Training method, feature extraction method and device and electronic equipment

Abstract

The embodiment of the invention provides a training method, a feature extraction method and device and electronic equipment. The training method comprises the steps that a first short-term feature setunder target classification corresponding to a sample object is input into a recurrent neural network, a second short-term feature set is obtained, and all short-term features in the first short-termfeature set correspond to the same first time granularity; and combining the second short-term feature sets into a long-term feature set according to a time sequence, with each long-term feature in the long-term feature set corresponding to the same second time granularity, and the second time granularity being greater than the first time granularity; the long-term feature set is inputted into aconvolutional neural network to obtain a target feature set of the target object corresponding to the target classification; the target feature set is inputted into a classification model used for identifying target classification so as to train a recurrent neural network and a convolutional neural network based on an identification result of the classification model for the sample object.

Description

technical field [0001] This document relates to the technical field of data processing, in particular to a training method, feature extraction method, device and electronic equipment. Background technique [0002] With the development of artificial intelligence, more and more scenarios will be applied to the deep learning model constructed by the neural network to achieve the purpose of mechanized processing information. In some of these scenarios, the model needs to be trained using features presented at different temporal granularities. What the existing technology does is to train the model separately for the features of each time granularity. In this way, firstly, the training efficiency is not high; secondly, the trained model cannot reflect the implicit correlation between short-term characteristics and long-term characteristics, resulting in poor model performance. [0003] In view of this, how to train a model that can associate short-term and long-term characteris...

AI Technical Summary

Problems solved by technology

In this way, firstly, the training efficiency is not high; secondly, the trained model cannot reflect the implicit correlation between short-term characteristics and long-term characteristics, resulting in poor model performance

Images