Auxiliary site selection method, equipment and medium for convenient service facilities

Abstract

The embodiments of this specification disclose an auxiliary site selection method, device and medium for convenience service facilities, which relate to the field of data processing technology. The method includes: obtaining candidate address data of multiple candidate addresses corresponding to the convenience service facility, and site selection influence data corresponding to each candidate address; determining the current auxiliary site selection model corresponding to each candidate address based on the candidate address data, the site selection influence data and a pre-built initial auxiliary site selection model; generating service demand parameters and service competition parameters through a data processing operator in the current auxiliary site selection model corresponding to each candidate address; obtaining the current service facility data of the convenience service facility, and determining the site selection decision score corresponding to each candidate address through a data processing operator based on the current service facility data, candidate address data, site selection influence data, service demand parameters and service competition parameters; and assisting the convenience service facility in site selection through the site selection decision score corresponding to each candidate address.

Description

Technical Field

[0001] This specification relates to the field of data processing technology, and in particular to an auxiliary site selection method, equipment, and medium for convenient service facilities. Background Art

[0002] Convenience service facilities are crucial infrastructure that provide convenient, fast, and comfortable living services to community residents. They can be divided into two categories based on the different groups they serve: one is facilities for all community residents, such as community medical and health clinics, cultural and sports venues; the other is welfare-oriented facilities for special resident groups, such as senior citizen cafeterias, life care centers, disability care centers, and rehabilitation centers. The construction of these types of convenience service facilities can make residents' lives more comfortable and convenient, enhance the quality and efficiency of community services, and generate positive social benefits. Site planning is a prerequisite for the rational construction of convenience service facilities and a crucial component and decision-making process. It guides the rational placement of convenience service facilities based on prudent principles. While meeting practical constraints, scientific methods are used to determine the optimal spatial location based on relevant indicators and data. Effective site planning for convenience service facilities not only impacts subsequent utilization efficiency and service quality, but also the convenience and practicality of the facilities. Therefore, addressing the site planning of convenience service facilities is of vital practical significance.

[0003] As a complex systemic project, the site selection and planning of public service facilities involves not only multiple influencing factors, but also complex, nonlinear coupling relationships among these factors, often interrelated and influencing each other. The site selection process must consider not only the number of service recipients within the proposed address's service coverage area, the size of the service provider, and the distance from the proposed address, as well as the interplay between these factors. It also considers the number of competitors within the proposed address's competitive influence area, the scale of their service provision, and their distance from the proposed address, as well as the interplay between these factors. Existing site selection methods fail to consider these multiple factors and the interrelationships between them, resulting in low site selection accuracy. Summary of the Invention

[0004] One or more embodiments of this specification provide an auxiliary site selection method, equipment and medium for convenience service facilities, which are used to solve the following technical problems: in existing site selection methods, multiple influencing factors and the correlation between each influencing factor are not taken into account, resulting in low site selection accuracy.

[0005] One or more embodiments of this specification adopt the following technical solutions:

[0006] One or more embodiments of the present specification provide an auxiliary site selection method for a convenience service facility, the method comprising: obtaining candidate address data of a plurality of candidate addresses corresponding to the convenience service facility, and site selection impact data corresponding to each candidate address, wherein the site selection impact data includes service object demand data and competitor object data; determining a current auxiliary site selection model corresponding to each candidate address based on the candidate address data, the site selection impact data, and a pre-constructed initial auxiliary site selection model, wherein the auxiliary site selection model includes a plurality of data processing operators; and determining a current auxiliary site selection model corresponding to each candidate address through the data in the current auxiliary site selection model corresponding to each candidate address. The data processing operator is used to quantify the site selection impact data to generate service demand parameters and service competition parameters; the current service facility data of the convenience service facility is obtained, and the impact of multiple candidate addresses of the convenience service facility is quantified through the data processing operator according to the current service facility data, the candidate address data, the site selection impact data, the service demand parameters and the service competition parameters, and the site selection decision score corresponding to each candidate address is determined; the site selection decision score corresponding to each candidate address of the convenience service facility is used to assist the convenience service facility in site selection.

[0007] Furthermore, before determining the current auxiliary site selection model corresponding to each candidate address based on the candidate address data, the site selection impact data and the pre-constructed initial auxiliary site selection model, the method also includes: pre-modeling the candidate addresses, service objects and competing objects of the convenience service facilities in the candidate area to obtain the candidate nodes corresponding to the candidate addresses, the demand nodes corresponding to the service objects and the competing nodes corresponding to the competing objects; constructing a node data set based on the candidate nodes, the demand nodes and the competing nodes, wherein the node data set includes a candidate node data set, a demand node data set and a competing node data set; constructing multiple data processing operators, wherein the data processing operators include a demand quantification operator, a competition quantification operator, a demand discount operator, a competition discount operator, a demand scoring operator, a competition scoring operator and a decision scoring operator; and constructing the initial auxiliary site selection model through the node data set and the multiple data processing operators.

[0008] Furthermore, according to the candidate address data, the site selection impact data and the pre-built initial auxiliary site selection model, the current auxiliary site selection model corresponding to each candidate address is determined, specifically including: obtaining the spatial position coordinates in the candidate address data, and constructing a current candidate node data set through the spatial position coordinates of each candidate address, wherein the spatial position coordinates include latitude data and longitude data; obtaining the service object demand data and the competitor object data in the site selection impact data, determining the service group scale data and the service object spatial position coordinates in the service object demand data, and determining the competitive service provision scale data and the competitive object spatial position coordinates in the competitive object data; constructing the current demand node data through the service group scale data and the service object spatial position coordinates set, and construct a current competition node data set through the competition service provision scale data and the spatial position coordinates of the competition object; determine the demand quantification operator, competition quantification operator, demand discount operator, competition discount operator, demand scoring operator, competition scoring operator and decision scoring operator in the data processing operator; obtain the service coverage radius and competition influence radius in the current service facility data of the convenience service facility, and calculate multiple parameters in the data processing operator according to the service coverage radius and the competition influence radius in a preset manner to determine the current data processing operator; determine the current auxiliary site selection model corresponding to each of the candidate addresses through the current candidate node data set, the current demand node data set, the current competition node data set and multiple current data processing operators.

[0009] Furthermore, according to a preset method, multiple parameters in the data processing operator are calculated based on the service coverage radius and the competition influence radius, specifically including: using a subjective right confirmation method or an objective right confirmation method to determine the weight coefficient corresponding to each feature data in the demand node data to determine the parameters of the demand quantification operator; using a subjective right confirmation method or an objective right confirmation method to determine the weight coefficient corresponding to each feature data in the competition node data to determine the parameters of the competition quantification operator; using a subjective right confirmation method to determine the demand scoring weight coefficient and the competition scoring weight coefficient in the decision scoring operator; obtaining the service group travel parameters in the service object demand data; based on the service group travel parameters and the The service coverage radius is used to determine the core service radius and the core service scale ratio of the convenience service facility, so as to determine the parameters of the demand discount operator through the core service radius and the core service scale ratio, wherein the core service scale ratio is the ratio of the size of the service group provided within the core service radius to the size of all service groups provided within the service coverage radius; the competition influence radius is determined through the service coverage radius of the convenience service facility, so as to determine the parameters of the competition discount operator through the competition influence radius; the positive ideal value of demand in the demand scoring operator and the negative ideal value of competition in the competition scoring operator are determined through the node ideal distribution diagram method.

