A store location recommendation method integrating multi-dimensional features

Abstract

The present invention relates to the field of store location recommendation, and discloses a store location recommendation method integrating multi-dimensional features, which includes the following steps: S10. Collect multi-dimensional data of the area where the candidate store location is located, and the multi-dimensional data includes: pedestrian flow, number of competing products, price, industry market size growth rate, regional planning trend, and consumer population change trend; S20. Preprocess the multi-dimensional data, including data cleaning and normalization processing; S30. Input the preprocessed multi-dimensional data into the store location recommendation model to obtain the recommendation value of each candidate store location; S40. After arranging the recommendation values of each candidate store location in descending order, obtain the store location recommendation sequence. The multi-dimensional data of the present invention is used for store location recommendation and fully considers various key factors affecting store operation, more comprehensively depicts the business environment of the candidate area, and thus can provide more accurate store location recommendations for stores, effectively improving the accuracy of location selection.

Description

Technical Field

[0001] The present invention relates to the field of store location recommendation, and particularly to a store location recommendation method integrating multi-dimensional features. Background Art

[0002] Currently, in the process of store location selection, traditional methods often only focus on a few limited factors such as pedestrian flow, the number of competitors, and price. However, this one-sided location selection method ignores important trend data, such as industry development trends, regional planning trends, and changes in the consumer population trend, etc.

[0003] Due to the lack of consideration of these trends, many stores face the risk of losses or even closures soon after opening. For example, with the development of the city, some originally popular commercial areas may gradually lose their advantages due to new traffic planning or the transfer of commercial centers, but stores located based on traditional factors such as historical pedestrian flow fail to adapt to this change in a timely manner. Another example is that the proportion and income level of the main consumer population are constantly changing. If these factors are not considered during location selection, the products or services provided by the store may not meet the local consumer demand, resulting in poor management. Therefore, it is of great significance to develop a store location recommendation method that can integrate multi-dimensional features. Summary of the Invention

[0004] The purpose of the present invention is to provide a store location recommendation method integrating multi-dimensional features to solve the above technical problems.

[0005] The purpose of the present invention can be achieved by the following technical solutions:

[0006] A store location recommendation method integrating multi-dimensional features includes the following steps:

[0007] S10. Collect multi-dimensional data of the area where the candidate store location is located, and the multi-dimensional data includes: pedestrian flow, the number of competitors, price, industry market size growth rate, regional planning trend, and changes in the consumer population trend;

[0008] S20. Preprocess the multi-dimensional data, including data cleaning and normalization processing;

[0009] S30. Input the preprocessed multi-dimensional data into the store location recommendation model to obtain the recommendation value of each candidate store location;

[0010] S40. After arranging the recommendation values of each candidate store location in descending order, obtain the store location recommendation sequence.

[0011] A further solution is that the expression of the store location recommendation model is:

[0012] ;

[0013] In the formula, represents the recommended value of the candidate store location, represents the th parameter value, represents a monitoring period, represents the start time of a monitoring period, represents the end time of a monitoring period, represents the adjustment coefficient corresponding to the th parameter, which is determined by comprehensive analysis of historical data and empirical data; represents the maximum value of the th parameter within a monitoring period, represents the minimum value of the th parameter within a monitoring period; , corresponding to the number of people , the number of competitors , price , the growth rate of the industry market scale , the regional planning trend and the changing trend of the consumer population parameters in sequence;

[0014] For a further solution, the method for obtaining the price parameter is as follows:

[0015] Obtain the rental price of the current candidate store location , and then obtain the average monthly consumer expenditure of the residents in the area where the current candidate store location is located ;

[0016] Through the formula: Calculate to obtain the price parameter ; In the formula, , are preset proportionality coefficients, determined based on historical data analysis, and ;

[0017] The method for obtaining the regional planning trend parameter is as follows:

[0018] If a new subway line is opened in the area where the current candidate store location is located, then , otherwise, ; In the formula, represents the influence factor, determined based on historical data analysis, represents the time interval between the expected opening time of the new subway line and the current time;

[0019] The method for obtaining the changing trend parameter of the consumer population The method is as follows:

[0020] Obtain the proportion F of the consumer group aged 20 - 40 and the growth rate G of the monthly income level of residents in the area where the current candidate store location is located;

[0021] Substitute into the formula: Calculate to obtain the consumer population change trend parameter ; In the formula, and represent preset weight factors, which are determined comprehensively based on historical data and empirical data, and .

