Intentional knowledge map representation learning method based on fusion of action roadmap

Affective knowledge graph constructs the objective world from the perspective of knowledge representation learning, and has certain reasoning and analysis capabilities. The reasoning analysis of the objective world includes intention analysis. The action and behavior route of the intention analysis is constructed as an event knowledge graph, and the relationship between the nodes in the event knowledge graph is used to explain the intention, and the intention analysis task can be completed by constructing the knowledge representation. However, in intention analysis, the number of actions and the position of actions in the overall action route are important indicators in the task of intention analysis. However, most of the knowledge graphs are two-node relationships, and the study of the position of nodes in the relationship only considers Symmetrical relationship. Aiming at the problem, a representation model of super nodes is proposed, in which information is integrated into the model, and attention is paid to network data set to test knowledge link prediction tasks. Experiments show that the model also achieves good results in the link prediction task.