CN-122022907-A - Shop site selection recommendation method and system based on big data

CN122022907ACN 122022907 ACN122022907 ACN 122022907ACN-122022907-A

Abstract

The application relates to the technical field of data processing, in particular to a store site selection recommendation method and system based on big data; the method comprises the steps of obtaining positions of a plurality of candidate shops and passenger flow data of a plurality of interesting points, determining passenger flow toughness intensity between the interesting points and the candidate shops for any candidate shop position, carrying out clustering processing on the passenger flow toughness intensity to obtain a plurality of commercial clusters, carrying out chain breaking processing on the interesting points in the commercial clusters and the correlation of the candidate shops to ensure that each interesting point is at most correlated with one candidate shop, calculating cooperative stability of the commercial clusters after the chain breaking processing, constructing an objective function of an ant colony optimization algorithm based on the cooperative stability, and carrying out optimization processing on the candidate shops by using the ant colony optimization algorithm to obtain a final shop site selection result. The application has the effect of improving the accuracy and reliability of the shop site selection result.

Inventors

OU JIARONG
ZHU ZHI

Assignees

广东赢商网数据服务股份有限公司

Dates

Publication Date: 20260512
Application Date: 20260128

Claims (10)

1. A store site selection recommendation method based on big data is characterized by comprising the steps of obtaining positions of a plurality of candidate stores and passenger flow data of a plurality of interest points, determining passenger flow toughness intensity between the interest points and the candidate stores based on the passenger flow data of the interest points and the route distance from the interest points to the candidate stores for any candidate store position, clustering the passenger flow toughness intensity to obtain a plurality of commercial clusters, conducting chain breaking on association of the interest points in the commercial clusters and the candidate stores to ensure that each interest point is associated with one candidate store at most, calculating cooperative stability of the commercial clusters after the chain breaking process, constructing an objective function of an ant colony optimization algorithm based on the cooperative stability, and conducting optimization on the candidate stores by using the ant colony optimization algorithm to obtain a final store site selection result.
2. The store site selection recommendation method based on big data according to claim 1, wherein, for the passenger flow volume data of any one point of interest, passenger flow volume data in a preset range around the point of interest is obtained by calling a crowd thermodynamic diagram or a passenger flow statistics interface provided by a map API.
3. The store location recommendation method based on big data according to claim 1, wherein the step of determining the intensity of the passenger flow toughness between the interesting point and the candidate store comprises dividing passenger flow data of any interesting point into a plurality of time periods, wherein each time period comprises a plurality of acquired passenger flow data, sequentially arranging the passenger flow data with the same acquisition time in different time periods to form corresponding passenger flow sequences, taking the ratio of the mean value and the standard deviation of the passenger flow sequences as a local stability index, taking the sum of the local stability indexes corresponding to the passenger flow sequences as a passenger flow stability index, and taking the product of the passenger flow stability index and the reciprocal of the route distance from the interesting point to the candidate store as the intensity of the passenger flow toughness.
4. The store site selection recommendation method based on big data according to claim 1, wherein the intensity of the passenger flow toughness is clustered by adopting a K-means clustering algorithm.
5. The big data based store location recommendation method of claim 4, wherein the number of clusters of the K-means clustering algorithm is determined using an elbow method.
6. The method for determining the co-stability of a business cluster according to claim 1, wherein the method for determining the co-stability of the business cluster comprises calculating an absolute value of a difference between the intensity of the guest flow toughness and a mean value of the co-stability in the business cluster for any guest flow toughness, taking a ratio of the intensity of the guest flow toughness to the absolute value as a local stability, and taking a mean value of a corresponding plurality of local stability in the business cluster as the co-stability.
7. The store site selection recommendation method based on big data according to claim 1, wherein the objective function construction method comprises the step of taking the sum of the collaborative stabilities of all commercial clusters after the broken link processing as the objective function.
8. The store site selection recommendation method based on big data according to claim 1, wherein in the ant colony optimization algorithm, the broken chain condition of all points of interest and candidate stores is represented as one-dimensional vector, and the one-dimensional vector is taken as the position of ants.
9. The method for recommending store location based on big data according to claim 1, wherein the final store location result comprises the steps of performing a chain breakage process on the candidate stores and the interest point corresponding to the element with the value of 0 in the binary vector output by the ant colony optimization algorithm, and taking the candidate stores which are still associated with the interest point after the chain breakage process as the final store location result.
10. Store location recommendation system based on big data, characterized by comprising a processor and a memory, the memory storing computer program instructions which, when executed by the processor, implement the store location recommendation method based on big data according to any of claims 1-9.

Description

Shop site selection recommendation method and system based on big data Technical Field The application relates to the technical field of data processing, in particular to a store site selection recommendation method and system based on big data. Background Shop location is one of the most important strategic decisions in the retail, catering, etc. industries. A scientific and reasonable site selection scheme not only can help the enterprise to obtain sufficient and stable passenger flow resources, but also can reduce market entry risk and promote the long-term profitability of the enterprise. Conversely, if the site selection is improper, insufficient passenger flow of the shops may be caused, the profit level may be reduced, and even the risk of operation failure may be faced. In the traditional model, enterprises typically rely on manager experience, intuition, or limited market research data to address. Although the method has certain operability in practice, the method has obvious limitations that firstly, multi-dimensional factors such as geospatial distribution, traffic convenience, consumer group characteristics, peripheral competition relation and the like are difficult to systematically cover by relying on experience judgment, and secondly, limited investigation data hardly reflect the dynamic and time sequence characteristics of passenger flow, so that the evaluation result has unilaterality and uncertainty. Therefore, the traditional site selection mode has stronger subjectivity and randomness, and long-term scientificity and stability are difficult to ensure in a strong market competition environment. With the development of big data technology, the quantitative analysis and intelligent decision of candidate store points are performed by utilizing massive multidimensional data, so that the method has become an important means for improving the scientificity and the precision of site selection. Shop site selection is essentially a complex optimization problem that merges multidimensional heterogeneous data such as geography, business, society and the like, and candidate solution spaces are usually characterized by high dimensionality and multiple peaks. Aiming at the path optimization problem, the prior art usually adopts an ant colony optimization algorithm to solve the path optimization problem. The algorithm has stronger global searching capability by simulating ant colony foraging behaviors. However, in a shop site selection scenario, there is a significant drawback in directly applying the original ant colony optimization algorithm. The objective function is usually simply set to maximize the traffic volume or minimize the cost, and this setting ignores the commercial cluster synergy formed between different points of interest, and fails to fully consider the potential resource competition relationship between multiple candidate stores for the same source, thereby affecting the accuracy and reliability of the final site selection recommendation result. Disclosure of Invention In order to improve accuracy and reliability of store site selection results, the application provides a store site selection recommendation method and system based on big data. In a first aspect, the present application provides a store site selection recommendation method based on big data, which adopts the following technical scheme: a store site selection recommendation method based on big data comprises the steps of obtaining positions of a plurality of candidate stores and passenger flow data of a plurality of interest points, determining passenger flow toughness intensity between the interest points and the candidate stores based on the passenger flow data of the interest points and route distances from the interest points to the candidate stores for any candidate store position, carrying out clustering processing on the passenger flow toughness intensity to obtain a plurality of commercial clusters, carrying out chain breaking processing on association of the interest points in the commercial clusters and the candidate stores to ensure that each interest point is associated with one candidate store at most, calculating cooperative stability of the commercial clusters after the chain breaking processing, constructing an objective function of an ant colony optimization algorithm based on the cooperative stability, and carrying out optimization processing on the candidate stores by using the ant colony optimization algorithm to obtain a final store site selection result. Firstly, a passenger flow toughness strength index is established for comprehensively quantifying the actual attraction capability of candidate shops to interested points, and the index simultaneously considers three factors of passenger flow scale, time stability and route distance, so that the conventional method only depends on the single evaluation of passenger flow total quantity or distance, and the measurement of candidate site selection is