Artificial intelligence-based document knowledge tree generation and interactive exploration method and system

By constructing a hierarchical knowledge tree structure and utilizing a large language model to achieve automatic document conversion and context-aware question answering, the problem of low document exploration efficiency in existing technologies is solved, and efficient and coherent document understanding and interactive exploration are realized.

CN122152825APending Publication Date: 2026-06-05NINGBO UNIV
View PDF 5 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-05-09
Publication Date
2026-06-05

Smart Images

  • Figure CN122152825A_ABST
    Figure CN122152825A_ABST
Patent Text Reader

Abstract

The application discloses a document knowledge tree generation and interactive exploration method and system based on artificial intelligence, relates to the technical field of artificial intelligence, and comprises the following steps: receiving a document uploaded by a user; extracting the text content of the document; calling a large language model based on the text content to perform analysis, so as to recursively construct a hierarchical knowledge tree structure; and in response to a query request initiated by a user at at least one knowledge node in the knowledge tree structure, taking each knowledge node as a target node, performing knowledge tree expansion based on the user query request; the method has the beneficial effects that: an unstructured document can be converted into a structured knowledge system, and the path tracing mechanism of the knowledge tree ensures the coherence of the context of multiple rounds of dialogue, so that the efficiency of deep understanding and interactive exploration of a complex document by a user is improved compared with the prior art.
Need to check novelty before this filing date? Find Prior Art

Citation Information

Patent Citations

  • Hierarchical semantic-driven retrieval enhancement generation method and system

    CN120632119A

  • Large model parallel interaction method and system based on tree topology structure

    CN120653737A

  • Multi-level container interaction method and system based on large language model

    CN120994092A

  • Engineering document generation method and system based on logic structure tree and LLM and medium

    CN121189289A

  • Inference enhanced RAG retrieval method and system based on semantic tree index

    CN121808045A