, while the related stores are those of other restaurant brands, such as restaurant brands 2 and 3.

[0019] Owned business refers to the services that the brand to which the selected store belongs can provide. Specific owned business refers to specific services that the brand to which the selected store belongs can provide. Non-specific owned business refers to other businesses besides the specific services that the brand to which the selected store belongs can provide. For example, if the selected store is a store of telecommunications operator A, then owned business can be exemplified by the various services that telecommunications operator A can provide. Specific owned business can be exemplified by services such as mobile phone sales and SIM card sales that telecommunications operator A can provide. Non-specific owned business can be exemplified by other businesses that telecommunications operator A can provide besides mobile phone sales and SIM card sales. Similarly, if a store is selected for restaurant brand 1 in this embodiment, then owned business can be exemplified by the various dishes that restaurant brand 1 can provide. Specific owned business can be exemplified by specific dishes such as dish 1 and dish 2 that restaurant brand 1 can provide. Non-specific owned business can be exemplified by other dishes that restaurant brand 1 can provide besides dish 1 and dish 2.

[0020] The volume of a specific proprietary business refers to the number of times the aforementioned specific proprietary business has been processed within each geographic grid within a certain period of time, such as 24 hours or 1 month. For example, the number of mobile phones sold or the number of communication cards sold by telecommunications operator A within a certain period of time, or the number of food items 1 and 2 sold by catering brand 1 within a certain period of time.

[0021] The volume of non-specific proprietary services refers to the number of times the aforementioned non-specific proprietary services have been processed within each geographic grid within a certain period, such as 24 hours or 1 month. For example, this could be the number of services processed by telecommunications operator A within a certain period, excluding specific services like mobile phone sales and SIM card sales; or the number of meals sold by catering brand 1 within a certain period, excluding specific dishes like dish 1 and dish 2. A higher volume of non-specific proprietary services indicates greater user demand.

[0022] The penetration rate of non-specific proprietary services represents the user share of a non-specific proprietary service within each geographic raster. A higher penetration rate indicates more users have used that service. Conversely, a lower penetration rate indicates fewer users have used that service, making it more suitable for opening a physical store. The calculation method for penetration rates differs for different non-specific proprietary services. In one example, the calculation method can be determined based on the service type of the non-specific proprietary service. This calculation method includes, but is not limited to, dividing the number of transactions for that non-specific proprietary service within the geographic raster by the number of people within that geographic raster.

[0023] People traffic data in a geographic raster can be the number of people appearing in the raster within a specified time period. The specified time period can be 8 hours, 24 hours, etc.

[0024] In one embodiment, location data for each geographic grid can be acquired, as well as user information for each user existing in each geographic grid, and the distribution location data of owned stores and related stores in each geographic grid. The acquired data can also be cleaned, including but not limited to data deduplication, missing value removal, and outlier removal. Based on the cleaned data, the number of owned stores, the number of related stores, and the pedestrian traffic data in each geographic grid are determined. For example, based on the cleaned distribution location data of owned stores and related stores in each geographic grid, the number of owned stores and related stores in each geographic grid are determined; and based on the user information for each user existing in each geographic grid, the pedestrian traffic data in each geographic grid is determined.

[0025] In step S104 above, the location weight of each geographic raster is determined based on the location reference data of each geographic raster, and the target raster is obtained by filtering among the geographic rasteres according to the location weight of each geographic raster.

[0026] In one embodiment, determining the location weight of a geographic raster based on location reference data includes: The store distribution factor of a geographic raster is determined based on the number of owned stores and related stores located in the geographic raster. The business volume impact factor of a geographic raster is determined based on the business volume of a specific proprietary business conducted within the geographic raster. The business penetration impact factor of geographic rasters is determined based on the business volume of non-specific proprietary businesses processed in geographic rasters and the business penetration rate of non-specific proprietary businesses processed in geographic rasters. Determine the pedestrian flow influencing factors of the geographic grid based on pedestrian flow data in the geographic grid; The location weight of a geographic grid is determined based on its store distribution factor, business volume impact factor, business penetration impact factor, and pedestrian traffic impact factor.

