This paper deals with the problem of identifying, evaluating, and ranking key nodes in complex networks by introducing a novel multi-parameter control graph convolutional network (MPC-GCN) for assessing node importance. Drawing inspiration from the multidimensional and hierarchical interactions between nodes in physical systems, this method integrates the automatic feature learning capabilities of graph convolutional networks (GCNs) with a comprehensive analysis of intrinsic properties of nodes, their interactions with neighbors, and their roles in the broader network. The MPC-GCN model provides an innovative framework for identifying key node by using GCNs to iteratively aggregate node and neighbor features across layers. This process captures and combines local, global, and positional characteristics, enabling a more nuanced, multidimensional assessment of node importance. Moreover, the model also includes a flexible parameter adjustment mechanism that allows for adjusting the relative weights of different dimensions, thereby adapting the evaluation process to various network structures. To validate the effectiveness of the model, we first test the influence of model parameters on randomly generated small networks. We then conduct extensive simulations on eight large-scale networks by using the susceptible-infected-recovered (SIR) model. Evaluation metrics, including the M( R) score, Kendall’s tau correlation, the proportion of infected nodes, and the relative size of the largest connected component, are used to assess the model’s performance. The results demonstrate that MPC-GCN outperforms existing methods in terms of monotonicity, accuracy, applicability, and robustness, providing more precise differentiation of node importance. By addressing the limitations of current methods, such as their reliance on single-dimensional perspectives and lack of adaptability, the MPC-GCN provides a more comprehensive and flexible approach to node importance assessment. This method significantly improves the breadth and applicability of node ranking in complex networks.