Flash store digital site selection management system and method based on multi-channel site selection

Abstract

The invention discloses a flash store digital site selection management system and method based on multi-channel site selection, relates to the field of flash store site selection management, and provides a mapping tool for subsequent mapping classification of site selection influence factor data of a plurality of to-be-selected points of a flash store by constructing a final category mapping equation; through mapping, flash store to-be-selected points with annual net profit data not meeting requirements are eliminated; a 0-1 integer programming model is constructed according to the construction cost data, the coverage data and the annual net profit data corresponding to each quick-flash store primary selection point, so as to solve the quick-flash store site selection points where quick-flash stores are constructed. The construction cost is smaller than the preset construction cost threshold value, and the corresponding total coverage range data is larger than or equal to the preset coverage range threshold value, so that the screened quick-flash store site selection point can meet various requirements at the same time, and the net profit maximization is achieved.

Description

Technical Field

[0001] The present invention belongs to the field of pop-up store site selection management, and in particular, relates to a digital site selection management system and method for pop-up stores based on multi-site selection. Background Art

[0002] Chinese patent CN113743999B discloses a chain brand site selection management system for multi-regional marketing strategies based on blockchain. It uses blockchain technology to store data from the site selection process on the chain, and makes these data public or encrypted to achieve data sharing, judge the competitive pressure of chain brands in the corresponding sub-regions, and whether the combined effect of existing brands and chain brands in the sub-regions is a positive effect.

[0003] A pop-up store is a temporary retail space, usually used for brand marketing and promotion activities; therefore, if the pop-up store does not take into account the impact of various factors during the site selection stage, such as target audience, market positioning, traffic flow, etc., unreasonable site selection will result in the pop-up store failing to achieve the desired effect, thereby causing losses to the company. Summary of the invention

[0004] In view of the problems in the related art, the present invention proposes a digital site selection management system and method for pop-up stores based on multi-site selection to overcome the above-mentioned technical problems existing in the existing related art.

[0005] To solve the above technical problems, the present invention is achieved through the following technical solutions: The present invention is a digital site selection management method for a pop-up store based on multi-site selection, comprising the following steps: S1. Set multiple types of factors influencing the location of pop-up stores to obtain a set of location influencing factor types; collect location influencing factor data of multiple pop-up store sites to be selected according to the set of location influencing factor types to obtain a location influencing factor data matrix set; S2. According to the location influencing factor type set, data on location influencing factors and corresponding annual net profit data of multiple existing pop-up stores are collected to obtain an average location influencing factor data matrix and an existing annual net profit data set; and a final category mapping equation is constructed using the average location influencing factor data matrix and the existing annual net profit data set; S3. Use the final category mapping equation to classify and map the data matrix set of factors affecting the site selection and calculate the average value to obtain the average data set of net profit in the selected year; screen multiple candidate sites for pop-up stores according to the average data set of net profit in the selected year to obtain a preliminary site set for pop-up stores; S4, constructing a 0-1 integer programming model according to the construction cost data, coverage data, and annual net profit data corresponding to each pop-up store preliminary selection point in the pop-up store preliminary selection point set; solving the 0-1 integer programming model to obtain a construction parameter set; S5. Screening multiple pop-up store preliminary selection points according to the pop-up store preliminary selection point set and the construction parameter set to obtain a pop-up store final selection point set; and selecting a pop-up store site according to the pop-up store final selection point set; Since multiple influencing factors need to be considered when selecting a site for a pop-up store, multiple types of influencing factors for the site selection of pop-up stores are set to provide a basis for collecting the site selection influencing factor data for the pop-up store site selection points, and also to collect the site selection influencing factor data for existing pop-up stores; by collecting the site selection influencing factor data for multiple pop-up store sites, data support is provided for mapping out the corresponding annual net profit data; and by collecting the site selection influencing factor data for multiple existing pop-up stores and the corresponding annual net profit data, data support is provided for the subsequent construction of a mapping model between the site selection influencing factor data and the annual net profit data; by constructing the final category mapping equation, a mapping tool is provided for the subsequent mapping and classification of the site selection influencing factor data for multiple pop-up store sites; The annual net profit data corresponding to the influencing factor data will be used to eliminate the pop-up store sites whose annual net profit data does not meet the requirements. Since the construction cost data and coverage data of each pop-up store site selection point are different, and when building a pop-up store at a certain pop-up store site selection point, the construction cost and coverage are factors that must be considered. Based on this, this scheme constructs a 0-1 integer programming model through the construction cost data, coverage data and annual net profit data corresponding to each pop-up store preliminary selection point to solve for which pop-up store site selection points have a corresponding construction cost less than a preset construction cost threshold and a corresponding total coverage data greater than or equal to a preset coverage threshold when building a pop-up store. The total annual net profit data is used as the objective function, so that the pop-up store site selection points selected in this way can meet multiple requirements at the same time, thereby maximizing the net profit.

[0006] Preferably, the S1 comprises the following steps: S11. Set multiple types of factors influencing the location selection of pop-up stores to obtain a set of factors influencing the location selection , a i represents the factors affecting the location of the i-th pop-up store. represents the total number of factors influencing the location of the pop-up store; then a location selection area is set, and multiple pop-up store selection sites are set in the location selection area to obtain a set of pop-up store selection sites. , represents the i-th pop-up store site to be selected in the site selection area, Indicates the total number of pop-up store sites to be selected in the site selection area; S12, based on the type set of factors affecting site selection Collect the location influencing factor data of each pop-up store candidate location at multiple time points in the pop-up store candidate location set to obtain the location influencing factor data matrix set , b i represents the data matrix of factors affecting site selection collected at the i-th time point, Indicates the total number of time points corresponding to the data matrix of multiple factors affecting site selection collected; b i as follows, ; Among them, b ijk represents the k-th type of location influencing factor data for the j-th pop-up store to be selected at the i-th time point; The types of factors affecting site selection include target audience factors, market positioning factors, foot traffic factors, surrounding competitive environment factors, and seasonal considerations, etc. By collecting data on site selection factors at multiple time points for each pop-up store site in the pop-up store site selection set, the collected data on site selection factors is richer and the randomness of the data is reduced.

