Faulty Interrogative Intent Recognition for Grid Cloud Platform Based on Bert-TextCNN
Fei Wang, Pan Hu, Yuanqi Yu · 2024
With the increase of business complexity of power information system, the traditional fault processing methods can no longer meet the requirements of fast and accurate, so this study uses deep learning technology to classify the intent of microservice fault interrogation sentences of the grid cloud platform by constructing a Bert- TextCNN model, which combines the bi-directional encoding feature extraction capability of BERT and the local feature capture capability of TextCNN. The experimental results show that the method outperforms other baseline models in terms of precision, recall and F1 value, and can effectively improve the efficiency and accuracy of fault processing.