摘要： 针对通用搜索技术难以满足不同背景、不同目的和不同时期的用户查询请求的缺陷，提出一种基于Lucence实现用户兴趣驱动的个性化搜索引擎方法。从Cookie文件分析用户搜索兴趣，构造用户兴趣向量，驱动搜索引擎，产生用户关注度高的搜索结果。实验结果表明，该用户兴趣驱动的个性化搜索引擎能够搜索出用户感兴趣的搜索结果，与传统搜索引擎相比，检索准确率有一定的提高。

关键词: Cookie文件, 个性化搜索, 搜索引擎, 兴趣向量, 用户兴趣

Abstract: Conventional search engine is unsuitable for search requests from people with different cultures, different goals or periods. A method on personalized search engine is proposed in the paper, which analyzes the user search pattern from Cookie, constructs the user interests vector from search pattern, drives the engine by search pattern, hence the presented approach can index the results with high correlation to user interests. It implements the personalized search engine based on Lucence, and experiments show that user interests driven personalized search engines can significantly index the user interested results.

Key words: Cookie file, personalized search, search engine, interest vector, user interests

中图分类号: 

• TP391