Text Classification Based on TextCNN for Power Grid User Fault Repairing Information
Yukun Cao, Tian Liang Zhao · 2018
Aiming at the problem that the fault information submitted by power grid users is difficult to be automatically analyzed and dealt with, We proposed a text classification model based on TextCNN (Text Convolutional Neural Network, TCNN) for fault repairing information of Power grid users. First of all, Using CBOW (Continuous Bag-of-Words) to learn the distributed representation of text. Second, The feature of pretrained word vector is learned through the text convolutional neural network model, and k-max pooling is used to further extract the high-level features. Finally, the classification model is obtained by softmax classifier. We use the model to classify and analysis the fault repairing information. Experimental results validate the effectiveness of our approach when compared to the state-of-the-art methods.