Outlier event detection and identification method based on replication neural network

The invention discloses an outlier event detection and recognition method based on a replicated neural network, relates to the technical field of information, and aims to solve the problems that mostmethods in the prior art seriously depend on abnormal data in order to smoothly complete deep learning model training, but the abnormal data is not easy to obtain, and the method comprises the following steps: step 1, obtaining to-be-processed Chinese text sequence data; 2, performing time sequence analysis on the Chinese text sequence data to be processed; 3, performing shallow semantic analysison the Chinese text sequence data after the time sequence analysis; 4, for the Chinese text sequence data subjected to shallow semantic analysis, recognizing and extracting event trigger words based on a deep learning strategy; 5, carrying out candidate event recognition on the Chinese text sequence data obtained after event trigger word recognition and extraction; and 6, taking the Chinese text sequence data after candida