[0022] For a further solution, the expression of the environmental impact index is: ; In the formula, represents the traffic congestion index of the area where the current candidate store location is located, represents the business district prosperity index of the area where the current candidate store location is located, represents the coincidence degree index, and represent reference values.

[0023] For a further solution, the method for obtaining the traffic congestion index of the area where the current candidate store location is located is:

[0024] Obtain the actual traffic flow Q, the actual average vehicle speed V, and the actual duration TC passing through the area where the current candidate store location is located within a unit time, and substitute them into the following formula:

[0025] Calculate to obtain the traffic congestion index of the area where the current candidate store location is located;

[0026] In the formula, and and represent weight coefficients, which are determined comprehensively based on historical data and empirical data, ; represents the speed limit value of the area, represents the shortest duration for passing through the area, represents the traffic flow that can be accommodated in the area under the maximum traffic capacity.

[0027] For a further solution, the method for obtaining the business district prosperity index of the area where the current candidate store location is located is:

[0028] Obtain the number of stores N, the average store sales volume W, and the passenger flow in the area where the current candidate store location is located, perform normalization processing and then substitute them into the following formula:

[0029] Calculate the prosperity index of the business district where the current candidate store location is located .

[0030] In a further embodiment, the overlap index The expression is:

[0031] ; In the formula, Indicates each traffic congestion period, Indicates the number of traffic congestion periods in a unit cycle, , Respectively represent The start and end time of each traffic congestion period, , Respectively represent the effective operation start time and end time of the reserved store.

[0032] A further solution is to obtain the traffic congestion period as follows:

[0033] Divide a unit period into n unit times at equal intervals;

[0034] The traffic congestion index corresponding to each unit time With preset traffic congestion threshold For comparison, if , the current unit time is marked as a traffic congestion period.

[0035] Beneficial effects of the present invention:

[0036] (1) The present invention integrates multi-dimensional data such as customer flow, number of competing products, price, industry market size growth rate, regional planning trend and consumer population change trend to recommend store locations. Compared with traditional methods, it fully considers various key factors affecting store operations and more comprehensively depicts the business environment of candidate areas, thereby providing more accurate location recommendations for stores and effectively improving the accuracy of location selection.

[0037] (2) By incorporating data such as the industry market size growth rate and regional planning trends, the present invention can help stores predict market changes and regional development trends in advance; when the industry is in its rising period, choosing to open stores in areas with great market potential and in line with industry development trends will help stores seize market opportunities and achieve rapid development; when there are positive planning changes in the region, such as the construction of a new subway line, early layout can enable stores to obtain more development dividends in the future; at the same time, paying attention to the changing trends of consumer groups enables stores to better meet the ever-changing needs of consumers, thereby enhancing the stores' adaptability to market changes and their ability to resist risks. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] The present invention will be further described below in conjunction with the accompanying drawings.

[0039] Figure 1 It is a method step diagram of the present invention. Specific embodiments

[0040] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0041] Please refer to Figure 1 As shown, the present invention is a store location recommendation method integrating multi-dimensional features, including the following steps:

[0042] S10. Collect multi-dimensional data of the area where the candidate store location is located. The multi-dimensional data includes: pedestrian flow, number of competing products, price, growth rate of the industry market scale, regional planning trend, and change trend of the consumer population;

[0043] S20. Preprocess the multi-dimensional data, including data cleaning and normalization processing; data cleaning includes removing noise data, duplicate data, and error data in the collected data. For example, for the obvious abnormal peaks or valleys in the pedestrian flow data, verify and correct them through comparison with historical data and on-site research; normalization processing: normalize the data of different dimensions;

[0044] S30. Input the preprocessed multi-dimensional data into the store location recommendation model to obtain the recommendation value of each candidate store location;

[0045] S40. After arranging the recommendation values of each candidate store location in descending order, obtain the store location recommendation sequence.

