Abstract: The current mainstream web search engines have many shortcomings such as the deficiency of personalization and the low precision. By introducing several improved techniques into a current algorithm, a new personalized query expansion method based on user’s historical interested web pages and historical query terms is proposed in this paper. When a user submits a query keyword to a search engine, the new algorithm can automatically locate the current user’s implicit search intention and compute the term-term associations according to the current user’s interest profile. More personalized expansion words then will be generated by the proposed algorithm and be submitted to the search engine together with the query keyword. Thereby different search results can be returned to different users even though they input the same query keywords. Experimental results show that this method is better than the current algorithm in average precision.

Key words: historical interested web pages, historical query terms, personalized query expansion, term-term associations, search engine

摘要： 针对当前主流web搜索引擎存在信息检索个性化效果差和信息检索的精确率低等缺点, 通过对已有方法的技术改进, 介绍了一种基于用户历史兴趣网页和历史查询词相结合的个性化查询扩展方法。当用户在搜索引擎上输入查询词时，能根据学习到的当前用户兴趣模型动态判定用户潜在兴趣和计算词间相关度，并将恰当的扩展查询词组提交给搜索引擎，从而实现不同用户输入同一查询词能返回不同检索结果的目的。实验验证了算法的有效性，检索精确率也比原方法有明显提高。

关键词: 历史兴趣网页, 历史查询词, 个性化查询扩展, 词间相关度, 搜索引擎