基于信息抽取的历代方剂药物知识发现方法及应用

An efficient approach of acquiring knowledge from ancient prescriptions and medicines based on information extraction

文章全面客观分析了现有中医方剂数据资源现状与问题,提出一种可以解决方剂数据自动结构化问题的信息抽取技术。在现有研究成果的基础上,设计和实现了一套适合历代方剂药物信息抽取系统,对半结构化的方剂数据进行处理。首先建立了中药术语、剂量单位等专业词典;然后通过分词、术语识别和标准化、剂量的自动规范化等步骤,快速准确地建立结构化的方剂数据库。最后基于生成的方剂数据库,以应用案例的形式,介绍了历代方剂药物知识发现的实现过程,并根据时间序列分析这一较为客观的证据,结合中国方剂发展演变的历史进程对千余年来方剂用药剂量的变化规律进行探讨与分析。

This paper put forward a technology of information extraction for solution of automatic structured of prescription database based on objective analysis of the current situation and problems of existing prescriptions of traditional Chinese medicine. An information extraction system was appropriate for information extraction of prescription and medicines of past dynasties were designed based on the current research achievements, and the semi-structure data of prescriptions were processed. Firstly, the specialized vocabularies such as traditional Chinese medicine terminology, dose unit and so on were built. Then the prescription database was built quickly and accurately by the steps of recognition and standardization of participle and terminology, automatic standardization of dose and so on. Finally, the discovery process of generations of prescription drugs knowledge was introduced in the form of application cases based on the generated prescription database, and objective evidence was analyzed according to time series. The change rule of dosage in prescriptions in thousands of years was discussed and analyzed combined with the historical development of prescriptions.