The ancient books on traditional Chinese medicine(TCM) are the source of knowledge for TCM physicians. Therapeutic principles and therapeutic methods for healing many diseases are recorded in these ancient TCM books, ...The ancient books on traditional Chinese medicine(TCM) are the source of knowledge for TCM physicians. Therapeutic principles and therapeutic methods for healing many diseases are recorded in these ancient TCM books, providing a huge number of references for modern TCM physicians on conducting diagnosis and administering treatment for different diseases. The ancient TCM books can be dated back thousands of years, and this vast knowledge is recorded in different medical books in the form of text. However, it is difficult to systematically assimilate much information in ancient TCM books. At present, many researchers are applying advanced analytical techniques to analyze the text data in the ancient TCM books. Advanced techniques that have been applied include database construction, cognitive linguistic analysis, fuzzy logic, data mining, and artificial intelligence(AI) technology. There are different characteristics in these advanced analytical techniques. In this study, we comprehensively review recent advances in these techniques applied to the study of ancient TCM books. Furthermore, as AI technology is increasingly utilized in the medical field as well as in the study of ancient TCM books, we also review the application of AI technology to the study of ancient TCM books.展开更多
Mazu is the most famous goddess of canal transport in China,and one of the three folk beliefs in China.Japan is our neighbor across the sea.As early as 1000 years ago,Japan was influenced by the Mazu ceremonial cultur...Mazu is the most famous goddess of canal transport in China,and one of the three folk beliefs in China.Japan is our neighbor across the sea.As early as 1000 years ago,Japan was influenced by the Mazu ceremonial culture.Through big data analysis,this study conducted database counting,screening,and analysis on the Mazu culture in Diaolong,the full-text database of Chinese and Japanese ancient books.Besides,it explored the hot topics of concern and emotional attitudes,and then analyzed the important role of Mazu culture in the cultural exchange and mutual learning between China and Japan in the new era,with a view to completing the contemporary task of“people-to-people bond”and achieving common development.展开更多
Objective To explore ancient and modern medication laws of aromatic Chinese medicines in treating angina pectoris, and to provide new ideas for the clinical treatment.Methods With “angina pectoris” as the key word, ...Objective To explore ancient and modern medication laws of aromatic Chinese medicines in treating angina pectoris, and to provide new ideas for the clinical treatment.Methods With “angina pectoris” as the key word, ancient books prescriptions and Chinese patent medicines related to angina pectoris were collected from China National Knowledge Infrastructure(CNKI), Traditional Chinese Medicine Database System, Chinese Medicine Prescription Database, New National Proprietary Chinese Medicine(2 nd edition), and Chinese Pharmacopoeia(2020 edition) from January 1, 2015 to December 31, 2021. Core highfrequency aromatic Chinese medicines were defined, and their potential medication rules were analyzed and summarized. Microsoft Access 2010 was used for data management. Data analysis software, including Excel and IBM SPSS Modeler 18.0 were used for drug association rule analysis, and Cytoscape 3.7.2 for visual display.Results There were 67 ancient books prescriptions and 258 Chinese patent medicines containing aromatic Chinese medicines treating angina pectoris collected from relevant databases. In ancient books prescriptions, there were nine aromatic Chinese medicines with the frequency ≥10, and the most commonly used medicine was Danggui(Angelicae Sinensis Radix), followed by Chenpi(Citri Reticulatae Pericarpium). There were 33 aromatic Chinese medicines with the frequency ≥10 in Chinese patent medicines, and the most commonly