基于ELK的用户访问行为分析技术  

Technology of User Behavior Analysis Based on ELK

作　　者：陈楠 陈东辉[1] 邓莉[1] Chen Nan;Chen Donghui;Deng Li(National Meteorological Information Centre, Beijing 100081)

机构地区：[1]国家气象信息中心,北京100081

出　　处：《气象科技进展》2018年第1期181-185,共5页Advances in Meteorological Science and Technology

基　　金：国家气象信息中心青年科技基金课题(NMICQJ201609)

摘　　要：针对国家气象业务内网用户访问行为记录,基于ELK(Elasticsearch日志检索+Logstash日志收集+Kibana查询展示)流量日志处理技术,建立了气象业务内网日志采集和智能分析系统,实现了对访问用户的行为跟踪和针对不同类别用户的访问热点分析、趋势分析和对比分析,通过对单个页面停留时间、点击流、相关点击量等指标结合关联、聚类分析等数据挖掘算法实现对网站流量日志的深度分析,为建设更加专业和有针对性的气象大数据服务平台提供参考。通过在国家气象业务内网建设中的应用,证明该系统有助于发掘共享用户的真正需求,对全面提升精细化、专业化气象数据服务能力有积极的作用。According to the users'logs into the National Meteorological Service Network,and based on ELK flow log processing technology,the meteorological network log data collection and intelligent analysis system is established.It realizes the analysis of user behavior tracking and data access for different types of users'access to the hot trend analysis and comparison based on a single page retention time,click stream model and the related click index.At the same time,it combines with correlation,clustering analysis and other data mining algorithms to achieve the depth analysis of the site traffic log.It provides a reference for the construction of more specialized and targeted meteorological data service platform.Through applications in the construction of the National Meteorological Service Network,it is proved that the system is helpful to discover the real needs of the users,and has a positive effect on improving the service ability of the refined and specialized meteorological data.

关 键 词：网站分析 ELK 用户行为分析 气象服务 

分 类 号：P409[天文地球—大气科学及气象学]