Machine learning method and system based on end, edge and cloud collaboration, and medium

The invention provides a machine learning method and system based on an end, edge and cloud collaborative architecture. The method comprises the following steps: extracting a plurality of general features of an input image; transmitting the plurality of generic features; receiving a plurality of universal features, and adaptively selecting at least one universal feature corresponding to the machine learning task; training a corresponding machine learning task according to the at least one general feature to obtain a trained machine learning model; and obtaining a prediction result of the machine learning task by the trained machine learning model according to the input image. According to the method, the universal features which can be used for various visual tasks are extracted at the end architecture, the universal features are only transmitted on the edge architecture without transmitting the original image acquired at the end, and finally, the universal features are utilized at the cloud architecture to t