基于职住地关系的城市轨道交通乘客出行特征挖掘和乘客分类
周琪1龚璐2马明辰1孙守胜1常青青2
Urban Rail Transit Passenger Travel Characteristics Mining and Passenger Classification Based on Workplace-residence Relationship
ZHOU Qi1GONG Lu2MA Mingchen1SUN Shousheng1CHANG Qingqing2
-
作者信息:1.同济大学电子与信息工程学院，201804，上海
2.公安部第三研究所，200031，上海
-
Affiliation:1.School of Electronics and Information Engineering, Tongji University, 201804, Shanghai, China
2.The Third Research Institute of the Ministry of Public Security, 200031, Shanghai, China
-
关键词:
-
Key words:
-
DOI:10.16037/j.1007-869x.2024.08.019
-
中图分类号/CLCN:U293.13
-
栏目/Col:研究报告
摘要:
［目的］依据城市轨道交通出行轨迹数据挖掘出行特征时，乘客出行活动模式与其居住地和就职地站点紧密关联，在出行轨迹上表现为乘客乘车线路固定、进出站站点集中等特征。同时，关联居住地和就职地的乘客出行轨迹也呈现出一定的波动性，与职住地强关联的出行数据和其他出行数据间往往表现出较明显的差异。为实现对乘客出行轨迹特征的精准挖掘，需厘清城市轨道交通乘客出行数据中的职住地关系。［方法］提出一种基于职住地关系的出行特征挖掘和乘客分类机制，从基于居住地、就职地、社会活动地的乘客轨迹活动热点角度形成初步职住地判断，探索与职住地关联性强的出行时空规律；通过基于乘客出行轨迹特征值提取的K-means(K均值)聚类算法对职住地判断后的乘客聚类结果，形成精准匹配乘客出行特征的乘客分类方法。［结果及结论］仿真验证结果表明，职住地关系明确的乘客出行模式分为两点式、两点两线式、三点式及多点式等4类，该出行模式分类结果是构建精细化乘客画像与制定智能安检策略的重要技术基础。
Abstracts:
［Objective］ When mining travel characteristics from urban rail transit travel trajectory data, passenger travel activity patterns are found closely related to the stations near their residence and workplace. This is reflected in their travel trajectories by fixed boarding/alighting routes and concentrated entry/exit stations. Meanwhile, passenger travel trajectories associated with residence and workplace exhibit certain fluctuations, and the travel data strongly related to workplace-residence often differ significantly from other travel data. To accurately extract passenger travel trajectory characteristics, it is essential to clarify the residence-workplace relationship within urban rail transit passenger travel data. ［Method］ A mechanism for mining travel characteristics and classifying passengers based on residence-workplace relationship is proposed. The preliminary workplace-residence judgments are formed by identifying the hotspots of passenger trajectory activities related to residence, workplace and social activity locations. Then, the spatio-temporal patterns strongly associated with workplace-residence are explored. A K-means clustering algorithm extracted on the basis of passenger travel trajectory characteristic values is used to cluster passengers according to their residence-workplace judgment, resulting in a passenger classification method that precisely matches the passenger travel characteristics. ［Result & Conclusion］ Simulation validation results indicate that passengers with clearly defined residence-workplace relationship exhibit four distinct travel patterns of two-point, two-point-two-line, three-point, and multi-point. These travel pattern classification results make up a crucial technical foundation for constructing detailed passenger profiles and developing intelligent security check strategies.
- 上一篇: 高铁物流运输模式及其可行性
- 下一篇: 碳纤维地铁列车的商用将开启轨道车辆用材的新时代
过刊浏览
资料下载
友情链接