[0027] In this embodiment, each geographic raster has four factors: store distribution factor, business volume impact factor, business penetration impact factor, and pedestrian flow impact factor. This embodiment determines these four factors for each geographic raster and, based on these four factors, determines the location selection weight for each geographic raster.

[0028] In one embodiment, determining the store distribution factor of a geographic raster based on the number of owned stores and the number of associated stores located within the geographic raster includes: The intermediate factor for store distribution in a geographic raster is determined based on the number of owned stores and related stores in the geographic raster. The intermediate factors of store distribution in each geographic grid are sorted to obtain the sorted value of each geographic grid. The sorting values ​​of each geographic grid are normalized to obtain the store distribution factor for each geographic grid.

[0029] For each geographic raster, the intermediate factor of store distribution for that raster is determined based on the number of owned stores and related stores located within that raster. In one example, taking any arbitrary raster, the intermediate factor of store distribution for that raster can be determined using the following formula.

[0030]

[0031] in, This indicates the number of owned stores in this geographic grid. This indicates the number of the first relevant stores in this geographic raster. The number of second-related stores in this geographic grid. Here, the first-related store is a store belonging to the same industry as the owned store but under a different brand, and the second-related store is a store belonging to the same industry as the owned store but under a different brand. The first-related store and the second-related store belong to the same industry but different brands. This represents the median factor of store distribution for this geographic grid. The formula is illustrated using the example of related stores belonging to two different brands within the same industry. This formula reflects that the more related stores there are, the larger the value of the median factor of store distribution.

[0032] The above formula determines the intermediate factor of store distribution for each geographic raster. Next, the intermediate factors of store distribution for each geographic raster are sorted, for example, in descending order, to obtain the sorted value for each raster. The sorted value is also the sequence number. The same sequence number may correspond to multiple geographic rasters with the same intermediate factor of store distribution. Sorting values ​​can be 1, 2, 3, 4, etc. Since the sorting is in descending order, the more related stores there are, the larger the intermediate factor of store distribution, and the smaller the overall store distribution factor. Conversely, the fewer related stores there are, the smaller the intermediate factor of store distribution, and the larger the overall store distribution factor.

[0033] Finally, the ranking values ​​of each geographic raster are normalized to obtain the store distribution factor for each raster. For example, normalizing the ranking values ​​of each geographic raster to the range [0,1] gives the normalized ranking value of each raster the store distribution factor for that raster. The store distribution factor can be... express.

[0034] Through this embodiment, the store distribution factor of each geographic grid can be calculated. The larger the value of the store distribution factor, the fewer related stores exist in the geographic grid, and the more suitable the geographic grid is for opening the store to be located, that is, opening its own store.

[0035] In one embodiment, for each geographic raster, a business volume impact factor is determined based on the business volume of a specific proprietary business conducted within that geographic raster. Specifically, this can be achieved by: normalizing the business volume of the specific proprietary business conducted within each geographic raster, and using the normalized value as the business volume impact factor for each geographic raster. The business volume impact factor can be... express.

[0036] In one embodiment, for each geographic raster, a business penetration impact factor is determined based on the volume of non-specific proprietary business conducted within that geographic raster and the business penetration rate of that non-specific proprietary business conducted within that geographic raster. In one example, taking any geographic raster as an example, the business penetration impact factor of that geographic raster can be determined using the following formula.

[0037]

[0038] in, As a factor influencing business penetration, This represents the normalized value of the business penetration rate for each non-specific proprietary business. This represents the normalized value of the business volume of each non-specific proprietary business, where i is a positive integer greater than or equal to 1. The larger the value of the business penetration impact factor of a geographic grid, the lower the business penetration rate of non-specific proprietary businesses within that geographic grid, the smaller the business volume of non-specific proprietary businesses, and the more suitable that geographic grid is for opening the store to be located, i.e., opening a proprietary store.

[0039] This embodiment enables the determination of the business penetration impact factor of a geographic raster based on the business volume and penetration rate of non-specific proprietary businesses processed within the geographic raster. By using the business penetration impact factor, the status of non-specific proprietary businesses within the geographic raster can be accurately measured.

