基于证券行业半结构化数据的抽取技术

An Extracting technology of Semi-Structured Data in Securities Business

半结构化数据是网络中一种重要的数据形式,其数据抽取和知识发现研究是半结构化数据各项研究的核心.针对互联网上的证券交易系统半结构化的个股资料,根据OEM模型,利用SAS软件建立了半结构化到结构化数据的转换.本文关于信息的抽取技术,提供了一种新的方法,无论为投资者还是为数据挖掘都提供了证券分析的基础,从而能更好地提高抗风险的能力.

Semi-instruetured data is a kind of the important type in networks, and its data extracting and knowledge discovery is the core for semi-structured researches. This paper uses SAS software to transform semi-structured data into structured ones from securities information based on OEM models. It provides a new method on information extracting technology and an analysis basis for both securities investors and data mining to raise abilities for risk prevention.