Abstract:Knowledge graph aims to provide more comprehensive and reliable services for various fields, the value in practical applications is immeasurable, in order to make it constantly updated and complete, knowledge graph completion technology began to be proposed; In recent years, with the rise of artificial intelligence and deep learning, many scholars at home and abroad have conducted in-depth research on the direction of knowledge graph completion, and many knowledge graph completion models for artificial intelligence deep learning have emerged, but there are not many relevant literature reviews. In order to provide a comprehensive understanding of the field, it helps readers to grasp the current research progress and applications, and provides some references for future research and applications; By introducing its concept and typical knowledge graph, the current knowledge graph completion model based on deep learning is analyzed and summarized from the three perspectives of deep learning knowledge completion technology, and the advantages and disadvantages of different models and the improved models are discussed. At the same time, the problems and challenges of the knowledge graph completion task at this stage are discussed, and the application direction and development prospects of this field are explored. In summary, deep learning has great exploration value in knowledge graph completion, and scholars are urgently needed to conduct more in-depth research and further innovation.