<p>Multi-hop knowledge graph question answering aims to find answer entities from the knowledge graph based on natural language questions. This is a challenging task because each step requires precise reasoning about entity relationships. When humans perform multi-hop reasoning, they usually focus on specific relations between different hops and determine the next entity. However, most algorithms often choose the wrong specific relation, causing the system to deviate from the correct reasoning path. In multi-hop question answering, the specific relation between each hop is crucial. The existing TransferNet model mainly relies on question representation for relation reasoning, but cannot accurately calculate the specific relation distribution, which will profoundly affect the performance of question answering. On this basis, this paper proposes an interpretable assiatance framework that makes full use of relation embedding and question semantics, and uses the attention mechanism to cross-fuse the relevant information of them to assist in calculating the relation distribution of each hop. Extensive experiments are conducted on two English datasets, WebQSP and CWQ, demonstrating that the proposed model outperforms state-of-the-art models by a large margin.</p>