Dynamic berth allocation method based on deep learning and objective weighting method

The invention discloses a parking space dynamic allocation method based on deep learning and an objective weighting method, and belongs to the field of computer vision and intelligent parking. On the basis of a first arrival first arrival parking mode, two reservation parking modes, namely, reservation first serving and auction reservation, are introduced, and two parameters are set; the parking berth proportion is a parking berth proportion # imgabs0 # for first arrival and first arrival parking and a parking berth proportion # imgabs1 # for first reservation and first service; according to the invention, the deep neural network and the CRITIC objective weighting method are used to realize the comprehensive decision-making and dynamic allocation of the parking space ratio in the hybrid parking mode, the parking resource configuration is optimized, the parking efficiency and convenience are improved, and a new thought is provided for the practical application of different parking reservation strategies. 本发明公开