In order to respond to the city"s growing logistics demand, improve transportation efficiency, and effectively alleviate the environmental pollution and road traffic congestion caused by the existing logistics model, a subway-based urban logistics distribution model is proposed. The subway transportation and urban road transportation are combined to study the location of the transit node of the urban logistics distribution system based on subway stations. Considering transportation costs, transit costs, fixed operating costs, management costs and investment costs, etc., a model for the location of transit nodes in the urban logistics distribution system with the goal of minimizing the total cost is constructed; at the same time, an improved immune genetic algorithm is designed to solve the model. Finally, taking the subway network of Shanghai as an example, a simulation experiment was carried out, and a more reasonable transfer node location scheme was obtained. The results prove the rationality and effectiveness of the model and algorithm.