Shift schedule is crucial in improving the dynamic and economic performance of electric vehicles (EVs) equipped with automatic mechanical transmission (AMT). As the driver, vehicle, and road constitute a closed-loop inseparable system, identifying the states of both vehicle and road is fundamental to realizing optimal shift schedule. However, the existing shift strategies neglect the coupling relationship of multiple parameters to the shift strategy. To minimize this gap, this paper presents a novel multi-parameter shift schedule based on model predictive control. Firstly, cubature Kalman filters (CKF) algorithm is employed to accurately estimate vehicle quality and road slope, which could improve the energy economy of EVs. Secondly, an artificial neural network (ANN) is adopted to forecast the compound future short horizon driving conditions, which contains the perdition information of vehicle velocity and road slope. Meanwhile, the AMT predictive shift schedule based on the above estimated and forecast information is constructed, which used dynamic programming to optimize in the rolling horizon. Simulation study results indicate that the ANN-based predictive approach shows better performance on accuracy and robustness than that of Markov chain, and the electricity consumption over China typical urban driving cycle (CTUDC) is further reduced by 6.79% than that of multi-parameter rule-based shift schedule.