主题信息搜索系统中的搜索策略研究

针对主题搜索引擎反馈信息主题相关度低的问题，提出了将遗传算法与基于内容的空间向量模型相结合的搜索策略。利用空间向量模型确定网页与主题的相关度，并将遗传算法应用于相关度判别，提高主题信息搜索的准确率和查全率。在Heritrix框架基础上，利用Eclipse3．3实现了相应功能。实验结果表明，搜索策略改进后的系统抓取主题页面所占比例与原系统相比提高了约30％。

Research of the Searching Strategy in the Topic Search System

To overcome the shortcomings of the subject search engine with low topic relevance in feedback, this paper pro- poses a searching strategy based on genetic algorithm and Vector Space Model. It identifies correlation between the web pages by vector space model, and distinguishes the correlation by genetic algorithm, to improve the precision rate and re- call rate in the process of topic search. Based on Heritrix, it implements the functions in the Eclipse 3.3 system. The ex- perimental results show that the new strategy improves the proportion between the topic page number and the total num- ber of pages about 30 %.