To solve the loading and unloading problems of RMG (Rail Mounted Gantry), quay crane and AGV (Automated Guided Vehicle), this paper proposes a hierarchical cooperative scheduling algorithm. Firstly, the operation task is converted into 2 parts: the vertical equipment and the horizontal one, which can be regarded as the passenger and the taxi, i.e., named as the ride-hailing problem. We introduce the Hungarian algorithm to accomplish the matching of the task and the AGV. Secondly, the overall tasks of the equipment are transformed into planning paths, and then each equipment can execute it respectively. Here the global optimization should be considered. Finally, after the planning paths are truncated, we design a novel Markov random field model for the global optimization, aiming at the efficiency and safety of all equipment. In experiments, the effectiveness of our algorithm is verified by the simulation and real tests. The performance of safety and efficiency has strong promotion significance in new terminals and old reconstructed ones.