Academic paper poster generation method and system fusing human-machine collaborative optimization mechanism
By employing a phased planning approach based on human-machine collaborative optimization and multi-agent reasoning technology, the problems of insufficient user interaction and aesthetic quality in academic poster generation have been solved, achieving efficient and flexible academic poster generation. The generated posters achieve high quality and stability in both visual appeal and content.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- NANKAI UNIV
- Filing Date
- 2026-01-26
- Publication Date
- 2026-06-09
AI Technical Summary
Existing academic poster generation methods struggle to provide users with the flexibility and control they need while maintaining high visual aesthetics and content coherence. Automated tools also struggle to balance automation efficiency with the need for personalized human instructions, and their layout lacks robustness.
It adopts a human-machine collaborative optimization mechanism, and through phased planning and multi-agent reasoning technology, it parses academic paper documents, structures the content and performs refined layout design, including content initialization, layout planning and panel refinement stages, allowing users to interact and adjust.
It significantly improves the flexibility, controllability, and aesthetic quality of academic poster generation. The generated posters have stable layouts and good structures, meet personalized needs, and improve design efficiency.
Smart Images

Figure CN122176091A_ABST