Convolutional neural network and self-attention mechanism fused operation record automatic coding method

The invention relates to a coding method, in particular to an automatic coding method for operation records fusing a convolutional neural network and a self-attention mechanism. According to the method, deep learning training is carried out on a large number of operation record texts, automatic coding of operation styles in operation records is achieved, and therefore work of coding personnel is assisted. Comprising the following steps: step 1, taking a surgical operation automatic coding task as a text multi-label classification task; and step 2, establishing a training model and realizing automatic coding through the training model. 本发明涉及一种编码方法，尤其涉及一种融合卷积神经网络与自注意力机制手术记录自动编码方法。其通过对大量手术记录文本进行深度学习训练，实现手术记录中术式的自动编码，从而辅助编码人员的工作。包括步骤：步骤1、将手术操作自动编码任务作为文本多标签分类任务。步骤2、建立训练模型并通过训练模型来实现自动编码。