基于本体的受限领域文本信息提取方法

摘要

Aiming at data conversion for non-formatted message in simulated training system of command informatization, this paper discusses an information extraction method from non-formatted message according to the demand of simulation-driven information. The paper builds the domain ontology model and the syntax rules after the ontology concept is introduced into the limited area ( military area) and proposes the information extraction method based on the ontology. With the technical support of eXtensible Markup Language (XML) Schema and VC + +. NET, the method achieves information extraction in practice. It lays foundation for data conversion in the actual simulation work.%针对指挥信息化模拟训练系统中自由格式报文转换问题，根据仿真驱动信息的需求，讨论了对自由格式报文进行信息提取的实现方法。在受限领域（军事领域）中引入本体概念，构建了领域本体模型及语法规则，提出了基于本体的信息提取方法，采用可扩展标记语言（eXtensible Markup Language,XML）和VC＋＋．NET技术相结合，实现对文书的信息提取，为进一步的数据转换和应用奠定了基础。