[0040] In one embodiment, for each geographic raster, a pedestrian flow impact factor is determined based on the pedestrian flow data within that raster. Specifically, for each geographic raster, the pedestrian flow data within that raster is normalized, and the normalized value is used as the pedestrian flow impact factor for that raster. The pedestrian flow impact factor can be represented by f.

[0041] In one embodiment, the location weight of a geographic raster is determined based on the raster's store distribution factor, business volume impact factor, business penetration impact factor, and pedestrian traffic impact factor, including: The large language model generates the first weight of the store distribution factor, the second weight of the business volume influence factor, the third weight of the business penetration influence factor, and the fourth weight of the traffic flow influence factor. Adjust the first, second, third, and fourth weights; The location weights of the geographic grid are determined based on the adjusted first weight, adjusted second weight, adjusted third weight, adjusted fourth weight, store distribution factor, business volume impact factor, business penetration impact factor, and pedestrian flow impact factor.

[0042] In this embodiment, a large language model can be used to generate the first weight of the store distribution factor, the second weight of the business volume influence factor, the third weight of the business penetration influence factor, and the fourth weight of the foot traffic influence factor. For example, by inputting store location suggestion words into the large language model, the model can generate the first weight of the store distribution factor, the second weight of the business volume influence factor, the third weight of the business penetration influence factor, and the fourth weight of the foot traffic influence factor based on historical location selection experience. The large language model can learn the correlation pattern between each factor (store distribution factor, business volume influence factor, business penetration influence factor, and foot traffic influence factor) and the location selection effect through machine learning algorithms based on a large amount of historical location selection data and business knowledge, thereby generating the initial weights of each factor. This method can make full use of the hidden information in the data and improve the objectivity and accuracy of weight allocation. An example of a store location suggestion word could be: "Based on historical successful location selection cases, please help me generate the first weight of the store distribution factor, the second weight of the business volume influence factor, the third weight of the business penetration influence factor, and the fourth weight of the foot traffic influence factor."

[0043] Then, the first weight, second weight, third weight, and fourth weight can be adjusted manually to obtain the adjusted first weight, adjusted second weight, adjusted third weight, and adjusted fourth weight.

[0044] Finally, based on the adjusted first weight, adjusted second weight, adjusted third weight, adjusted fourth weight, store distribution factor, business volume impact factor, business penetration impact factor, and pedestrian traffic impact factor, the location weight of each geographic grid is determined. The location weight P of each geographic grid can be calculated using the following formula:

[0045] in, Business penetration impact factor for each geographic raster, f is the pedestrian traffic impact factor for each geographic raster. Store distribution factor for each geographic raster. This represents the traffic impact factor for each geographic raster. 0.6, 0.2, 30, and 1 are the respective weights. For each geographic raster, the location weight can be calculated using the above formula.

[0046] Therefore, this embodiment allows for the accurate determination of the location weight for each geographic grid. A higher location weight indicates that the geographic grid is more suitable for opening its own store.

[0047] In step S104 above, target rasters are selected from each geographic raster based on their location selection weights. In practical applications, the predetermined geographic area of ​​a county or city for store location selection can be divided into individual geographic rasters of a certain size, such as 50 meters by 50 meters, thus obtaining multiple geographic rasters for store location selection. Furthermore, each county or city is treated as a geographic region, and within each region, the top 5% of geographic rasters, ranked from highest to lowest location selection weight, are selected as target rasters. By selecting target rasters, on the one hand, the data scale can be effectively compressed, removing a large number of low-value or insignificant geographic rasters, reducing the amount of data for subsequent analysis and processing, and improving work efficiency; on the other hand, focusing on high-value geographic rasters allows for more precise location of areas with key characteristics or potential value.

[0048] In step S106 above, each target raster is clustered according to its geographical location to obtain multiple raster cluster combinations, and each raster cluster combination includes at least two target rasters.

[0049] In this embodiment, after screening high-value target rasters, clustering is required to clearly and accurately map the geographic regions. The core objective of this clustering is to ensure the continuity of the resulting raster regions, thus more intuitively displaying the distribution of geographic features. To achieve this, an adjacent raster clustering method is used. Specifically, it determines whether two target rasters belong to the same category: if these two target rasters are in contact, whether through edge contact or corner contact, they can be grouped into the same category, assigned a unified group number, and classified into the same raster cluster group. That is, when two rasters have geographically adjacent regions, they are classified into the same raster cluster group. This clustering method focuses on the geographic spatial adjacency of rasters, efficiently integrating spatially continuous rasters to form regions with actual geographic significance. It is understood that each raster cluster group includes at least two target rasters, and may include three, four, or even more target rasters.

