The work aims to establish an effective express packaging recycling network and select reasonable locations regarding the phenomena of low recycling rate of express packaging and difficult recycling, in order to reduce the cost of the network and improve the recycling benefits. The improved K-means clustering and set covering model were combined to study the location of the recycling point. First, the improved K-means clustering was used to perform cluster analysis on the express outlets. The average difference of the express outlets was solved and the initial cluster center was obtained through the selection principle. The number of iterations was reduced, and the final cluster center was used as the candidate recycling point. Then, the set covering model was used for optimization, and the recycling points were selected on the basis of the candidate recycling points. In order to make full use of the existing logistics resources, the nearest express outlet was selected as the recycling point. All express outlets were covered by the least number of recycling points, reducing the network’s recycling cost and improves the efficiency of express packaging recycling. Through the combination of these two methods, a suitable express outlet is selected as the recycling point. SPSS and Matlab software are used to analyze the location of the SY city-wide recycling point to prove that the proposed method is effective.