Abstract: The knowledge graph is a structured representation of knowledge, which typically employs a triplet to convey information. However, the long-tail distribution that characterizes most large-scale knowledge bases poses serious challenges regarding entity and relationship information in the long-tail segment, such as data sparsity and incomplete knowledge. To address these challenges and enhance the completeness of the knowledge graph, this paper proposes a novel model for knowledge representation learning in the context of knowledge graph completion. Specifically, the model maps entities to a two-dimensional Minkowski space and defines relationships as rotations. Additionally, the Adam optimizer is employed to optimize the training process. Finally, the model's efficacy is evaluated via link prediction tasks using public datasets FB15k, WN18, FB15k-237, and WB18RR, with results being compared to those derived from classical knowledge representation models. The empirical analysis reveals that the proposed model achieves superior performance across most evaluation metrics. Keywords: Knowledge graph completion, knowledge representation learning, 2D Minkowski space. Mathematics Subject Classification: Primary: 58F15, 58F17; Secondary: 53C35. Citation: \begin{equation} \\ \end{equation}