Medical event extraction method based on generative model

A medical event extraction method based on a generative model comprises the following steps: 1) obtaining electronic medical record text data in a database, and presetting an entity type and an event template which need to be extracted; 2) in the electronic medical record text, marking entities and events in the medical record through a marking tool according to a set template; (3) a transformer model is used as a text encoder, and a text is converted into vector representation; 4) marking entities by using a pointer network; 4) classifying event types by using a pooling layer and a linear layer; (5) generating an event information sequence by using a generative transformer; and 6) extracting argument roles in the event information sequence, and summarizing event information. According to the method, the unstructured data in the medical electronic medical record is extracted by using the joint extraction algorithm, so that the structured event information is obtained, and powerful help is provided for subsequ