A subway passenger flow built environment feature analysis method based on large language model ensemble learning

Abstract

This invention discloses a method for analyzing the built environment characteristics of subway passenger flow based on ensemble learning of large language models. The method includes first collecting passenger data and multi-source built environment data; selecting several pre-trained large language models and training each model based on the passenger data and multi-source built environment data to obtain several finally trained large language models; then obtaining the comprehensive performance index of each large language model, and obtaining the corresponding performance weight based on the comprehensive performance index; finally, obtaining the analysis results and optimization suggestions for subway construction based on the passenger data, multi-source built environment data, each large language model, and the corresponding performance weights. This invention can provide a more scientific, rapid, and low-cost pre-assessment for urban planning, and has stronger practical significance and application value compared with traditional analysis methods.

Images