📄 中文摘要
在深不确定性下的社会环境规划中，研究人员需要在探索政策和实施计划之前识别和概念化问题。传统的基于模型的规划方法通常依赖参与建模，将利益相关者的自然语言描述转化为定量模型，这一过程复杂且耗时。为简化此过程，提出了一种使用大型语言模型进行初步概念化的模板化工作流程。在该工作流程中，研究人员能够利用大型语言模型从利益相关者的直观问题描述中识别出关键模型组件，并探讨不同的观点和方法。此方法旨在提高问题概念化的效率和准确性，从而支持更有效的社会环境规划。
生成性人工智能辅助的深不确定性下的社会环境规划参与建模
📄 English Summary
Generative AI-assisted Participatory Modeling in Socio-Environmental Planning under Deep Uncertainty
This research proposes a templated workflow that utilizes large language models to assist in the initial conceptualization process of socio-environmental planning under deep uncertainty. In such planning, identifying and conceptualizing problems is crucial before exploring policies and deploying plans. Traditionally, this process relies on participatory modeling to translate stakeholders' natural-language descriptions into quantitative models, which can be complex and time-consuming. The proposed workflow allows researchers to leverage large language models to identify essential model components from stakeholders' intuitive problem descriptions, facilitating the exploration of diverse perspectives and approaches. This method aims to enhance the efficiency and accuracy of problem conceptualization, thereby supporting more effective socio-environmental planning.