An Intelligent Assistant Diagnosis Method for Autistic Children based on Chinese Multimodal Discourse Corpus

To meet the needs of auxiliary diagnosis of autistic children, this paper adopts the cross research method of corpus in the field of linguistics and artificial intelligence in the field of computer science. In this paper, a deep learning neural network model is designed. This model should be able to take the multimodal data of autistic children as input, and then output the type of autistic children corresponding to this data, as well as the severity, hobbies, and possible appropriate intervention programs. Finally, according to the results of the prediction, we can not only know the type, severity, and other information used for auxiliary diagnosis of autistic children, At the same time, it can also analyze the interests of autistic children, as well as the appropriate personalized intervention programs based on their interests.