Intelligent agent collaborative document structuring method and system using intermediate representation

By constructing a unified structured intermediate representation and multi-agent collaborative scheduling, the problems of structural mapping and multimodal semantic instability in presentation generation are solved, achieving high-quality consistency between text and graphics and visual interactivity, which is suitable for scenarios such as academic presentations and course teaching.

CN122242477APending Publication Date: 2026-06-19BEIJING INST OF TECH
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN Β· China
Patent Type
Applications(China)
Current Assignee / Owner
BEIJING INST OF TECH
Filing Date
2026-01-22
Publication Date
2026-06-19

AI Technical Summary

Technical Problem

Existing presentation generation technologies suffer from instability in structural mapping and multimodal semantics, resulting in inconsistent generation effects and high error rates. They also lack interactive and interpretable intermediate processes, making it difficult to generate high-quality, consistent presentations.

Method used

By constructing a unified structured intermediate representation and adopting a multi-agent collaborative scheduling approach, including parsing, planning, reduction, rendering, and visual optimization agents, narrative planning, semantic reduction, template rendering, and graphic optimization are performed to generate presentations with clear structure and consistent graphics.

Benefits of technology

It significantly improves the interpretability and stability of the presentation generation process, reduces error accumulation, enhances the structural coherence and readability of the generated results, supports editable output and visual interaction, and is suitable for scenarios such as academic presentations and course teaching.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122242477A_ABST
    Figure CN122242477A_ABST
Patent Text Reader

Abstract

This invention discloses a method and system for generating structured documents through intelligent agents using intermediate representation, belonging to the interdisciplinary application technology of natural language processing, multimodal content generation, and human-computer interaction. The implementation method of this invention is as follows: 1. Perform structural and element analysis on reducible information sources to form a structured intermediate representation; 2. Utilize data contracts to perform rollback, repair, and update processing on the triggering conditions of the multi-agent set, and initialize the scheduler; 3. Allocate text and multimodal elements to generate the outline structure and page-level organization scheme of the presentation; 4. Generate the final draft of the specification; 5. Select the corresponding template and fill the template slots with fields to generate structured pages; 6. The visual optimization agent optimizes the text style and visual expression of the structured pages; 7. Form a presentation and extract the speech text. Compared with existing technologies, this invention improves the consistency of text and graphics and the visual interactivity of automatically generated presentations.
Need to check novelty before this filing date? Find Prior Art