在训练集中数据和标签已知的情况下，输入测试数据，将测试数据的特征与训练集中对应的特征进行相互比较，找到训练集中与之最为相似的前K个数据，则该测试数据对应的类别就是K个数据中出现次数最多的那个分类。(In the case where the training data and the tag are known, the test data is input, the characteristics of the test data are compared with the characteristics corresponding to the training set, and the former K data with the most similarity in the training set are found. The category is the sort of the largest number of occurrences of K data.)