Emotion recognition method, system and device and storage medium

Abstract

The embodiment of the invention provides an emotion recognition method, system and device and a storage medium, and the method comprises the steps: obtaining terminal motion data, terminal environment data and terminal use data of a target user in a preset time period, and employing a preset feature extraction algorithm, performing feature extraction on the terminal motion data, the terminal environment data and the terminal use data to obtain a user behavior feature set, performing normalization processing on the user behavior feature set by using a preset normalization algorithm to obtain a user behavior data set, and performing feature fusion on the user behavior data set by using a preset weight feature fusion algorithm to obtain a user behavior data set; and fusing various types of data in the user behavior data set in a vector dimension to obtain a user behavior feature vector, inputting the user behavior feature vector into a preset annular emotion recognition model for processing, and determining an emotion identifier of the target user in a preset time period according to a processing result of the preset annular emotion recognition model. According to the invention, the recognition precision of the user emotion is improved.

Description

technical field [0001] The present invention relates to the field of emotion recognition, in particular to an emotion recognition method, system, device and storage medium. Background technique [0002] The existing emotion recognition technology mainly collects the user's daily behavior data through wearable devices or smart mobile terminals, and extracts the features of the daily behavior data to establish a feature library, and uses the discrete emotion model as the benchmark for recognition. [0003] Due to the limited range of emotions that can be described by existing discrete emotion models. When the actual emotional state of the user is not in the enumerated discrete emotional state, the existing discrete emotional model cannot add emotional labels to the current data, which reduces the recognition accuracy. At the same time, the existing collected behavior data only reflects the user's objective behavior, but the emotions are mostly the user's subjective behavior c...

AI Technical Summary

Problems solved by technology

When the user's actual emotional state is not in the enumerated discrete emotional state, the existing discrete emotional model cannot add emotional labels to the current data, which reduces the recognition accuracy

At the same time, the existing behavior data collected only reflects the objective behavior of users, but emotions are mostly subjective behavior changes of users

Therefore, the behavioral data collected by the existing technology cannot accurately reflect the user's emotional changes.

It can be seen that the existing technology cannot achieve accurate recognition of emotions

Images