Named entity recognition method and device based on multi-task learning

A named entity recognition method based on multi-task learning comprises the steps that a main task and one or more sub-tasks are generated according to an original task recognized by a named entity,the main task is consistent with the original task, and the sub-tasks are tasks assisting in achieving the main task; inputting the training text into a named entity recognition network model; training the named entity recognition network model; wherein the named entity identification network model at least comprises a main task network and a sub-task network, the sub-task network is used for executing the sub-task and outputting sub-task prediction information to the main task network, and the main task network is combined with the sub-task prediction information to execute the main task andoutput a main task prediction result; and inputting a to-be-identified text into the named entity identification network model, and determining an identification result according to the output of themain task network. 一种基于多任务学