[0010] Furthermore, the location impact data is quantified through the data processing operator in the current auxiliary location selection model corresponding to each of the candidate addresses to generate service demand parameters and service competition parameters, specifically including: quantifying the service demand data in the location impact data through the demand quantification operator in the data processing operator to generate corresponding service demand parameters; quantifying the service competition data in the location impact data through the competition quantification operator in the data processing operator to generate corresponding service competition parameters.

[0011] Furthermore, based on the current service facility data, the candidate address data, the site selection impact data, the service demand parameters and the service competition parameters, the impact of the multiple candidate addresses of the convenience service facilities is quantified, and the site selection decision score corresponding to each candidate address is determined, specifically including: calculating the service demand score and service competition score corresponding to each candidate address according to the current service facility data in the current service facility data, the spatial position coordinates of the candidate address data, the site selection impact data, the competition demand parameters and the service demand parameters through the data processing operator; and determining the site selection decision score corresponding to each candidate address according to the service demand score and the service competition score through the decision scoring operator in the data processing operator.

[0012] Furthermore, the data processing operator is used to calculate the service demand score and service competition score corresponding to each of the candidate addresses based on the service coverage radius in the current service facility data, the spatial position coordinates of the candidate address data, the site selection impact data, the competition demand parameter and the service demand parameter, specifically including: calculating the demand discount coefficient generated by each demand node for each of the candidate addresses based on the service coverage radius in the current service facility data of each of the candidate addresses, the spatial position coordinates of the service object in the service object demand data in the site selection impact data and the spatial position coordinates in the candidate address data through the demand discount operator in the data processing operator; calculating the demand discount coefficient generated by each demand node for each of the candidate addresses based on the competition discount operator in the data processing operator. According to the competition impact radius in the current service facility data of each candidate address, the spatial position coordinates of the competition object in the competition object data in the site selection impact data and the spatial position coordinates in the candidate address data, calculate the competition discount coefficient generated by each competition node for each candidate address; use the demand scoring operator in the data processing operator to generate the demand score generated by all demand nodes within the service coverage radius for the candidate address according to the demand discount coefficient generated by each demand node for each candidate address; use the competition scoring operator in the data processing operator to generate the competition score generated by all competition nodes within the service coverage radius for the candidate address according to the competition discount coefficient generated by each competition node for each candidate address.

[0013] Furthermore, the decision scoring operator in the data processing operator is used to determine the site selection decision score corresponding to each of the candidate addresses according to the service demand score and the service competition score, specifically including: dcs (P i , D, C) = θ d f ds (P i , D)+θ c sgn(f ds (P i ,D))f cs (P i , C), calculating the site selection decision score corresponding to each of the candidate addresses according to the service demand score and the service competition score; wherein the f dcs (P i ,D,C) is the decision scoring operator, P i is the candidate node data association vector, D is the demand node data set, C is the competition node data set, θ d is the demand score weight coefficient, θ c is the competition score coefficient, f ds (P i ,D) is the node to be selected Pi The service demand score, f cs (P i ,C) is the node to be selected P i The service competition score is , and sgn() is the symbolic function.

[0014] One or more embodiments of this specification provide an auxiliary site selection device for a convenience service facility, including:

[0015] at least one processor; and,

[0016] a memory communicatively connected to the at least one processor; wherein,

[0017] The memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to:

[0018] Obtain candidate address data of multiple candidate addresses corresponding to a convenience service facility, and location influence data corresponding to each candidate address, wherein the location influence data includes service object demand data and competitor object data; determine a current auxiliary location model corresponding to each candidate address based on the candidate address data, the location influence data and a pre-constructed initial auxiliary location model, wherein the auxiliary location model includes multiple data processing operators; quantify the location influence data through the data processing operators in the current auxiliary location model corresponding to each candidate address to generate service demand parameters and service competition parameters; obtain current service facility data of the convenience service facility, and quantify the impact of multiple candidate addresses of the convenience service facility through the data processing operators based on the current service facility data, the candidate address data, the location influence data, the service demand parameters and the service competition parameters to determine a location decision score corresponding to each candidate address; assist the convenience service facility in location selection through the location decision score corresponding to each candidate address of the convenience service facility.

[0019] One or more embodiments of this specification provide a non-volatile computer storage medium storing computer-executable instructions, wherein the computer-executable instructions are configured to:

[0020] Obtain candidate address data of multiple candidate addresses corresponding to a convenience service facility, and location influence data corresponding to each candidate address, wherein the location influence data includes service object demand data and competitor object data; determine a current auxiliary location model corresponding to each candidate address based on the candidate address data, the location influence data and a pre-constructed initial auxiliary location model, wherein the auxiliary location model includes multiple data processing operators; quantify the location influence data through the data processing operators in the current auxiliary location model corresponding to each candidate address to generate service demand parameters and service competition parameters; obtain current service facility data of the convenience service facility, and quantify the impact of multiple candidate addresses of the convenience service facility through the data processing operators based on the current service facility data, the candidate address data, the location influence data, the service demand parameters and the service competition parameters to determine a location decision score corresponding to each candidate address; assist the convenience service facility in location selection through the location decision score corresponding to each candidate address of the convenience service facility.

[0021] At least one of the above-mentioned technical solutions adopted in the embodiments of this specification can achieve the following beneficial effects: through the above-mentioned technical solution, the current auxiliary site selection model corresponding to each candidate address is determined based on the candidate address data, site selection impact data and the pre-constructed initial auxiliary site selection model, and an auxiliary site selection model composed of a data set and a data processing operator is proposed on the basis of fully considering the influencing factors such as service demand, service competition, spatial location, effective range, and following the principles of comprehensiveness, feasibility, and standardization; through the auxiliary site selection model of convenient service facilities, the site selection data corresponding to the candidate address of the convenient service facility is calculated as a site selection decision score that can reflect the expected service demand and the pros and cons of potential service competition, effectively solving the need to fully consider various influencing factors in the candidate area, reasonably analyze the relationship between different influencing factors, construct an influencing factor system, determine related indicator data, and construct a site selection model based on the indicator data that can provide site selection decision guidance, providing reasonable decision guidance and effective technical support for the site selection planning of convenient service facilities. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the embodiments of this specification or the technical solutions in the prior art, the following briefly introduces the drawings required for the embodiments or the description of the prior art. Obviously, the drawings described below are only some of the embodiments described in this specification. For those skilled in the art, other drawings can be obtained based on these drawings without inventive work. In the drawings:

[0023] Figure 1A flowchart of an auxiliary site selection method for a convenience service facility provided in an embodiment of this specification;

[0024] Figure 2 A schematic diagram of a model framework of an auxiliary site selection model provided in an embodiment of this specification;

[0025] Figure 3 A diagram showing the relationship between a discount coefficient and distance provided in an embodiment of this specification;

[0026] Figure 4 An ideal distribution diagram of demand nodes provided in the embodiment of this specification;

[0027] Figure 5 A negative ideal distribution diagram of competing nodes provided in an embodiment of this specification;

[0028] Figure 6 A schematic diagram of the structure of an auxiliary site selection system for a convenience service facility provided in an embodiment of this specification;

[0029] Figure 7 This is a structural diagram of an auxiliary site selection device for a convenience service facility provided in an embodiment of this specification. DETAILED DESCRIPTION

[0030] To help those skilled in the art better understand the technical solutions in this specification, the following will provide a clear and complete description of the technical solutions in the embodiments of this specification, in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of this specification, not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of this specification without creative work should fall within the scope of protection of this specification.

