META-LEARNING-BASED METHOD FOR DATA SCREENING MODEL CONSTRUCTION, DATA SCREENING METHOD, APPARATUS, COMPUTER DEVICE, AND STORAGE MEDIUM

摘要

A meta-learning-based method for data screening model construction, a data screening method and apparatus, a computer device, and a storage medium, the method comprising: constructing a meta-learning-based data screening model and, on the basis of said model, extracting a feature vector for each category from among categories to be screened, and a feature vector for data among data to be screened to serve respectively as a first target feature vector and a second target feature vector; splicing the first and second target feature vectors so as to generate a third feature vector corresponding to each data to be screened; comparing the attribution value of the target feature vector of each data to be screened to a preset attribution threshold corresponding to each category, so as to use preset labels to label target data as a category corresponding to the third target feature vector.