基于WEB日志挖掘优化VOD系统中影片的归类  

MINING WEBLOGS TO IMPROVE THE FILM CLASSIFICATION ON VOD SYSTEM

作　　者：翁小兰[1] 孙蕾[2] 

机构地区：[1]淮阴师范学院计算机系,江苏淮安223001 [2]华东师范大学计算机系,上海200062

出　　处：《计算机应用与软件》2007年第10期125-127,共3页Computer Applications and Software

摘　　要：提出一种从Web日志出发根据用户访问路径找出用户期望的影片归类的方法,通过该方法可以优化视频点播系统的站点结构,提高用户访问效率。算法的主要思想是基于Web日志统计出用户在查找目标影片过程中经过的类别页,并把这些类别页对应的类别作为用户的候选期望归类,最后根据影片各类别的期望支持度确定影片的恰当归类。A way to find the users＇ expected classification of films is proposed according to the users＇ access paths based on Web-log. This way can improve the web structure and enhance the access efficiency of the VOD system. The main idea of the algorithm is that all classification pages which the users have visited when they looked for the films are noted down, and these classifications may be the users＇ expected classifications for the films, and at last a proper classification of every film is produced according to the expected support degree of the classifications.

关 键 词：VOD 网络日志 访问模式 期望支持度 

分 类 号：TP311.13[自动化与计算机技术—计算机软件与理论]