摘要
在分析了传统索引技术的缺陷的基础上,提出了一种基于XML架构信息抽取的多层向量空间的模型,重点阐述了如何建立一个基于XML的Web信息抽取平台,从构造知识库、网页优化和信息抽取这三方面进行研究,并阐述了基于XML的多层向量空间模型及其形成。通过这种技术不仅使网页内容得到了清晰的剖析和抽取,更能大大提高对Web网页文档检索效率和准确率。目的在于寻求一种更为高效简洁的检索方法。
By analyzing the limitations of traditional searching technolcgy, proposes a platform of Web information extraction based on XML and a model of searching technology based on XML construction and multilayer vector space, both of which greatly improve the efficiency of indexing documents. This model not only anatomizes and extracts the documents clearly, but also promotes the efficiency of Web documents searching. The main purpose of it is to find a more efficient and compact searching method.
出处
《计算机技术与发展》
2007年第7期49-52,共4页
Computer Technology and Development
基金
江苏省高技术研究项目(BG2005019)
教育部"高校博士点科研基金项目"(20040285016)
教育部科研重点项目(205059)