[0046] The expression of the store location recommendation model is:

[0047] ;

[0048] In the formula, represents the recommendation value of the candidate store location, represents the th parameter value, represents a monitoring period, represents the start time of a monitoring period, represents the end time of a monitoring period, represents The adjustment coefficient corresponding to each item parameter is determined by comprehensive analysis of historical data and empirical data, and is used to adjust the importance of each parameter in the model, because different parameters have different importance for different types of stores; represents the maximum value of the th item parameter within a monitoring period, represents the minimum value of the th item parameter within a monitoring period; , corresponding in sequence to the number of people flow , the number of competing products , price , the growth rate of the industry market scale , the regional planning trend and the changing trend of the consumer group parameters; is an environmental impact indicator. It should be noted that the monitoring period corresponding to each parameter is different and can be adjusted adaptively according to the actual situation; among them, These two values are used to measure the fluctuation of the parameter within the monitoring period, reflecting the stability or change range of this factor; taking the growth rate of the industry market scale as an example, if the difference between its maximum value and minimum value within the monitoring period is large, it indicates that the development of this industry is unstable, and there may be greater risks or opportunities, which need to be focused on when evaluating the site selection.

[0049] The present invention integrates multi-dimensional data such as the number of people flow, the number of competing products, price, the growth rate of the industry market scale, the regional planning trend, and the changing trend of the consumer group to recommend store site selection; compared with traditional methods, it fully considers various key factors affecting store operation, and more comprehensively depicts the business environment of the candidate area, so as to be able to provide more accurate store site selection recommendations, effectively improving the accuracy of site selection; for example, when evaluating the site selection of a potential catering store, not only the current number of people flow and the number of surrounding competing products are analyzed, but also factors such as the growth trend of the local catering industry market scale, whether there is a traffic construction plan in the region in the future, and the proportion change of the key consumer group are combined to comprehensively judge the feasibility of this site selection, greatly reducing the risk of business failure caused by improper site selection;

[0050] Meanwhile, by incorporating data such as the growth rate of the industry market size and regional planning trends, the present invention can help stores anticipate market changes and regional development trends in advance; when the industry is in an upward period, choosing to open stores in regions with large market potential and in line with the industry development trend helps stores seize market opportunities and achieve rapid development; when there are positive planning changes in a region, such as the construction of a new subway line, early layout enables stores to obtain more development dividends in the future; at the same time, paying attention to the changing trends of the consumer population enables stores to better meet the ever-changing needs of consumers, enhancing the adaptability and risk resistance of stores to market changes; accurate store location recommendations can guide the rational distribution of commercial resources, avoid the over-concentration of resources in some seemingly popular but actually limited development potential regions, and reduce resource waste.

[0051] The method for obtaining the price parameter is as follows:

[0052] Obtain the rental price of the current candidate store location , and then obtain the average monthly consumer expenditure of residents in the region where the current candidate store location is located ;

[0053] Through the formula: Calculate to obtain the price parameter ; In the formula, , are preset proportionality coefficients, determined based on historical data analysis, and ;

[0054] The method for obtaining the regional planning trend parameter is as follows:

[0055] If there is a new subway line opened in the region where the current candidate store location is located, then , otherwise, ; In the formula, represents the influence factor, determined based on historical data analysis, represents the time interval between the expected opening time of the new subway line and the current time;

[0056] The method for obtaining the consumer population change trend parameter is as follows:

[0057] Obtain the proportion F of the consumer group aged 20 - 40 and the growth rate G of the average monthly income level of residents in the region where the current candidate store location is located;

[0058] Substitute into the formula: Calculate to obtain the consumer population change trend parameter ; In the formula, , represent preset weight factors, determined by comprehensive consideration of historical data and empirical data, and 。

[0059] Through the above technical solution, the price parameter , the regional planning trend parameter , and the changing trend parameter of the consumer population are given specific acquisition methods.

