Multi-hop Reasoning Method Oriented Question Answering in Time-Constrained Temporal Knowledge Graph

Knowledge Graph Question Answering (KGQA) has gained significant attention in recent years, but many existing methods struggle to effectively reason over temporal constraints. This limitation reduces accuracy in temporal contexts and creates challenges in maintaining consistency and detecting conflicts within temporal knowledge graphs. To address this, a temporal constraint-based multi-hop reasoning approach is proposed, consisting of four modules: temporal information parsing, fact retrieval, constraint extraction and subgraph temporal reasoning. By incorporating temporal constraints, the model identifies implicit time-related information, thereby improving answer accuracy. Unlike conventional methods that focus on entities, this approach applies the attention mechanism at the relationship level to enhance reasoning performance. Experiments conducted on two public datasets, CronQuestions and ComplexCronQuestions, demonstrate the method’s superiority over state-of-the-art models. On CronQuestions, the model improves Hits@1 by 4.8% for complex questions and 3.9% for entity answers. On ComplexCronQuestions, it achieves Hits@1 gains of 10.4%, 6.8%, and 2.0% for temporal precedence, extremum, and conjunction questions, respectively. Additionally, a 7.9% improvement in Hits@10 is observed for temporal precedence questions, with an overall Hits@1 increase of 8.2%, highlighting its effectiveness in temporal KGQA tasks.