Abnormal Behavior Recognition Approach for Enterprises Using Graph Convolution Network and Bidirectional Recurrent Neural Network

With the rapid development of big data and artificial intelligence technology, the scale and complexity of enterprise behavior data are increasing, and traditional anomaly detection methods have been difficult to meet the needs of practical applications. In this study, two advanced neural network architectures, Graph Convolutional Network (GCN) and Bidirectional Recurrent Neural Network (BiRNN), are introduced. From the perspective of big data analysis, a large number of business behaviors of enterprises are analyzed and abnormal business behaviors are found. The GCNs and GCN-BiRNNs composite model, which includes GCN and BiRNN, is constructed. The effectiveness of the algorithm in the task of abnormal enterprise behavior identification is verified by experiments. The experimental results show that the model can accurately identify the abnormal situation in the enterprise behavior, and has high recognition accuracy and robustness. This research not only provides a new technical means for enterprise risk management, but also provides a new idea for the application of deep learning in the field of anomaly detection.