Prediction model training method and device, storage medium and computer equipment
The invention discloses a prediction model training method and device based on a neural network, a storage medium and computer equipment, and mainly aims to reduce the number of manually labeled samples and avoid a large amount of repeated labor, thereby improving the training efficiency and predict...
Saved in:
Main Authors | , , , |
---|---|
Format | Patent |
Language | Chinese English |
Published |
15.11.2019
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | The invention discloses a prediction model training method and device based on a neural network, a storage medium and computer equipment, and mainly aims to reduce the number of manually labeled samples and avoid a large amount of repeated labor, thereby improving the training efficiency and prediction precision of a prediction model. The method comprises the steps of obtaining labeled sample dataand unlabeled sample data; inputting the labeled sample data into a preset neural network model for training to obtain a preliminary model corresponding to the prediction model; inputting the unlabeled sample data into the preliminary model for prediction to obtain confidence coefficients of the unlabeled sample data corresponding to each prediction category; determining a prediction category ofwhich the confidence does not meet a preset condition, selecting unlabeled sample data under the determined prediction category for labeling, and updating the labeled sample data by utilizing newly labeled sample data; and inp |
---|---|
Bibliography: | Application Number: CN201910559074 |