Research on flow and planning of scenic spots based on multi-objective dynamic programming and NSGA-II

Abstract

In view of the impact of closed management on the tourism industry under the epidemic situation, this paper first puts forward differential flow-limiting schemes for scenic spots in different risk levels with the help of the cellular automata model and Mason rotation algorithm. It is carried on the scenic spot tourist flow simulation. Then based on the gray wolf multi-objective dynamic programming algorithm and NSGA-II multi-objective optimization model, the quantitative model is analyzed, and the BP (Back Propagation) convolution neural network algorithm is used to predict and test the multi-objective programming and optimization model. Finally, it is concluded that the lower the potential risk of the epidemic situation in the area, the smaller the limited flow of the scenic spot, and the greater the maximum and instantaneous carrying capacity of the scenic spot. In turn, it leads to the increase of the income of the scenic spot, and the improvement of the tourism experience of tourists is studied. Finally, it is combined with the above analysis. The paper puts forward a differentiated management scheme for the scenic spots at different risk levels.