The optimization of traffic signal systems is a critical challenge in urban transportation planning, requiring quick and reliable access to precise and context-specific information. Despite advancements in adaptive signal control technologies and performance measurement systems, a gap remains in integrating these technologies effectively and making their knowledge widely and quickly accessible. To address this gap, we introduce SignalVerse, a specialized chatbot designed to support traffic engineers by providing reliable answers to complex queries about traffic signal operations and management. SignalVerse employs a dual-response system that merges information from a custom-built knowledge base—comprising specialized traffic signal documents —with responses sourced globally. This allows users to compare the relevance and accuracy of different sources of information. Our methodology involved continuous user feedback to refine its' responses, ensuring they meet the real-world needs of traffic engineers. The results indicate that SignalVerse provides highly satisfactory and contextually relevant answers, significantly aiding traffic signal optimization tasks. While SignalVerse shows great promise, it has limitations, such as the initial scope of its knowledge base. Future research focuses on expanding the knowledge base, enhancing natural language processing techniques, and exploring broader applications in traffic engineering. In conclusion, SignalVerse represents a significant advancement in the field, offering a practical solution for traffic engineers to access specialized knowledge quickly and reliably. By addressing the critical need for efficient information retrieval in traffic signal management, SignalVerse contributes to safer and more efficient urban transportation systems.

Keywords: SignalVerse, Traffic Signal Management, Natural Language Processing, Performance Measurement Systems, Urban Transportation Optimization