Abstract: With rapid development of mobile edge computing, providing high-quality mobile services requires considering various factors that affect network communication. These factors should be diversified according to the real-time changes of user mobility trajectories, and service migration paths should be dynamically planned. Addressing existing gaps in service migration path planning studies, particularly the lack of predictive models for user mobility in urban scenarios and low similarity between planned and actual user paths, a algorithm was proposed for service migration path selection based on real-time user mobility trajectories. The proposed algorithm initially predicts user’s future movement trajectory through a trajectory prediction algorithm based on Long Short-Term Memory (LSTM) model and a road network matching algorithm based on Hidden Markov Model (HMM). Then, according to predicted movement trajectory and status information of nearby local base stations, it selects optimal migration edge server, thereby completing service migration path selection in urban scenario. On the dataset constructed from taxi trajectory data set and mobile base station status data set in Shenzhen, compared to the improved Depth-First Search (DFS) algorithm, improved A-Star algorithm, Matrix-based Dynamic Multi-path Selection (MDMPS) algorithm and Grid Division-based Service Migration Path Selection (GDSMPS),the proposed algorithm reduces the average service migration time by 34.7%, 44.5%, 24.9% and 12.7% respectively, and increases average path similarity by 26.2%, 49.7%, 14.3% and 4.7% respectively. On noise data set and long path data set, the proposed algorithm has the smallest fluctuation in average service migration time and the highest average trajectory similarity. Experimental results show that the proposed algorithm can not only effectively reduce service migration time, enhance the similarity between migration path and user movement path, but also has good resistance to data noise and excellent long-distance path planning capability.