基于元搜索的结果融合模型的改进与实现*

作者：温颖 日期：2009-06-17/span> 浏览：2793 查看PDF文档

基于元搜索的结果融合模型的改进与实现*

温颖
(杭州职业技术学院 信息电子系,浙江 杭州 310018)

摘要：针对元搜索引擎返回结果无序的问题，提出了运用特征模板的模糊积分算法来辅助实现文档评价的排序，以“个性化旅游服务平台”为实验基础平台，运用元搜索与垂直搜索相结合的方法，验证了该种改进后的结果融合模型的可行性及其优势。实验结果表明，该方法既能很好地体现文档的行业特性，又能很好地体现文档中特征向量与特征向量之间的相互关系对文档评价的影响。
关键词：模糊积分；元搜索引擎；垂直搜索；特征模板；特征向量
中图分类号：TP311文献标识码：A文章编号：1001-4551(2009)05-0069-04

Implement and enhancement of the metasearchbased results combining model
WEN Ying
(Department of Information Science and Electronic, Hangzhou Vocational & Technical College, Hangzhou 310018, China)
Abstract: Aiming at the disorder problem of results from the metasearch engine, the fuzzy integral algorithm using feature template was adopted to achieve aided sort of documents evaluation. Combining metasearch and verticalsearch, the platform of “personalized tourist service”was used to verify the applicable and advantage of the improved results combining model. The experimental results show that the method finely realizes not only the industry characters of the documents, but also the impact to the documents evaluation with the relationship among characteristics vectors.
Key words: fuzzy integral; metasearch engine; vertical search; feature template; characteristics vectors
参考文献(References):
［1］MENG W Y, YU C, LIU K L. Building Efficient and Effective Meta Search Engines［J］. Acm Computing Surveys, 2002,34(1):48-89.
［2］CHAU M. Spidering and Filtering Web Pages for Vertical Search Engines［J］. Program,1980,14:130-137.
［3］LAM K W, LEUNG C H. Rank Aggregation for metasearch Engines.Department of Computer Science and Engineering［D］. HongKong: The Chinese University of Hong Kong,2001.
［4］ASLAM J A, MONTAGUE M. Bayes optimal metasearch:a probabilistic model for combining the results of multiple retrieval systems［R］. Athens, Greece: Special Interest Group on Information Retrieval,2000.
［5］张强弓，喻国宝，廖湖声，等.一种元搜索引擎的查询结果处理模型［J］.华南理工大学学报：自然科学版，2004（S1）:47-51.
［6］VOGT C C, COTT RELL G W. Fusion via a linear combination of scores［J］. Information Retrieval,1998,1(3):151-173.
［7］MUROFUSHI T, SUGENO M. Fuzzy measure and fuzzy integral［R］. Japan: Department of Computational Intelligence and Systems Science, Tokyo Institute of Technology, 4259-G3-47 Nagatsuta, Midoriku, 226-8502 Yokohama.
［8］BEITZEL S M, JENSEN E C, CHOWDHURY A, et al. Results on fusion of effective retrieval strategies in the same information retrieval system［R］. Chicago: Information Retrieval Laboratory Department of Computer Science Illinois Institute of Technology, IL 60616.
［9］GODOY D, AMANDI A. Modeling user interests by conceptual clustering［R］. ISISTAN Research Institute, UNICEN University Campus Universitario, Tandil(7000), Buenos Aires, Argentina,2005.