[0007] Preferably, S2 comprises the following steps: S21, based on the type set of factors affecting site selection Collect the location influencing factors data of multiple existing pop-up stores at multiple time points within a year and the corresponding annual net profit data to obtain the existing location influencing factors data matrix set And the existing annual net profit dataset , represents the data matrix of existing location influencing factors of multiple existing pop-up stores at the i-th time point within one year, Indicates the total number of time points corresponding to the collected data on location influencing factors of multiple existing pop-up stores at multiple time points within a year; represents the annual net profit data of the i-th existing pop-up store collected, and c represents the total number of existing pop-up stores collected; as follows, ; in, express The location influencing factors data of the kth type of the jth existing pop-up store; S22, the existing data matrix set of factors affecting site selection The location influencing factor data in the above table are averaged at each time point to obtain the average location influencing factor data matrix. ;as follows, ; in, It represents the average value of the k-th type of location influencing factor data collected for the j-th existing flash point at multiple time points; the calculation formula is as follows: ; S23, setting the initial category mapping equation; according to the average site selection influencing factor data matrix And the existing annual net profit dataset Optimize the initial mapping equation to obtain the final category mapping equation; By collecting the location influencing factor data and the corresponding annual net profit data of multiple existing pop-up stores at multiple time points within a year, a data basis is provided for the subsequent construction of the mapping relationship between the location influencing factor data and the annual net profit data.

[0008] Preferably, the S23 comprises the following steps: S231, set the initial category mapping equation; as follows, ; In the formula, is the dependent variable, indicating the annual net profit data; d 2i is the ith independent variable, representing the ith type of location influencing factor data; d 1i Indicates d 2i The corresponding initial independent variable coefficients are, Indicates the offset; S232, setting an annual net profit mapping error threshold; converting the average site selection influencing factor data matrix Substitute the location influencing factor data in the initial category mapping equation for classification mapping to obtain the annual net profit initial mapping data set , represents the initial mapping data of annual net profit obtained by substituting the collected data of average location influencing factors of the i-th existing pop-up store into the initial category mapping equation; When the absolute value of the difference between the annual net profit mapping data in the annual net profit initial mapping data set and the corresponding existing annual net profit data in the existing annual net profit data set is greater than or equal to the annual net profit mapping error threshold, optimizing the initial mapping equation to obtain a final category mapping equation; Otherwise, there is no need to optimize the initial mapping equation, and the initial mapping equation is used as the final category mapping equation; By optimizing the independent variable coefficient and bias of the initial category mapping equation according to the error between the data mapped by the initial category mapping equation and the actual data, the final category mapping equation is more accurate in mapping the location influencing factor data and the corresponding annual net profit data, and the accuracy of subsequent mapping of the location influencing factor data of multiple pop-up store locations is also improved.

[0009] Preferably, optimizing the initial mapping equation in S232 to obtain the final category mapping equation includes the following steps: S2321. Establishing the first tuna population , represents the i-th tuna in the first tuna population, e 1 represents the size of the first tuna population; sets the maximum number of iterations of the first tuna population to , the current number of iterations is , respectively recorded as the first maximum number of iterations and the first current number of iterations; the search space dimension of the first tuna population is +1; S2322, setting the value interval of each independent variable coefficient and bias in the initial category mapping equation to obtain a value interval set ;as follows, ; in, , Respectively represent the lower limit and upper limit of the value of the i-th independent variable coefficient in the initial category mapping equation; , respectively represent the lower limit and upper limit of the bias value in the initial category mapping equation; According to the value interval set Set the initial position of each tuna in the first tuna population to obtain the first initial position matrix ;as follows, ; in, represents the position component of the initial position of the i-th tuna in the first tuna population in the j-th dimension; , The calculation formulas are as follows: ; ; In the formula, rand ij , Respectively for as well as Generate a random number between 0 and 1; S2323, initially mapping the data set based on the annual net profit And the existing annual net profit dataset Construct the fitness function f of the first tuna population 1 ;as follows, ; In the formula, β is a positive number, indicating the correction parameter; S2324, start iteration, before iteration, set the first current iteration number Set to 1; the fitness function f of the first tuna population is used in the first round of iteration 1 Calculate the first initial position matrix The fitness value of the initial position of each tuna in the first fitness value set is obtained to obtain a first fitness value set; the maximum fitness value and the corresponding initial position in the first fitness value set are respectively used as the first global optimal fitness value and the first global optimal position; the first initial position matrix is ​​adjusted according to the first global optimal fitness value and the first global optimal position. After the update is completed, the first current iteration number is Add 1 and enter the next iteration; In each other iteration, the fitness function f of the first tuna population is used. 1 Calculate the fitness value of each tuna position updated in the previous round of iterations to obtain a second fitness value set; use the maximum fitness value in the second fitness value set and the corresponding initial position as the second global optimal fitness value and the second global optimal position respectively; update the position of each tuna updated in the previous round of iterations according to the second global optimal fitness value and the second global optimal position; after the update is completed, the first current iteration number Add 1 and enter the next iteration; S2325, when When , the iteration is stopped to obtain the first final global optimal position; the first final global optimal position is substituted into the initial category mapping equation to obtain the adjusted category mapping equation; the location influencing factor data in the average location influencing factor data matrix is ​​substituted into the adjusted category mapping equation for classification mapping to obtain the adjusted mapping data set of annual net profit; When the absolute value of the difference between the annual net profit mapping data that does not exist in the annual net profit adjusted mapping data set and the corresponding existing annual net profit data in the existing annual net profit data set is greater than or equal to the annual net profit mapping error threshold, the adjusted category mapping equation is used as the final category mapping equation; otherwise, return to S2324 to continue iterating until the absolute value of the difference between the annual net profit mapping data that does not exist in the annual net profit adjusted mapping data set and the corresponding existing annual net profit data in the existing annual net profit data set is greater than or equal to the annual net profit mapping error threshold; The tuna optimization algorithm shows a faster convergence speed when solving optimization problems, can find a better solution within a smaller number of iterations, and can find a high-quality solution to the problem with higher solution accuracy. It combines the spiral foraging and parabolic foraging strategies, which helps to balance global exploration and local development in the search process. Based on the above, this scheme optimizes the independent variable coefficients and bias of the initial mapping equation by using the tuna optimization algorithm, and uses the mapping error of the initial mapping equation as the fitness function. As the iteration proceeds, the mapping error becomes smaller and smaller, and finally meets the mapping requirements.

