［目的/意义］ 从数字人文视角出发，实现敦煌吐鲁番医药文献的数字化及知识组织与可视化，为敦煌吐鲁番医药文献的传承、普及与智能化服务做出贡献。［方法/过程］ 采用自顶向下方法，参考BIBFRAME书目模型及中医药学语言系统（TCMLS）构建敦煌吐鲁番医药文献本体模型，利用哈工大语言技术云平台LTP实现词性标注与三元组自动抽取，构建敦煌吐鲁番医药文献知识图谱。［结果/结论］ 利用所构建的本体及知识图谱可实现敦煌吐鲁番医药文献知识组织工作，知识图谱能够实现语义查询，为敦煌吐鲁番医药文献的智能化理解奠定基础。
[Purpose/Significance] From the perspective of digital humanities, this paper tries to realize the digitization, knowledge organization and visualization of Dunhuang Turpan medical documents, and contribute to the inheritance, popularization and intelligent service of Dunhuang Turpan medical documents. [Method/Process] The ontology model of Dunhuang Turpan medical literature was constructed by using the top-down method, referring to BIBFRMAE model and TCMLS language system. The part of word tagging and triplet automatic extraction were realized by using the Harbin Institute of Technology language technology cloud platform LTP to construct the Dunhuang Turpan medical literature knowledge graph. [Result/Conclusion] The research successfully used the constructed ontology and knowledge graph to realize the knowledge organization of Dunhuang Turpan medical literature. The knowledge graph can realize semantic query, and lay the foundation of intelligent understanding of Dunhuang Turpan medical literature.
[1] 习近平.决胜全面建成小康社会夺取新时代中国特色社会主义伟大胜利[N].人民日报,2017-10-28(1).
[2] 林穗芳.罗伯托·布萨和世界最早用计算机辅助编辑的巨著《托马斯著作索引》[J].河南大学学报(社会科学版),2007(4):167-174.
[3] 王晓光,徐雷,李纲.敦煌壁画数字图像语义描述方法研究[J].中国图书馆学报,2014,40(1):50-59.
[4] 沈澍农.敦煌吐鲁番医药文献新辑校[M].北京:高等教育出版社,2016.
[5] 裴丽,褚长海.中医古籍文献资源数字化建设探讨[J].图书馆学研究,2001(6):67-68.
[6] 李兵,刘国正,符永驰,等.从中医古籍数据库建设看中医古籍数字化[J].中国中医药信息杂志,2009,16(3):92-93.
[7] 周树斌,周宇婷,施州州,等.基于可视化和内容分析的我国中医古籍数字化研究现状与展望[J].图书情报研究,2020,13(4):101-108.
[8] 雷亚玲,阮绍萍,曹瑾,等.基于古籍文献及名老中医经验的郁病用药规律数据挖掘[J].湖南中医药大学学报,2019,39(3):357-361.
[9] 陈兹满,张伟键,庞龙,等.基于数据挖掘对中医古籍眼科点眼方剂用药规律分析[J].新中医,2017,49(9):142-146.
[10] 宋亚南,邓艳芳,屈乐,等.基于数据挖掘的《儒门事亲》用药规律分析[J].中华中医药杂志,2015,30(8):3017-3020.
[11] CHANDA S, BAAS J, HAITINK D E, et al. Zero-Shot learning based approach for medieval word recognition using deep-learned features[C]//16th international conference on frontiers in handwriting recognition. New York:IEEE, 2018.
[12] FENG S L, MANMATHA R. Classification models for historical manuscript recognition[C]//8th international conference on document analysis and recognition. Seoul:IEEE, 2005.
[13] GROSSO A M D, FIHRI D F, MOHAJIR M E, et al. Digital safeguard of laminated historical manuscripts:the treatise "Poem in Rajaz on medicine" as a case study[C]//20206th IEEE congress on information science and technology. Agadir-Essaouira:IEEE, 2020.
[14] 丛春雨.敦煌中医药精粹发微[M].北京:中国古籍出版社,2000.
[15] 刘冉,李铁华.敦煌脉书《玄感脉经》研究[J].中国中医基础医学杂志,2022,28(3):482-485.
[16] 范崇峰,卞雅莉.敦煌写本《张仲景五脏论》校补[J].中医文献杂志,2021,39(5):1-4.
[17] 周艳,魏玉婷,王觉,等.敦煌针灸医学文献中刺血疗法的发展与应用[J].中国中医基础医学杂志,2020,26(11):1671-1673.
[18] 葛政,万芳.敦煌佛道医方刍考[J].中国中医基础医学杂志,2022,28(3):379-382.
[19] 杨富学,张田芳.回鹘文《针灸图》及其与敦煌针灸文献之关联[J].中医药文化,2018,13(2):5-18.
[20] 张永萍.敦煌医药文书整理[J].甘肃高师学报,2016,21(7):17-21.
[21] 甘肃中医学院. 俄罗斯藏敦煌医药文献的整理研究[Z/OL]. 国家科技成果.[2022-09-09].https://kns.cnki.net/KCMS/detail/detail.aspx?dbname=SNAD&filename=SNAD000001339928.
[22] 孙源源,朱佩枫,李洁,等.基于知识组织的中医知识现代转化模式与路径研究[J].中华中医药杂志,2021,36(8):4843-4846.
[23] 马捷,王珏,孙恒宇,等.基于医案元数据的中医诊疗数据集构建方法与实证研究[J].图书情报工作,2021,65(2):27-36.
[24] 王国玺,李兵,张华敏,等.基于知识组织的医案古籍知识库的构建与思考[J].西部中医药,2019,32(9):49-52.
[25] 李金定.叙词表、元数据与本体之间关系探究[J].图书馆学研究,2007(8):61-64.
[26] 李伊然,钟相根,杨凤,等.基于知识元标引的"病脉证并治"标引模板之构建[J].中国医药导报,2021,18(28):133-138.
[27] 丁侃,张丽君.中医古籍数字资源动态管理经验谈[J].中国医药导报,2018,15(33):110-113.
[28] 丁侃,张丽君.基于本体的中医学术传承脉络构建[J].中医文献杂志,2018,36(5):32-35.
[29] 汤伟平,许坚,李兵,等.岭南温病古籍知识库构建的思路探讨[J].中国医药导报,2020,17(11):136-139.
[27] 林尔正.基于中医骨伤古籍本体的语义检索研究[D].福州:福建中医学院,2008.
