Information processing method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention discloses an information processing method and device, electronic equipment and a storage medium. The information processing method comprises the following steps: acquiring first data provided by first equipment and a data label of the first data; acquiring second data acquired by the first equipment and the second equipment at the same time; classifying the first data and the second data; according to a classification result, transmitting a data label of the first data to the second data belonging to the same class as the first data; constructing a training setbased on the second data and the data label of the second data; and training a recognition model based on the training set.

Description

technical field [0001] The present invention relates to the field of electronic technology, in particular to an information processing method and device, electronic equipment and a storage medium. Background technique [0002] In the existing technology, machine learning is usually used for model training, so that the trained model can be used for application. For example, the trained model is used to classify data or label the data with corresponding data labels. Based on the classification or data labels, the device performs corresponding operation. For example, in an application scenario of a wearable device, the wearable device needs to recognize a user's actions. The collected user action data is input data, and action recognition can be regarded as action classification or data label marking. In application scenarios, wearable devices are usually added to the recognition scene, and old devices are also removed from the recognition scene. When a new device is added, ...

AI Technical Summary

Problems solved by technology

However, the acquisition of training data is difficult due to user privacy and / or sample collection costs, which makes it difficult to obtain data, which in turn makes it difficult to train new devices.

In addition, during the training process, the sample data obtained may be complex, resulting in a complex training process, and the reliability of the trained recognition model is low

Images