[0010] Preferably, S3 comprises the following steps: S31, substituting the data matrix of the location influencing factors at each time point in the location influencing factors data matrix set into the final category mapping equation for classification mapping to obtain the net profit data matrix of the selected year ;as follows, ; in, represents the annual net profit data of the i-th pop-up store to be selected in the site selection area at the j-th time point obtained by mapping; S32, calculating the net profit data matrix of the selected year The average annual net profit data of each pop-up store at multiple time points in the selected location is obtained to obtain the average annual net profit data set for the selected location. , It represents the average annual net profit data of the i-th pop-up store to be selected in the site selection area at multiple time points; the calculation formula is as follows: ; S33, setting the annual net profit site selection standard threshold; extracting the annual net profit average data set to be selected The pop-up store locations corresponding to the annual net profit site selection standard threshold that is greater than or equal to the annual net profit site selection standard threshold and the corresponding annual net profit average data are obtained to obtain the initial selection point set of the pop-up store And the annual net profit average preliminary data set , represents the extracted preliminary selection point of the i-th pop-up store, Indicates the total number of pop-up store preliminary selection points extracted, represents the annual net profit data of building a pop-up store at the extracted i-th pop-up store preliminary selection point; By calculating the average annual net profit data of each pop-up store candidate location at multiple time points, the average annual net profit data finally obtained can more accurately represent the annual net profit data of each pop-up store candidate location.

[0011] Preferably, the S4 comprises the following steps: S41. Set a threshold for pop-up store construction costs , coverage threshold , the cost of constructing a pop-up store at each of the pop-up store preliminary selection points in the pop-up store preliminary selection point set and the coverage of constructing a pop-up store at each of the pop-up store preliminary selection points in the pop-up store preliminary selection point set, to obtain a preliminary construction cost data set and the primary coverage dataset , , They respectively represent the cost data of constructing a pop-up store corresponding to the i-th pop-up store preliminary selection point and the coverage data of constructing a pop-up store; S42. Based on the annual net profit average preliminary data set and the pop-up store construction cost threshold , coverage threshold , the preliminary construction cost data set and the preliminary coverage data set are used to construct a 0-1 integer programming model; the objective function and constraint condition group of the 0-1 integer programming model are as follows: ; ; In the formula, Represents the total annual net profit data of multiple pop-up stores; Indicates the i-th 0-1 variable set, , Indicates that a pop-up store will not be built at the i-th pop-up store preliminary selection point extracted. Indicates building a pop-up store at the extracted i-th pop-up store preliminary selection point; S43, solving the 0-1 integer programming model to obtain a set of construction parameters , represents the construction parameters corresponding to the construction of the pop-up store at the i-th pop-up store preliminary selection point, ; Preferably, the S43 comprises the following steps: S431. Constructing the second tuna population , represents the i-th tuna in the second tuna population, e 2 represents the size of the second tuna population; sets the maximum number of iterations of the second tuna population to , the current number of iterations is , respectively recorded as the second maximum number of iterations and the second current number of iterations; the search space dimension of the second tuna population is ; S432: setting the initial position of each tuna in the second tuna population according to the objective function and constraint condition group of the 0-1 integer programming model to obtain a second initial position matrix ;as follows, ; in, represents the position component of the initial position of the i-th tuna in the second tuna population in the j-th dimension; ; S433, using the objective function of the 0-1 integer programming model as the fitness function of the second tuna population; S434, start iteration, before iteration, set the second current iteration number Set to 1; in the first round of iteration, the second initial position matrix is ​​calculated using the fitness function of the second tuna population The fitness value of the initial position of each tuna in the third fitness value set is obtained to obtain a third fitness value set; the maximum fitness value in the third fitness value set and the corresponding initial position are respectively used as the third global optimal fitness value and the third global optimal position; the second initial position matrix is ​​set according to the third global optimal fitness value and the third global optimal position and in conjunction with the constraint condition group of the 0-1 integer programming model. After the update is completed, the second current iteration number Add 1 and enter the next iteration; In each other round of iteration, the fitness function of the second tuna population is used to calculate the fitness value of the position of each tuna updated in the previous round of iteration to obtain a fourth fitness value set; the maximum fitness value in the fourth fitness value set and the corresponding initial position are respectively used as the fourth global optimal fitness value and the fourth global optimal position; the position of each tuna updated in the previous round of iteration is updated again according to the fourth global optimal fitness value and the fourth global optimal position in conjunction with the constraint condition group of the 0-1 integer programming model; after the update is completed, the second current iteration number is Add 1 and enter the next iteration; S435, when When , the iteration is stopped, and the second final global optimal position is obtained; the second final global optimal position is used as the pruning parameter set ; By using the tuna optimization algorithm to perform multiple iterative optimizations on the uncertainties in the 0-1 integer programming model, the total annual net profit data corresponding to the site selection result is ultimately maximized, making the site selection more in line with the actual needs of the enterprise.

