摘要
针对现有的搜索引擎难以满足企业不断增长的需求的问题,在传统搜索引擎的基础上提出了一种企业专用搜索引擎的模型框架,给出了利用粗糙集和数据挖掘方法进行Web内容分析的算法以及基于Bayes方法的个性化学习算法,从而使搜索策略得到了优化,提高了搜索引擎的智能。最后给出了企业专业搜索引擎的体系结构,讨论了系统的实现并验证了系统的可行性。
With the explosive growth of information available on WWW, current search engines cannot meet the increasing requirement of enterprise users. Based on traditional search engines, this paper proposes a modeling framework for enterprise professional search engines. The Web content analysis algorithms based on rough set and data mining as well as an individuation learning algorithm based on the Bayesian method are also presented, which enable users to optimize the search strategies and to improve the intelligence of search engines. Lastly, the architecture and implementation of the search engines are discussed. The feasibility is also validated.
出处
《西安理工大学学报》
CAS
2006年第1期10-14,共5页
Journal of Xi'an University of Technology
基金
国家自然科学基金资助项目(50475039)
陕西省自然科学基金资助项目(2004E202)
关键词
数据挖掘
专业搜索引擎
粗糙集
学习算法
data mining
professional search engine
rough set
learning algorithm