居民出行与轨迹行为交互模式挖掘与关联技术

doi:10.11947/j.AGCS.2021.20200072

摘要/Abstract

摘要： 出租车是居民出行的重要交通工具，其轨迹数据蕴含着丰富的居民出行信息。原始出租车轨迹数据因缺少语义信息无法直观反映居民出行规律。通过轨迹数据挖掘技术处理之后的出租车轨迹数据能够反映居民活动规律和行为模式，从而为城市规划决策提供参考依据。本文重点研究了基于语义的交互模式度量，通过出租车停留点推断其语义信息；然后根据语义信息构建语义交互矩阵，用以推断和描述行为目的交互模式；最后选取北京市中心为研究区域进行方法验证。结果表明，中心城区内不同类别的停留点聚集分布规律不同，围绕高校和商圈聚集较明显；工作日各类停留点的活跃度持续时间较非工作日长；工作日和非工作日行为目的交互模式差别显著，工作日以职住和工作交互为主，非工作日以休闲和居住交互为主。本文研究可以为城市规划管理、资源调度和应急管理提供一定的决策支持。

关键词: 轨迹数据, 语义类别, 停留点活跃度, 语义交互矩阵, 交互模式

Abstract: As one of the effective means of transportation, taxis carry much valuable residents’ traveling information in their trajectory data. However, unprocessed trajectory data is incapable of revealing the information due to the lack of semantic information. Trajectory, data mining technology, provides a method to unveil residents activating regular patterns, which can support urban planning. This paper provides an interactive mode measuring method based on semantic information to mine the implicit relationship between residents’ behavioral purpose and trajectory. Firstly, the author discovers the semantic information from the location of the stay points. Then constructs the Interactive matrix of semantic to infer the interaction mode of behavior purpose. Finally, it takes the central area of Beijing as the research area to test the method. The test shows the association of the property of stay points and their distribution, which is in accord with the reality: here are apparent clusters around universities and business districts; the active of stay points is more durable on weekdays than on the weekends. There is a significant difference in the interactive mode between weekdays and weekends: the primary interactive mode is dwelling-working on the weekdays and is dwelling-relaxing on the weekend. This research can provide an essential reference for urban planning, resource allocation, and emergency management.

Key words: trajectory data, semantic type, stay poin activity, interactive matrix of semantic, interactive mode

中图分类号:

P208

代维秀, 陈占龙, 谢鹏. 居民出行与轨迹行为交互模式挖掘与关联技术[J]. 测绘学报, 2021, 50(4): 532-543.

DAI Weixiu, CHEN Zhanlong, XIE Peng. Research on the interactive mode of residents’ behavior based on trajectory data mining[J]. Acta Geodaetica et Cartographica Sinica, 2021, 50(4): 532-543.

