Rail transit passenger flow prediction method and system based on passenger travel information

Abstract

The invention relates to the technical field of rail transit passenger flow prediction, in particular to a rail transit passenger flow prediction method and system based on passenger travel information, and the method comprises the steps: obtaining passenger travel data, building a passenger travel information index system based on the passenger travel data, counting and calculating each piece of index information in the passenger travel information index system; based on part of index information calculated in the passenger travel information index system, estimating return passenger flow volumes in different time periods in the station; and taking the return passenger flow volume of the passengers in the station as a covariable and adding the covariable into the passenger flow prediction model to predict the pull-in passenger flow of the station. According to the multi-source travel data of the passengers, the travel rule of the passengers is mined, a passenger travel information three-level index information system is established on the basis, and statistical calculation of all index information is achieved. Meanwhile, the invention provides a prediction method for identifying the return passenger flow for the passenger travel information and effectively improving the accuracy of the passenger flow entering the station according to the return passenger flow.

Description

technical field [0001] The invention relates to the technical field of rail transit passenger flow forecasting, in particular to a rail transit passenger flow prediction method and system based on passenger travel information. Background technique [0002] Accurately predicting passenger demand at stations is critical to the operation of urban subway systems. Previous studies mainly regard the passenger flow values ​​at several moments in the past as time series to predict the passenger flow at a certain moment in the future. However, this approach basically ignores the travel behavior patterns of individual passengers. For example, if a passenger gets off at a subway station for work in the morning, he or she is likely to get on at the same station at night to go home. Existing studies have shown that it is necessary to add travel behavior components to passenger flow forecast time series. According to the concept of user travel information, easy-to-understand, represent...

AI Technical Summary

Problems solved by technology

At present, the passenger travel information of rail transit still has the following deficiencies: the multi-source travel information of passengers has not been deeply excavated, resulting in a large waste of data; the index system of passenger travel information established through data analysis is not perfect, and further excavation is still needed

Images