Speaker
Description
In the field of High Energy Physics, numerous large research infrastructures regularly solicit experimental proposals from researchers. The proposal management process encompasses a comprehensive sequence of stages: submission, multi-tiered review, approval of beamtime, scheduling, on-site execution, and outcome reporting. To address this, we have developed a scientific user service software that enables end-to-end management of experimental proposals.
Given the rapid advancements in Artificial Intelligence (AI), we further designed a human-computer collaborative platform powered by large language models. This platform seamlessly integrates AI capabilities throughout the entire workflow—from proposal drafting and review to evaluation, experiment planning, and knowledge consolidation. By incorporating intelligent assistance, the system significantly enhances both the efficiency and quality of proposal processing.The core objective of this platform is to establish a collaborative working mode in which human insight and AI intelligence are deeply intertwined. In this partnership, researchers act as strategic directors and final decision-makers, while large language models serve as powerful intelligent assistants. Together, they transform innovative ideas into executable experimental plans.
This work outlines the requirements analysis for the user service software, describes the developed framework, elaborates on the core functional modules, and presents specific design strategies for AI-enhanced implementation.
| I read the instructions above | Yes |
|---|