Intelligent Customer Service System of Subway Based on Semantic Decision-Making Judgment

This study introduces an intelligent customer service system for urban rail transit, addressing inefficiencies and high labor costs in existing systems' problem classification and feedback mechanisms. Leveraging semantic understanding, the system integrates advanced speech recognition, intention classification, and entity extraction to automate the processing and intelligent classification of passenger hotline calls. Post-evaluation, the system demonstrated a minimum of 4.55% enhancement in data processing accuracy and F1 score, respectively, validating its efficacy in enhancing efficiency and precision. Furthermore, the research delves into the practical application of entity recognition, offering insights into the integration of natural language processing in intelligent customer service systems.