[0050] The entire raster clustering process will be performed in a database environment. Databases possess efficient data storage, management, and processing capabilities, enabling rapid traversal, comparison, and classification of large amounts of raster data. Implementing clustering algorithms within the database fully leverages its indexing and query optimization features, improving clustering efficiency and ensuring the completion of clustering tasks for massive amounts of raster data in a short time. Furthermore, clustering within the database facilitates easy association and integration with other geospatial and business data, providing comprehensive data support for subsequent block mapping and integrated analysis.

[0051] In step S106 above, the recommended store location area is determined based on the various grid clustering combinations obtained by clustering, and the store location area is used for visualization display.

[0052] In one embodiment, the recommended store location area is determined based on the various grid clustering combinations obtained from clustering, including: Based on the number of target rasters included in each raster cluster combination, target raster cluster combinations are selected from each raster cluster combination; the number of target rasters included in the target raster cluster combination is greater than a preset value; the preset value is greater than 2; Based on the geographical location of the target grid in the target grid cluster combination, the recommended store location area is determined.

[0053] In this embodiment, a target grid cluster combination is selected from each grid cluster combination, where the number of target grids included is greater than a preset value. The preset value can be a number greater than 2, such as 3, 4, or 5. Then, based on the geographical location of the target grids in the target grid cluster combination, a recommended store location area is determined.

[0054] In one embodiment, determining recommended store location areas based on the geographic location of target rasters in a target raster clustering combination includes: Connect the center points of each target raster in the target raster cluster combination to generate a convex polygon geographic region corresponding to the target raster cluster combination; Expand the boundaries of the convex polygon geographic region to obtain the recommended store location area; the recommended store location area includes at least each target raster in the target raster cluster combination.

[0055] First, the center point positions of each target raster in the target raster cluster combination are identified, and these center point positions are then connected. A preset workflow can be used to determine the connection order of the center point positions. Based on this order, the center point positions are connected to generate the convex polygon geographic region corresponding to the target raster cluster combination. Connecting in this order generates the convex polygon geographic region with the largest area.

[0056] Then, considering that the convex polygon geographic region is formed by connecting the center points of the target graticles, it may not be able to cover all the target graticles in the target graticle cluster combination. Therefore, the boundary of the convex polygon geographic region is expanded outward by a certain distance to obtain a geographic region with smooth boundaries that can cover all the target graticles. This geographic region is the recommended store location area. Therefore, it can be understood that the recommended store location area includes at least each target graticle in the target graticle cluster combination.

[0057] Therefore, the recommended store location area obtained through the embodiments of this application can cover each target grid in the target grid combination, and each target grid combination corresponds to a recommended store location area. Thus, after the store location area is displayed to the user, the user can further determine the store location according to their needs in the recommended store location area. Compared with the method of determining the store location by relying on human experience in related technologies, the accuracy of determining the store location is greatly improved.

[0058] In this embodiment, the recommended store location areas are used for visualization. In one example, a data visualization platform can be used to display the filtered target grids using different colors. The color of each target grid indicates the pedestrian traffic volume of that grid. Additionally, the recommended store location areas are displayed, with the target grids within these areas also using color to indicate pedestrian traffic volume, thus facilitating users in selecting the desired location to open a store. The recommended store location areas and target grids can be displayed in map software.

[0059] Specifically, in the front-end development process, it is necessary to perform a traversal operation on the target rasters transmitted from the back-end. This involves carefully processing the data format of these target rasters to convert them into a format compatible with map software requirements. During this process, pedestrian traffic is selected as a key indicator to measure the color intensity of the target rasters, visually representing the density of pedestrian traffic in different areas. To enhance the flexibility and practicality of the target raster display, the boundary values ​​are set to a dynamically adjustable mode. Users can adjust the boundary length parameters in real time using interactive controls provided on the front-end page. In this way, the display effect of the target rasters will dynamically change with the boundary length, thereby meeting diverse data display needs and helping users gain deeper insights into the patterns and characteristics behind the data from different dimensions.

