摘要
元搜索引擎结果覆盖面广,易于维护,实现简单,能够提供比较全面的结果给用户。后缀树聚类算法(STC)充分考虑了文本集合的语言学特征,并引入了短语特性,从而产生了较好的聚类效果。本文将后缀树聚类算法应用到元搜索引擎中,从而增强了结果的可浏览性,提高了搜索的精度。实验结果表明,STC算法在查准率和时间性能方面都高于传统的聚类算法。
Meta search engine has many advantage,its retrieve results corver a wide range,it easy to maintain and achieve,it also can provide a more comprehensive results to users. Suffix tree clustering algorithm （STC） does not treat a document as a set of word but rather as a string,making use of proximity information between words,so it has a good clustering effect. Suffix tree clustering algorithm applied to the meta search engine,thus enhancing the browsing of retrieve results,improving the accuracy of the retrieve results.The experimental results show that STC algorithm has a better performance than traditional clustering algorithm.
出处
《微计算机信息》
2010年第3期204-206,共3页
Control & Automation
基金
基金申请人:杨天奇
项目名称:基于神经网络的时序数据库相挖掘方法研究
基金颁发部门:广东省自然科学基金项目(5006102)
关键词
元搜索引擎
文本聚类
后缀树
meta search engine
Text Clustering
Suffix tree