[0012] Preferably, the S5 comprises the following steps: S51, cooperate with the pop-up store preliminary point set to set the construction parameter set The initial selection points of the pop-up stores corresponding to the construction parameters that are not 0 are extracted to obtain the final selection point set of the pop-up stores , represents the final location of the i-th pop-up store, Indicates the total number of locations finally selected for the pop-up stores; S52, according to the final selection point set of the pop-up store Conduct site selection for pop-up stores; A digital site selection management system for pop-up stores based on multi-economic site selection, comprising a site selection influencing factor type setting module, a site selection influencing factor data collection module, an existing pop-up store data collection module, a mapping equation construction module, a classification mapping module, a first site selection point screening module, an integer programming model construction module, a solution module, a second site selection point screening module and a site selection module; The location selection influencing factor type setting module is used to set the types of influencing factors for location selection of multiple pop-up stores to obtain a location selection influencing factor type set; The location influencing factor data collection module is used to collect location influencing factor data of multiple pop-up store sites to be selected according to the location influencing factor type set to obtain a location influencing factor data matrix set; The existing pop-up store data collection module is used to collect location influencing factor data and corresponding annual net profit data of multiple existing pop-up stores according to the location influencing factor type set, and obtain an average location influencing factor data matrix and an existing annual net profit data set; The mapping equation construction module is used to construct a final category mapping equation using an average location influencing factor data matrix and an existing annual net profit data set; The classification mapping module is used to classify and map the location influencing factor data matrix set using the final classification mapping equation and calculate the average value to obtain the average data set of net profit for the selected year; The first site selection point screening module is used to screen multiple pop-up store sites according to the average net profit data set of the selected year to obtain a preliminary site set of pop-up stores; The integer programming model is used to construct a module to construct a 0-1 integer programming model according to the construction cost data, coverage data and annual net profit data corresponding to each pop-up store preliminary selection point in the pop-up store preliminary selection point set; The solution module is used to solve the 0-1 integer programming model to obtain a set of repair parameters; The second site selection point screening module is used to screen multiple pop-up store preliminary selection points according to the pop-up store preliminary selection point set and the construction parameter set to obtain a final pop-up store selection point set; The site selection module is used to select a site for a pop-up store based on the final site selection set for the pop-up store.

[0013] The present invention has the following beneficial effects: 1. The present invention provides a mapping tool for mapping and classifying the location influencing factor data of multiple pop-up store sites by constructing a final category mapping equation; eliminates the pop-up store sites whose annual net profit data do not meet the requirements by mapping the annual net profit data corresponding to the location influencing factor data of multiple pop-up store sites; constructs a 0-1 integer programming model through the construction cost data, coverage data and annual net profit data corresponding to each pop-up store preliminary site, so as to find out at which pop-up store site selection points, when building a pop-up store, its construction cost is less than a preset construction cost threshold and its corresponding total coverage data is greater than or equal to a preset coverage threshold, so that the pop-up store site selection points selected in this way can meet multiple requirements at the same time, thereby maximizing the net profit.

[0014] 2. In the present invention, the independent variable coefficient and bias of the initial category mapping equation are optimized according to the error between the data mapped by the initial category mapping equation and the actual data, so that the final category mapping equation is more accurate in mapping the location influencing factor data and the corresponding annual net profit data, and the accuracy of subsequent mapping of the location influencing factor data of multiple pop-up store locations is also improved.

[0015] 3. In the present invention, the uncertainty in the 0-1 integer programming model is optimized multiple times by using the tuna optimization algorithm, so as to maximize the total annual net profit data corresponding to the site selection result, so that the site selection is more in line with the actual needs of the enterprise.

[0016] Of course, any product implementing the present invention does not necessarily need to achieve all of the advantages described above at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions of the embodiments of the invention, the drawings required for describing the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the invention. For ordinary technicians in this field, they can also obtain drawings based on these drawings without paying creative work.

[0018] Figure 1 The present invention is a flowchart of a method for digital site selection management of a pop-up store based on multiple site selection methods. DETAILED DESCRIPTION

[0019] The following will be combined with the drawings in the embodiments of the invention to clearly and completely describe the technical solutions in the embodiments of the invention. Obviously, the described embodiments are only part of the embodiments of the invention, not all of the embodiments. Based on the embodiments in the invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the invention.

[0020] In the description of the present invention, it is necessary to understand that the terms "opening", "upper", "lower", "top", "middle", "inside" and the like indicating orientation or positional relationship are only for the convenience of describing the invention and simplifying the description, and do not indicate or imply that the components or elements referred to must have a specific orientation, be constructed and operate in a specific orientation, and therefore cannot be understood as limiting the invention.

