Book knowledge question-answering method based on knowledge graph enhanced large language model

The invention discloses a knowledge graph enhanced large language model-based book knowledge question-answering method. The method comprises the following steps of: firstly, extracting knowledge through a large language model and constructing a knowledge graph; the method comprises the following steps: after an original document is obtained, performing logic division on the original document by adopting multiple division methods to obtain fragments, and inputting the fragments into a large language model for vectorization to obtain fragment vectors; obtaining a knowledge vector and a complete question vector after obtaining a question input by a user; after the knowledge vector and the complete problem vector are spliced, similarity calculation is carried out on the spliced vector and all fragment vectors, and the fragment vector with the highest similarity score is taken as a context; and generating prompt information based on the context and the question input by the user, inputting the prompt information i