Data processing method and its device, computer system and readable medium

Abstract

The present disclosure provides a data processing method, including: collecting the data to be marked of the measured object, wherein the data to be marked is used to record the behavior state of the measured object in the acquisition sequence; collecting the EEG signal data of the measured object, Wherein, the EEG signal data is used to represent the cognitive state of the measured object in the collection time series; and based on the EEG signal data and the data to be marked, the labeled data of the measured object is generated. The present disclosure also provides a data processing device, a computer system, and a computer-readable medium.

Description

technical field [0001] The disclosure relates to a data processing method and its device, a computer system and a readable medium. Background technique [0002] In the artificial intelligence algorithm that perceives and recognizes the cognitive state (emotion, attention, etc.) of the measured object, training a data-driven machine learning model requires a large amount of labeled data. It determines the accuracy of the training model and directly affects the recognition result of the cognitive state of the tested object. [0003] In the process of realizing the disclosed concept, the inventors found that there are at least the following defects in the related technologies: the data sets (video, audio, eye movement, myoelectricity, etc.) used in the current machine learning research in the industry have a huge amount of data. are manually annotated by annotators. However, human emotions, attention and other psychological and cognitive state data are difficult for annotator...

AI Technical Summary

Problems solved by technology

[0003] In the process of realizing the disclosed concept, the inventors found that there are at least the following defects in the related technologies: the data sets (video, audio, eye movement, myoelectricity, etc.) used in the current machine learning research in the industry have a huge amount of data. Annotated manually by annotators

However, human emotions, attention and other psychological and cognitive state data are difficult for annotators to accurately calibrate through the data sets (video, audio, eye movement, myoelectricity, etc.) used, often due to individual deviations of different annotators , resulting in poor consistency of the labeling data of multiple labelers, and low reliability of the labeling results, which ultimately leads to the inability of the machine learning model to accurately predict the cognitive state of the tested object.

Images