摘要
大数据具有多数据形式、大数据量、传输快捷等优势,大数据分析已逐渐影响和改变人们解决问题的思维方式。本文利用滴滴打车数据和感兴趣点分析人们的打车需求,识别出打车活跃区域。对打车需求数据进行时间划分,核密度分析得到打车聚集区域。统计了打车点附近各类型POI的个数,分析了各区域内打车需求与时间段、地理位置、工作日和周末的关系。发现早高峰(7点到9点)打车与住宅区POI相关,晚高峰(17点到19点)与商铺POI相关,夜晚(21点到2点)打车与公司POI相关,且同一地区在周末与工作日的打车活跃时间不同。
Big Data have the features of variety forms, high-volume, convenient and immediate transmission, with the increasing influence on our daily life and ways in solving issues. We analyze the taxi demand quantity base on didi data and point of interest to recognize the active district with high taxi demand. We divided taxi demand data into several portions by the periods of time, identified the district with high frequency of taxi demand, followed by a statistics of the POI amount around the neighborhood. We also analyzed relationship of taxi demand quantity and time slot, location, weekday or weekend in different district. The paper shows morning peak(from 7 o'clock to 9 o'clock) is related to residential POIs, the evening peak(from 17 o'clock to 9 o'clock) with the commercial POIS,and the night time(from 21 o'clock to23 o'clock) with company POIs, but showing different time slot between weekdays and weekends, even in the identical district.
引文
[1]王家耀,武芳,郭建忠,等.时空大数据面临的挑战与机遇[J].测绘科学,2017,42(7):1-7.
[2]Ye,Mao,Yin,et al.Exploiting Geographical Influence for Collaborative Point-of-Interest Recommendation[J].2011:325-334.
[3]Xie Z,Yan J.Kernel Density Estimation of Traffic Accidents in a Network Space[J].Computers,Environment and Urban Systems,2008,32(5):396-406.
[4]Yuan Q,Cong G,Ma Z,et al.Time-aware Point-ofInterest Recommendation[C]//International ACM SIGIRConference on Research and Development in Information Retrieval,2013:363-372.
[5]Liu B,Fu Y,Yao Z,et al.Learning Geographical Preferences for Point-of-Interest Recommendation[C]//ACM SIGKDD International Conference on Knowledge Discovery and Data Mining,2013:1043-1051.
[6]Cheng C,Yang H,Lyu M R,et al.Where You Like to Go Next:Successive Point-of-Interest Recommendation[C]//International Joint Conference on Artificial Intelligence,2013.
[7]Lian D,Zhao C,Xie X,et al.GeoMF:Joint Geographical Modeling and Matrix Factorization for Point-of-Interest Recommendation[C]//Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining,2014:831-840.
[8]禹文豪,艾廷华.核密度估计法支持下的网络空间POI点可视化与分析[J].测绘学报,2015,44(1):82-90.
[9]王爽,李炯.基于城市网络空间的POI分布密度分析及可视化[J].城市勘测,2015,21(1):21-25.
[10]Yuan J,Zheng Y,Xie X.Discovering Regions of Different Functions in a City Using Human Mobility and POIs[C].ACM SIGKDD International Conference on Knowledge Discovery and Data Mining,2012:186-194.
[11]胡庆武,王明,李清泉.利用位置签到数据探索城市热点与商圈[J].测绘学报,2014,43(3):314-321.
[12]王波,甄峰,张浩.基于签到数据的城市活动时空动态变化及区划研究[J].地理科学,2015,35(2):151-160.
[13]陈蔚珊,柳林,梁育填.基于POI数据的广州零售商业中心热点识别与业态集聚特征分析[J].地理研究,2016,35(4):703-716.
[14]Shen Y,Karimi K.Urban Function Connectivity:Characterisation of Functional Urban Streets with Social Media Check-in Data[J].Cities,2016,55:9-21.
[15]Zhi Y,Li H,Wang D,et al.Latent Spatio-temporal Activity Structures:A New Approach to Inferring Intra-urban Functional Regions Via Social Media Check-in Data[J].Geo-spatial Information Science,2016,19(2):94-105.
[16]Li Q,Zhang T,Wang H,et al.Dynamic Accessibility Mapping Using Floating Car Data:A Network-constrained Density Estimation Approach[J].Journal of Transport Geography,2011,19(3):379-393.
[17]钟少颖,岳未祯,张耘.基于公交刷卡数据和兴趣点数据的城市街区功能类型识别研究--以北京市朝阳区为例[J].城市与环境研究,2016(3):67-85.
[18]程静,刘家骏,高勇.基于时间序列聚类方法分析北京出租车出行量的时空特征[J].地球信息科学学报,2016,18(9):1 227-1 239.
[19]Parzen E.On Estimation of a Probability Density Function and Mode[J].Ann.Math.Statist.,1962,33(3):1 065-1 076.