Flying recognition method and device, storage medium and processor

The invention discloses a lie recognition method and device, a storage medium and a processor. The method comprises the following steps: acquiring a face image of a target object in a preset time period; extracting image features of the face image by using a preset mask recurrent neural network; acquiring voice information of the target object in a preset time period; extracting voice features of the voice information by using a long short-term memory network; the image features and the voice features are analyzed by using maximum soft classification, a lie recognition result of the target object is determined, the maximum soft classification is trained by using multiple groups of data through machine learning, and each group of data in the multiple groups of data comprises the image features, lie tags identified by the image features, lie tags identified in the voice features and lie tags identified in the voice features; the lie tag is used for indicating lie. Through the method and the device, the problem