Data enhancement method and device

Abstract

The invention provides a data enhancement method and a data enhancement device. The data enhancement method comprises the steps of: acquiring N training data subsets, wherein each training data subsetcorresponds to one emotion type, and N is a positive integer; determining a to-be-processed data set from the N training data subsets according to a proportion between the data volume of the N training data subsets and the total data volume of the N training data subsets; performing at least one reverse translation on the to-be-processed data set to obtain a reverse translation data set, the reverse translation is a process of performing non-Chinese translation on any text data and then performing Chinese translation; and acquiring a target training data set according to the N training data subsets and the reverse translation data set, thereby expanding the data volume of the training data, weakening the problem of unbalanced distribution of the training data, improving the quality of thetraining data, and improving the performance of the target training model and the classification effect of emotion types.

Description

technical field [0001] The invention relates to the field of computer technology, in particular to a data enhancement method and device. Background technique [0002] With the rapid development of e-commerce, the number of online shopping groups has grown exponentially, and customer service robots have emerged as the times require. In the service process, the customer robot needs to make accurate judgments on the customer's emotions. At this time, the customer's text data can be transformed into a problem of emotion classification, that is, the deep learning neural network model (referred to as the training model) can determine the identification corresponding to the text data. emotional type. [0003] It is well known that the performance of training models depends heavily on the training data. In general, the larger the amount of training data, the better the performance of the training model; the more features of the training data, the better the performance of the trai...

AI Technical Summary

Problems solved by technology

[0005] The present invention provides a data enhancement method and device to solve the problem in the prior art that the total amount of training data data is insufficient or the data volume distribution of training data corresponding to various emotion types is unbalanced

Images