used medicine was Danshen(Salviae Miltiorrhizae Radix et Rhizoma), followed by Chuanxiong(Chuanxiong Rhizoma) and Sanqi(Notoginseng Radix et Rhizoma). In ancient books prescriptions, the medicines mainly belonged to intenal-warming medicines, Qi-regulating medicines, and blood circulation promoting and blood stasis removing medicines.There were eight medicine pairs with confidence equal to 100% in ancient books prescriptions, the most frequently used pairs were Chuanxiong(Chuanxiong Rhizoma) +Danggui(Angelicae Sinensis Radix), and Xiangfu(Cyperi Rhizoma) + Chenpi(Citri Reticulatae Pericarpium). In Chinese patent medicines, the aromatic Chinese medicine Chuanxiong(Chuanxiong Rhizoma) could be combined with many other Chinese medicines, among which the Confidence and Support of Chuanxiong(Chuanxiong Rhizoma) + Danshen(Salviae Miltiorrhizae Radix et Rhizoma) were at a high level.Conclusion Aromatic Chinese medicines for the treatment of angina pectoris of coronary heart disease are mainly warm, and the flavors are mainly pungent, sweet, and bitter. They mainly access to the liver, gallbladder, and pericardium meridians. The treatment of angina pectoris of coronary heart disease mainly focuses on warming heart pulse, and promoting blood circulation and removing blood stasis.展开更多
基于“预训练+微调”范式的实体关系联合抽取方法依赖大规模标注数据,在数据标注难度大、成本高的中文古籍小样本场景下微调效率低,抽取性能不佳;中文古籍中普遍存在实体嵌套和关系重叠的问题,限制了实体关系联合抽取的效果;管道式抽取...基于“预训练+微调”范式的实体关系联合抽取方法依赖大规模标注数据,在数据标注难度大、成本高的中文古籍小样本场景下微调效率低,抽取性能不佳;中文古籍中普遍存在实体嵌套和关系重叠的问题,限制了实体关系联合抽取的效果;管道式抽取方法存在错误传播问题,影响抽取效果。针对以上问题,提出一种基于提示学习和全局指针网络的中文古籍实体关系联合抽取方法。首先,利用区间抽取式阅读理解的提示学习方法对预训练语言模型(PLM)注入领域知识以统一预训练和微调的优化目标,并对输入句子进行编码表示;其次,使用全局指针网络分别对主、客实体边界和不同关系下的主、客实体边界进行预测和联合解码,对齐成实体关系三元组,并构建了PTBG(Prompt Tuned BERT with Global pointer)模型,解决实体嵌套和关系重叠问题,同时避免了管道式解码的错误传播问题;最后,在上述工作基础上分析了不同提示模板对抽取性能的影响。在《史记》数据集上进行实验的结果表明,相较于注入领域知识前后的OneRel模型,PTBG模型所取得的F1值分别提升了1.64和1.97个百分点。可见,PTBG模型能更好地对中文古籍实体关系进行联合抽取,为低资源的小样本深度学习场景提供了新的研究思路与方法。展开更多
基金the China Postdoctoral Science Foundation (Grant No. 2019M650598)the Fundamental Research Funds for the Central Universities (Grant No. 2019-JYB-JS-005)。
文摘The ancient books on traditional Chinese medicine(TCM) are the source of knowledge for TCM physicians. Therapeutic principles and therapeutic methods for healing many diseases are recorded in these ancient TCM books, providing a huge number of references for modern TCM physicians on conducting diagnosis and administering treatment for different diseases. The ancient TCM books can be dated back thousands of years, and this vast knowledge is recorded in different medical books in the form of text. However, it is difficult to systematically assimilate much information in ancient TCM books. At present, many researchers are applying advanced analytical techniques to analyze the text data in the ancient TCM books. Advanced techniques that have been applied include database construction, cognitive linguistic analysis, fuzzy logic, data mining, and artificial intelligence(AI) technology. There are different characteristics in these advanced analytical techniques. In this study, we comprehensively review recent advances in these techniques applied to the study of ancient TCM books. Furthermore, as AI technology is increasingly utilized in the medical field as well as in the study of ancient TCM books, we also review the application of AI technology to the study of ancient TCM books.
文摘Mazu is the most famous goddess of canal transport in China,and one of the three folk beliefs in China.Japan is our neighbor across the sea.As early as 1000 years ago,Japan was influenced by the Mazu ceremonial culture.Through big data analysis,this study conducted database counting,screening,and analysis on the Mazu culture in Diaolong,the full-text database of Chinese and Japanese ancient books.Besides,it explored the hot topics of concern and emotional attitudes,and then analyzed the important role of Mazu culture in the cultural exchange and mutual learning between China and Japan in the new era,with a view to completing the contemporary task of“people-to-people bond”and achieving common development.
