Entity recognition method and device based on Chinese medical records, equipment and storage medium

Abstract

The invention discloses an entity recognition method based on a Chinese medical record, and belongs to the field of natural language processing. The method comprises the following steps: carrying outword segmentation on Chinese medical records; outputting a first feature vector used for representing the position of each word in the word group; identifying the radicals of each character in the Chinese medical record, and comparing the identified radicals of each character with preset entity radicals one by one; outputting a second feature vector for representing a comparison result corresponding to each word; splicing the output first feature vector and second feature vector corresponding to each word behind the initial vector of each word to obtain a vector set for representing the Chinese medical record; and inputting the vector set into the trained model to extract entities therein. According to the method, corresponding features are extracted from the text content in the Chinese case and converted into feature vectors to serve as input of the model, so that the entity recognition accuracy of the model is improved.

Description

technical field [0001] The invention relates to the field of natural language processing, and relates to an entity recognition method, device, equipment and storage medium based on Chinese medical records. Background technique [0002] At present, there is a great demand for the application of named entity recognition in medical cases, such as querying, searching, sorting, etc., in order to achieve the purpose of building medical knowledge base, medical knowledge graph and promoting medical automatic question answering. [0003] The effect of existing Chinese named entity recognition based on deep learning is difficult to improve, and it was previously applied to other languages, such as English. Because of the limitations of deep learning models and the differences in language characteristics between languages, this limits the application of named entity tasks in Chinese. And because of the differences between the general field, other fields and the medical field, its appl...

AI Technical Summary

Problems solved by technology

[0004] The technical problem to be solved by the present invention is to overcome the problem of low accuracy of Chinese named entity recognition based on deep learning in the prior art, and propose a method, device, equipment and storage medium for entity recognition based on Chinese medical records. The corresponding features of the text content in the Chinese cases are extracted and converted into feature vectors, and then the feature vectors are used as the input of the model to improve the accuracy of entity recognition

Images