[0060] The expression of the environmental impact index is: ; in the formula, represents the traffic congestion index of the area where the current candidate store location is located, represents the business district prosperity index of the area where the current candidate store location is located, represents the coincidence degree index, , represents the reference value.

[0061] In the present invention, the environmental impact index is calculated through the formula . Obviously, the traffic congestion index reflects the traffic conditions in the area, and congestion means a large flow of people; the business district prosperity index reflects the business vitality of the area; the coincidence degree index measures the coincidence degree between the effective operation time of the store and the traffic congestion period; the environmental impact index combines these aspects and further adjusts the final site selection recommendation value to make the recommendation result more in line with the actual business scenario.

[0062] The acquisition method of the traffic congestion index of the area where the current candidate store location is located is as follows:

[0063] Obtain the actual traffic flow Q, the actual average vehicle speed V and the actual duration TC passing through the area where the current candidate store location is located within a unit time, and substitute them into the following formula:

[0064] Calculate the traffic congestion index of the area where the current candidate store location is located ;

[0065] In the formula, , , represent weight coefficients, which are determined comprehensively based on historical data and empirical data, ; represents the speed limit value of the area, represents the shortest duration passing through the area, represents the traffic flow that can be accommodated in the area under the maximum traffic capacity.

[0066] Get the business district prosperity index of the current candidate store location area The method is:

[0067] Get the number of stores N, the average sales volume W and the customer flow in the area where the current candidate store is located , after normalization, it is entered into the following formula:

[0068] Calculate the prosperity index of the business district where the current candidate store location is located .

[0069] In the present invention, by , thus integrating the number of stores N, the average store sales W and customer flow The actual traffic volume / the traffic volume that the area can accommodate under the maximum traffic capacity is combined to obtain the prosperity index of the business district where the current candidate store location is located, the number of stores N, the average sales volume W of the stores and the customer flow The larger the value, the more prosperous the business district where the current candidate store is located. The larger the value is, the greater the traffic volume in the area where the current candidate store is located. The more prosperous the business district is, the more prosperous the current candidate store location is.

[0070] The coincidence index The expression is:

[0071] ; In the formula, Indicates each traffic congestion period, Indicates the number of traffic congestion periods in a unit cycle, , Respectively represent The start and end time of each traffic congestion period, , Respectively represent the effective operation start time and end time of the reserved store.

[0072] The method to obtain traffic congestion period is:

[0073] Divide a unit period into n unit times at equal intervals;

[0074] The traffic congestion index corresponding to each unit time With preset traffic congestion threshold For comparison, if , the current unit time is marked as a traffic congestion period.

[0075] In the present invention, The effective operating time reserved for the store is Calculate the overlapping duration between each traffic congestion period and the effective business hours of the store; that is, first find the end time (take the minimum of the end times of the two time intervals) and the start time (take the maximum of the start times of the two time intervals) of the intersection of the two time intervals, and then calculate their difference. If the difference is negative, it means that the two intervals do not overlap, and the overlapping duration is 0 at this time; then through the formula Add up the overlapping durations between each traffic congestion period and the effective business hours of the store to obtain the total overlapping duration; finally, through the formula Divide the total overlapping duration by the total effective business hours of the store to obtain the coincidence degree; through the above technical solution, the coincidence degree between the effective business hours of the store location and the traffic congestion periods in the current business district is introduced into the calculation formula of the environmental impact index. Obviously, the larger the coincidence degree index, the higher the recommended value of the area where the store location is located.

[0076] For example: There are three candidate store location areas A, B, and C in the current city, and select the most suitable store address for a chain coffee shop; as shown in the following table:

[0077]

[0078] It can be seen from the above table that the recommended order for selecting the most suitable store address for the chain coffee shop is: A, C, B.

[0079] It should be noted that: The calculation formula and each parameter participating in the operation in the present invention are all pre-dimensionless processed, and the process of dimensionless processing is well-known in the industry and will not be described here.