[0060] Through the above embodiments, the spatial distribution characteristics of recommended areas at the county and city levels can be presented intuitively and accurately by combining target grids with store location areas. This visualization method not only effectively conveys spatial differences in regional pedestrian traffic but also provides decision-makers with more operational spatial references through clearly defined area boundaries, thereby assisting them in making more scientific and rational decisions.

[0061] In one embodiment, a large language model can also be used to determine the most suitable store location for a user within a defined selection area, based on factors such as the user's rent requirements, orientation requirements, and unit type requirements. For example, inputting the prompt "Please help me select a 50-square-meter south-facing storefront in this area" into the large language model can quickly locate the store location that the user is most likely to need.

[0062] In summary, this embodiment achieves at least the following technical effects: 1. More Accurate Weight Allocation. By employing a large-scale model inference combined with manual fine-tuning, weights are allocated to key site selection factors. This method leverages the learning capabilities of the large-scale model based on extensive historical data and business knowledge, while also incorporating professional judgment and experience from human personnel. This results in a more scientific and reasonable weight allocation, more accurately reflecting the relative importance of each factor in site selection decisions. Furthermore, the site selection decision not only considers conventional factors such as foot traffic and the number of competitors, but also delves into specific factors such as the distribution of proprietary channels and business penetration. These factors are crucial for the company's long-term development and market layout. By comprehensively considering these factors, this embodiment provides more comprehensive and in-depth support for site selection decisions. 2. Raster clustering technology ensures the continuity of the site selection area. By using raster adjacency clustering technology, the geographical continuity of the site selection area is ensured. This is crucial for site selection decisions in practical applications because it helps to form areas with actual geographical significance, facilitating subsequent planning and management. 3. More intuitive and effective visualization. Utilizing raster segmentation and visualization technology, key information such as pedestrian flow distribution is displayed intuitively, providing more intuitive and effective support for site selection decisions. Through heat maps (different colors represent different pedestrian flows), decision-makers can clearly see the density of pedestrian flow in different areas, thus making more scientific decisions. Furthermore, dividing the raster into county and city categories based on latitude and longitude information, and processing and managing raster data in batches, can reduce the complexity of data processing and improve data processing speed. At the same time, by retaining high-value raster cells, the data scale is effectively compressed, reducing the amount of data for subsequent analysis and processing, and improving work efficiency.

[0063] Figure 2 This is a schematic diagram of the structure of a store location processing device provided in an embodiment of the present disclosure, as shown below. Figure 2 As shown, the device includes: The data acquisition unit 21 is used to acquire site selection reference data for each geographic grid used for store site selection; the site selection reference data includes: the number of owned stores located in the geographic grid, the number of related stores located in the geographic grid, the business volume of specific owned businesses handled in the geographic grid, the business volume of non-specific owned businesses handled in the geographic grid, the business penetration rate of the non-specific owned businesses handled in the geographic grid, and the pedestrian traffic data in the geographic grid. The grid filtering unit 22 is used to determine the location weight of the geographic grid according to the location reference data, and to filter the target grid in each geographic grid according to the location weight of each geographic grid. The region determination unit 23 is used to cluster each of the target grids according to their geographical locations, and to determine the recommended store location area based on the clustering combination of the grids obtained from the clustering; the store location area is used for visualization display.

[0064] Optionally, the grid filtering unit 22 is specifically used to: determine the store distribution factor of the geographic grid based on the number of owned stores and related stores located in the geographic grid; determine the business volume influence factor of the geographic grid based on the business volume of specific owned businesses handled in the geographic grid; determine the business penetration influence factor of the geographic grid based on the business volume of non-specific owned businesses handled in the geographic grid and the business penetration rate of the non-specific owned businesses handled in the geographic grid; determine the traffic flow influence factor of the geographic grid based on the traffic flow data in the geographic grid; and determine the location weight of the geographic grid based on the store distribution factor, the business volume influence factor, the business penetration influence factor, and the traffic flow influence factor.