[0031] Convenience service facilities are crucial infrastructure that provide convenient, fast, and comfortable living services to community residents. They can be divided into two categories based on the different groups they serve: one is facilities for all community residents, such as community medical and health clinics, cultural and sports venues; the other is welfare-oriented facilities for special resident groups, such as senior citizen cafeterias, life care centers, disability care centers, and rehabilitation centers. The construction of these types of convenience service facilities can make residents' lives more comfortable and convenient, enhance the quality and efficiency of community services, and generate positive social benefits. Site planning is a prerequisite for the rational construction of convenience service facilities and a crucial component and decision-making process. It guides the rational placement of convenience service facilities based on prudent principles. While meeting practical constraints, scientific methods are used to determine the optimal spatial location based on relevant indicators and data. Effective site planning for convenience service facilities not only impacts subsequent utilization efficiency and service quality, but also the convenience and practicality of the facilities. Therefore, addressing the site planning of convenience service facilities is of vital practical significance.

[0032] As a complex systemic project, the site selection and planning of public service facilities involves not only multiple influencing factors, but also complex, nonlinear coupling relationships among these factors, often interrelated and influencing each other. The site selection process must consider not only the number of service recipients within the proposed address's service coverage area, the size of the service provider, and the distance from the proposed address, as well as the interplay between these factors. It also considers the number of competitors within the proposed address's competitive influence area, the scale of their service provision, and their distance from the proposed address, as well as the interplay between these factors. Existing site selection methods fail to consider these multiple factors and the interrelationships between them, resulting in low site selection accuracy.

[0033] The embodiments of this specification provide an auxiliary site selection method for a convenience service facility. It should be noted that the execution subject in the embodiments of this specification can be a server or any device with data processing capabilities. Figure 1 A flowchart of an auxiliary site selection method for a convenience service facility provided in an embodiment of this specification is shown as follows: Figure 1 As shown, it mainly includes the following steps:

[0034] Step S101: Acquire candidate address data of a plurality of candidate addresses corresponding to convenient service facilities, and location selection impact data corresponding to each candidate address.

[0035] The location selection impact data includes service object demand data and competitor object data;

[0036] In one embodiment of the present specification, the factors affecting the site selection and the required data are determined, and the service objects of the convenience service facilities are single residential buildings, residential areas or communities, and the service groups are residents or a certain type of special residents among the service objects. The service demand of the service objects is an important factor affecting the site selection planning, which can be measured by the size of the service group they have. The larger the service group owned by the service object, the greater its service demand, and the greater the positive impact on the site selection of the convenience service facilities. In order to reasonably use the size of the service group to reflect the actual situation of the service demand, the service groups can be divided into a detailed manner according to the service content and nature of the convenience service facilities according to age, physical condition, health status, family structure, economic situation and other conditions to obtain a number of data as site selection data. It should be noted that service demand is a positive site selection influencing factor for the site selection of convenience service facilities, and the corresponding site selection data are also efficiency-based data. For example, for convenience service facility A that serves the elderly, the service group can be divided into 20 location data that can reflect the size of the service group based on physical condition, family structure, age and other conditions: empty-nest elderly, elderly living alone, disabled elderly, elderly widowed and widowed, and other elderly people. Each category of elderly people can be further divided into four categories: 60 to 70 years old, 70 to 80 years old, 80 to 90 years old, and over 90 years old.

[0037] The competitors of convenience service facilities are existing convenience service facilities of the same type. Service competition from competitors is an important factor influencing site selection planning and can be measured by the scale of service provision. The larger the scale of service provision of the competitor, the greater the service competition, and the greater the negative impact on the site selection of the convenience service facility. To reasonably use the service provision scale to describe the potential situation of service competition, data such as the number of service personnel, number of service products, average number of service visits, and maximum number of passengers that can reflect service capabilities can be used as site selection data. It is worth noting that service competition is a negative factor influencing the site selection of convenience service facilities, and the corresponding site selection data are all cost-based data. For convenience service facility A, the above four service provision scale data can be selected as its site selection data in terms of service competition.

[0038] Spatial location is a key factor influencing service demand and competition. The closer the spatial location of a convenience service facility is to its intended recipients, the more convenient services are provided to the latter's target audience, and the smaller the discount on demand for the corresponding services. The further away a convenience service facility is from its competitors, the less the latter can influence the former, and the larger the discount on service competition. Specifically, site selection data that can reflect spatial location primarily includes the latitude and longitude data of the potential addresses for the service recipients, competitors, and convenience service facilities.

[0039] The effective scope is an important factor affecting service demand and service competition. The effective scope is a circular range with the convenience service facility as the center and a radius of a certain reasonable length, which mainly includes the service coverage scope and the competition influence scope. The service coverage scope is the effective scope in which the convenience service facility can provide services. Only the service objects within this scope can be provided with services. During the site selection process, the service coverage scope should include as many service objects with a larger service group as possible. The competition influence scope is the effective scope in which the convenience service facility is affected by competition. Only within this scope can it be affected by competitors. During the site selection process, the competition influence scope should include as few competitors with a larger service provision scale as possible. Specifically, the site selection data that can determine the effective scope include the service coverage radius and the competition influence radius.

[0040] In one embodiment of the present specification, the candidate address data of multiple candidate addresses corresponding to the convenience service facilities are obtained. The candidate address data are the spatial location coordinates of the multiple candidate addresses, which can be expressed in longitude and latitude. In addition, it is necessary to obtain the location influence data corresponding to each candidate address. The location influence data includes service object demand data and competitor data. The service object demand data includes service group size data and service object spatial location coordinates. The service group size data here can be selected based on the service content and nature of the convenience service facilities, and multiple data obtained by carefully dividing the service group according to age, physical condition, health status, family structure, economic situation and other conditions. The competitor data includes competitive service provision scale data and competitive object spatial location coordinates. The competitive service provision scale data refers to data that can reflect the service capacity, such as the number of service personnel, the number of service products, the average number of service personnel, the maximum number of service personnel, etc.

[0041] Step S102 : determining a current auxiliary site selection model corresponding to each candidate address based on the candidate address data, the site selection impact data and the pre-built initial auxiliary site selection model.

[0042] Among them, the auxiliary site selection model includes multiple data processing operators.

