Knowledge graph completion method based on path awareness of convolutional network and related equipment

The invention provides a path-aware knowledge graph completion method based on a convolutional network and related equipment. The method comprises the following steps: acquiring an initial triple set from a knowledge graph; determining a candidate triple set based on the initial triple set; inputting the candidate triple set into a pre-constructed sorting model, outputting a relation score of each candidate triple in the candidate triple set through the sorting model, determining at least one candidate triple from the candidate triple set based on the relation scores, and supplementing the at least one candidate triple into the knowledge graph; wherein the sorting model is pre-trained. According to the completion method disclosed by the invention, by introducing the path information of the triple and further considering the local and global importance of the path, the knowledge graph completion accuracy is improved. 本公开提供基于卷积网络的路径感知的知识图谱补全方法及相关设备，该方法包括：从所述知识图谱中获取初始三元组集合；基于所述初始三元组集合确定候选三元组集合；将所述候选三元组集合输入至预先构建的