The widespread application of clinical pathways has improved the quality of medical care in hospitals in China, enabling patients to better medical services. However, due to the large population base in China, the therapeutic resources are relatively few, and the medical resources of the hospital are also limited. The resource scheduling problem of the clinical pathway is gradually highlighted. In this paper, the clinical pathway resource scheduling problem is abstracted as a multi-project scheduling problem under resource constraints, and the improved particle swarm optimization algorithm is utilized to complete the resource scheduling optimization experiment on the clinical pathway of type2 diabetes. At the same time, aiming at the problem that particle swarm optimization is easy to fall into local optimum, the grey wolf algorithm is combined with particle swarm optimization. Finally, the particle swarm optimization algorithm and the grey wolf algorithm are compared with the improved algorithm. The experimental results show that when the number of patients treated increases, the results obtained by the improved particle swarm optimization algorithm are better than the particle swarm optimization algorithm and the grey wolf algorithm, effectively avoiding the problem of a local optimal solution.