参考文献

[1] MARR B. Big data:using smart big data, analytics and metrics to make better decisions and improve performance[M]. London:John Wiley & Sons, 2015.
[2] 裴韬, 刘亚溪, 郭思慧, 等. 地理大数据挖掘的本质[J]. 地理学报, 2019, 74(3):586-598. PEI Tao, LIU Yaxi, GUO Sihui, et al. Principle of big geodata mining[J]. Acta Geographica Sinica, 2019, 74(3):586-598.
[3] 牟乃夏, 张恒才, 陈洁, 等. 轨迹数据挖掘城市应用研究综述[J]. 地球信息科学学报, 2015, 17(10):1136-1142. MOU Naixia, ZHANG Hengcai, CHEN Jie, et al. A review on the application research of trajectory data mining in urban cities[J]. Journal of Geo-Information Science, 2015, 17(10):1136-1142.
[4] GUO Diansheng. Flow mapping and multivariate visualization of large spatial interaction data[J]. IEEE Transactions on Visualization and Computer Graphics, 2009, 15(6):1041-1048.
[5] 陈占龙, 周路林, 禹文豪, 等. 顾及兴趣点潜在上下文关系的城市功能区识别[J]. 测绘学报, 2020, 49(7):907-920. DOI:10.11947/j.AGCS.2020.20190315. CHEN Zhanlong, ZHOU Lulin, YU Wenhao, et al. Identification of the urban functional regions considering the potential context of interest points[J]. Acta Geodaetica et Cartographica Sinica, 2020, 49(7):907-920. DOI:10.11947/j.AGCS.2020.20190315.
[6] 姜晶莉, 郭黎, 李豪. 基于出租车轨迹数据的道路空驶率分析[J]. 兰州交通大学学报, 2019, 38(3):95-100. JIANG Jingli, GUO Li, LI Hao. Analysis of empty-run rate based on taxi trajectory data[J]. Journal of Lanzhou Jiaotong University, 2019, 38(3):95-100.
[7] 姚尧, 张亚涛, 关庆锋, 等. 使用时序出租车轨迹识别多层次城市功能结构[J]. 武汉大学学报(信息科学版), 2019, 44(6):875-884. YAO Yao, ZHANG Yatao, GUAN Qingfeng, et al. Sensing multi-level urban functional structures by using time series taxi trajectory data[J]. Geomatics and Information Science of Wuhan University, 2019, 44(6):875-884.
[8] 贾涛, 李琦, 马楚, 等. 武汉市出租车轨迹二氧化碳排放的时空模式分析[J]. 武汉大学学报(信息科学版), 2019, 44(8):1115-1123. JIA Tao, LI Qi, MA Chu, et al. Computing the CO₂ emissions of taxi trajectories and exploring their spatiotemporal patterns in Wuhan city[J]. Geomatics and Information Science of Wuhan University, 2019, 44(8):1115-1123.
[9] 赵夏君. 基于GPS轨迹数据的城市路段交通拥堵时序分析[J]. 湖南交通科技, 2018, 44(3):210-215. ZHAO Xiajun. Urban traffic congestion timing analysis based on GPS trajectory data[J]. Hunan Communication Science and Technology, 2018, 44(3):210-215.
[10] 邬群勇, 张良盼, 吴祖飞. 利用出租车轨迹数据识别城市功能区[J]. 测绘科学技术学报, 2018, 35(4):413-417, 424. WU Qunyong, ZHANG Liangpan, WU Zufei. Identifying city functional area using taxi trajectory data[J]. Journal of Geomatics Science and Technology, 2018, 35(4):413-417, 424.
[11] LAHA A K, PUTATUDA S. Real time location prediction with taxi-GPS data streams[J]. Transportation Research PartC:Emerging Technologies, 2018, 92:298-322.
[12] ZHOU Zuojian, DOU Wanchun, JIA Guochao, et al. A method for real-time trajectory monitoring to improve taxi service using GPS big data[J]. Information & Management, 2016, 53(8):964-977.
[13] GONG Shuhui, CARTLIDGE J, BAI Ruibin, et al. Activity modelling using journey pairing of taxi trajectory data[C]//Proceedings of the 4th IEEE International Conference on Big Data Analytics (ICBDA). Suzhou, China:IEEE, 2019:236-240.
[14] 李明晓, 张恒才, 仇培元, 等. 一种基于模糊长短期神经网络的移动对象轨迹预测算法[J]. 测绘学报, 2018, 47(12):1660-1669. LI Mingxiao, ZHANG Hengcai, QIU Peiyuan, et al. Predicting future locations with deep fuzzy-LSTM network[J]. Acta Geodaetica et Cartographica Sinica, 2018, 47(12):1660-1669.
[15] 许涛. 基于海量出租车轨迹数据的旅行时间预测[D]. 上海:华东师范大学, 2017. XU Tao. Travel time prediction based on massive taxi trajectory data[D]. Shanghai:East China Normal University, 2017.
[16] 许震洲. 轨迹大数据下城市异常移动模式研究及可视化[D]. 西安:西北大学, 2019. XU Zhenzhou. Anomaly urban mobility detection and visualization design based on large trajectory data[D]. Xi'an:Northwest University, 2019.
[17] IWAN L H, SAFAR M. Pattern mining from movement of mobile users[J]. Journal of Ambient Intelligence and Humanized Computing, 2010, 1(4):295-308.
[18] GONG Li, LIU Xi, WU Lun, et al. Inferring trip purposes and uncovering travel patterns from taxi trajectory data[J]. Cartography and Geographic Information Science,2016, 43(2):103-114.
[19] LI Aoyong, AXHAUSEN K W. Trip purpose imputation for taxi data[C]//Proceedings of the 18th Swiss Transport Research Conference (STRC 2018). Ascona, Switzerland:STRC, 2018.
[20] XIE Kexin, DENG Ke, ZHOU Xiaofang. From trajectories to activities:a spatio-temporal join approach[C]//Proceedings of 2009 International Workshop on Location Based Social Networks. Seattle, Washington:ACM, 2009:25-32.
[21] HUANG Lian, LI Qingquan, YUE Yang. Activity identification from GPS trajectories using spatial temporal POIs' attractiveness[C]//Proceedings of the 2nd ACM SIGSPATIAL International Workshop on Location based Social Networks. San Jose, California:ACM, 2010:27-30.
