Sample denoising method and device based on regression prediction active learning framework, storage medium and equipment

The invention discloses a sample denoising method and device based on a regression prediction active learning framework, a storage medium and equipment, and belongs to the technical field of civil construction material scientificity. The method comprises the steps that a sample set is acquired, and the sample set is a concrete strength data set; inputting the sample set into the constructed regression prediction active learning framework to obtain a de-noised sample set, and completing sample de-noising; the invention provides a regression prediction active learning framework based on remarking, the framework focuses on processing label samples with label noise, the accuracy of a model is improved through a remarking strategy, the framework selects the most valuable sample for marking in each iteration so as to reduce the demand of sample marking, and the accuracy of the model is improved. And label noise is processed by adopting a specific re-marking method. In this way, the frame can be balanced in accuracy