[0043] Before determining the current auxiliary site selection model corresponding to each candidate address based on the candidate address data, the site selection impact data and the pre-constructed initial auxiliary site selection model, the method also includes: pre-modeling the candidate address, service object and competitor of the convenience service facility in the candidate area to obtain the candidate node corresponding to the candidate address, the demand node corresponding to the service object and the competition node corresponding to the competitor; constructing a node data set based on the candidate node, the demand node and the competition node, wherein the node data set includes a candidate node data set, a demand node data set and a competition node data set; constructing multiple data processing operators, wherein the data processing operators include a demand quantification operator, a competition quantification operator, a demand discount operator, a competition discount operator, a demand scoring operator, a competition scoring operator and a decision scoring operator; and constructing the initial auxiliary site selection model through the node data set and the multiple data processing operators.

[0044] Because the site selection and planning of public service facilities involves multiple factors, the site selection process must consider not only the number of service recipients within the proposed location's service coverage area, the size of the service provider, and the distance from the proposed location, as well as the interplay between these factors. It also considers the number of competitors within the proposed location's competitive influence area, the scale of their service offerings, and their distance from the proposed location, as well as the interplay between these factors. Furthermore, the complex relationships among these factors must be summarized into actionable data processing logic, and the data processing operators and decision-making support models constructed based on this logic must be feasible. Finally, site selection data must be standardized based on its characteristics to obtain standardized site selection data. The resulting data should then be optimized and selected based on unified criteria. The goal of public service facility site selection planning is to, based on adherence to site selection principles, integrate and calculate a site selection decision score that reflects expected service demand and potential service competition, providing a reasonable reference for site selection decision-making.

[0045] In one embodiment of the present specification, an auxiliary site selection model consisting of a node data set and a data processing operator is constructed. In the candidate area, the candidate address of the convenience service facility, the service object, and the competing object are modeled as a candidate node, a demand node, and a competing node, respectively; the spatial location data of the service object and the standardized service group scale data are used as the demand node data, the spatial location data of the competing object and the standardized service provision scale data are used as the competing node data, and the spatial location data of the candidate address of the convenience service facility is used as the candidate node data. Figure 2 A schematic diagram of a model framework of an auxiliary site selection model provided in an embodiment of this specification, such as Figure 2 As shown in Figure 2, the initial auxiliary site selection model is:

[0046]

[0047] First, construct the node dataset. represents the candidate node dataset, P i is the data association vector of the candidate node, and The latitude and longitude of the spatial location coordinates of the candidate node corresponding to the candidate address.

[0048] Denotes the demand node dataset, D i represents the demand node data association vector, Represents the various subdivision data in the standardized service group size data, and It is the latitude and longitude in the spatial coordinates corresponding to the required node.

[0049] represents the competition node dataset, C i is the competition node data association vector, Represents the various subdivided data in the standardized service provision scale data. and is the latitude and longitude in spatial coordinates.

[0050] Secondly, construct the data processing operator. dq :D→[0,+∞) represents the demand quantization operator, f dq (D i ) means D i The demand is calculated as follows:

[0051]

[0052] in, It is the weight coefficient corresponding to the k-th feature data of the demand node data association vector.

[0053] f cq :C→[0,+∞) represents the competitive quantization operator, f cq (C i ) means C i The competition amount is calculated as follows:

[0054]

[0055] in, It is the weight coefficient corresponding to the k-th feature data of the competition node data association vector.

[0056] f dd :P×D→(0,1) represents the demand discount operator, fdd (P i , D j ) means D j About P i The demand discount coefficient is calculated as follows:

[0057]

[0058] Among them, R d is the service coverage radius of the convenience service facilities, λ∈(0,1) is the core service range (the distance to the convenience service facilities is less than or equal to 0.5R d The proportion of the group served within the range (the corresponding radius is called the core service radius) to the total group served; d:R 4 →[0, +∞) represents the distance calculation function based on spatial position data. d(x1, y1, x2, y2) represents the distance between the latitude and longitude coordinate points (x1, y1) and (x2, y2). The calculation formula is as follows:

[0059]

[0060] Among them, R e =6371.293km is the average radius of the earth.

[0061] f cd :P×C→(0,1) represents the competition discount operator, f cd (P i ,C j ) means C j About P i The competition discount coefficient is calculated as follows:

[0062]

[0063] Among them, R c The competitive influence radius of the convenience service facilities is usually set as R c =2R d .

[0064] f ds :P×{D}→[0,1] represents the demand scoring operator, f ds (P i ,D) represents the candidate node P i The demand score is calculated as follows:

[0065]

[0066] in, Indicates that at the candidate node P i The set of demand nodes within the service coverage area, γd The ideal value for demand.

[0067] f cs :P×{C}→[0,1] represents the competitive scoring operator, f cs (P i ,C) represents the candidate node P i The competitive score is calculated as follows:

[0068]

[0069] in, Indicates that at the candidate node P i The set of competing nodes within the competitive influence range, γ c Negative ideal value for competition.

[0070] f dcs :P×{D}×{C}→[0,1] represents the decision scoring operator, f dcs (P i ,D,C) represents the candidate node P i The decision score is calculated as follows:

[0071] f dcs (P i ,D,C)=θ d f ds (P i ,D)+θ c sgn(f ds (P i ,D))f cs (P i ,C),

[0072] Where sgn(·) is the sign function, θ d and θ c are the weight coefficients of demand score and competition score respectively.

[0073] According to the candidate address data, the site selection impact data and the pre-built initial auxiliary site selection model, the current auxiliary site selection model corresponding to each candidate address is determined, specifically including: obtaining the spatial position coordinates in the candidate address data, and constructing a current candidate node data set through the spatial position coordinates of each candidate address, wherein the spatial position coordinates include latitude data and longitude data; obtaining the service object demand data and the competitor object data in the site selection impact data, determining the service group scale data and the service object spatial position coordinates in the service object demand data, and determining the competitive service provision scale data and the competitive service object spatial position coordinates in the competitor object data; constructing the current demand node data through the service group scale data and the service object spatial position coordinates The method comprises the following steps: obtaining a set of competitive service data and constructing a current competitive node data set through the competitive service provision scale data and the competitive service spatial location coordinates; determining the demand quantification operator, competition quantification operator, demand discount operator, competition discount operator, demand scoring operator, competition scoring operator and decision scoring operator in the data processing operator; obtaining the service coverage radius and competition influence radius in the current service facility data of the convenience service facility, and calculating multiple parameters in the data processing operator according to the service coverage radius and the competition influence radius in a preset manner to determine the current data processing operator; determining the current auxiliary site selection model corresponding to each candidate address through the current candidate node data set, the current demand node data set, the current competitive node data set and multiple current data processing operators.

