Engineering document index consistency proofreading method and system based on multi-modal large model

CN121145835APending Publication Date: 2025-12-16CHINA STATE SHIPBUILDING CORP LTD RESEARCH INSTITUTE 719
View PDF 2 Cites 10 Cited by

Patent Information

Application Number
CN202511294481.6
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-09-11
Publication Date
2025-12-16

AI Technical Summary

Technical Problem

Existing technologies struggle to effectively identify and verify multimodal information in engineering documents, resulting in low efficiency in indicator consistency verification. Furthermore, they are unable to handle indicator verification issues related to unstructured data such as charts, leading to high costs, low efficiency, and a high risk of omissions and errors in manual verification.

Method used

A multimodal large model is used for optical character recognition, table and formula processing, image understanding, text block segmentation and indicator information extraction. Combined with knowledge graph construction and intelligent agent workflow, the consistency verification of engineering document indicators is realized. Redundant information is eliminated by confidence threshold and semantic consistency check, and multi-level similarity threshold is used to identify indicator associations and generate detailed verification reports.

Benefits of technology

It significantly improves the accuracy and efficiency of engineering document indicator verification, reduces computing resource consumption, provides a reliable knowledge verification system, and supports knowledge management and professional decision-making in complex fields.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN121145835A_ABST
    Figure CN121145835A_ABST
Patent Text Reader

Abstract

The invention relates to an engineering document index consistency proofreading method and system based on a multi-modal large model, and the method comprises the steps: Q1. OCR detection and recognition: carrying out the optical character recognition and format analysis of a source document, converting an uploaded PDF document into a processable text message in a Markdown format, and carrying out the format discrimination of a table, a formula and a plain text; and Q2, table and formula processing: adopting a hierarchical processing strategy, intelligently selecting an optimal processing mode according to the complexity of the table, and converting table information into a descriptive long text through a language large model and cue words. According to the method, accurate, reliable and efficient document index checking service can be provided for a user, the quality and efficiency of professional document processing are remarkably improved, the efficiency and quality of knowledge graph construction are remarkably improved, a knowledge verification system capable of being evolved continuously is established, and the method is suitable for popularization and application. And a reliable technical support is provided for knowledge management and professional decision-making in a complex field.
Need to check novelty before this filing date? Find Prior Art

Citation Information

Patent Citations

  • Document index evaluation method based on large model

    CN118608084A

  • Document consistency auditing method and system based on large model and storage medium

    CN119441393A

Cited By

  • Construction scheme intelligent auditing method and system

    CN121435921A

  • Structured form processing method and system based on intelligent identification and storage medium

    CN121503450A

  • Intelligent recognition-based structured form processing method and system, and storage medium

    CN121503450B

  • Prompt word optimization method, device and equipment based on AI, RPA, LLM and AI Agent

    CN121525881A

  • Document generation method and system based on self-evolution intelligent agent

    CN121766288A