Purpose/Significance To utilize local large models combined with local knowledge base to optimize the osteoporosis disease database construction process, and to reduce the risk of medical data leakage. Method/Process Firstly, relevant clinical research literature and business data information are collected and a local knowledge base is built. Then, based on the local large model application architecture, the local knowledge base is used to limit the generated content of the local large model. Finally, based on the graphical question-and-answer interface and programming interface of the local large model application architecture, natural language queries and programming methods are used to guide the local large model to generate osteoporosis disease database field sets and data production. Result/Conclusion The local large models combined with the local knowledge base can summarize the fields involved in previous osteoporosis researches and effectively improve the efficiency and quality of osteoporosis disease database construction, but the processing results need to be manually verified.