English

应用科学学报 ›› 2003, Vol. 21 ›› Issue (4): 357-361.

• 论文 • 上一篇    下一篇

基于蚁群算法的Web站点导航

业宁1,2, 梁作鹏1, 董逸生1   

  1. 1 东南大学计算机科学与工程系 江苏 南京 210096;
    2 南京林业大学计算机系 江苏 南京 210037
  • 收稿日期:2002-09-22 修回日期:2002-12-27 出版日期:2003-12-10 发布日期:2003-12-10
  • 作者简介:业宁(1967-),男,江苏江宁人,博士生;董逸生(1940-),男,江苏启东人,教授,博导.
  • 基金资助:
    江苏省九五重点攻关课题(BJ980171);江苏省十五高科技(BJ2001013);校科研基金(X020701(Z))资助项目

A Web Site Navigation Based on Ant Colony Algorithm

YE Ning1,2, LIANG Zuo-peng1, DONG Yi-sheng1   

  1. 1. Department of Computer Science and Engineering, Southeast University, Nanjing 210096, China;
    2. Department of Computer, Nanjing Forestry University, Nanjing 210037, China
  • Received:2002-09-22 Revised:2002-12-27 Online:2003-12-10 Published:2003-12-10

PDF

73

被引次数

12

摘要： 提出了一种Web站点的导航方法.首先利用蚁群算法对已经存在的Web日志进行训练,构造一个有向图,该有向图的节点和边保存了网页与网页间的链接概率和用户行为规则.利用训练结果,预测访问网站的用户行为,根据其行为推荐网页,最后的测试结果表明该方法比单纯的概率分析和关联规则具有更高的精度.

关键词: 蚁群算法, Web日志, Web导航, 数据挖掘

Abstract: A web site navigation algorithm based on the ant colony algorithm is proposed in this paper, First the algorithm is trained against the previous web log. As a result, a directed graph is obtained with each vertex containing a set of users' navigation rules and each edge containing the linking probability between adjacent pages. Next we forecast users' navigation according to the directed graph. Finally, the recommended pages based on the predicted navigation can be obtained. The experiment result was satisfactory.

Key words: Web navigation, Web log, ant colony algorithm, data mining

中图分类号: