Unmanned aerial vehicle (UAV) delivery has the advantages of small size, high speed, and low cost. A new drone delivery path optimization model with loading and unloading integration is proposed in this study to make full use of UAV(drone) delivery by improving its efficiency. The model considers drone range constraints and loading capacity limitations, analyzes the start and end points of multiple orders, assigns orders to drones from the optimal distribution centers, calculating the order and time to visit all sets and delivery points, and pursuing the least transportation mileage. The ant colony optimization (ACO) algorithm is adopted to solve the problem in two stages. In the first stage, construction rules and pheromones of the solution are defined, and the orders to the UAVs are assigned. In the second stage, by adding constraints to the ACO algorithm, the sequence order of the UAVs visiting the set and delivery points is determined to obtain the optimal path. Finally, a GIS-based delivery platform is developed using Java Development Kit, which is used to produce the optimal scheduling scheme for an example case. A sensitivity analysis of the model parameters is conducted t, which proves the proposed model effectiveness.