Wang Zhifei, Xie Yanming, Wang Yongyan
Institute of Basic Research in Clinical Medicine, China Academy of Chinese Medical Sciences, Beijing 100700, China.
Zhongguo Zhong Yao Za Zhi. 2011 Oct;36(20):2888-90.
Computerizing extracting information from Chinese medicine literature seems more convenient than hand searching, which could simplify searching process and improve the accuracy. However, many computerized auto-extracting methods are increasingly used, regular expression is so special that could be efficient for extracting useful information in research. This article focused on regular expression applying in extracting information from Chinese medicine literature. Two practical examples were reported in this article about regular expression to extract "case number (non-terminology)" and "efficacy rate (subgroups for related information identification)", which explored how to extract information in Chinese medicine literature by means of some special research method.
将中医药文献中的信息进行计算机提取似乎比手工检索更方便，这可以简化检索过程并提高准确性。然而，许多计算机自动提取方法越来越多地被使用，正则表达式很特别，在研究中提取有用信息时可能很有效。本文重点介绍正则表达式在中医药文献信息提取中的应用。本文报告了两个关于正则表达式提取“病例数（非术语）”和“有效率（用于相关信息识别的亚组）”的实际例子，探讨了如何通过一些特殊的研究方法在中医药文献中提取信息。
