Smart city is developing at a rapid speed, which will make a huge change in the production mode and industry, and “smart” design and construction in environmental art design will be the future development trend. This paper takes the construction of park green space as a research case, establishes a multi-objective optimization model based on genetic algorithm by combining the characteristics of the research area, and plans 33 candidate park green spaces in the area with low level of park green space service by combining the information of urban land use planning. In view of the shortcomings of traditional genetic algorithm, which is easy to fall into local optimization, simulated annealing algorithm is introduced to improve the standard genetic algorithm by composing hybrid geneticsimulated annealing (GA-SA) algorithm. The results show that the convergence speed of the hybrid geneticsimulated annealing algorithm is significantly improved, which is stronger than the simple genetic algorithm. The optimization model can ensure the goal of planning the minimum green area of the park, and the spatial distribution separation is kept in the range of 0.577 to 0.596, which has a better design. The research method of this paper is of reference and guidance to the environmental design and planning of the smart city.
