摘 要：基于移动大数据，本文对用户通话到达情况（次数）进行了研究。由于人们生活习惯具有时间规律性，齐次的泊松过程不能完全适合基站的通话到达规律，因此本文引入非齐次泊松过程，在一定程度上解决了齐次泊松过程的不足。根据用户通话到达情况，提出采用非齐次复合泊松过程来估算一段时间某一基站通话总共的时间，从而根据通话流量为基站的合理调度、分配资源提供依据。
关键词：用户行为；通话到达；非齐次泊松过程；复合泊松过程
中图分类号：TP274 文献标识码：A 文章编号：2096-4706（2019）12-0058-03
Research on Mobile User Behavior Analysis Based on Big Data
WANG Changhui1，MA Qingli2
（1.Unit 31431，Shenyang 110000，China；2.University of Science and Technology of China，Hefei 230026，China）
Abstract：Based on mobile big data，this paper studies the call arrival condition （times） of users. Due to the time regularityof people’s living habits，the homogeneous poisson process is not completely suitable for the call arrival rule of the base station.Therefore，this paper introduces the non-homogeneous poisson process to solve the deficiency of the homogeneous poisson process tosome extent. According to the arrival condition of the user’s call，the non-homogeneous compound poisson process is proposed toestimate the total time of a base station’s call in a certain period of time，so as to provide a basis for the reasonable scheduling andresource allocation of the base station according to the call flow.
Keywords：user behavior；call arrival；nonhomogeneous poisson process；compound poisson process
参考文献：
[1] Cisco. Cisco Visual Networking Index：Global Mobile DataTraffic Forecast Update，2016–2021 White Paper [EB/OL]. https://www.cisco.com/c/en/us/solutions/collateral/service-provider/visualnetworking-index-vni/white-paper-c11-738429.html，2017-03-28.
[2] Willkomm D，Machiraju S，Bolot J，et al. Primary userbehavior in cellular networks and implications for dynamic spectrumaccess [J]. IEEE Communications Magazine，2009，47（3）：88-95.
[3] Erlang A.K. The Theory of Probabilities and TelephoneConversations [J]. Nyt Tidsskrift for Matematik B，1909（20）：33.
[4] Jabbari B. Teletraffic aspects of evolving and next-generationwireless communication networks [J]. IEEE Pers. Commun.，1996，3（6）：4-9.
[5] Opechowski Z，Correia L M. Analysis of traffic distributionsin GSM [C]// Microwaves，Radar and Wireless Communications. 2000.MIKON-2000. 13th International Conference on. S.l.：s.n.，2000：390-394.
[6] Yuksel B，Cingoz M，Karabulut G，et al. Call arrivalmodel for GSM network including handover [C]// IEEE InternationalSymposium on Advanced Networks & Telecommunication Systems.IEEE，2009.
作者简介：
王长会（1974-），男，汉族，陕西西安人，工程师，硕士，研究方向：电工技术、网络安全.
马庆利（1982-），男，汉族，山西怀仁人，博士，研究方向：数据融合、模式识别、语音编码。