| 基于模糊聚类的超链分析算法 |
| |
| 引用本文： | 严海兵,崔志明.基于模糊聚类的超链分析算法[J].情报学报,2007,26(3):361-365. |
| |
| 作者姓名： | 严海兵 崔志明 |
| |
| 作者单位： | 1. 苏州科技学院信息资源与技术开发研究所,苏州,215011;苏州大学计算机科学与技术学院,苏州,215006
2. 苏州大学计算机科学与技术学院,苏州,215006 |
| |
| 摘 要： | 基于关键字匹配的搜索引擎排序网页时仅仅考虑评价网页的重要性,而忽视分类;基于分类目录的搜索引擎很难动态分析Web信息。本文在分析它们不足的前提下,提出利用模糊聚类的方法对搜索引擎的检索结果进行动态分类,依据超链分析算法PageRank和Web文档隶属度相结合进行分类排序,并给出具有调节值的结合公式。实验证明,该算法能够更有效地满足用户的需要,提高检索效率。
|
| 关 键 词： | 知网 聚类 K-mean算法 |
| 修稿时间： | 2006年6月19日 |
An Auto-Categorizing Algorithm for Web Pages Ranking |
| |
| Yan Haibing,Cui Zhiming.An Auto-Categorizing Algorithm for Web Pages Ranking[J].Journal of the China Society for Scientific andTechnical Information,2007,26(3):361-365. |
| |
| Authors: | Yan Haibing Cui Zhiming |
| |
| Abstract: | Search engines on string match take into account Web pages ranking by estimating the pages' authority,while ignoring Web pages categorizing.It is difficult for search engines on directory categories to auto-categorize Web pages in the Intemet.For these deficiency of displaying the results in the current search engines,this paper attempts to improve pages ranking algorithm on hyperlink analysis in another point of view.By integrating the traditional hyperlink analysis and fuzzy clustering theory,the authors present an algorithm based on Auto-Categorizing,thereby a coefficient is got to adjust to the practical conditions.And the authors' experiment shows that this algorithm has better performance. |
| |
| Keywords: | fuzzy clustering hyperlink analysis search engine Web cluster |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
