ReChat: A Task‐Based Chatbot for EV Charging Management Optimization

ABSTRACT The increasing adoption of electric vehicles (EVs) and the evolution of connected vehicle systems have led to a growing need for intelligent charging management solutions. This article introduces ReChat, a task‐based multilingual chatbot designed to optimize EV charging management through reliable task‐oriented intent understanding and safe action dispatch. By leveraging natural language processing (NLP), ReChat enables seamless user interaction with charging systems across six languages (Spanish, English, German, French, Italian and Portuguese). A custom dataset was developed to train and evaluate the chatbot's intent‐classification capabilities, ensuring robust performance in diverse linguistic contexts. A comparative analysis of multilingual Bidirectional Encoder Representations from Transformers (mBERT)‐based intent classifiers shows that a single pooled multilingual mBERT model achieves macro‐1 values between 68.0% and 78.4% across languages, while language‐specific mBERT models yields 64.7% to 78.9%. This work advances the development of robust conversational AI systems for smart transportation, outlining a modular architecture and empirical evidence on multilingual adaptability in real‐world applications.