Training sample expansion method and device, electronic equipment and storage medium

Abstract

The invention discloses a training sample expansion method. The method comprises the following steps: determining samples of target disease types of which the quantity is less than a preset quantity threshold as target samples; performing vector conversion on the disease name corresponding to the target sample to obtain a name vector; according to a pre-trained first disease classification model,based on the precision of the first disease classification model and the gradient change of the discrimination network, training the generation network to obtain a trained generation model; inputtingthe name vector into a trained generation model to obtain a generated sample data set; and if a plurality of generation samples in the generation sample data set can be used for model training, determining the real sample data set and the generation sample data set as a first training sample data set of the auxiliary diagnosis model. The invention further provides a training sample expansion device, electronic equipment and a storage medium. The number of training samples can be increased, and the accuracy of the auxiliary diagnosis model is improved.

Description

technical field [0001] The invention relates to the technical field of neural networks, in particular to a training sample expansion method, device, electronic equipment and storage medium. Background technique [0002] At present, with the development of neural network algorithms, more and more auxiliary diagnostic models for auxiliary diagnosis have emerged, and these auxiliary diagnostic models can provide great convenience for medical work. However, in practice, it is found that in the sample data set used to train the auxiliary diagnosis model, because some types of diseases are relatively rare, there may be a small number of samples of certain types of disease symptoms, and a small number of disease symptoms is used. Using samples to train the auxiliary diagnosis model will lead to low accuracy of the trained auxiliary diagnosis model. [0003] Therefore, how to expand the number of training samples to improve the accuracy of the auxiliary diagnosis model is a technic...

AI Technical Summary

Problems solved by technology

However, in practice, it is found that in the sample data set used to train the auxiliary diagnosis model, because some types of diseases are relatively rare, there may be a small number of samples of certain types of disease symptoms, and a small number of disease symptoms is used. Samples are used to train the auxiliary diagnosis model, which will lead to low accuracy of the trained auxiliary diagnosis model

Images