基金Jiangxi Provincial Department of Science and Technology Major Research and Development Program(20194ABC28009 and 20202BBGL73008)National Key Research and Development Program(2018YFC1706404)。
文摘Objective To explore ancient and modern medication laws of aromatic Chinese medicines in treating angina pectoris, and to provide new ideas for the clinical treatment.Methods With “angina pectoris” as the key word, ancient books prescriptions and Chinese patent medicines related to angina pectoris were collected from China National Knowledge Infrastructure(CNKI), Traditional Chinese Medicine Database System, Chinese Medicine Prescription Database, New National Proprietary Chinese Medicine(2 nd edition), and Chinese Pharmacopoeia(2020 edition) from January 1, 2015 to December 31, 2021. Core highfrequency aromatic Chinese medicines were defined, and their potential medication rules were analyzed and summarized. Microsoft Access 2010 was used for data management. Data analysis software, including Excel and IBM SPSS Modeler 18.0 were used for drug association rule analysis, and Cytoscape 3.7.2 for visual display.Results There were 67 ancient books prescriptions and 258 Chinese patent medicines containing aromatic Chinese medicines treating angina pectoris collected from relevant databases. In ancient books prescriptions, there were nine aromatic Chinese medicines with the frequency ≥10, and the most commonly used medicine was Danggui(Angelicae Sinensis Radix), followed by Chenpi(Citri Reticulatae Pericarpium). There were 33 aromatic Chinese medicines with the frequency ≥10 in Chinese patent medicines, and the most commonly used medicine was Danshen(Salviae Miltiorrhizae Radix et Rhizoma), followed by Chuanxiong(Chuanxiong Rhizoma) and Sanqi(Notoginseng Radix et Rhizoma). In ancient books prescriptions, the medicines mainly belonged to intenal-warming medicines, Qi-regulating medicines, and blood circulation promoting and blood stasis removing medicines.There were eight medicine pairs with confidence equal to 100% in ancient books prescriptions, the most frequently used pairs were Chuanxiong(Chuanxiong Rhizoma) +Danggui(Angelicae Sinensis Radix), and Xiangfu(Cyperi Rhizoma) + Chenpi(Citri Reticulatae Pericarpium). In Chinese patent medicines, the aromatic Chinese medicine Chuanxiong(Chuanxiong Rhizoma) could be combined with many other Chinese medicines, among which the Confidence and Support of Chuanxiong(Chuanxiong Rhizoma) + Danshen(Salviae Miltiorrhizae Radix et Rhizoma) were at a high level.Conclusion Aromatic Chinese medicines for the treatment of angina pectoris of coronary heart disease are mainly warm, and the flavors are mainly pungent, sweet, and bitter. They mainly access to the liver, gallbladder, and pericardium meridians. The treatment of angina pectoris of coronary heart disease mainly focuses on warming heart pulse, and promoting blood circulation and removing blood stasis.
文摘基于“预训练+微调”范式的实体关系联合抽取方法依赖大规模标注数据,在数据标注难度大、成本高的中文古籍小样本场景下微调效率低,抽取性能不佳;中文古籍中普遍存在实体嵌套和关系重叠的问题,限制了实体关系联合抽取的效果;管道式抽取方法存在错误传播问题,影响抽取效果。针对以上问题,提出一种基于提示学习和全局指针网络的中文古籍实体关系联合抽取方法。首先,利用区间抽取式阅读理解的提示学习方法对预训练语言模型(PLM)注入领域知识以统一预训练和微调的优化目标,并对输入句子进行编码表示;其次,使用全局指针网络分别对主、客实体边界和不同关系下的主、客实体边界进行预测和联合解码,对齐成实体关系三元组,并构建了PTBG(Prompt Tuned BERT with Global pointer)模型,解决实体嵌套和关系重叠问题,同时避免了管道式解码的错误传播问题;最后,在上述工作基础上分析了不同提示模板对抽取性能的影响。在《史记》数据集上进行实验的结果表明,相较于注入领域知识前后的OneRel模型,PTBG模型所取得的F1值分别提升了1.64和1.97个百分点。可见,PTBG模型能更好地对中文古籍实体关系进行联合抽取,为低资源的小样本深度学习场景提供了新的研究思路与方法。