Picture book creation has a rich metaphorical connotation, which is becoming more and more popular along with the development of digitalization. In this paper, the textual metaphors of picture book creation are extracted by combining the textual feature extraction model of the BERT pre-training model and HAN network, the ResNet50 network extracts the illustration metaphors of picture book creation, and the extracted metaphorical features are multimodal fused and recognized with the help of fully connected layer. In addition, a picture book metaphor dataset was constructed, and after analyzing the basic features of picture book metaphors, the effect of the constructed multimodal metaphor recognition was explored, and the recognition and communication of metaphors in picture book creation was studied. The results showed that the recognition accuracy in picture book creation ranged from 0.67 to 0.77, and the high degree of metaphor recognition in picture book creation showed a positive correlation with the average response time of communication, with the regression equation RT=138.45*IdentificationStd+1045.The results of the analysis of the metaphorical picture book creation pictures with textual references showed that the degree of communication comprehension (M=22.38. Std.=3.68), communication liking (M=94.86, Std.=13.58) and reaction time (M=82.44s, Std.=14.15s). Picture books facilitate better interactive communication through their metaphorical expression.