[0021] Embodiment 1

[0022] This embodiment is a method for digital site selection and management of a pop-up store based on multiple site selection methods, comprising the following steps: S1. Set multiple types of factors influencing the location of pop-up stores to obtain a set of location influencing factor types; collect location influencing factor data of multiple pop-up store sites to be selected according to the set of location influencing factor types to obtain a location influencing factor data matrix set; The S1 comprises the following steps: S11. Set multiple types of factors influencing the location selection of pop-up stores to obtain a set of factors influencing the location selection , a i represents the factors affecting the location of the i-th pop-up store. represents the total number of factors influencing the location of the pop-up store; then a location selection area is set, and multiple pop-up store selection sites are set in the location selection area to obtain a set of pop-up store selection sites. , represents the i-th pop-up store site to be selected in the site selection area, Indicates the total number of pop-up store sites to be selected in the site selection area; S12, based on the type set of factors affecting site selection Collect the location influencing factor data of each pop-up store candidate location at multiple time points in the pop-up store candidate location set to obtain the location influencing factor data matrix set , b i represents the data matrix of factors affecting site selection collected at the i-th time point, Indicates the total number of time points corresponding to the data matrix of multiple factors affecting site selection collected; b i as follows, ; Among them, b ijk represents the k-th type of location influencing factor data for the j-th pop-up store to be selected at the i-th time point; S2. According to the location influencing factor type set, data on location influencing factors and corresponding annual net profit data of multiple existing pop-up stores are collected to obtain an average location influencing factor data matrix and an existing annual net profit data set; and a final category mapping equation is constructed using the average location influencing factor data matrix and the existing annual net profit data set; The S2 comprises the following steps: S21, based on the type set of factors affecting site selection Collect the location influencing factors data of multiple existing pop-up stores at multiple time points within a year and the corresponding annual net profit data to obtain the existing location influencing factors data matrix set And the existing annual net profit dataset , represents the data matrix of existing location influencing factors of multiple existing pop-up stores at the i-th time point within one year, Indicates the total number of time points corresponding to the collected data on location influencing factors of multiple existing pop-up stores at multiple time points within a year; represents the annual net profit data of the i-th existing pop-up store collected, and c represents the total number of existing pop-up stores collected; as follows, ; in, express The location influencing factors data of the kth type of the jth existing pop-up store; S22, the existing data matrix set of factors affecting site selection The location influencing factor data in the above table are averaged at each time point to obtain the average location influencing factor data matrix. ;as follows, ; in, It represents the average value of the k-th type of location influencing factor data collected for the j-th existing flash point at multiple time points; the calculation formula is as follows: ; S23, setting the initial category mapping equation; according to the average site selection influencing factor data matrix And the existing annual net profit dataset Optimize the initial mapping equation to obtain the final category mapping equation; The S23 comprises the following steps: S231, set the initial category mapping equation; as follows, ; In the formula, is the dependent variable, indicating the annual net profit data; d 2i is the ith independent variable, representing the ith type of location influencing factor data; d 1i Indicates d 2i The corresponding initial independent variable coefficients are, Indicates the offset; S232, setting an annual net profit mapping error threshold; converting the average site selection influencing factor data matrix Substitute the location influencing factor data in the initial category mapping equation for classification mapping to obtain the annual net profit initial mapping data set , represents the initial mapping data of annual net profit obtained by substituting the collected data of average location influencing factors of the i-th existing pop-up store into the initial category mapping equation; When the absolute value of the difference between the annual net profit mapping data in the annual net profit initial mapping data set and the corresponding existing annual net profit data in the existing annual net profit data set is greater than or equal to the annual net profit mapping error threshold, optimizing the initial mapping equation to obtain a final category mapping equation; Otherwise, there is no need to optimize the initial mapping equation, and the initial mapping equation is used as the final category mapping equation; In S232, the initial mapping equation is optimized to obtain a final category mapping equation, which includes the following steps: S2321. Establishing the first tuna population , represents the i-th tuna in the first tuna population, e 1 represents the size of the first tuna population; sets the maximum number of iterations of the first tuna population to , the current number of iterations is , respectively recorded as the first maximum number of iterations and the first current number of iterations; the search space dimension of the first tuna population is +1; S2322, setting the value interval of each independent variable coefficient and bias in the initial category mapping equation to obtain a value interval set ;as follows, ; in, , Respectively represent the lower limit and upper limit of the value of the i-th independent variable coefficient in the initial category mapping equation; , respectively represent the lower limit and upper limit of the bias value in the initial category mapping equation; According to the value interval set Set the initial position of each tuna in the first tuna population to obtain the first initial position matrix ;as follows, ; in, represents the position component of the initial position of the i-th tuna in the first tuna population in the j-th dimension; , The calculation formulas are as follows: ; ; In the formula, rand ij , Respectively for as well as Generate a random number between 0 and 1; S2323, initially mapping the data set based on the annual net profit And the existing annual net profit dataset Construct the fitness function f of the first tuna population 1 ;as follows, ; In the formula, β is a positive number, indicating the correction parameter; S2324, start iteration, before iteration, set the first current iteration number Set to 1; the fitness function f of the first tuna population is used in the first round of iteration 1 Calculate the first initial position matrix The fitness value of the initial position of each tuna in the first fitness value set is obtained to obtain a first fitness value set; the maximum fitness value and the corresponding initial position in the first fitness value set are respectively used as the first global optimal fitness value and the first global optimal position; the first initial position matrix is ​​adjusted according to the first global optimal fitness value and the first global optimal position. After the update is completed, the first current iteration number is Add 1 and enter the next iteration; In each other iteration, the fitness function f of the first tuna population is used. 1 Calculate the fitness value of each tuna position updated in the previous round of iterations to obtain a second fitness value set; use the maximum fitness value in the second fitness value set and the corresponding initial position as the second global optimal fitness value and the second global optimal position respectively; update the position of each tuna updated in the previous round of iterations according to the second global optimal fitness value and the second global optimal position; after the update is completed, the first current iteration number Add 1 and enter the next iteration; S2325, when When , the iteration is stopped to obtain the first final global optimal position; the first final global optimal position is substituted into the initial category mapping equation to obtain the adjusted category mapping