This research is dedicated to addressing user recommendation matching and multi-objective optimization problems in ride-sharing services. For addressing the challenge of node classification in social networks, the Graph Attention Network with Opinion Dynamics (OD-GAT) is proposed. This model combines opinion dynamics and attention mechanism, which can make full use of multi-dimensional information for social relationship reasoning, and at the same time simulate the influence of individuals by other objects in the group, realize more accurate prediction and reasoning of social relationships, improved service quality and ride-sharing safety. To address the intricate task of balancing multiple objectives, including average detour cost, average response rate, and average user similarity rate, we introduce a novel evolutionary computation method for optimizing ride-sharing scenarios. This approach tackles the dynamic ride-sharing matching problem by emphasizing human factors in the optimization goals, successfully overcoming challenges related to local optima and convergence. Experimental validation confirms the effectiveness of OD-GAT in feature extraction and classification, showcasing the method’s fastest convergence speed and global optimum achievement across three key metrics.

This study addresses the Multiple Flying Sidekicks Traveling Salesman Problem (mFSTSP), where parallel Unmanned Aerial Vehicles (UAVs, or Drones) work alongside truck to enhance delivery efficiency. Existing scheduling approaches face challenges in high computational costs and the risk of converging to local optima due to excessive exploration in unknown environments, especially in large-scale mFSTSP. This study proposed a Large Language Model Enhanced Q-Learning Approach (LLM-QL) to solve mFSTSP, which combines the local exploration advantages of Q-Learning with the global understanding of unknown environments provided by LLMs, thus improving the efficiency of path planning. A novel prompt strategy is also provided, transforming the problem modeling into a format easily understood by LLMs, guiding the algorithm's exploration and significantly improving convergence. We also provide a proof of the convergence of LLM-QL. Experimental results demonstrate that LLM-QL achieves up to a 1.35 x improvement in key performance metrics such as total completion time, algorithm runtime, and UAV utilization, compared to existing state-of-the-art methods.