[0074] According to the preset method, multiple parameters in the data processing operator are calculated based on the service coverage radius and the competition influence radius, specifically including: using the subjective right confirmation method or the objective right confirmation method to determine the weight coefficient corresponding to each feature data in the demand node data, so as to determine the parameters of the demand quantification operator; using the subjective right confirmation method or the objective right confirmation method to determine the weight coefficient corresponding to each feature data in the competition node data, so as to determine the parameters of the competition quantification operator; using the subjective right confirmation method to determine the demand score weight coefficient and the competition score weight coefficient in the decision scoring operator; obtaining the service group travel parameters in the service object demand data; based on the service group travel parameters and The service coverage radius is used to determine the core service radius and the core service scale ratio of the convenience service facility, and the parameters of the demand discount operator are determined through the core service radius and the core service scale ratio, wherein the core service scale ratio is the ratio of the size of the service group provided within the core service radius to the size of all service groups provided within the service coverage radius; the competition influence radius is determined through the service coverage radius of the convenience service facility, and the parameters of the competition discount operator are determined through the competition influence radius; the positive ideal demand value in the demand scoring operator and the negative ideal competition value in the competition scoring operator are determined through the node ideal distribution diagram method.

[0075] In one embodiment of this specification, first, it is necessary to determine the weight parameters in the demand quantification operator, competition quantification operator, and decision scoring operator, namely, α k , β k ,θ d and θ c . The calculation methods include subjective right confirmation method and objective right confirmation method. Regarding the subjective right confirmation method, the hierarchical analysis method can be used. The main steps include: establishing an indicator hierarchy model based on the indicator category of the service group scale data of the node data association vector; relevant professionals use the indicator pairwise comparison method to refer to the Saaty nine-level scale table to construct a judgment matrix based on their professional knowledge, experience and specific needs of the actual consideration of the problem; the column data of the judgment matrix are summed and normalized, and the weight of each indicator is determined using the arithmetic mean method; the judgment matrix is ​​tested for consistency based on the consistency ratio calculated by the weight. If the test fails, the judgment matrix needs to be adjusted and the weights recalculated according to the second step. In practical applications, in order to make the determined weights more reasonable, multiple relevant professionals can use the hierarchical analysis method to determine the weights and calculate the average weights after integration and summary.

[0076] Regarding objective weighting methods, the entropy weighting method can be used. The main steps include: constructing a judgment matrix based on the node data association vector, normalizing the columns of the matrix using the corresponding operators in the range method for benefit-based and cost-based indicators, summing and normalizing the columns of the resulting standard matrix, and calculating the information entropy corresponding to each column of data. The weights of various indicators are determined by calculating the redundancy of the information entropy.

[0077] Continuing with the example of the convenience service facility A in the previous example, for the site selection planning of the convenience service facility A, the weight parameters in the data processing operator are determined using the hierarchical analysis method as follows:

[0078]

[0079] For the relevant parameters in the discount operator, it is necessary to determine the service coverage radius of the convenience service facilities and the proportion of the groups provided with services within the service core area to the total groups provided with services. It should be noted that the discount operators here refer to the demand discount operator and the competition discount operator.

[0080] Typically, the service population of a convenience service facility primarily comes from those within a 3,000-meter radius. The service coverage radius can be initially set at 3,000 meters. If specific requirements arise, adjustments can be made based on the inherent characteristics of the service population, travel modes, travel time, and other constraints. During this adjustment process, it must be ensured that the population served within the core service area accounts for at least 80% of the total population served.

[0081] Take the convenience service facility A as an example. For the convenience service facility A, the main travel data of its service group is walking and the average walking speed is 1.25 meters per second to 1.32 meters per second. Considering that the time spent on a one-way trip to seek services should not exceed 20 minutes, this data can be obtained through survey data or other means. The corresponding parameters can be set as follows: R d =2000,λ=0.9. Thus, we can get R c =2R d =4000, Figure 3 A diagram showing the relationship between the discount coefficient and the distance provided in the embodiment of this specification is shown as follows: Figure 3 As shown in the figure, the discount coefficient calculated by the discount operator decreases as the distance increases. When the distance between the service object and the address to be selected is greater, the demand discount coefficient is smaller, that is, the demand impact on the address to be selected is smaller. When the distance between the service object and the address to be selected exceeds 2000 meters, the obtained discount coefficient is close to 0, that is, it exceeds the service coverage radius; when the distance between the competition object and the address to be selected is greater, the competition discount coefficient is smaller, that is, the competition impact on the address to be selected is smaller.

[0082] For the relevant parameters in the scoring operator, it is necessary to determine the positive ideal value of demand and the negative ideal value of competition. The main method is the node ideal distribution diagram method. The scoring operators here include the demand scoring operator and the competition scoring operator. Considering the limited service coverage, a positive ideal distribution diagram can be constructed based on the reasonable shape of the actual area occupied by the service object and the service coverage radius of the convenience service facilities to reflect the demand nodes within the service coverage of the candidate node when the distribution density is high. The positive ideal value of demand is the product of the sum of the demand discount coefficients of all demand nodes within the service coverage of the candidate node in the distribution diagram and the average or maximum demand volume. Considering the limited competition influence range, a negative ideal distribution diagram can be constructed based on the competition influence radius of the convenience service facilities and the service core radius to reflect the competition nodes within the competition influence range of the candidate node when the distribution density is high. The negative ideal value of competition is the product of the sum of the competition discount coefficients of all competition nodes within the competition influence range of the candidate node in the distribution diagram and the average or maximum competition volume.

[0083] For the convenience service facility A, after setting the service coverage radius to 2000 meters and the actual corresponding area of ​​the demand node to a square area of ​​400 meters by 400 meters, the ideal distribution map of the demand nodes can be determined according to the above method. Figure 4 This is a positive ideal distribution diagram of demand nodes provided in the embodiment of this specification. After setting the competition impact radius to 4000 meters and considering the service range of the competition node as a circular range with a radius of 1000 meters, the negative ideal distribution diagram of the competition node can be determined according to the above method. Figure 5This is a negative ideal distribution diagram of competition nodes provided in the embodiments of this specification. Based on symmetry, the demand nodes in the distribution diagram can be divided into 10 different types based on distance, and the competition nodes can be divided into 3 different types. Combined with the determined demand discount operator, the number of each demand node and the corresponding demand discount coefficient are obtained as follows:

[0084]

[0085] Combined with the determined competition discount operator, the number of each type of competition nodes and the corresponding competition discount coefficient are obtained as follows:

[0086]

[0087]

[0088] In summary, we can calculate γ d =18.1125l d and γ c =3.3623l c , where l d and l c are the average or maximum values ​​of demand and competition, respectively. It should be noted that the positive ideal demand value refers to the optimal service target size. Since the optimal state for the competition ideal value is when there are no competitors, that is, when the number of competitors is zero, the competition ideal value is set to the negative ideal competition value when determining the parameters in the competition scoring operator.

[0089] Step S103 : quantifying the location influence data by using the data processing operator in the current auxiliary location selection model corresponding to each candidate address to generate service demand parameters and service competition parameters.

[0090] The location influence data is quantified by the data processing operator in the current auxiliary location selection model corresponding to each of the candidate addresses to generate service demand parameters and service competition parameters, specifically including: quantifying the service demand data in the location influence data by the demand quantification operator in the data processing operator to generate corresponding service demand parameters; quantifying the service competition data in the location influence data by the competition quantification operator in the data processing operator to generate corresponding service competition parameters.

