Research on the Digital Wayfinding System Design Based on Flow Experience Accessibility and Big Data Analysis: A Case Study of Beijing Subway Line 6

The exponential growth and complexity of urban rail transit requires effective wayfinding solutions to solve the dynamic needs of passengers. Existing wayfinding systems depends on static sign system that is failed to provide timely, adaptive guidance in crowded and complex subway environments. This research work presents a modern digital wayfinding system that is designed to optimize passenger navigation in the Beijing Subway Line 6. This utilizes big data analysis and algorithmic optimization to solve the issues. Travel patterns of the passengers are analyzed to identify high-traffic zones and peak congestion times using real-time data. This work makes use of Long Short-Term Memory (LSTM) and K-means clustering to build customized and adaptive guidance for passengers. The proposed system is compared with static guidance system to validate the significant improvements in transfer time, congestion distribution, passenger satisfaction, and flow efficiency. This work shows the importance of AI-based adaptive wayfinding system to reduce passenger anxiety and enhance navigation experience in complex transit networks.