基于公共交通智能卡数据的可视化分析  

Visual analysis based on public traffic smart card data

作　　者：夏婷 牛颢[2] 何丽坤 范小朋 朱敏[1] Xia Ting;Niu Hao;He Likun;Fan Xiaopeng;Zhu Min(College of Computer Science,Sichuan University,Chengdu 610065,China;Sichuan Institute of Computer Sciences,Chengdu 610041,China;Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences,Shenzhen Guangdong 518055,China)

机构地区：[1]四川大学计算机学院,成都610065 [2]四川省计算机研究院,成都610041 [3]中国科学院深圳先进技术研究院,广东深圳518055

出　　处：《计算机应用研究》2020年第6期1750-1754,共5页Application Research of Computers

基　　金：国家“973”计划资助项目(2015CB352400);成都市科技惠民项目(2016-HM01-00411-SF)。

摘　　要：针对现有公共交通数据的可视分析方法很难在不同空间粒度下对乘客时空分布、客流时空分布、区域间客流时序变化进行多任务分析的问题,设计实现了一个多视图融合的可视化分析系统。该系统结合城市公共交通的智能卡数据、车辆GPS数据、地铁和公交线路信息,利用出行链路模型和基于出行时空特征的回归模型完成了乘客起讫点(origin-destination,OD)推断;然后,设计了层次聚类的地图可视化方法,结合了融合方位信息的玫瑰图和动态对比堆叠折线流图来分析各区域间的客流时序特点、关联关系;最后,利用真实的深圳市公共交通数据的可视分析结果验证了系统的有效性。A visual analysis method for existing public transportation data is difficult to analyze the spatial and temporal distribution of passengers,the spatial and temporal distribution of passenger flow,and the inter-regional passenger flow timing changes under different spatial granularities. This paper proposed a multi-view fusion visual analysis system. The system combined smart card data,vehicle GPS data,subway and bus route information of urban public transportation,then used the travel link model the regression model based on travel time and space characteristics’ to complete the origin-destination( OD) inference.Then,this paper designed the hierarchical visualization method of map visualization,and combined the rose map and the dynamic contrast stacking line graph to analyze the passenger flow timing characteristics and correlation between regions. Finally,visual analysis’ results of real public transportation data in Shenzhen verify the effectiveness of the system.

关 键 词：公共交通数据 OD推断 层次聚类地图可视化 可视化研究 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]