Knowledge-driven milk cow disease text classification method

The invention discloses a milk cow disease text classification method based on knowledge driving, and the method comprises the following steps: obtaining disease features of a milk cow disease description text, and converting the disease features into word vectors; constructing a disease text classification model based on a convolutional neural network and a long-short-term memory network; inputting the word vectors into the disease text classification model for processing to obtain final disease features of the dairy cow disease text; and classifying the dairy cow disease texts based on the final disease features. According to the method, recessive features and dominant features of the dairy cow disease text are captured, and more identification features are provided for dairy cow disease text classification. 本发明公开了一种基于知识驱动的奶牛疾病文本分类方法，包括以下步骤：获取奶牛病情描述文本的疾病特征，并将所述疾病特征转化为词向量；基于卷积神经网络和长短期记忆网络，构建疾病文本分类模型；将所述词向量输入到所述疾病文本分类模型中进行处理，获得奶牛疾病文本的最终疾病特征；基于所述最终疾病特征对奶牛疾病文本进行分类。本发明捕捉了奶牛疾病文本的隐性特征和显性特征，为奶牛疾病文本分类提供了更多的鉴别性特征。