Hierarchical category named entity recognition model design method based on multi-task learning

The invention relates to a hierarchical category named entity recognition model design method based on multi-task learning, and belongs to the technical field of natural language processing. According to the named entity recognition method, modeling for the category relationship is added into a named entity recognition model, so that the model can recognize a plurality of categories of the named entity at the same time, and meanwhile, the model based on multi-task learning is provided to solve the problem of named entity recognition with hierarchical categories. The model uses a multi-task learning mechanism to learn named entity recognition tasks of multiple levels at the same time, the tasks share the same coding layer, and therefore coding vectors learned by the coding layer can adapt to named entity recognition of multiple levels at the same time instead of being over-fitted to a certain independent level. And finally, two information transmission mechanisms are respectively designed to transmit identific