<p>With the increasing volume of temporal data and the expanding range of application domains, research on temporal knowledge graph completion (TKGC) has become a prominent topic in the fields of artificial intelligence and data science. The primary objective of TKGC methods is to infer and model missing entities and relations, thereby enhancing the completeness and accuracy of knowledge graphs to provide more reliable and comprehensive information for various downstream tasks. Existing methods fail to adequately consider the importance of query-relevant historical information when balancing local and global historical data. Moreover, they lack effective modeling of the underlying relationships and periodic features among events in snapshots at specific times. To address these issues, we propose a completion method based on temporal-aware encoding and entity attention contrast (TEEAC). The TEEAC model employs a local–global encoder to encode local and global historical information separately, thereby capturing different types of dependencies in temporal knowledge graphs. On this basis, a temporal entity encoder is introduced to capture query-relevant historical information and explore the influence of temporal periodicity on historical snapshot events. Additionally, the TEEAC model incorporates an entity attention encoder that dynamically adjusts the embedding weights of different entities within historical information, enhancing the model’s ability to capture query-relevant historical information. Furthermore, by adopting local–global contrastive learning, the model effectively distinguishes entities with high relevance from historical information, thereby achieving improved prediction performance in the extrapolation task. Finally, comparative experiments conducted on four public datasets validate the effectiveness of the proposed TEEAC model.</p>