面向电子交易的商品供应信息抽取模型

随着互联网的普及和电子商务的发展,形成了大量的商品供应信息资源。从企业门户网站和电子市场的海量商品网页中抽取出供应信息资源,是电子交易迫切需要解决的问题。在分析信息抽取过程和商品网页结构的基础上,构建了基于网页DOM树的商品供应信息抽取模型。该模型由网页采集层、HTML文档解析层、信息抽取层和结果处理层组成,并重点对信息抽取层的抽取规则进行了探讨。

Product Information Extraction Model for Electronic Trading

With the development of Internet and electronic commerce, there exists tremendous of product supplying information resources. The crucial problem of electronic trading is the ability to extract useful resources from the huge product pages of enterprises portal and electronic marketplaces. Based on the analysis of information extraction process and the structure of product web page, a product information extraction model based on DOM tree is established. This model is composed by page gathering layer, document parsing layer, information extracting layer and result processing layer. And the extraction rules of information extracting layer is highlighted.