equation; the location influencing factor data in the average location influencing factor data matrix is ​​substituted into the adjusted category mapping equation for classification mapping to obtain the adjusted mapping data set of annual net profit; When the absolute value of the difference between the annual net profit mapping data that does not exist in the annual net profit adjusted mapping data set and the corresponding existing annual net profit data in the existing annual net profit data set is greater than or equal to the annual net profit mapping error threshold, the adjusted category mapping equation is used as the final category mapping equation; otherwise, return to S2324 to continue iterating until the absolute value of the difference between the annual net profit mapping data that does not exist in the annual net profit adjusted mapping data set and the corresponding existing annual net profit data in the existing annual net profit data set is greater than or equal to the annual net profit mapping error threshold; S3. Use the final category mapping equation to classify and map the data matrix set of factors affecting the site selection and calculate the average value to obtain the average data set of net profit in the selected year; screen multiple candidate sites for pop-up stores according to the average data set of net profit in the selected year to obtain a preliminary site set for pop-up stores; The S3 comprises the following steps: S31, substituting the data matrix of the location influencing factors at each time point in the location influencing factors data matrix set into the final category mapping equation for classification mapping to obtain the net profit data matrix of the selected year ;as follows, ; in, represents the annual net profit data of the i-th pop-up store to be selected in the site selection area at the j-th time point obtained by mapping; S32, calculating the net profit data matrix for the selected year The average annual net profit data of each pop-up store at multiple time points in the selected location is obtained to obtain the average annual net profit data set for the selected location. , It represents the average annual net profit data of the i-th pop-up store to be selected in the site selection area at multiple time points; the calculation formula is as follows: ; S33, setting the annual net profit site selection standard threshold; extracting the annual net profit average data set to be selected The pop-up store locations corresponding to the annual net profit site selection standard threshold that is greater than or equal to the annual net profit site selection standard threshold and the corresponding annual net profit average data are obtained to obtain the initial selection point set of the pop-up store And the annual net profit average preliminary data set , represents the extracted preliminary selection point of the i-th pop-up store, Indicates the total number of pop-up store preliminary selection points extracted, represents the annual net profit data of building a pop-up store at the extracted i-th pop-up store preliminary selection point; S4, constructing a 0-1 integer programming model according to the construction cost data, coverage data, and annual net profit data corresponding to each pop-up store preliminary selection point in the pop-up store preliminary selection point set; solving the 0-1 integer programming model to obtain a construction parameter set; The S4 comprises the following steps: S41. Set a threshold for pop-up store construction costs , coverage threshold , the cost of constructing a pop-up store at each of the pop-up store preliminary selection points in the pop-up store preliminary selection point set and the coverage of constructing a pop-up store at each of the pop-up store preliminary selection points in the pop-up store preliminary selection point set, to obtain a preliminary construction cost data set and the primary coverage dataset , , They respectively represent the cost data of constructing a pop-up store corresponding to the i-th pop-up store preliminary selection point and the coverage data of constructing a pop-up store; S42. Based on the annual net profit average preliminary data set and the pop-up store construction cost threshold , coverage threshold , the preliminary construction cost data set and the preliminary coverage data set are used to construct a 0-1 integer programming model; the objective function and constraint condition group of the 0-1 integer programming model are as follows: ; ; In the formula, Represents the total annual net profit data of multiple pop-up stores; Indicates the i-th 0-1 variable set, , Indicates that a pop-up store will not be built at the i-th pop-up store preliminary selection point extracted. Indicates building a pop-up store at the extracted i-th pop-up store preliminary selection point; S43, solving the 0-1 integer programming model to obtain a set of construction parameters , represents the construction parameters corresponding to the construction of the pop-up store at the i-th pop-up store preliminary selection point, ; The S43 comprises the following steps: S431. Constructing the second tuna population , represents the i-th tuna in the second tuna population, e 2 represents the size of the second tuna population; sets the maximum number of iterations of the second tuna population to , the current number of iterations is , respectively recorded as the second maximum number of iterations and the second current number of iterations; the search space dimension of the second tuna population is ; S432: setting the initial position of each tuna in the second tuna population according to the objective function and constraint condition group of the 0-1 integer programming model to obtain a second initial position matrix ;as follows, ; in, represents the position component of the initial position of the i-th tuna in the second tuna population in the j-th dimension; ; S433, using the objective function of the 0-1 integer programming model as the fitness function of the second tuna population; S434, start iteration, before iteration, set the second current iteration number Set to 1; in the first round of iteration, the second initial position matrix is ​​calculated using the fitness function of the second tuna population The fitness value of the initial position of each tuna in the third fitness value set is obtained to obtain a third fitness value set; the maximum fitness value in the third fitness value set and the corresponding initial position are respectively used as the third global optimal fitness value and the third global optimal position; the second initial position matrix is ​​set according to the third global optimal fitness value and the third global optimal position and in conjunction with the constraint condition group of the 0-1 integer programming model. After the update is completed, the second current iteration number Add 1 and enter the next iteration; In each other round of iteration, the fitness function of the second tuna population is used to calculate the fitness value of the position of each tuna updated in the previous round of iteration to obtain a fourth fitness value set; the maximum fitness value in the fourth fitness value set and the corresponding initial position are respectively used as the fourth global optimal fitness value and the fourth global optimal position; the position of each tuna updated in the previous round of iteration is updated again according to the fourth global optimal fitness value and the fourth global optimal position in conjunction with the constraint condition group of the 0-1 integer programming model; after the update is completed, the second current iteration number is Add 1 and enter the next iteration; S435, when When , the iteration is stopped, and the second final global optimal position is obtained; the second final global optimal position is used as the pruning parameter set ; S5. Screening multiple pop-up store preliminary selection points according to the pop-up store preliminary selection point set and the construction parameter set to obtain a pop-up store final selection point set; and selecting a pop-up store site according to the pop-up store final selection point set; The S5 comprises the following steps: S51, cooperate with the pop-up store preliminary point set to set the construction parameter set The initial selection points of the pop-up stores corresponding to the construction parameters that are not 0 are extracted to obtain the final selection point set of the pop-up stores , represents the final location of the i-th pop-up store, Indicates the total number of locations finally selected for the pop-up stores; S52, according to the final selection point set of the pop-up store Select a location for your pop-up store.

