Traditional Chinese medicine case named entity identification method, system and device and medium

The invention provides a named entity recognition method, system and device for traditional Chinese medicine cases and a medium, and relates to the field of information processing. The method comprises the following steps: firstly, sending a target text comprising traditional Chinese medicine case information into an LEBERT pre-training model, performing boundary division on named entities by utilizing preset vocabulary information, and then performing label division processing on the named entities by utilizing a BILSTM neural network model, and finally, carrying out classification processing on prediction tags output by the BILSTM neural network model by utilizing a CRF layer according to a preset constraint condition so as to improve the accuracy of target text named entity recognition. According to the method, the named entity recognition step is optimized, so that the problem of difficulty in entity recognition caused by the problems of fuzzy entity boundaries, similar meaning but different affiliations