Urban rail transit holiday passenger flow prediction system

Abstract

The invention provides an urban rail transit holiday passenger flow prediction system. The system comprises: a holiday passenger flow prediction server, a basic model server, a data management server, and a data acquisition server, wherein the data acquisition server crawls urban rail transit internal road network passenger flow data, long-distance traffic data, urban POI data, and event data, and sends the data to the data management server; the basic model server provides a gravity model, an OD classification model, a travel willingness grading model, and a data driving model; based on data in the data management server, the holiday passenger flow prediction server calls the OD classification model, the gravity model, and the travel willingness grading model to perform holiday short-term passenger flow prediction; on the basis of the short-time passenger flow prediction, a data driving model that is based on high-dimensional feature coding in the basic model server is called to carry out real-time holiday OD passenger flow prediction. The system provides travel OD demand prediction for passenger transport organizations during holidays and improves the scientific rationality of the passenger transport organizations.

Description

technical field [0001] The invention relates to the technical field of urban rail transit operation organization, in particular to a passenger flow prediction system for urban rail transit on holidays. Background technique [0002] The rapid development of urban rail transit has attracted a large number of urban traffic passenger flows. Passenger flow during holidays is significantly different from daily commuting, which poses challenges to urban rail transit capacity allocation, station passenger flow organization, and staffing. Accurately predicting passenger flow can provide scientific decision-making for urban rail transit operation organizations. [0003] At present, the methods for predicting passenger flow during holidays in urban rail transit in the prior art are based on the internal traffic of the system, historical passenger flow during holidays, and land use around the station as the main basis for research from the perspective of data; from the perspective of m...

AI Technical Summary

Problems solved by technology

[0004] The disadvantages of the method for predicting passenger flow in urban rail transit holidays in the above-mentioned prior art are: lack of comprehensive utilization of road traffic and long-distance connection traffic information, and lack of comprehensive utilization of external event information such as weather, public opinion, epidemic situation, major events, etc. Also lacking is the comprehensive utilization of interpretable and data-driven models

Images