交通运输系统工程与信息 ›› 2020, Vol. 20 ›› Issue (3): 89-94.

• 智能交通系统与信息技术 • 上一篇    下一篇

基于网约车数据的城市区域出行时空特征识别与预测研究

张政1,陈艳艳* 1,梁天闻2   

  1. 1.北京工业大学城市交通学院,北京 100124;2. 交通运输部公路科学研究院,北京 100088
  • 收稿日期:2019-11-14 修回日期:2020-02-17 出版日期:2020-06-25 发布日期:2020-06-28
  • 作者简介:张政(1992-),男,山东人,博士生.
  • 基金资助:

    国家重点研发计划/National Key Research and Development Program of China(2016YFE0206800).

Regional Travel Demand Mining and Forecasting Using Car-hailing Order Records

ZHANG Zheng1, CHEN Yan-yan1, LIANG Tian-wen2   

  1. 1. College of Metropolitan Transportation, Beijing University of Technology, Beijing 100124, China; 2. Research Institute of Highway Ministry of Transport, Beijing 100088, China
  • Received:2019-11-14 Revised:2020-02-17 Online:2020-06-25 Published:2020-06-28

摘要:

针对交通需求特征识别和需求预测问题,构建改进的LDA(Latent Dirichlet Allocation)城市区域内出行需求识别与预测组合模型,快速识别城市区域内出行需求特征并对需求做出预测. 构建城市交通小区尺度内的空间和时间维度下的主要出行需求特征分布挖掘辨识方法,以及数据集在不同时间尺度下时间维度出行特征构建及预测方法. 利用北京市三环内网约车出行订单数据,验证模型的有效性和准确性. 结果表明,模型能够对不同时间窗口下的区域出行需求特征进行辨识和预测,取得较好的结果.

关键词: 城市交通, 交通需求识别和预测, LDA模型, 网约车

Abstract:

This paper proposed a combined model that can fast mining traffic demand and prediction based on the Latent Dirichlet Allocation (LDA) analysis model. This combined analysis framework is able to deal with demand identification and prediction at the same time. The study first developed the traffic demand identification model at the traffic analysis zone (TAZ) scale for presenting the demand characteristics at both the spatial and temporal dimension.Then it proposed a prediction method under a multi-scale time window. The effectiveness and accuracy of the model was verified using car-hailing order data within Beijing's third-ring road. The results show that the model can identify and predict the regional travel demand under different time windows, and achieve good results.

Key words: urban traffic, transportation demand identification and forecasting, Latent Dirichlet Allocation (LDA), car-hailing services

中图分类号: