In high rock slope engineering, monitoring the rock mass displacement during the excavation process is critical for assessing and determining the slope stability. It is of practical significance to utilize the monitoring data during the excavation to conduct an inverse analysis of the rock parameters in order to predict the slope displacement caused by subsequent excavations. This study proposes an efficient Bayesian updating framework that integrates monitoring data to predict excavation-induced slope displacements. This framework employs Bayesian updating with Subset Simulation (BUS) method to address the “curse of dimensionality” resulting from the extensive number of rock parameters updating. Furthermore, to enhance the computational efficiency of the Bayesian updating, Artificial Neural Network (ANN) is employed to replace the time-consuming finite element computation. The displacements of the subsequent excavation and anchoring stages of the left-bank high rock slope for the Baihetan hydropower station is predicted by integrating the slope displacement data with the proposed framework, thereby validating the proposed framework in this study.