The development of large language models in the field of Traditional Chinese Medicine(TCM)using artificial intelli-gence has significantly contributed to both the innovation and preservation of TCM.This paper outlines the current research status and process of large language models in TCM,focusing on three key tasks:collecting TCM data,fine-tuning models with specific instruc-tions,and using different methods to evaluate model performance.It also highlights cutting-edge techniques,such as prompt engineer-ing,retrieval-augmented generation,and reinforcement learning from human feedback,which have enhanced the models'adaptability in various TCM applications.The challenges faced by TCM language models,such as data privacy,ethical biases,model interpret-ability,technical difficulties,and evaluation standards,are also analyzed,indicating areas for further improvement.Looking ahead,the combination of these models with advanced AI techniques like deep learning,and the integration of multimodal information such as TCM diagnostic data and herbal images,can open new possibilities for large language models in TCM.This will enhance their applica-tion in areas like syndrome differentiation diagnosis,prescription recommendations,TCM knowledge graph construction,and TCM edu-cation.

The development of large language models in the field of Traditional Chinese Medicine(TCM)using artificial intelli-gence has significantly contributed to both the innovation and preservation of TCM.This paper outlines the current research status and process of large language models in TCM,focusing on three key tasks:collecting TCM data,fine-tuning models with specific instruc-tions,and using different methods to evaluate model performance.It also highlights cutting-edge techniques,such as prompt engineer-ing,retrieval-augmented generation,and reinforcement learning from human feedback,which have enhanced the models'adaptability in various TCM applications.The challenges faced by TCM language models,such as data privacy,ethical biases,model interpret-ability,technical difficulties,and evaluation standards,are also analyzed,indicating areas for further improvement.Looking ahead,the combination of these models with advanced AI techniques like deep learning,and the integration of multimodal information such as TCM diagnostic data and herbal images,can open new possibilities for large language models in TCM.This will enhance their applica-tion in areas like syndrome differentiation diagnosis,prescription recommendations,TCM knowledge graph construction,and TCM edu-cation.

This study was aimed to analyze the research status of marine medicine in China. The research hot issues and feature rules were summarized in order to discuss development trends for the clinic application and further development of marine medicine in recent 20 years. The CNKI library was used as a source to retrieve literatures on marine medicine. The bibliometric methods and Cytoscape 3.1.1 were used to analyze. The results showed that 582 papers were included. A total of 260 papers were published during 2010 to 2014. And 52 papers were published annually. 266 papers in this field were funded. The papers were mostly published in theChinese Journal of Marine Drugs. A total of 278 research institutes were engaged in the research. And the institute published the most paper was the Ocean University of China. There were 12 researchers who had published more than 5 articles. This study focused on the keywords with highly frequency, which were marine drugs, chemical composition, marine natural products, fingerprints and antitumor. It was concluded that marine medicine had become hot issues. The core of the group has been formed. However, most researches had focused on natural products and pharmacological aspects. Traditional Chinese medicine (TCM) theory had not been taken seriously and the infrastructure was weak, which obstructed the clinical application of marine medicine. We should expand the discovery and study of knowledge on ancient herbal literature as well as clinic application of marine medicine in order to build the knowledge database of marine medicine and experience mode of clinic application.

Objective To compare the differences of insomnia prescription laws between ancient and mordern acupuncture. Methods Collected ancient and mordern acupuncture treatment of insomnia prescriptions literature, using fourteen frequency, percentage of acupuncture acupoints, the points of the distribution and distribution in different parts of the body, the specific acupoint application and prescription features for statistical description. Results The ancient physicians selected points more dispersed, acupoints are mainly concentrated in the chest , abdomen and leg. Modern physicians point selection is relatively concentrated, prescription relatively fixed, the acupoints are mainly concentrated in the head and neck and lower limb;acupoints are mainly concentrated in the Urinary bladder meridian of foot Taiyang, the ancient physicians also more choice of Ren pointss, modern physicians are more optional Du points. Conclusion The physicians prescriptions are quite different, but in the meridian points and the type of use is similar, mostly concentrated in the selection of points Urinary bladder meridian of foot Taiyang, especially the five Shu points. Du, Ren, Spleen meridian and Stomach meridian of Foot Yangming using positive significance for the treatment of insomnia by acupuncture choice.