文章编号： 1672-5328（2016）01-0030-07

杨超，张玉梁，张帆
(1.同济大学道路与交通工程教育部重点实验室，上海201804；2.中国科学院深圳先进技术研究院，广东深圳， 518055)

摘要： 通过手机话单数据提取用户的出行特征具有可行性。然而，手机话单数据的稀疏性对提取居 民出行时间特征造成困难。通过对深圳市手机话单数据的挖掘分析识别居民职住地，得到居民特征 通勤序列，进而基于早、晚不同情况对居民通勤特征进行描述和分析。对比分析显示，通过手机话 单数据得到的居民通勤距离和时间特征与居民出行调查结果较为一致，说明该方法可用以描述居民 通勤特征。研究表明，深圳市居民通勤开始时间受通勤距离影响不大，大于10 km的中长距离通勤 出行对应的平均通勤时间维持在一个比较稳定的值(45~50 min)。

关键词： 交通规划；通勤出行特征；手机话单数据；通勤距离；通勤时间；深圳市

中图分类号： U491

文献标识码：A

Commuting Characteristics Analysis Based on Mobile Phone Calling Records: A Case Study in Shenzhen

Yang Chao, Zhang Yuliang, Zhang Fan
(1.Key Laboratory of Road and Traffic Engineering of the Ministry of Education, Tongji University, Shanghai 201804, China; 2.Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen Guangdong 518055, China)

Abstract： It is feasible to use mobile phone calling records to analyze commuting characteristics. However, the sparsity of calling records could potentially hurdle the data acquisition for commuting time estimation. This paper identifies location of users' residence and work place using mobile phone calling records in Shenzhen, which can be used to analyze residents' commuting characteristics during morning and evening commuting times. The analyses show that the similar commuting characteristics are observed from both data sources, i.e, the conventional travel surveys and mobile phone calling records, which approves phone calling records can be utilized for commuting studies. The results also reveal that there is no significant differences between commuting departure time and commuting distance in Shenzhen, and commuting time relatively remains constant (45~50 min) for commuting trips longer than 10 km.

Keywords： transportation planning; commuting characteristics; mobile phone calling records; commuting distance; commuting time; Shenzhen