[0080] The above has described a detailed description of an embodiment of the present invention, but the content described is only a preferred embodiment of the present invention and cannot be considered as used to limit the scope of implementation of the present invention. All equivalent changes and improvements made according to the scope of the present invention application should still fall within the scope covered by the patent of the present invention.

Claims

1. A store location recommendation method integrating multi-dimensional features, characterized in that: The steps include: S10, collecting multi-dimensional data of the area where the candidate store location is located, the multi-dimensional data including: traffic, number of competing products, price, industry market size growth rate, regional planning trend and consumer population change trend; S20, preprocessing the multidimensional data, including data cleaning and normalization; S30, inputting the pre-processed multidimensional data into a store location recommendation model to obtain a recommended value for each candidate store location; S40, after arranging the recommended values ​​of each candidate store location in descending order, a store location recommendation sequence is obtained; The expression of the store location recommendation model is: ； In the formula, represents the recommended value of the candidate store location, Indicates Item parameter value, Represents a monitoring cycle, Indicates the start time of a monitoring cycle. Indicates the end time of a monitoring cycle. express The adjustment coefficient corresponding to the item parameter; Indicates the number of The maximum value of the item parameter, Indicates the number of The minimum value of the item parameter; , corresponding to the flow of people 、Number of competing products , price parameters 、Industry market size growth rate , Regional planning trend parameters And consumer population change trend parameters ; It is an environmental impact indicator; The expression of the environmental impact index is: ; In the formula, Indicates the traffic congestion index of the area where the current candidate store location is located. Indicates the prosperity index of the business district where the current candidate store location is located. represents the coincidence index, , Indicates reference value; The price parameters The method to obtain is: Get the rental price of the current candidate store location , and then obtain the average monthly consumer expenditure of residents in the area where the current candidate store location is located ; By formula: Calculate the price parameters ; In the formula, , is the preset scale factor, and ; Get the planning trend parameters of the area The method is: If a new subway line is opened in the area where the current candidate store is located, ,otherwise, ; In the formula, represents the impact factor, Indicates the time interval between the expected opening time of the new subway line and the current time; Get the consumer population change trend parameters The method is: Obtain the proportion F of the consumer group aged 20-40 and the growth rate G of the monthly income level of residents in the area where the current candidate store location is located; Substituting into the formula: Calculate the trend parameters of consumer population changes ; In the formula, , represents the preset weight factor, and .

2. The store location recommendation method integrating multi-dimensional features according to claim 1 is characterized in that: The traffic congestion index of the area where the current candidate store location is located The method to obtain is: Get the actual traffic volume Q, actual average vehicle speed V and actual time TC of the area where the current candidate store location is located in a unit time, and substitute them into the following formula: Calculate the traffic congestion index of the area where the current candidate store location is located ; In the formula, , , represents the weight coefficient, ; Indicates the speed limit value of the area. Indicates the shortest time to pass through the area. It indicates the traffic volume that the area can accommodate at the maximum capacity.

3. The store location recommendation method integrating multi-dimensional features according to claim 2 is characterized in that: Get the business district prosperity index of the current candidate store location area The method is: Get the number of stores N, the average sales volume W and the customer flow in the area where the current candidate store is located , after normalization, it is entered into the following formula: Calculate the prosperity index of the business district where the current candidate store location is located .

4. The store location recommendation method integrating multi-dimensional features according to claim 1 is characterized in that: The coincidence index The expression is: ; In the formula, Indicates each traffic congestion period, Indicates the number of traffic congestion periods in a unit cycle, , Respectively represent The start and end time of each traffic congestion period, , Respectively represent the effective operation start time and end time of the reserved store.

5. The store location recommendation method integrating multi-dimensional features according to claim 4 is characterized in that: The method to obtain traffic congestion period is: Divide a unit period into n unit times at equal intervals; The traffic congestion index corresponding to each unit time With preset traffic congestion threshold For comparison, if , the current unit time is marked as a traffic congestion period.

Images