[0091] In one embodiment of the present specification, the formula Quantify the service demand data in the location impact data and generate the corresponding service demand quantity, that is, the service demand parameter. The service competition data in the location impact data is quantified to generate the service competition quantity, namely the service competition parameter.

[0092] Step S104, obtain the current service facility data of the convenience service facilities, and through the data processing operator, quantify the impact of multiple candidate addresses of the convenience service facilities based on the current service facility data, candidate address data, site selection impact data, service demand parameters and service competition parameters, and determine the site selection decision score corresponding to each candidate address.

[0093] According to the current service facility data, the candidate address data, the site selection impact data, the service demand parameter and the service competition parameter, the impact of the multiple candidate addresses of the convenience service facility is quantified, and the site selection decision score corresponding to each candidate address is determined, specifically including: using the data processing operator, according to the current service facility data in the current service facility data, the spatial position coordinates of the candidate address data, the site selection impact data, the competition demand parameter and the service demand parameter, calculating the service demand score and the service competition score corresponding to each candidate address; using the decision scoring operator in the data processing operator, according to the service demand score and the service competition score, determining the site selection decision score corresponding to each candidate address.

[0094] Through the data processing operator, according to the service coverage radius in the current service facility data, the spatial position coordinates of the candidate address data, the site selection impact data, the competition demand parameter and the service demand parameter, the service demand score and service competition score corresponding to each candidate address are calculated, specifically including: through the demand discount operator in the data processing operator, according to the service coverage radius in the current service facility data of each candidate address, the spatial position coordinates of the service object in the service object demand data in the site selection impact data and the spatial position coordinates in the candidate address data, calculating the demand discount coefficient generated by each demand node for each candidate address; through the competition discount operator in the data processing operator, according to each The competition discount coefficient generated by each competing node for each of the candidate addresses is calculated based on the competition influence radius in the current service facility data of the candidate address, the competition object spatial position coordinates in the competition object data in the site selection influence data, and the spatial position coordinates in the candidate address data; the demand scoring operator in the data processing operator is used to generate the demand score generated by all demand nodes in the service coverage radius for the candidate address according to the demand discount coefficient generated by each demand node for each of the candidate addresses; the competition scoring operator in the data processing operator is used to generate the competition score generated by all competing nodes in the service coverage radius for the candidate address according to the competition discount coefficient generated by each competing node for each of the candidate addresses.

[0095] In one embodiment of the present specification, the demand discount coefficient, f dd (P i ,D j) means D j About P i The demand discount coefficient is calculated as follows: Among them, R d is the service coverage radius of the convenience service facilities, λ∈(0,1) is the core service scale ratio, that is, the core service range (the distance from the convenience service facilities is less than or equal to 0.5R d The proportion of the group served within the range (the corresponding radius is called the core service radius) to the total group served; d:R 4 →[0,+∞) represents the distance calculation function based on spatial location data. d(x1,y1,x2,y2) represents the distance between the latitude and longitude coordinate points (x1,y1) and (x2,y2), that is, the distance between the selected address and the service object. The calculation formula is as follows: R e = 6371.293 km is the average radius of the Earth. For example, there are demand nodes 1 and 2, both with a corresponding demand of 100. The distance between demand node 1 and the candidate node is 2000 meters, and the distance between demand node 2 and the candidate node is 2400 meters. Under the same demand, the influence of demand node 1 on the candidate node is greater than that of demand node 2. Here, the demand discount coefficient 1 corresponding to demand node 1 is greater than the demand discount coefficient 2 corresponding to demand node 2.

[0096] The competition discount coefficient is calculated by the competition discount operator in the data processing operator, f cd (P i ,C j ) means C j About P i The competition discount coefficient is calculated as follows:

[0097] Among them, R c The competitive influence radius of the convenience service facilities is usually set as R c =2R d It should be noted that the competition discount coefficient can be understood as a weight coefficient set for the service competition amount. For example, there are competition nodes 1 and 2, and their corresponding competition amounts are both 100. The distance between competition node 1 and the candidate node is 2000 meters, and the distance between competition node 2 and the candidate node is 2400 meters. Under the same competition amount, the influence of competition node 1 on the candidate node is greater than the influence of competition node 2 on the candidate node. Here, the competition discount coefficient 1 corresponding to competition node 1 is greater than the competition discount coefficient 2 corresponding to competition node 2.

[0098] The demand score of the candidate node corresponding to the candidate address is calculated through the demand score operator, f ds (Pi ,D) represents the candidate node P i The demand score is calculated as follows:

[0099]

[0100] Indicates that at the candidate node P i The set of demand nodes within the service coverage area, γ d is the ideal positive value of demand. It should be noted that since there are multiple service objects in the candidate area, that is, the service objects are in the form of a set, after calculating the demand quantity and demand discount coefficient of each service object within the service coverage of the candidate address, the demand score of the candidate address is generally obtained by weighted summation. However, in this case, the value range of the final value cannot be guaranteed and cannot provide a good decision-making reference. Therefore, according to the demand scoring operator, when scoring the expected service demand of the candidate address, the purpose of controlling the score generation range and providing a better decision-making reference can be achieved.

[0101] The competition score operator is used to calculate the competition score of the candidate node corresponding to the candidate address, f cs (P i ,C) represents the candidate node P i The competitive score is calculated as follows: in, Indicates that at the candidate node P i The set of competing nodes within the competitive influence range, γ c Negative ideal value for competition.

[0102] By using the decision scoring operator in the data processing operator, the site selection decision score corresponding to each candidate address is determined according to the service demand score and the service competition score, specifically including: dcs (P i ,D,C)=θ d f ds (P i ,D)+θ c sgn(f ds (P i ,D))f cs (P i ,C), calculate the site selection decision score corresponding to each candidate address based on the service demand score and the service competition score; where the f dcs (P i ,D,C) is the decision scoring operator, P i is the candidate node data association vector, D is the demand node data set, C is the competition node data set, θ d is the demand scoring weight coefficient. cis the competition score coefficient, f ds (P i ,D) is the node to be selected P i The service demand score, f cs (P i ,C) is the node to be selected P i The service competition score is , and sgn() is the symbolic function.

[0103] It should be noted that the sign function sgn() is a mathematical function used to determine the sign of a real number. If the input is a positive real number, the value of the sgn() function is 1. If the input is a negative real number, the value of the sgn() function is -1. If the input is 0 or zero, the value of the sgn() function is 0. Because in the decision scoring operator, there may be a situation where the service demand score is zero, but when the service demand score is zero, the obtained location decision score is only related to the service competition score. When the service demand score is 0, it has no reference significance, that is, there is no demand in this area, only competition, resulting in the obtained score cannot be used as a basis for location selection, so the sgn() function is set. After setting the sgn() function, f ds (P i ,D) is the node to be selected p i The service demand score of sgn(f ds (p i ,D)) is 0, the decision scoring operator is 0 as a whole; when the service demand score is not 0, sgn(f ds (P i ,D)) is 1.

[0104] Step S105 , assisting the convenience service facility in selecting a site by using the site selection decision score corresponding to each candidate address of the convenience service facility.

