Document processing method, device, electronic device and storage medium

By obtaining a document collection and performing segmentation processing and document summarization, paragraph word vectors and document summary word vector indexes are generated and stored in a search engine cluster. This solves the problems of inaccurate retrieval results and limited semantic understanding in existing document retrieval methods, and achieves efficient semantic and topic retrieval.

CN117609418BActive Publication Date: 2025-09-23BEIJING BAIDU NETCOM SCI & TECH CO LTD
3 Cites 0 Cited by

Patent Information

Application Number
CN202311665938.0
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2023-12-06
Publication Date
2025-09-23
Estimated Expiration
2043-12-06

Smart Images

  • Figure CN117609418B_ABST
    Figure CN117609418B_ABST
Patent Text Reader

Abstract

The present disclosure provides a document processing method, apparatus, electronic device, and storage medium, relating to the field of data processing technology. A specific implementation scheme comprises: obtaining a document collection, the document collection including multiple candidate documents, and determining segmented paragraphs and document summaries for the candidate documents; obtaining paragraph word vectors for the segmented paragraphs and summary word vectors for the document summaries, generating a vector index based on the paragraph word vectors and summary word vectors, and storing the index in a search engine cluster; and generating an inverted index based on the candidate documents and document summaries, and storing the index in the search engine cluster.
Need to check novelty before this filing date? Find Prior Art

Citation Information

Patent Citations

  • Document query method and device, equipment and storage medium

    CN116226350A

  • Retrieval method, device and equipment for computer field documents in question-answering system

    CN116595122A

  • Document information query method based on large language model

    CN116991974A