日志采掘.pptVIP

Data Mining and Warehousing: Session 8 Mining Complex Data and Advanced Mining Techniques Weblog mining and Web mining Mining Complex Data and Advanced Mining Techniques Time-series data mining Spatial data mining Multimedia data mining Text and image data mining Visual data mining On-Line Analytical Mining (OLAP mining) Weblog mining and Web mining Outline Weblog Mining: 日志采掘 Collection of Web Accesses Tools for Web Log Analysis 日志分析 Data Cleaning and Transformation 数据整理 Data Cube Creation 数据立方 OLAP on Web Log Databases 日志库联机处理 Data Mining on Web Log Records日志记录采掘 Time Series Analysis 时序分析 Towards Data Mining in Digital Libraries.数字图书馆 What Is Weblog Mining? 什么是 Web Servers register a log entry for every single access they get. WEB每项有日志 A huge number of accesses (hits) are registered and collected in an ever-growing web log. 日志数据量大 Weblog mining: Condense these colossal files of raw web log data in order to mine significant and useful information.从日志中发现有意义的信息 Motivation: Why Weblog Mining? 为什么 Enhance server performance 改善服务 Improve web site navigation改善导航 Improve system design of web applications 应用 Target customers for electronic commerce 电子商业 Identify potential prime advertisement locations找出潜在的广告对象 Existing Web Log Analysis Tools 现成工具 There are more than 30 commercially available applications. 30个相关软件 Many more are available free. 还有免费软件 We reviewed over 20 such analysis tools.分析20个 Many of them are slow and make assumptions to reduce the size of the log file to analyse.慢 Most are limited in the result they provide, mainly frequency counts . 结果只有访问频度 Existing Web Log Analysis Tools (cont.)现成工具 Frequently used, pre-defined reports: Rreport of hits and bytes transferred 点次，字节 List of top requested URLs ` 顶层URL清单 List of top referrers 顶层连接 List of most common browsers Hits per hour/day/week/month 被查次数/时间 Hits per Internet domain 被查次数/域 Error report 出错被告 Directory tree report, etc. 目录树 Tools are limited in thei