Intelligent acupuncture diagnosis Agent system based on large language model and diagnosis method

Abstract

The invention provides an intelligent acupuncture diagnosis Agent system and diagnosis method based on a large language model, and the method comprises the steps: constructing a core model which comprises an embedded model, a reordering model and a large language model; constructing a knowledge base based on an embedded model and a large language model, wherein the knowledge base comprises a general acupuncture knowledge base, an acupuncture point information knowledge base, a symptom-acupuncture point knowledge base and an acupuncture field knowledge graph; classifying the questions input by the user by using a large language model, and outputting classification information including general recognition questions and treatment questions; based on the core model and the knowledge base, performing matching processing on the general recognition type questions or the treatment type questions, and outputting preliminary knowledge point answers of the general recognition type questions or preliminary treatment schemes of the treatment type questions; and performing error correction on the preliminary theoretical answer or the preliminary treatment scheme based on a multi-strategy extraction method to obtain a final theoretical answer or treatment scheme. The diagnosis and treatment scheme is accurate and can be flexibly adjusted, and associated symptoms can be actively mined.