Rail travel feature extraction method based on adjacency matrix and signaling triggering rule

Abstract

The invention discloses a rail travel feature extraction method based on an adjacency matrix and a signaling triggering rule. The rail travel feature extraction method comprises the following steps: step 1, creating a rail information database; 2, designing a travel route for an experiment, collecting signaling data, recording a travel log at the same time, and searching a rail travel signaling triggering rule; 3, deleting repeated data, missing data, communication failure data and small sample data, and sorting signaling data with rail travel according to time; 4, removing ping-pong switchingand signal drifting data, and forming basic data of user travel mobile phone signaling; and step 5, identifying rail travel characteristics. The method aims to solve the problems that in an existingrail passenger flow investigation method, investigation data are not in time, investigation information is incomplete, the collection effect is easily affected by the outside, and an identification method depends on experience judgment, and passenger rail transit travel path identification can be achieved through the method. A transfer platform form is analyzed in combination with trigger signaling features.

Description

technical field [0001] The invention belongs to the field of identification of signaling data information of traffic big data, and in particular aims at the identification of same-station transfer and different-station transfer under the background of multiple rail transfers. Background technique [0002] With the continuous expansion of cities in various countries and the clarification of functional distribution, the number of trips by residents is increasing, and the travel distance is increasing, and the demand for transportation volume and distance of transportation is gradually increasing. Rail transit has attracted the attention of governments of various countries due to its long-distance and large-capacity characteristics, and has become the backbone of urban transportation. Keep abreast of the travel behavior of residents on the track, and provide basic support for finding out the travel situation of residents, passenger flow direction and traffic planning. Traditio...

AI Technical Summary

Problems solved by technology

However, the existing methods usually ignore the occurrence rules of transfer signaling, which may easily cause misidentification of transfer stations. In addition, the numbering of base stations is too idealized, and the spatio-temporal threshold method mostly relies on actual experience. With the complexity of the track network, the analysis is complex There are limitations when transferring multiple lines under the network

Images