[0023] Embodiment 2 This embodiment discloses a digital site selection management system for pop-up stores based on multi-element site selection, and the system can implement the method of the above embodiment, including a site selection influencing factor type setting module, a site selection influencing factor data collection module, an existing pop-up store data collection module, a mapping equation construction module, a classification mapping module, a first site selection point screening module, an integer programming model construction module, a solution module, a second site selection point screening module and a site selection module; The location selection influencing factor type setting module is used to set the types of influencing factors for location selection of multiple pop-up stores to obtain a location selection influencing factor type set; The location influencing factor data collection module is used to collect location influencing factor data of multiple pop-up store sites to be selected according to the location influencing factor type set to obtain a location influencing factor data matrix set; The existing pop-up store data collection module is used to collect location influencing factor data and corresponding annual net profit data of multiple existing pop-up stores according to the location influencing factor type set, and obtain an average location influencing factor data matrix and an existing annual net profit data set; The mapping equation construction module is used to construct a final category mapping equation using an average location influencing factor data matrix and an existing annual net profit data set; The classification mapping module is used to classify and map the location influencing factor data matrix set using the final classification mapping equation and calculate the average value to obtain the average data set of net profit for the selected year; The first site selection point screening module is used to screen multiple pop-up store sites according to the average net profit data set of the selected year to obtain a preliminary site set of pop-up stores; The integer programming model is used to construct a module to construct a 0-1 integer programming model according to the construction cost data, coverage data and annual net profit data corresponding to each pop-up store preliminary selection point in the pop-up store preliminary selection point set; The solution module is used to solve the 0-1 integer programming model to obtain a set of repair parameters; The second site selection point screening module is used to screen multiple pop-up store preliminary selection points according to the pop-up store preliminary selection point set and the construction parameter set to obtain a final pop-up store selection point set; The site selection module is used to select a site for a pop-up store based on the final site selection set for the pop-up store.

[0024] In the description of this specification, the description with reference to the terms "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0025] The preferred embodiments of the invention disclosed above are only used to help explain the invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to the specific implementation methods described. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the invention, so that those skilled in the art can understand and use the invention well.

Claims

1. A digital site selection management method for pop-up stores based on multi-site selection, characterized in that: The following steps are involved: S1. Set multiple types of factors influencing the location of pop-up stores to obtain a set of location influencing factor types; collect location influencing factor data of multiple pop-up store sites to be selected according to the set of location influencing factor types to obtain a location influencing factor data matrix set; S2. According to the location influencing factor type set, data on location influencing factors and corresponding annual net profit data of multiple existing pop-up stores are collected to obtain an average location influencing factor data matrix and an existing annual net profit data set; and a final category mapping equation is constructed using the average location influencing factor data matrix and the existing annual net profit data set; S3, using the final category mapping equation to classify and map the data matrix set of factors affecting site selection and calculate the average value to obtain the average data set of net profit for the selected year; Screen multiple pop-up store sites based on the average net profit data set of the candidate years to obtain a preliminary pop-up store site set; S4, constructing a 0-1 integer programming model according to the construction cost data, coverage data, and annual net profit data corresponding to each pop-up store preliminary selection point in the pop-up store preliminary selection point set; solving the 0-1 integer programming model to obtain a construction parameter set; S5. Screening multiple pop-up store preliminary selection points according to the pop-up store preliminary selection point set and the construction parameter set to obtain a final pop-up store selection point set; The pop-up store site is selected based on the final set of pop-up store sites.

2. A method for digital site selection management of a pop-up store based on multiple site selection according to claim 1, characterized in that: The S1 comprises the following steps: S11, setting multiple types of factors influencing the location of pop-up stores to obtain a set of factors influencing the location; then setting a location selection area, setting multiple locations to be selected for pop-up stores in the location selection area, and obtaining a set of locations to be selected for pop-up stores; S12. According to the site selection influencing factor type set, data on the site selection influencing factors of each pop-up store candidate site in the pop-up store candidate site set at multiple time points are collected to obtain a site selection influencing factor data matrix set.

3. The method for digital site selection and management of a pop-up store based on multiple site selection according to claim 2, characterized in that: The S2 comprises the following steps: S21, collecting location influencing factor data and corresponding annual net profit data of multiple existing pop-up stores at multiple time points within a year according to the location influencing factor type set, to obtain an existing location influencing factor data matrix set and an existing annual net profit data set; S22, calculating the average value of the location influencing factor data in the existing location influencing factor data matrix set at each time point to obtain an average location influencing factor data matrix; S23, setting an initial category mapping equation; optimizing the initial mapping equation according to the average site selection influencing factor data matrix and the existing annual net profit data set to obtain a final category mapping equation.

