Data processing method, computer device and readable storage medium

Abstract

The embodiment of the present application discloses a data processing method, computer equipment, and a readable storage medium, wherein the method includes: acquiring audio data, performing attribute identification on the audio data, and obtaining the target audio basic attribute corresponding to the audio data; according to at least two audio The mapping relationship between the basic attribute and at least two audio emotion tags, and the target audio basic attribute, the audio data is emotionally identified, and the target audio emotion tag corresponding to the audio data is obtained; the at least two audio emotion tags include the target audio emotion tag; Bind target audio sentiment tags to audio data. The embodiments of the present application can be applied to various scenarios such as cloud technology, artificial intelligence, intelligent transportation, and assisted driving. By adopting the present application, the emotion classification of audio data can be automatically completed, thereby improving the efficiency of emotion label binding on audio data.

Description

technical field [0001] The present application relates to the technical field of the Internet, and in particular to a data processing method, computer equipment and a readable storage medium. Background technique [0002] As audio data is more and more widely used in life, the division of audio data emotion is getting more and more attention. [0003] In practical applications, it is usually possible to search for matching songs in music applications through the selection of song emotion types, and the realization of this function requires setting the corresponding song emotion types for songs in advance. Currently, it is usually through manual listening to songs and manual analysis. To get the emotional type of a song, and then bind the emotional type of the song obtained through human experience to the song, so there may be different emotional types of the song analyzed by different analysts for the same song , resulting in unstable accuracy of the analyzed emotional type...

AI Technical Summary

Problems solved by technology

[0003] In practical applications, it is usually possible to search for matching songs in music applications through the selection of song emotion types, and the realization of this function requires setting the corresponding song emotion types for songs in advance. Currently, it is usually through manual listening to songs and manual analysis. To get the emotional type of a song, and then bind the emotional type of the song obtained through human experience to the song, so there may be different emotional types of the song analyzed by different analysts for the same song , resulting in unstable accuracy of the analyzed emotional type of the song, that is, the accuracy of the emotional type of the song cannot be guaranteed, and the method of manual analysis will also lead to low efficiency in identifying the emotional type of the song

Images