[0105] In one embodiment of the present specification, the site selection of the convenience service facility is assisted by the site selection decision score corresponding to each candidate address of the convenience service facility, and the address with the highest site selection decision score among multiple candidate addresses is selected as the final site.

[0106] Through the above technical solution, the current auxiliary site selection model corresponding to each candidate address is determined based on the candidate address data, site selection impact data and the pre-built initial auxiliary site selection model. Taking into full consideration the influencing factors such as service demand, service competition, spatial location, effective range, and adhering to the principles of comprehensiveness, feasibility, and standardization, an auxiliary site selection model composed of a data set and a data processing operator is proposed; through the auxiliary site selection model of convenient service facilities, the site selection data corresponding to the candidate address of the convenience service facility is calculated as a site selection decision score that can reflect the expected service demand and the pros and cons of potential service competition, effectively solving the need to fully consider various influencing factors in the candidate area, reasonably analyze the relationship between different influencing factors, construct an influencing factor system, determine related indicator data, and construct a site selection model based on the indicator data that can provide site selection decision guidance, providing reasonable decision guidance and effective technical support for the site selection planning of convenient service facilities.

[0107] Figure 6 This is a schematic diagram of the structure of an auxiliary site selection system for a convenience service facility provided in an embodiment of this specification, such as Figure 6As shown, the auxiliary site selection system includes a weighted calculation module, a discount calculation module, a scoring calculation module, and a data storage module. The weighted calculation module consists of a demand quantification operator and a competition quantification operator. Its main function is to quantify the service demand of service objects and the service competition of competitors. It calculates the various sub-data related to the service group size in the demand node data association vector into a demand quantity used to measure the expected service demand level, and calculates the various sub-data related to the service provision scale data in the competition node data association vector into a competition quantity used to measure the potential service competition level. The discount calculation module consists of a demand discount operator and a competition discount operator. Its main function is to quantify the connection information between the candidate address, service object, and competitor. It converts the longitude and latitude data in the demand node and candidate node data association vectors into the distance between the two and further calculates it into a demand discount coefficient used to measure the demand discount level. It converts the longitude and latitude data in the competition node and candidate node data association vectors into the distance between the two and further calculates it into a competition discount coefficient used to measure the competition discount level. The scoring calculation module consists of a demand scoring operator, a competition scoring operator, and a decision scoring operator. Its main function is to calculate the decision score of the candidate address based on demand, demand discount coefficient, competition, and competition discount coefficient. It calculates the standard demand score by multiplying the demand of all demand nodes within the service coverage of the candidate node by the demand discount coefficient. It calculates the standard competition score by multiplying the competition of all competing nodes within the competitive influence range of the candidate node by the competition discount coefficient. The demand score and competition score are calculated as the decision score of the candidate node. The data storage module consists of a node dataset and a subsequent calculation dataset. Its main function is to store the demand node dataset, the competing node dataset, the candidate node dataset, and the datasets calculated based on the node dataset using other functional modules.

[0108] The embodiment of this specification also provides an auxiliary site selection device for convenient service facilities, such as Figure 7 As shown, the device includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to:

[0109] Obtain the candidate address data of multiple candidate addresses corresponding to the convenience service facility, and the site selection impact data corresponding to each candidate address, wherein the site selection impact data includes service object demand data and competition object data; determine the current auxiliary site selection model corresponding to each candidate address based on the candidate address data, the site selection impact data and a pre-built initial auxiliary site selection model, wherein the auxiliary site selection model includes multiple data processing operators; quantify the site selection impact data through the data processing operator in the current auxiliary site selection model corresponding to each candidate address to generate service demand parameters and service competition parameters; obtain the current service facility data of the convenience service facility, and quantify the impact of multiple candidate addresses of the convenience service facility through the data processing operator based on the current service facility data, the candidate address data, the site selection impact data, the service demand parameters and the service competition parameters to determine the site selection decision score corresponding to each candidate address; assist the convenience service facility in site selection through the site selection decision score corresponding to each candidate address of the convenience service facility.

[0110] The embodiments of this specification also provide a non-volatile computer storage medium storing computer-executable instructions, wherein the computer-executable instructions are configured as follows:

[0111] Obtain the candidate address data of multiple candidate addresses corresponding to the convenience service facility, and the site selection impact data corresponding to each candidate address, wherein the site selection impact data includes service object demand data and competition object data; determine the current auxiliary site selection model corresponding to each candidate address based on the candidate address data, the site selection impact data and a pre-built initial auxiliary site selection model, wherein the auxiliary site selection model includes multiple data processing operators; quantify the site selection impact data through the data processing operator in the current auxiliary site selection model corresponding to each candidate address to generate service demand parameters and service competition parameters; obtain the current service facility data of the convenience service facility, and quantify the impact of multiple candidate addresses of the convenience service facility through the data processing operator based on the current service facility data, the candidate address data, the site selection impact data, the service demand parameters and the service competition parameters to determine the site selection decision score corresponding to each candidate address; assist the convenience service facility in site selection through the site selection decision score corresponding to each candidate address of the convenience service facility.

[0112] The various embodiments in this specification are described in a progressive manner. Similar portions between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from the other embodiments. In particular, the device, apparatus, and non-volatile computer storage medium embodiments are generally similar to the method embodiments, so their descriptions are relatively simplified. For relevant details, refer to the descriptions of the method embodiments.

[0113] The foregoing description of this specification describes specific embodiments. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in an order different from that described in the embodiments and still achieve the desired results. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order shown or the sequential order to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0114] The devices and media provided in the embodiments of this specification correspond one-to-one to the methods. Therefore, the devices and media also have similar beneficial technical effects to their corresponding methods. Since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the devices and media will not be repeated here.

[0115] Those skilled in the art will appreciate that the embodiments of this specification may be provided as methods, systems, or computer program products. Therefore, this specification may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, this specification may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0116] This specification is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of this specification. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0117] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0118] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0119] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0120] Memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.

[0121] Computer-readable media includes permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. The information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory computer-readable media (transitory media), such as modulated data signals and carrier waves.

[0122] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a ..." does not exclude the presence of other identical elements in the process, method, commodity, or apparatus that includes the element.

[0123] The foregoing description is merely one or more embodiments of this specification and is not intended to limit this specification. It will be apparent to those skilled in the art that various modifications and variations may be made to one or more embodiments of this specification. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of one or more embodiments of this specification are intended to be within the scope of the claims of this specification.

