Emotion category prediction method and device, storage medium and electronic equipment

Abstract

The invention discloses an emotion category prediction method and device, a storage medium and electronic equipment, which can be applied to a vehicle-mounted scene. The method comprises the following steps: obtaining a set of first feature vectors and a set of second feature vectors, wherein the set of first feature vectors comprise feature vectors obtained by encoding each first element unit in a set of first element units, the set of first element units comprise each first element unit in a target text, one group of second feature vectors comprises a feature vector obtained by encoding each second element unit in one group of second element units, and one group of second element units comprises second element units obtained by performing word segmentation on the target text; according to the inclusion relation between the group of second element units and the group of first element units, performing feature vector fusion on the group of first feature vectors and the group of second feature vectors to obtain a group of fused feature vectors; and inputting the group of fused feature vectors into a target prediction model to obtain a predicted emotion category.

Description

technical field [0001] The present application relates to the computer field, and in particular, relates to an emotion category prediction method and device, storage medium and electronic equipment. Background technique [0002] The self-media platform can display the media information (such as articles, videos, etc.) produced by users in the form of information flow. While consuming media information, users can interact with these media information through behaviors such as comments, likes, reposts, and collections. [0003] Due to the low threshold for users to publish content, any user can publish media information at any time if the requirements are met, which will lead to uneven quality of media information produced by users, and the production of low-quality content (that is, low-quality media information) and behaviors that seriously affect the platform ecology. A prediction model capable of predicting emotion type may be used to predict the emotion category of the ...

AI Technical Summary

Problems solved by technology

[0005] The embodiment of the present application provides an emotion category prediction method and device, storage medium, and electronic equipment, to at least solve the problem of the accuracy of emotion category prediction caused by the high uncertainty of word meaning in the emotion category prediction method in the related art low problem

Images