数智时代背景下的广义经典名方遴选
Selection of generalized ancient classic traditional Chinese medicine prescriptions under the background of digital and intelligence era
李可千 1朱彦 2姚克宇2
作者信息
- 1. 长春中医药大学医药信息学院,长春 130117
- 2. 中国中医科学院中医药信息研究所,北京 100700
- 折叠
摘要
经典名方是中药方剂中最为杰出的代表,是中医药传承发展的重要突破口之一.由于现有经典名方的遴选标准缺失客观量化指标,人工遴选过程难以确保可持续性和一致性,有可能遗漏掉部分有潜在开发价值的方剂,难以满足后续批次经典名方发布及新药研发的现实需要.数智时代背景下,采用循证、大数据、自然语言处理技术、本体技术、人工智能等方法,可以从高质量数据支撑、古籍证据等级评价、经典名方筛选综合评价模型等方面,为大规模的经典名方遴选提供辅助.为经典名方的持续性研究与发布、经典名方知识产权保护和新药研发等方面提供支持.
Abstract
Ancient classic traditional Chinese medicine(TCM)prescriptions are the most outstanding representatives of traditional Chinese medicine prescriptions and one of the important breakthroughs in the TCM inheritance and development.Due to the lack of objective quantitative indicators in the selection criteria for ancient classic TCM prescriptions,it is difficult to ensure sustainability and consistency in the manual selection process,and it is possible to omit some prescriptions with potential development value,which is difficult to meet the practical needs of the release of subsequent batches of ancient classic TCM prescriptions,active protection of intellectual property rights and new drug research and development.Under the background of the era of digital intelligence,evidence-based,big data,natural language processing technology,ontology technology and artificial intelligence can provide high-quality data support,grade evaluation of ancient book evidence,and finally form a comprehensive evaluation model for the screening of ancient classic TCM prescriptions,thus providing support for large-scale continuous research,selection and release of classic and famous prescriptions,and new drug research and development.
关键词
经典名方/机器学习/人工智能/数据挖掘/方剂/遴选Key words
Ancient classic traditional Chinese medicine prescriptions/Machine learning/Artificial intelligence/Data mining/Prescription/Selection引用本文复制引用
基金项目
国家自然科学基金项目(82174534)
中央级公益性科研院所基本科研业务费专项(ZZ13-YQ-126)
中国中医科学院基本科研业务费自主选题项目(ZZ160311)
中国中医科学院中医药信息研究所所级课题(JJY202308-2019YFC1710401)
出版年
2024
NETL
NSTL
万方数据