Article Details

Abstract

Traditional Chinese Medicine (TCM) dietary therapy, a treasured heritage of the Chinese nation, holds unique value in disease prevention and health maintenance. However, its relatively complex knowledge system and extensive specialized terminology often pose challenges for general users in comprehension and application. This paper proposes a TCM dietary therapy dialogue system that integrates a knowledge graph with a large language model. By constructing a structured knowledge graph to ensure professionalism and accuracy, and leveraging the DeepSeek model to generate natural and fluent responses, the system achieves an effective combination of professional knowledge and a favorable interactive experience. In a comprehensive evaluation based on a five-point scale across ten large language models. The system receives a score of 4.59 in professionalism and relevance, and 4.46 in accuracy, demonstrating its practical value to some extent in professional domain question-answering.

Keywords

Traditional Chinese Medicine dietary therapy; Knowledge Graph; Large Language Model; dialogue system; intelligent question-answering

References

1. [1] Fan Lijuan The regulatory effect of traditional Chinese medicine dietary therapy on the human body and its experience [J]. Chinese Journal of Ethnic and Folk Medicine, 2009, 18 (21): 81-82
2. [2] Yang Yifan, Liu Zhongbo, Zhou Yuxin Overview of the Construction and Application of Traditional Chinese Medicine Knowledge Graph [J]. Software Guide, 2025, 24 (8): 17-26
3. [3] Devlin J，Chang M W，Lee K，et al. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding [C]//Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies，2019：4171-4186.
4. [4] Liu Y H，Ott M，Goyal N，et al. RoBERTa: A Robustly Optimized BERT Pretraining Approach [PP/OL].arXiv:1907.11692[cs.CL].https://arxiv.org/abs/1907.11692?ref = gptechblog.com.
5. [5] Raffel C，Shazeer N，Roberts A，et al. Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer [PP/OL].arXiv:1910.10683 [cs.LG].https://arxiv.org/abs/1910.10683?ref = joe-cecil.com.
6. [6] Pan S，Luo L，Wang Y，et al. Unifying Large Language Models and Knowledge Graphs: A Roadmap [J].IEEE Transactions on Knowledge and Data Engineering，2024，36（7）：3580-3599.
7. [7] Min Rui, Jiang Dan, Wang Yonggang Research on Medical Question Answering System Based on LangChain and Large Model [J]. Computer Science and Applications, 2025, 15 (2): 33-43
8. [8] Zhang Baoyi, Tang Jiacheng, Zhang Tongyun, etc Construction of Geological Mineral Exploration Knowledge Graph and Q&A Model Empowered by Large Language Model [J]. Earth Science, 2026, 51 (3): 982-995
9. [9] Guan X Y，Liu Y J，Lin H Y，et al. Mitigating Large Language Model Hallucinations via Autonomous Knowledge Graph-based Retrofitting [C]//Proceedings of the AAAI Conference on Artificial Intelligence，2024，38（16）：18126-18134.
10. [10] Mondal D，Modi S，Panda S，et al. Kam-cot: Knowledge Augmented Multimodal Chain-of-thoughts Reasoning [C]//Proceedings of the AAAI Conference on Artificial Intelligence，2024，38（17）：18798-18806.
11. [11] Liu Qiao, Li Yang, Duan Hong, etc Overview of Knowledge Graph Construction Techniques [J]. Computer Research and Development, 2016, 53 (3): 582-600
12. [12] Ma Ang, Yu Yanhua, Yang Shengli, etc A Review of Knowledge Graph Based on Reinforcement Learning [J]. Computer Research and Development, 2022, 59 (8): 1694-1722
13. [13] Zhang Haili, Cao Shigi, Guo Zulong LangChain Practice [M]. Electronic Industry Press: 2024
14. [14] Topsakal O，Akinci T C. Creating Large Language Model Applications Utilizing LangChain: A Primer on Developing LLM Apps Fast [C]//International Conference on Applied Engineering and Natural Sciences，2023，1（1）：1050-1056.
15. [15] Jung T，Joe I. An Intelligent Docent System with a Small Large Language Model (sLLM) Based on Retrieval-Augmented Generation (RAG) [J/OL].Applied Sciences，2025，15（17）：9398.https://doi.org/10.3390/app15179398.

Funding

Social Science Planning Fund Project of Liaoning Province in 2024 (L24BTQ002); Research Project on Undergraduate Education and Teaching Reform of Dalian University for Nationalities in 2025 (ZBA202507); 2025 Liaoning Province College Students Innovation and Entrepreneurship Training Program Project (202512026124)

About the authors

Pan Haiyan (2004-), female, Han ethnicity, from Laibin, Guangxi, undergraduate student, research interests include knowledge graphs and data mining; Corresponding author: Meng Jiana (1972-), female, Han ethnicity, from Siping, Jilin, professor, doctoral student, research interests include machine learning and text mining.