Claims

1. An auxiliary site selection method for convenient service facilities, characterized in that: The method comprises: Acquire candidate address data of a plurality of candidate addresses corresponding to convenient service facilities, and location influence data corresponding to each candidate address, wherein the location influence data includes service object demand data and competitor object data; Determining a current auxiliary site selection model corresponding to each candidate address based on the candidate address data, the site selection impact data, and a pre-built initial auxiliary site selection model, wherein the auxiliary site selection model includes a plurality of data processing operators; Quantitatively processing the location impact data by using the data processing operator in the current auxiliary location selection model corresponding to each of the candidate addresses to generate service demand parameters and service competition parameters; Obtaining current service facility data of the convenience service facility, and quantifying the impact of multiple candidate addresses of the convenience service facility based on the current service facility data, the candidate address data, the site selection impact data, the service demand parameter, and the service competition parameter through the data processing operator, and determining a site selection decision score corresponding to each candidate address; Assisting the convenience service facility in site selection by using the site selection decision score corresponding to each of the candidate addresses of the convenience service facility; Determining a current auxiliary site selection model corresponding to each candidate address based on the candidate address data, the site selection impact data, and a pre-built initial auxiliary site selection model, specifically including: Acquire the spatial position coordinates in the candidate address data, and construct a current candidate node data set through the spatial position coordinates of each candidate address, wherein the spatial position coordinates include latitude data and longitude data; Obtaining service object demand data and competitor data from the site selection impact data, determining service group size data and service object spatial location coordinates from the service object demand data, and determining competing service provision size data and competitor spatial location coordinates from the competitor data; Constructing a current demand node dataset using the service group scale data and the service object spatial position coordinates, and constructing a current competition node dataset using the competition service provision scale data and the competition object spatial position coordinates; Determining a demand quantification operator, a competition quantification operator, a demand discount operator, a competition discount operator, a demand scoring operator, a competition scoring operator, and a decision scoring operator in the data processing operator; Obtaining a service coverage radius and a competition influence radius from the current service facility data of the convenience service facility, and calculating, in a preset manner, multiple parameters in the data processing operator based on the service coverage radius and the competition influence radius to determine a current data processing operator; Determine a current auxiliary site selection model corresponding to each of the candidate addresses through the current candidate node data set, the current demand node data set, the current competition node data set, and a plurality of current data processing operators; According to a preset method, multiple parameters in the data processing operator are calculated based on the service coverage radius and the competition impact radius, specifically including: Use subjective or objective rights confirmation methods to determine the weight coefficient corresponding to each feature data in the demand node data to determine the parameters of the demand quantification operator; Use subjective or objective rights confirmation methods to determine the weight coefficient corresponding to each feature data in the competition node data to determine the parameters of the competition quantization operator; Using a subjective right confirmation method, determining a demand score weight coefficient and a competition score weight coefficient in the decision scoring operator; Obtaining travel parameters of the service group in the service object demand data; Based on the travel parameters of the service group and the service coverage radius, determine the core service radius and the core service scale ratio of the convenience service facility, so as to determine the parameters of the demand discount operator through the core service radius and the core service scale ratio, wherein the core service scale ratio is the ratio of the size of the service group provided within the core service radius to the size of all service groups provided within the service coverage radius; Determining a competition impact radius based on the service coverage radius of the convenience service facility, and determining parameters of the competition discount operator based on the competition impact radius; The positive ideal value of demand in the demand scoring operator and the negative ideal value of competition in the competition scoring operator are determined by a node ideal distribution diagram method.

2. The auxiliary site selection method for a convenience service facility according to claim 1, characterized in that: Before determining the current auxiliary site selection model corresponding to each candidate address based on the candidate address data, the site selection impact data, and the pre-built initial auxiliary site selection model, the method further includes: Modeling the candidate addresses, service objects, and competition objects of the convenient service facilities in the candidate area in advance to obtain candidate nodes corresponding to the candidate addresses, demand nodes corresponding to the service objects, and competition nodes corresponding to the competition objects; Constructing a node data set based on the candidate node, the demand node, and the competing node, wherein the node data set includes a candidate node data set, a demand node data set, and a competing node data set; Constructing multiple data processing operators, wherein the data processing operators include a demand quantification operator, a competition quantification operator, a demand discount operator, a competition discount operator, a demand scoring operator, a competition scoring operator, and a decision scoring operator; The initial auxiliary site selection model is constructed using the node data set and the multiple data processing operators.

3. The auxiliary site selection method for a convenience service facility according to claim 1, characterized in that: The location influence data is quantified by the data processing operator in the current auxiliary location selection model corresponding to each candidate address to generate service demand parameters and service competition parameters, specifically including: quantifying the service demand data in the location impact data by using a demand quantification operator in the data processing operator to generate corresponding service demand parameters; The service contention data in the location influence data is quantified by the competition quantization operator in the data processing operator to generate corresponding service contention parameters.

4. The auxiliary site selection method for a convenience service facility according to claim 1, characterized in that: Quantifying the impact of multiple candidate addresses of the convenience service facility based on the current service facility data, the candidate address data, the site selection impact data, the service demand parameter, and the service competition parameter, and determining a site selection decision score corresponding to each candidate address, specifically including: Calculating, by the data processing operator, a service demand score and a service competition score corresponding to each candidate address based on the current service facility data in the current service facility data, the spatial location coordinates of the candidate address data, the site selection impact data, the service competition parameter, and the service demand parameter; The decision scoring operator in the data processing operator is used to determine the site selection decision score corresponding to each of the candidate addresses according to the service demand score and the service competition score.

5. The auxiliary site selection method for a convenience service facility according to claim 4, characterized in that: The data processing operator calculates the service demand score and service competition score corresponding to each candidate address based on the service coverage radius in the current service facility data, the spatial location coordinates of the candidate address data, the site selection impact data, the service competition parameter, and the service demand parameter, specifically including: Calculate, by means of a demand discount operator in the data processing operator, a demand discount coefficient generated by each demand node for each of the candidate addresses based on the service coverage radius in the current service facility data of each of the candidate addresses, the spatial location coordinates of the service objects in the service object demand data in the site selection impact data, and the spatial location coordinates in the candidate address data; Calculate, by means of a competition discount operator in the data processing operator, a competition discount coefficient generated by each competing node for each of the candidate addresses based on the competition influence radius in the current service facility data of each of the candidate addresses, the spatial position coordinates of the competitor in the competitor data in the site selection influence data, and the spatial position coordinates in the candidate address data; Using the demand scoring operator in the data processing operator, generating a demand score generated by all demand nodes within the service coverage radius for the candidate address based on the demand discount coefficient generated by each demand node for each candidate address; Using the competition scoring operator in the data processing operator, a competition score generated by all competing nodes within the service coverage radius for the candidate address is generated according to the competition discount coefficient generated by each competing node for each candidate address.

6. The auxiliary site selection method for a convenience service facility according to claim 4, characterized in that: Determining the site selection decision score corresponding to each of the candidate addresses according to the service demand score and the service competition score through the decision scoring operator in the data processing operator, specifically including: pass , calculating a site selection decision score corresponding to each of the candidate addresses according to the service demand score and the service competition score; Among them, the is the decision scoring operator, is the candidate node data association vector, D is the demand node data set, C is the competition node data set, is the demand scoring weight coefficient, is the competition score weight coefficient, Candidate node Service demand score, Candidate node Service competition score, is a symbolic function.

7. An auxiliary site selection device for convenient service facilities, characterized in that: The device comprises: at least one processor; and, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor. The instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 6.

8. A non-volatile computer storage medium storing computer-executable instructions, characterized in that: The computer executable instructions are configured to execute the method according to any one of claims 1 to 6.

Images