Multi-modal map construction method and device, information processing method and device, electronic equipment and medium

The invention provides a multi-modal graph construction method and device, an information processing method and device, electronic equipment and a medium, and relates to the technical field of artificial intelligence, in particular to the technical field of knowledge graphs, natural language processing, computer vision and deep learning. According to the specific implementation scheme, a visual knowledge graph is constructed according to image information of a scene chart; constructing a text knowledge graph according to the text information of the scene chart; constructing a first intermediate multi-modal knowledge graph according to the visual knowledge graph and the text knowledge graph; the first intermediate multi-modal knowledge graph is processed according to similarity relation information, a target multi-modal knowledge graph is obtained, and the similarity relation information represents relation information of at least one of an equivalence relation and an inclusion relation between the two objects