Classification model training method and device, equipment, storage medium and program product

Abstract

The invention discloses a classification model training method and device, equipment, a storage medium and a program product, and relates to the field of machine learning. The method comprises the following steps: acquiring sample data, wherein data in a data set to which the sample data belongs is correspondingly marked with a data label; determining an adjustment parameter based on the label value distribution condition of the data label; performing classification prediction on the sample data through the classification model to obtain a sample prediction probability; performing balance adjustment on the loss determination process of the sample prediction probability by using the adjustment parameter to obtain a loss value; and training the classification model through the loss value to obtain a data classification model used for classifying the target data in the data label range. Through the method, the adjustment parameters are determined according to the data in the data set and the data labels, and the sample data are analyzed, so that the problem of inaccurate classification results caused by unbalanced data feature attributes is avoided. The method can be applied to various scenes such as cloud technology, artificial intelligence and intelligent transportation.

Description

technical field [0001] The embodiments of the present application relate to the field of machine learning, and in particular to a training method, device, equipment, storage medium, and program product for a classification model. Background technique [0002] Data classification is the process of classifying data by its attributes or characteristics. Recognizing the value of data at different levels and analyzing the data correctly is the basis for obtaining correct analysis results. [0003] In related technologies, the data to be classified is usually input into a general classification model, and the classification model performs multi-label classification on the data based on the characteristics of the data to be classified. [0004] However, when multi-label classification is performed by the above method, when there is a feature imbalance in multiple data to be classified, for example: when judging the lesion type of a medical image, when most of the data to be classi...

AI Technical Summary

Problems solved by technology

[0004] However, when multi-label classification is performed by the above method, when there is a feature imbalance in multiple data to be classified, for example: when judging the lesion type of a medical image, when most of the data to be classified are non-medical images, only a small part For medical images with lesions, the classification model often tends to judge that the data to be classified belongs to the situation corresponding to the classification result with a large proportion of features—that is, it is judged that the data to be classified belongs to natural images, so it cannot be more accurate when classifying the data. Classification results for

Images