4. The method for digital site selection and management of a pop-up store based on multiple site selection according to claim 3, characterized in that: The S23 comprises the following steps: S231, setting an initial category mapping equation; S232, setting an annual net profit mapping error threshold; substituting the location influencing factor data in the average location influencing factor data matrix into the initial category mapping equation for classification mapping, and obtaining an annual net profit initial mapping data set; When the absolute value of the difference between the annual net profit mapping data in the annual net profit initial mapping data set and the corresponding existing annual net profit data in the existing annual net profit data set is greater than or equal to the annual net profit mapping error threshold, the initial mapping equation is optimized to obtain the final category mapping equation; otherwise, the initial mapping equation does not need to be optimized, and the initial mapping equation is used as the final category mapping equation.

5. The method for digital site selection management of a pop-up store based on multiple site selection according to claim 4, characterized in that: In S232, the initial mapping equation is optimized using the tuna optimization algorithm.

6. A method for digital site selection management of a pop-up store based on multiple site selection according to claim 5, characterized in that: The S3 comprises the following steps: S31, substituting the data matrix of the location influencing factors at each time point in the location influencing factors data matrix set into the final category mapping equation for classification mapping to obtain the net profit data matrix for the selected year; S32, calculating the average annual net profit data of each pop-up store to be selected at multiple time points in the data matrix of net profit to be selected, to obtain an average data set of net profit to be selected; S33. Set an annual net profit site selection standard threshold; extract the pop-up store sites and corresponding annual net profit average data corresponding to the annual net profit site selection standard threshold that is greater than or equal to the annual net profit site selection standard threshold from the annual net profit average data set to be selected, and obtain a pop-up store preliminary site set and an annual net profit average preliminary data set.

7. A method for digital site selection management of a pop-up store based on multiple site selection according to claim 6, characterized in that: The S4 comprises the following steps: S41, setting a pop-up store construction cost threshold, a coverage threshold, a cost of constructing a pop-up store at each pop-up store preliminary selection point in the pop-up store preliminary selection point set, and a coverage range of constructing a pop-up store at each pop-up store preliminary selection point in the pop-up store preliminary selection point set, to obtain a preliminary construction cost data set and a preliminary coverage data set; S42, constructing a 0-1 integer programming model according to the annual net profit average preliminary data set, the pop-up store construction cost threshold, the coverage threshold, the preliminary construction cost data set, and the preliminary coverage data set; S43, solving the 0-1 integer programming model to obtain a set of construction parameters.

8. The method for digital site selection and management of a pop-up store based on multiple site selection according to claim 7, characterized in that: The S43 comprises the following steps: S431, constructing a second tuna population; setting the maximum number of iterations of the second tuna population to , the current number of iterations is , respectively recorded as the second maximum number of iterations and the second current number of iterations; S432, setting the initial position of each tuna in the second tuna population according to the objective function and the constraint condition group of the 0-1 integer programming model to obtain a second initial position matrix; S433, using the objective function of the 0-1 integer programming model as the fitness function of the second tuna population; S434, start iteration; in each round of iteration, use the fitness function of the second tuna population to calculate the fitness value of the position of each tuna updated in the previous round of iteration, and obtain a fourth fitness value set; use the maximum fitness value in the fourth fitness value set and the corresponding initial position as the fourth global optimal fitness value and the fourth global optimal position respectively; update the position of each tuna updated in the previous round of iteration again according to the fourth global optimal fitness value and the fourth global optimal position in conjunction with the constraint condition group of the 0-1 integer programming model; S435, when When , the iteration is stopped to obtain the second final global optimal position; the second final global optimal position is used as the pruning parameter set.

9. A method for digital site selection management of a pop-up store based on multiple site selection according to claim 8, characterized in that: The S5 comprises the following steps: S51, extracting the pop-up store preliminary selection points corresponding to the construction parameters in the construction parameter set that are not 0 according to the pop-up store preliminary selection point set, to obtain the pop-up store final selection point set; S52: Select a location for a pop-up store according to the final set of selected locations for the pop-up store.

10. A system for implementing a digital site selection management method for a pop-up store based on multiple site selection as claimed in any one of claims 1 to 9, characterized in that: It includes a location selection influencing factor type setting module, a location selection influencing factor data collection module, an existing pop-up store data collection module, a mapping equation construction module, a classification mapping module, a first location selection point screening module, an integer programming model construction module, a solution module, a second location selection point screening module and a location selection module; The location selection influencing factor type setting module is used to set the types of influencing factors for location selection of multiple pop-up stores to obtain a location selection influencing factor type set; The location influencing factor data collection module is used to collect location influencing factor data of multiple pop-up store sites to be selected according to the location influencing factor type set to obtain a location influencing factor data matrix set; The existing pop-up store data collection module is used to collect location influencing factor data and corresponding annual net profit data of multiple existing pop-up stores according to the location influencing factor type set, and obtain an average location influencing factor data matrix and an existing annual net profit data set; The mapping equation construction module is used to construct a final category mapping equation using an average location influencing factor data matrix and an existing annual net profit data set; The classification mapping module is used to classify and map the location influencing factor data matrix set using the final classification mapping equation and calculate the average value to obtain the average data set of net profit for the selected year; The first site selection point screening module is used to screen multiple pop-up store sites according to the average net profit data set of the selected year to obtain a preliminary site set of pop-up stores; The integer programming model is used to construct a module to construct a 0-1 integer programming model according to the construction cost data, coverage data and annual net profit data corresponding to each pop-up store preliminary selection point in the pop-up store preliminary selection point set; The solution module is used to solve the 0-1 integer programming model to obtain a set of repair parameters; The second site selection point screening module is used to screen multiple pop-up store preliminary selection points according to the pop-up store preliminary selection point set and the construction parameter set to obtain a final pop-up store selection point set; The site selection module is used to select a site for a pop-up store based on the final site selection set for the pop-up store.

Images