基于TextCRNN-OvR的患者咨询文本分类方法

Patient Consultation Text Classification Method Based on TextCRNN-OvR

人工智能技术加速了互联网医疗发展,患者在线问诊逐渐成为新趋势。然而大多数患者自身医学知识匮乏,往往出现挂错科室的情况。因此,患者咨询文本分类对于引导患者线上选择就诊科室显得十分重要。本文提出一种结合卷积循环神经网络与OvR策略的文本多分类方法,既可以捕捉文本局部特征,又可以学习词序信息。本文爬取了39问答网上的患者咨询文本作为数据源,对所提方法进行了验证,并与已有的分类算法作对比,结果表明所提方法在精度、召回率、F1值及准确率指标上具有更优越的算法性能。其中,相较于其他SOTA的文本分类模型,TextCRNN-OvR在文本分类精度上取得了1%~4%不同程度上的提高,这进一步说明了TextCRNN在提取文本特征方面以及本文OvR多分类策略的有效性。

The development of Internet medical treatment has been accelerated by artificial intelligence technology, then online patient consultation is becoming a new trend. However, most patients often choose the wrong department due to a lack of adequate medical expertise. Therefore, the classification of patient consultation text is very important for guiding patients to choose departments online. This paper proposes a text multiple classification method combining the convolutional recurrent neural network and OvR strategy, which can capture local features of text but also learn word order information. In this paper, the proposed method is verified by crawling the patient consultation text on 39ask.com as the data source. Compared with existing classification algorithms, the results show that the proposed method has better performance in terms of precision, recall rate, F1 score and accuracy. Among them, compared with other SOTA text classification models, TextCRNN-OvR has improved the accuracy of text classification by 1% to 4% to varying degrees, which further illustrates the advantages of TextCRNN in extracting text features and the effectiveness of the OvR multi-classification strategy in this paper.