Real-Time Data Informed Traffic Analytics Framework Powered by Large Language Model (LLM)

Abstract

The digitization of traffic sensing infrastructure has significantly accumulated an extensive real-time traffic data warehouse, which presents unprecedented challenges for traffic analytics. The complexities associated with querying large-scale multi-table databases require specialized programming expertise and labor-intensive development. Additionally, traditional analysis methods have focused mainly on numerical data, often neglecting the semantic aspects that could enhance interpretability and understanding. Furthermore, real-time traffic data access is typically limited due to privacy concerns. To bridge this gap, the integration of Large Language Models (LLMs) into the domain of traffic management presents a transformative approach to addressing the complexities and challenges inherent in modern transportation systems. This thesis proposes an intelligent traffic analytics framework based on LLM for efficient customized transportation surveillance and management empowered by a large real-time traffic database. The innovative framework leverages contextual and generative intelligence of language models to generate accurate SQL queries and natural-language data interpretations by employing transportation-specialized prompts, Chain-of-Thought prompting, few-shot learning, multi-agent collaboration strategy, and chat memory. Experimental study demonstrates that the approach outperforms state-of-the-art baselines such as GPT-4 and PaLM 2 on a challenging traffic-analysis benchmark TransQuery. This study would aid researchers and practitioners in real-time transportation surveillance and management in a privacy-preserving, equitable, and customizable manner.