abstract |
The invention relates to a medical named entity recognition system and method based on RWLSTM model fusion. ; Model modeling module, which builds the framework of the model according to the task; Entity extraction module, which extracts and categorizes the information after the operation of building the model and after feature extraction; Dictionary building module, constructs the named entity corpus dictionary of medical records. Data preprocessing is performed on the text of electronic medical records, the Chinese word segmentation module performs word segmentation on the text, and the entity labeling module labels the text, and then some erroneous and useless data are eliminated; the data preprocessing module is used to clean the electronic medical records, which is effective Reduce the time cost of model training; solve the problem of named entity recognition in the field of electronic medical records in the medical field. |