[0065] Optionally, the grid filtering unit 22 is further configured to: determine the intermediate factor of store distribution of the geographic grid based on the number of owned stores and the number of related stores located in the geographic grid; sort the intermediate factors of store distribution of each geographic grid to obtain the sort value of each geographic grid; and normalize the sort value of each geographic grid to obtain the store distribution factor of each geographic grid.

[0066] Optionally, the grid filtering unit 22 is further configured to: generate a first weight for the store distribution factor, a second weight for the business volume influence factor, a third weight for the business penetration influence factor, and a fourth weight for the pedestrian flow influence factor using a large language model; adjust the first weight, the second weight, the third weight, and the fourth weight; and determine the location weight of the geographic grid based on the adjusted first weight, the adjusted second weight, the adjusted third weight, the adjusted fourth weight, the store distribution factor, the business volume influence factor, the business penetration influence factor, and the pedestrian flow influence factor.

[0067] Optionally, the region determination unit 23 is specifically used to: filter out target grid clusters from each grid cluster combination based on the number of target grids included in each grid cluster combination; the number of target grids included in the target grid cluster combination is greater than a preset value; the preset value is greater than 2; and determine the recommended store location area based on the geographical location of the target grids in the target grid cluster combination.

[0068] Optionally, the region determination unit 23 is further configured to: connect the center point positions of each of the target grids in the target grid clustering combination to generate a convex polygon geographical region corresponding to the target grid clustering combination; expand the boundary of the convex polygon geographical region to obtain the recommended store location area; the recommended store location area includes at least each of the target grids in the target grid clustering combination.

[0069] The store location processing device provided in this embodiment of the invention can realize the various processes in the embodiments corresponding to the above-mentioned store location processing method. To avoid repetition, it will not be described again here.

[0070] It should be noted that the store location processing device provided in this embodiment of the invention and the store location processing method provided in this embodiment of the invention are based on the same inventive concept. Therefore, the specific implementation of this embodiment can refer to the implementation of the aforementioned store location processing method, and the repeated parts will not be described again.

[0071] Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention, such as... Figure 3 As shown, electronic devices can vary considerably due to differences in configuration or performance. They may include one or more processors 301 and memories 302. Memories 302 may store one or more application programs or data. Memories 302 may be temporary or persistent storage. Application programs stored in memories 302 may include one or more modules (not shown), each module including a series of computer-executable instructions for the electronic device. Furthermore, processors 301 may be configured to communicate with memories 302 and execute the series of computer-executable instructions stored in memories 302 on the electronic device. The electronic device may also include one or more power supplies 303, one or more wired or wireless network interfaces 304, one or more input / output interfaces 305, and one or more keyboards 306.

[0072] Specifically, in this embodiment, the electronic device includes a processor, a communication interface, a memory, and a communication bus; wherein, the processor, the communication interface, and the memory communicate with each other through the bus; the memory is used to store computer programs; and the processor is used to execute the programs stored in the memory to implement the steps of the store site selection processing method.

[0073] This invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of a store location selection method.

[0074] This invention also provides a computer program product. When the computer program is executed by a processor, it implements the various processes of the above-described store location processing method embodiments and achieves the same technical effect. To avoid repetition, it will not be described again here.

[0075] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, apparatus, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can 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, etc.) containing computer-usable program code.

[0076] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0077] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0078] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0079] In a typical configuration, an electronic device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0080] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0081] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media 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 technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0082] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0083] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, apparatus, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can 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, etc.) containing computer-usable program code.

[0084] The above description is merely an embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principle of the present invention should be included within the scope of the claims of the present invention.

Claims

1. A method for processing store site selection, characterized in that, include: For each geographic grid used for store site selection, obtain the site selection reference data for the geographic grid; The site selection reference data includes: the number of owned stores located in the geographic grid, the number of related stores located in the geographic grid, the business volume of specific owned businesses handled in the geographic grid, the business volume of non-specific owned businesses handled in the geographic grid, the business penetration rate of the non-specific owned businesses handled in the geographic grid, and the pedestrian traffic data in the geographic grid. Based on the location reference data, the location weight of the geographic grid is determined, and the target grid is obtained by filtering among the geographic grids according to the location weight of each geographic grid. Based on the geographical location of each target grid, the target grids are clustered, and based on the clustering combinations of the grids obtained, a recommended store location area is determined; the store location area is used for visualization display.

