首页 | 本学科首页   官方微博 | 高级检索  
     

基于PageRank和HITS的Web搜索
引用本文:常庆,;周明全,;耿国华. 基于PageRank和HITS的Web搜索[J]. 微机发展, 2008, 0(7): 77-79
作者姓名:常庆,  周明全,  耿国华
作者单位:西北大学可视化研究所 陕西西安710127
基金项目:国家自然科学基金(17020503)
摘    要:介绍了目前应用较为广泛的两种算法——PageRank算法和HITS算法。PageRank算法是基于用户随机的向前浏览网页的直觉知识,HITS算法考虑的是Authoritive网页和Hub网页间的加强关系。PageRank算法的基本思想是:如果一个页面被许多其他页面引用,则这个页面很可能是重要页面;一个页面尽管没有被多次引用,但被一个重要页面引用,那么这个页面很可能也是重要页面;一个页面的重要性被均分并传递到它所引用的页面。而HITS算法则专注于改善泛指主题检索的结果,通过一定的计算(迭代计算)方法以得到针对某个检索提问的最具价值的网页,即排名最高的authority。

关 键 词:PageRank  HITS  特征向量  检索主题  链按分析

PageRank and HITS-Based Web Search
CHANG Qing,ZHOU Ming-quan,GENG Guo-hua. PageRank and HITS-Based Web Search[J]. Microcomputer Development, 2008, 0(7): 77-79
Authors:CHANG Qing  ZHOU Ming-quan  GENG Guo-hua
Affiliation:CHANG Qing, ZHOU Ming-quan, GENG Guo-hua ( Institute of Visualization Technology, Northwest University, Xi' an 710127, China)
Abstract:Introduce the wider application of the present two algorithms:PageRank algorithm and HITS algorithm.PageRank algorithm is based on random users browse the website ahead of intuitive knowledge.HITS algorithm considered is Authoritive and Hub website homepage the strengthening of relations.PageRank algorithm's basic idea: if a page is used in many other pages,this page is likely to be important pages;although no one page was repeatedly quoted,but it was an important quote pages,this page may also be important page;the importance of a page are transfered to the pages which it cites.HITS algorithm focus on improving the generic theme of the search results,through some calculation(iterative) method in order to get a response to a search of the most valuable pages,the highest ranking authority.
Keywords:PageRank  HITS  eigenvector  search theme  link analysis
本文献已被 CNKI 维普 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号