基于话单数据的移动通信用户画像研究
|
摘要
用户通话产生的详细话单数据具有丰富的时空信息和社交信息,这些信息在一定程度上反映了用户的生活习惯和社交模式,对于移动通信用户画像研究具有重要意义.我们的研究是基于中国某运营商提供的10 000名用户一个月详细话单数据,本文从用户日常移动模式方面提取移动距离、回旋半径、访问点个数和移动方向熵特征,从用户社交生活方面提取通话时长、联系人数量、主叫比率和社交熵特征,利用上述特征对用户进行群体划分和构建用户词云名片,从而完成对移动通信用户的画像研究.本文使用用户话单数据为推测用户属性、理解用户特征提供了新的视角.
Call detail records contain rich spatio-temporal information and social information, which partly reflect users' habits and social pattern. It is of great significance for the study of mobile communication user profiling. Our study is based on a monthly call detail records of 10 000 subscribers provided by a Chinese telecom operator. In this study, on the one hand, we extract the moving distance, the radius of gyration, the number of access points, and the entropy of moving directions to characterize user's mobile pattern. On the other hand, we extract the call duration, the number of contact, the ratio of calling, and the entropy of sociality to characterize user's social life. Then users are divided into groups and each user gets a word cloud card based on these features. So the portrait study of mobile communication users is completed.Our work is a promising step towards inferring user attributes and understanding user characteristics using call detail records.
Call detail records contain rich spatio-temporal information and social information, which partly reflect users' habits and social pattern. It is of great significance for the study of mobile communication user profiling. Our study is based on a monthly call detail records of 10 000 subscribers provided by a Chinese telecom operator. In this study, on the one hand, we extract the moving distance, the radius of gyration, the number of access points, and the entropy of moving directions to characterize user's mobile pattern. On the other hand, we extract the call duration, the number of contact, the ratio of calling, and the entropy of sociality to characterize user's social life. Then users are divided into groups and each user gets a word cloud card based on these features. So the portrait study of mobile communication users is completed.Our work is a promising step towards inferring user attributes and understanding user characteristics using call detail records.
引文
1 Calabrese F,Diao M,Di Lorenzo G,et al.Understanding individual mobility patterns from urban sensing data:A mobile phone trace example.Transportation Research Part C:Emerging Technologies,2013,26:301-313.[doi:10.1016/j.trc.2012.09.009]
2 Becker R,Cáceres R,Hanson K,et al.Human mobility characterization from cellular network data.Communications of the ACM,2013,56(1):74-82.[doi:10.1145/2398356]
3 González MC,Hidalgo CA,Barabási AL.Understanding individual human mobility patterns.Nature,2008,453(7196):779-782.[doi:10.1038/nature06958]
4 Amini A,Kung K,Kang CG,et al.The impact of social segregation on human mobility in developing and industrialized regions.EPJ Data Science,2014,3:6.[doi:10.1140/epjds31]
5 J?rv O,Ahas R,Saluveer E,et al.Mobile phones in a traffic flow:A geographical perspective to evening rush hour traffic analysis using call detail records.PLoS One,2012,7(11):e49171.[doi:10.1371/journal.pone.0049171]
6 Thuillier E,Moalic L,Lamrous S,et al.Clustering weekly patterns of human mobility through mobile phone data.IEEE Transactions on Mobile Computing,2018,17(4):817-830.[doi:10.1109/TMC.2017.2742953]
7 Yang XP,Fang ZX,Xu Y,et al.Understanding spatiot emporal patterns of human convergence and divergence using mobile phone location data.ISPRS International Journal of Geo-Information,2016,5(10):177.[doi:10.3390/ijgi5100177]
8 Schneider CM,Belik V,CouronnéT,et al.Unravelling daily human mobility motifs.Journal of the Royal Society Interface,2013,10(84):20130246.[doi:10.1098/rsif.2013.0246]
9 Jiang S,Ferreira J,Gonzalez MC.Activity-based human mobility patterns inferred from mobile phone data:A case study of Singapore.IEEE Transactions on Big Data,2017,3(2):208-219.[doi:10.1109/TBDATA.2016.2631141]
10 Kanungo T,Mount DM,Netanyahu NS,et al.An efficient kmeans clustering algorithm:Analysis and implementation. IEEE Transactions on Pattern Analysis and Machine Intelligence,2002,24(7):881-892.[doi:10.1109/TPAMI.2002.1017616]
2 Becker R,Cáceres R,Hanson K,et al.Human mobility characterization from cellular network data.Communications of the ACM,2013,56(1):74-82.[doi:10.1145/2398356]
3 González MC,Hidalgo CA,Barabási AL.Understanding individual human mobility patterns.Nature,2008,453(7196):779-782.[doi:10.1038/nature06958]
4 Amini A,Kung K,Kang CG,et al.The impact of social segregation on human mobility in developing and industrialized regions.EPJ Data Science,2014,3:6.[doi:10.1140/epjds31]
5 J?rv O,Ahas R,Saluveer E,et al.Mobile phones in a traffic flow:A geographical perspective to evening rush hour traffic analysis using call detail records.PLoS One,2012,7(11):e49171.[doi:10.1371/journal.pone.0049171]
6 Thuillier E,Moalic L,Lamrous S,et al.Clustering weekly patterns of human mobility through mobile phone data.IEEE Transactions on Mobile Computing,2018,17(4):817-830.[doi:10.1109/TMC.2017.2742953]
7 Yang XP,Fang ZX,Xu Y,et al.Understanding spatiot emporal patterns of human convergence and divergence using mobile phone location data.ISPRS International Journal of Geo-Information,2016,5(10):177.[doi:10.3390/ijgi5100177]
8 Schneider CM,Belik V,CouronnéT,et al.Unravelling daily human mobility motifs.Journal of the Royal Society Interface,2013,10(84):20130246.[doi:10.1098/rsif.2013.0246]
9 Jiang S,Ferreira J,Gonzalez MC.Activity-based human mobility patterns inferred from mobile phone data:A case study of Singapore.IEEE Transactions on Big Data,2017,3(2):208-219.[doi:10.1109/TBDATA.2016.2631141]
10 Kanungo T,Mount DM,Netanyahu NS,et al.An efficient kmeans clustering algorithm:Analysis and implementation. IEEE Transactions on Pattern Analysis and Machine Intelligence,2002,24(7):881-892.[doi:10.1109/TPAMI.2002.1017616]