2. The method according to claim 1, characterized in that, Determining the location weight of the geographic raster based on the location reference data includes: The store distribution factor of the geographic raster is determined based on the number of owned stores and related stores located in the geographic raster. The business volume impact factor of the geographic raster is determined based on the business volume of a specific proprietary business processed in the geographic raster. The business penetration impact factor of the geographic raster is determined based on the business volume of non-specific proprietary business processed in the geographic raster and the business penetration rate of the non-specific proprietary business processed in the geographic raster. Based on the pedestrian traffic data in the geographic raster, determine the pedestrian traffic influencing factor of the geographic raster; The location weight of the geographic raster is determined based on the store distribution factor, the business volume influence factor, the business penetration influence factor, and the pedestrian flow influence factor of the geographic raster.

3. The method according to claim 2, characterized in that, The step of determining the store distribution factor of a geographic raster based on the number of owned stores and related stores located in the geographic raster includes: The intermediate factor of store distribution for a geographic raster is determined based on the number of owned stores and related stores located in the geographic raster. The intermediate factors of store distribution for each of the geographic graticles are sorted to obtain the sorting value for each of the geographic graticles; The sorting values ​​of each of the geographic rasters are normalized to obtain the store distribution factor of each of the geographic rasters.

4. The method according to claim 2, characterized in that, The step of determining the site selection weight of a geographic raster based on its store distribution factor, business volume impact factor, business penetration impact factor, and pedestrian flow impact factor includes: Using a large language model, the first weight of the store distribution factor, the second weight of the business volume influence factor, the third weight of the business penetration influence factor, and the fourth weight of the foot traffic influence factor are generated. The first weight, the second weight, the third weight, and the fourth weight are adjusted. The location weight of the geographic grid is determined based on the adjusted first weight, the adjusted second weight, the adjusted third weight, the adjusted fourth weight, the store distribution factor, the business volume influence factor, the business penetration influence factor, and the pedestrian flow influence factor.

5. The method according to claim 1, characterized in that, The step of determining the recommended store location area based on the various grid clustering combinations obtained by clustering includes: Based on the number of target rasters included in each of the raster clustering combinations, a target raster clustering combination is obtained by filtering from each of the raster clustering combinations; the number of target rasters included in each target raster clustering combination is greater than a preset value; the preset value is greater than 2; The recommended store location area is determined based on the geographical location of the target grid in the target grid cluster combination.

6. The method according to claim 5, characterized in that, The step of determining the recommended store location area based on the geographical location of the target grid in the target grid cluster combination includes: The center points of each target raster in the target raster cluster combination are connected to generate a convex polygon geographic region corresponding to the target raster cluster combination; The recommended store location area is obtained by expanding the boundary of the convex polygon geographical region; the recommended store location area includes at least each of the target grids in the target grid cluster combination.

7. A store location selection processing device, characterized in that, include: The data acquisition unit is used to acquire location reference data for each geographic grid used for store location selection. The site selection reference data includes: the number of owned stores located in the geographic grid, the number of related stores located in the geographic grid, the business volume of specific owned businesses handled in the geographic grid, the business volume of non-specific owned businesses handled in the geographic grid, the business penetration rate of the non-specific owned businesses handled in the geographic grid, and the pedestrian traffic data in the geographic grid. The grid filtering unit is used to determine the location weight of the geographic grid based on the location reference data, and to filter the target grid from each geographic grid according to the location weight of each geographic grid. The region determination unit is used to cluster each of the target grids according to their geographical locations, and to determine the recommended store location area based on the clustering combination of the grids obtained from the clustering; the store location area is used for visualization display.

8. An electronic device, characterized in that, The system includes a processor, a communication interface, a memory, and a communication bus; wherein the processor, the communication interface, and the memory communicate with each other via the bus; the memory is used to store computer programs; and the processor is used to execute the programs stored in the memory to implement the steps of the method as described in any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the steps of the method as described in any one of claims 1-6.

10. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the steps of the method as described in any one of claims 1-6.

Images