| 基于页面聚类的个性化推荐算法研究 |
| |
| 引用本文： | 王志松,张晶磊.基于页面聚类的个性化推荐算法研究[J].燕山大学学报,2007,31(3):217-220. |
| |
| 作者姓名： | 王志松 张晶磊 |
| |
| 作者单位： | 1. 燕山大学,机械工程学院,河北,秦皇岛,066004
2. 中国农业大学,信息与电气工程学院,北京,100083 |
| |
| 摘 要： | 聚类分析算法作为一种主要的Web使用挖掘技术，在个性化推荐系统中得到了广泛应用，然而面对Web动态性所引起的网页的更新以及用户行为方式的改变，已有的聚类算法并不能很好地解决这一问题。针对这一问题，本文以一种无向图的形式表示用户对网站的访问，提出一种可实时反映网站及用户行为变化情况的增量式页面聚类算法，并在页面聚类的基础上提出相应的推荐决策算法动态生成页面推荐。
|
| 关 键 词： | 页面聚类 个性化 推荐算法 |
| 文章编号： | 1007-791X（2007）03-0217-04 |
| 修稿时间： | 2006-11-20 |
Research on personalized recommendation algorithm based on web clustering |
| |
| WANG Zhi-song,ZHANG Jing-lei.Research on personalized recommendation algorithm based on web clustering[J].Journal of Yanshan University,2007,31(3):217-220. |
| |
| Authors: | WANG Zhi-song ZHANG Jing-lei |
| |
| Institution: | 1. College of Mechanical Engineering, Yanshan University, Qinhuangdao, Hebei 066004, China; 2. College of Information and Electrical Engineering, China Agricultural University, Beijing 100083, China |
| |
| Abstract: | As a main web usage mining technology,the clustering algorithm has been widely used in the personalized recommen- dation systems.However,because the update of the web caused by the dynamic web and the change of the user's browsing,the existent clustering algorithm can not solve this problem very well.Here a kind of no-direction graph is employed to express the user's browsing on the web.And a incremental web clustering algorithm that can represent the change of user browsing behavior is proposed in this paper.Based on this,a dynamic web recommendation algorithm is given. |
| |
| Keywords: | web clustering personalized recommendation algorithm |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
