Intelligent store site selection recommendation method and system based on multi-dimensional data

Abstract

The invention discloses an intelligent store site selection recommendation method and system based on multi-dimensional data, and the method comprises the steps: collecting data needed for constructing an index, carrying out the cleaning and fusion of the data, constructing an enterprise site selection index, carrying out the assignment of each index according to the collected data, constructing a machine learning model, and carrying out the training of the machine learning model, and inputting the GIS geographic data of the power utilization place needing to be judged and the corresponding index data, and repeatedly carrying out iteration until the difference of the probability values of the two outputs is within a set threshold value to obtain a final site selection result. According to the method, complete electric power big data in a region and market public full-amount third-party data are used as fusion, cross-region and multi-point transverse comparison can be performed on brand stores of the same customer group, the problem of insufficient samples in machine learning is solved, a site selection strategy is quantified, the site selection efficiency is greatly improved, and the site selection cost and the labor cost of an enterprise are saved.

Description

technical field [0001] The invention belongs to the technical field of electric power big data processing, and in particular relates to a multi-dimensional data-based intelligent store location recommendation method and system. Background technique [0002] A good location is the first step in the successful operation of offline stores. At present, enterprises generally collect information artificially through offline visits by site selection managers. This method is inefficient, inaccurate, and expensive to collect. Finally, the collected information is scored and evaluated by experts, and the decision-making team can only make judgments based on subjective meaning, and the cost of trial and error is high. The industry lacks effective and authoritative data to support indicators such as the flow of people, consumption power, analysis of competing products in the same industry, rental costs, industry ecology, and location traffic that are the focus of site selection scenar...

AI Technical Summary

Problems solved by technology

This method is inefficient, inaccurate, and expensive to collect

Finally, the collected information is scored and evaluated by experts, and the decision-making team can only make judgments based on subjective meaning, which leads to high trial and error costs

The industry lacks effective and authoritative data to support indicators such as the flow of people, consumption power, analysis of competing products in the same industry, rental costs, industry ecology, and location traffic that are focused on in site selection scenarios.

Images