面向汽车行业的品牌竞争分析与可视化  

Detecting Competitive Relationship and Visualization for Auto Brands

作　　者：梁磊[1] 刘玉华[1] 王晓玲[1] 赵大鹏[1] 王长波[1] Liang Lei;Liu Yuhua;Wang Xiaoling;Zhao Dapeng;Wang Changbo(Shanghai Key Laboratory of Trustworthy Computing, East China Normal University, Shanghai 200062)

机构地区：[1]华东师范大学上海市高可信计算重点实验室,上海200062

出　　处：《计算机辅助设计与图形学学报》2017年第4期651-660,共10页Journal of Computer-Aided Design & Computer Graphics

基　　金：国家自然科学基金(615320212;61472141)

摘　　要：互联网的飞速发展,使人们得以从更广泛的平台获取有价值的信息."汽车之家"等论坛网站的数据能帮助企业掌握市场格局,了解自身产品的不足.文中基于"汽车之家"论坛数据,设计了基于图挖掘的社群搜索算法MDect,能够根据用户输入的车系快速定位其所在的竞争社群,实验验证了该算法寻找出的车系社群不仅结构上联系紧密,属性上也具有较高的相似性.此外,还设计了一款整合弦图、流量图、口碑词云等多种视图的可视化系统,以展示车系之间的竞争状况与优劣势原因;最后通过用户调研与案例说明可视化方法的有效性.With the rapid development of Internet,people can get increasing number of valuable data fromvarious platforms.Effective visual analysis of data from professional websites like Autohome can be used tograsp the competitive community and disadvantages of products.In this paper,we proposed an algorithmMDect based on graph mining to detect the competitive market of specific cars.Experiments demonstratethat our method achieves a good balance between structural and attribute similarities.An interactive systemcontaining chord diagram,stream and cloud tags were developed to display the competition.Eventually weillustrated the utility of visualization through user study and cases.

关 键 词：汽车数据 竞争可视化 社群搜索 弦图 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]