Multi-modal named entity recognition method and device, equipment and storage medium

The invention relates to the technical field of natural language processing, in particular to a multi-modal named entity recognition method, which comprises the following steps: obtaining document data and a preset multi-modal named entity recognition model, inputting a sentence into a text feature extraction module for feature extraction, and obtaining a text feature representation corresponding to the sentence; inputting the image into the visual feature extraction module for feature extraction to obtain visual feature representation corresponding to the image; inputting the visual feature representation into the visual attention extraction module for attention extraction, and obtaining the visual feature representation after attention extraction; inputting the text feature representation and the visual feature representation after attention extraction into a cross-modal interaction module for feature interaction to obtain a cross-modal feature representation; and inputting the cross-modal feature represent