With the increasing popularity of ChatGPT, large language models (LLMs) have demonstrated their capabilities in communication and reasoning, promising for transportation sector intelligentization. However, they still face challenges in domain-specific knowledge. This paper aims to leverage LLMs' reasoning and recognition abilities to replace traditional user interfaces and create an "intelligent operating system" for transportation simulation software, exploring their potential with transportation modeling and simulation. We introduce Network Generation AI (NGAI), integrating LLMs with road network modeling plugins, validated through experiments for accuracy and robustness. NGAI's effective use has reduced modeling costs, revolutionized transportation simulations, optimized user steps, and proposed a novel approach for LLM integration in the transportation field.

翻译：随着ChatGPT的日益普及，大语言模型（LLMs）在通信与推理方面展现出强大能力，为交通领域的智能化带来了广阔前景。然而，大语言模型在领域特定知识方面仍面临挑战。本文旨在利用大语言模型的推理与识别能力，替代传统用户界面，为交通仿真软件打造"智能操作系统"，并探索其在交通建模与仿真中的潜力。我们提出了路网生成人工智能（NGAI），将大语言模型与路网建模插件相集成，并通过实验验证了其准确性与鲁棒性。NGAI的有效应用降低了建模成本，革新了交通仿真流程，优化了用户操作步骤，并为大语言模型在交通领域的集成应用提出了一种新范式。