A security data detection and management method in digital library network based on deep learning

Abstract

Listen

Translate article

With the rapid growth of data volume in digital library and the increasingly complex network environment, traditional network security measures are no longer able to meet their security needs. In response to the problems of low detection accuracy and long detection time in traditional network security methods, we propose a digital library network security data detection and management method based on bidirectional gated recurrent unit and temporal convolutional network detector (BiGRU-TCNDetector) using the powerful capabilities of deep learning technology. It efficiently and intelligently detects and manages security data in digital library network. The method combines the structures of temporal convolutional network (TCN) and bidirectional gated recurrent unit (BiGRU) to extract spatial and temporal features from digital library network security data. And it improves the accuracy of security data detection based on BiGRU-TCN. In addition, the importance of each security data feature is calculated through attention mechanism to reduce the loss of important digital network security data information, which is then output by the global pooling layer to the classifier for classification. Finally, comparative experiments are conducted to verify that the digital library network security data detection method based on BiGRU-TCNDetector has better detection performance compared to other methods, providing a solid technical guarantee for the stable operation and sustainable development of digital library.