State detection method and device, detection equipment and storage medium

Abstract

The invention provides a state detection method and device, detection equipment and a storage medium, and belongs to the technical field of artificial intelligence. The method comprises the steps that a plurality of training samples are acquired, each training sample comprises a first number of sample audio features, the first number of sample audio features correspond to a first number of audio frames in the same piece of sample audio data, and the sample audio data are acquired under the condition that the electronic equipment operates normally; inputting each training sample into a state detection model to obtain a prediction probability corresponding to each training sample; and training a state detection model based on the prediction probabilities corresponding to the plurality of training samples, the trained state detection model being used for detecting the running state of any electronic device. According to the method provided by the invention, the relatively accurate state detection model is trained in an unsupervised training mode, and the accuracy of state detection is ensured.

Description

technical field [0001] The present application relates to the technical field of artificial intelligence, and in particular to a state detection method, device, detection equipment and storage medium. Background technique [0002] With the development of artificial intelligence technology and the wide application of electronic equipment, it has become a common way to detect the state of electronic equipment based on neural network models. In related technologies, a state detection model is usually trained. Based on the state detection model, the audio data generated during the operation of the electronic device can be detected to obtain a detection result, which can indicate whether the electronic device is operating normally. [0003] However, when training the state detection model, it is necessary to collect a large number of training samples, including positive audio data generated when the electronic equipment is operating normally and negative audio data generated when...

AI Technical Summary

Problems solved by technology

[0003] However, when training the state detection model, it is necessary to collect a large number of training samples, including positive audio data generated when the electronic equipment is operating normally and negative audio data generated when the electronic equipment is abnormal. However, due to the lack of negative audio data, it is impossible to train out Accurate state detection model, which leads to insufficient accuracy of state detection

Images