基于DPI数据的人群分析方法及实践  

Crowd Analysis Method and Practice Based on DPI Data

作　　者：范家杰 宫云平[1] FAN Jiajie;GONG Yunping(Research Institute of China Telecom Co.,Ltd.,Guangzhou 510630,China)

机构地区：[1]中国电信股份有限公司研究院,广东广州510630

出　　处：《移动通信》2020年第10期61-65,共5页Mobile Communications

摘　　要：随着社会的发展,人们对公众场合安全问题越来越重视,对热点区域人流监控的需求日益旺盛。传统的方法是通过摄像头、红外等设备进行监控[1],但是这种方法投入大,耗时耗力,不太适合大范围监控区域。针对这一问题,提出一种基于DPI数据的实时人群分析方案,通过采集用户上网行为形成的海量DPI数据,对DPI数据进行实时解析,可以获得包括地理位置、访问网站、使用时长等信息,然后根据地理位置划分出不同区域,最后按区域进行分类汇总分析,并输出人群分布以及使用爱好等情况。本方案已经成功应用于实际系统,取得良好效果。With the development of society,people pay the increasing attention to the safety of public places,and the demand for crowd monitoring in hot regions is growing.The traditional method is to monitor through cameras,infrared and other equipment,but this method is expensive,time-consuming and unsuitable for large-scale monitoring regions.In order to solve this issue,this paper proposes a real-time crowd analysis solution based on DPI data.By collecting massive DPI data formed by*users online behavior and analyzing the DPI data in real time,we first obtain information including geographic location,website visits,usage time,etc.,and then divide different regions according to geographical location.Finally,the classification and summary analysis are performed and the crowd distribution and usage preferences are output.The proposed solution has been successfully applied to the actual system and achieved good results.

关 键 词：DPI 结构化流 人群分析 

分 类 号：TN91[电子电信—通信与信息系统]