Research on Aviation Unsafe Information Text Analysis Based on Improved CNN-BiGRU-att Model

Descriptive information of many accidents and accident symptoms is contained in voluntary reports on civil aviation safety. In order to solve the shortcomings of manual analysis of aviation unsafe information text at this stage, a multi-channel text convolutional neural network-bidirectional gated recurrent unit (TextCNN-BiGRU) analysis model based on attention mechanism is proposed. Firstly, the initial text is vectorized by word2vec, the window values are selected through experiments to form three channels. Then, the strong learning ability of CNN is used to extract local features, the bidirectional gated recurrent unit is used to extract contextual global information, and the attention layer and pooling layer are used to obtain And optimize the important features. Finally, using the softmax function is to minimize the error loss. The simulation experimental verification results show that the classification performance of the proposed model has a classification accuracy of 94%, and the loss function value is stable at about 0.22%.It has good generalization ability and can effectively solve the problem of incomplete information mining for a single model and effectively improve the classification effect.