Real-time recognition method for getting-off stations of bus passengers based on historical travel characteristics

Abstract

The invention relates to the technical field of resident travel trajectory analysis and computer applications, and provides a real-time recognition method for getting-off stations of bus passengers based on historical travel features. The real-time recognition method comprises the steps of firstly realizing getting-on station recognition for the bus passengers by integrating bus GPS data and IC card data; then building a historical travel feature library containing historical travel trajectory features of residents and historical getting-on rate features of stations through mining historical data; and finally completing real-time recognition for getting-off stations of the passengers through performing similarity matching on the historical data and the historical travel feature library. The method can be applied to the fields such as resident travel trajectory analysis, bus operation dispatching and urban construction planning, and provides an accurate data support.

Description

technical field [0001] The invention relates to the technical field of resident travel trajectory analysis and computer application, in particular to a method for identifying bus passenger alighting stations based on historical travel characteristics. Background technique [0002] With the upgrading of public transportation hardware equipment, the public transportation one-card system continues to popularize, and the utilization rate of IC cards continues to increase. The accumulated mass of IC cards and GPS data provide feasibility for public transportation big data analysis. Taking Chongqing as an example, the public transportation card system in the main urban area covers ground buses, rail transit, taxis, cableways and escalators, etc., and IC usage accounts for 88%. However, at present, major cities generally adopt the one-ticket IC card system, which only records information such as the time when passengers get on the bus and the number of the vehicle they take. There...

AI Technical Summary

Problems solved by technology

The recognition algorithm based on the travel chain theory can only identify the passenger alighting stations with complete closed travel characteristics, which needs to be processed offline and has a low recognition rate; the method based on the probability of alighting at the stations needs to consider many factors affecting the stations, and does not take into account the individual characteristics of passengers , the number of people getting off at each station can only be calculated through probability, but the exact location of each passenger cannot be obtained, and it cannot reflect the difference in passenger choice at different times of the day. This method is highly subjective and has low accuracy.

Images