Pseudo code signaling data preprocessing and trip chain identification method

Abstract

The invention discloses a pseudo code signaling data preprocessing and trip chain identification method. The pseudo code signaling data preprocessing and trip chain identification method includes thefollowing steps: (1) merging redundant signaling records and culling abnormal records; (2) according to parameter characteristics of ping-pong effect records, identifying the ping-pong records and deleting the ping-pong records; (3) calculating the user residence centroid, setting the time and space thresholds when the trip occurs, and identifying the start record point; and (4) setting the user residence time and space threshold, and identifying the record point for ending of the trip, thus completing the trip chain identification. The pseudo code signaling data preprocessing and trip chain identification method effectively cleans and filters the data, improves the data precision, extracts the complicated data as valuable trip OD information, and improves the availability of data in various fields such as transportation. The pseudo code signaling data preprocessing and trip chain identification method is wide in the application range, and is simple and practicable.

Description

technical field [0001] The invention relates to the technical field of big data processing and analysis in the transportation industry, specifically, from the perspective of the application of the pseudo-code signaling data in the transportation industry, a method for preprocessing the pseudo-code signaling data and identifying travel links. Background technique [0002] With the advent of the era of big data, pseudo-code signaling data has emerged in many fields such as transportation and urban planning. The extensive research and application of big data technology has brought new opportunities for solving "traffic disease" problems such as traffic congestion. [0003] However, the application of big data has just started, and big data processing and analysis technology is still in the development stage. How to extract effective data from rough massive data and accurately identify travel link information that is valuable to the transportation industry is a key issue for res...

AI Technical Summary

Problems solved by technology

[0004] In terms of data cleaning, the existing technology mainly uses the traditional data preprocessing algorithm to clean the signaling data, including redundant data deletion, abnormal data filtering, etc., without considering the characteristics of the signaling data itself, such as the unique ping-pong effect, etc. It can "prescribe the right medicine" to achieve a high level of data cleaning, which reduces the accuracy and credibility of the data, and greatly reduces the usability of signaling data in the transportation field

Considering the data ping-pong effect, the existing technologies for removing ping-pong records only filter for a single record, and cannot effectively remove ping-pong records that are mixed with multiple consecutive records

The imperfection of the above data cleaning technology limits the credibility of the application of big data in the transportation industry

[0005] In terms of travel chain identification, the existing technology is mainly based on the user's moving speed, and uses the clustering method to identify the user's motion state. However, due to the characteristics of the signaling data collection being affected by the trigger mechanism, the calculated speed parameters are not accurate, and can only be For reference, there is also a certain deviation in identifying travel status based on speed

However, in the existing technology for identifying travel chains based on the distance and time parameter features between records, the concept of resident centroid has not been proposed to improve the accuracy of travel recognition.

Images