[22] PHITHAKKITNUKOON S, HORANONTT, DI LORENZO G, et al. Activity-aware map:identifying human daily activity pattern using mobile phone data[C]//Proceedings of 2010 International Workshop on Human Behavior Understanding. Berlin:Springer, 2010:14-25.
[23] FURLETTI B, CINTIA P, RENSO C, et al. Inferring human activities from GPS tracks[C]//Proceedings of the 2nd ACM SIGKDD International Workshop on Urban Computing. Chicago, Illinois:ACM, 2013:1-8.
[24] XIAO XIANGYE, ZHENG Yu, LUO Qiong, et al. Inferring social ties between users with human location history[J]. Journal of Ambient Intelligence and Humanized Computing,2014, 5(1):3-19.
[25] 吕明琪. 基于轨迹数据挖掘的语义化位置感知计算研究[D]. 杭州:浙江大学, 2012. LÜ Mingqi. Research on the semantic location-aware computing based on trajectory data mining[D]. Hangzhou:Zhejiang University, 2012.
[26] 廖律超, 蒋新华, 邹复民, 等. 一种支持轨迹大数据潜在语义相关性挖掘的谱聚类方法[J]. 电子学报, 2015, 43(5):956-964. LIAO Lüchao, JIANG Xinhua, ZOU Fumin, et al. A spectral clustering method for big trajectory data mining with latent semantic correlation[J]. Acta Electronica Sinica, 2015, 43(5):956-964.
[27] 普树芳. 基于移动计算平台的轨迹数据挖掘语义化感知技术研究[J]. 科技资讯, 2019, 17(24):23-24. PU Shufang. Research on semantic sensing technology of trajectory data mining based on mobile computing platform[J]. Science & Technology Information, 2019, 17(24):23-24.
[28] 章静蕾, 石海龙, 崔莉. 基于出行方式及语义轨迹的位置预测模型[J]. 计算机研究与发展, 2019, 56(7):1357-1369. ZHANG Jinglei, Shi Hailong, CUI Li. Location prediction model based on transportation mode and semantic trajectory[J]. Journal of Computer Research and Development, 2019, 56(7):1357-1369.
[29] 刘春, 周燕, 李鑫. 挖掘语义轨迹频繁模式及拼车应用研究[J]. 计算机工程与应用, 2019, 55(15):96-103. LIU Chun, ZHOU Yan, LI Xin. Mining semantic trajectory frequent pattern and car pooling application research[J]. Computer Engineering and Applications, 2019, 55(15):96-103.
[30] 吴瑕, 唐祖锴, 祝园园. 近似到达时间约束下的语义轨迹频繁模式挖掘[J]. 软件学报, 2018, 29(10):3184-3204. WU Xia, TANG Zukai, ZHU Yuanyuan. Frequent pattern mining with approximate arrival-time in semantic trajectories[J]. Journal of Software, 2018, 29(10):3184-3204.
[31] WANG Pengfei, LIU Guannan, FU Yanjie, et al. Spotting trip purposes from taxi trajectories:a general probabilistic model[J]. ACM Transactions on Intelligent Systems and Technology, 2017, 9(3):1-26.
[32] ALSGER A, TAVASSOLI A, MESBAHM, et al. Public transport trip purpose inference using smart card fare data[J]. Transportation Research Part C:Emerging Technologies, 2018, 87:123-137.
[33] CHEN Chao, LIAO Chengwu, XIE Xuefeng, et al. Trip2Vec:a deep embedding approach for clustering and profiling taxi trip purposes[J]. Personal and Ubiquitous Computing, 2019, 23(1):53-66.
[34] MA Xiaolei, WU Y J, WANG Yinhai, et al. Mining smart card data for transit riders'travel patterns[J]. Transportation Research Part C:Emerging Technologies, 2013, 36:1-12.
[35] GIANNOTTI F, NANNI M, PEDRESCHI D, et al. Unveiling the complexity of human mobility by querying and mining massive trajectory data[J]. The VLDB Journal, 2011, 20(5):695.
[36] GAFFNRY S, SMYTH P. Trajectory clustering with mixtures of regression models[C]//Proceedings of the 5th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. San Diego, California, USA:ACM, 1999:63-72.
[37] KALNIS P, MAMOULIS N, BAKIRAS S. On discovering moving clusters in spatio-temporal data[C]//Proceedings of 2005 International Symposium on Spatial and Temporal Databases. Berlin:Springer, 2005:364-381.
[38] LEE J G, HAN Jiawei, WHANG K Y. Trajectory clustering:a partition-and-group framework[C]//Proceedings of 2007 ACM SIGMOD International Conference on Management of Data. Beijing, China:ACM, 2007:593-604.
[39] ZHENG Yu, ZHANG Lizhu, XIE Xing, et al. Mining interesting locations and travel sequences from GPS trajectories[C]//Proceedings of the 18th International Conference on World Wide Web. Madrid, Spain:ACM, 2009:791-800.
[40] ZHAO Pengxiang, KWAN M P, QIN Kun. Uncovering the spatiotemporal patterns of CO₂ emissions by taxis based on individuals' daily travel[J]. Journal of Transport Geography, 2017, 62:122-135.
[41] DASZYKOWSKI M, WALCZAK B, MASSART D L. Looking for natural patterns in data:Part 1. Density-based approach[J]. Chemometrics and Intelligent Laboratory Systems, 2001, 56(2):83-92.
[42] MOREIRA-MATIAS L, GAMA J, FERREIRA M, et al. A predictive model for the passenger demand on a taxi network[C]//Proceedings of the 15th International IEEE Conference on Intelligent Transportation Systems. Anchorage, AK, USA:IEEE, 2012:1014-1019.