摘要
B2B垂直搜索引擎是垂直搜索引擎在电子商务领域的应用。怎样更好地对互联网中海量的企业产品信息进行抽取和去噪,是当前B2B垂直搜索引擎构建中所面临的重要问题。介绍了B2B垂直搜索引擎的特征;分析了一般企业网站的基本结构,在此基础上提出一种面向B2B垂直搜索引擎的企业站点产品信息去噪方法;给出了该方法的实验结果。使用这种方法抽取到的产品信息可用于指导产品进一步的分类工作。
B2B vertical search engine is a kind of vertical searching engines and used for E - business. Now it is an important issue that how to eliminate noise and extract useful manufacture information from corporation websites. The characters of B2B vertical search engine is introduced briefly first, then the general structure of the corporation websites is analyzed, and a method of eliminating noisy information in corporation websites is proposed, at last the result of experiments is given. The information extracted by that method can help the manufacture classification.
出处
《计算机技术与发展》
2008年第12期70-73,共4页
Computer Technology and Development
基金
国家自然科学基金(60675030)
关键词
B2B垂直搜索引擎
信息抽取
去噪
企业站点树
B2B vertical search engine
information extraction
noise elimination
corporation website tree
