Study on the Role of Generative Artificial Intelligence in Advancing the Knowledge System of Traditional Chinese Medicine in Higher Education

The transfer and promotion of effectively inheritance and innovation of knowledge is a problem that higher education of Chinese medicine must face. This study provides a novel generative AI framework to promote the inheritance and innovative development of knowledge in traditional Chinese medical education. Utilizing multi-modal data processing (textual, visual and experiential) to construct a knowledge base, the model is based on Generative Adversarial Networks (GANs) and Transformer-based architecture. This context-aware and semantic-rich embedding is made possible using state-of-the-art technology, including attention mechanism and knowledge graph embedding. The learning structure of the model foreshadows the traditional Chinese medicine teaching model and cultivates students as good at in-depth understanding and creative application of knowledge. Furthermore, through transfer learning and domain-specific fine-tuning, the framework attains high fidelity of captured knowledge representation while also supporting the generation of new hypotheses and therapeutics. Our generative AI model improves knowledge transfer accuracy and depth, and encourage innovative thinking compared to traditional educational methodologies, as we demonstrate through experimental results.