Note generation method, related equipment, storage medium and program product

Abstract

The invention discloses a note generation method, related equipment, a storage medium and a program product. The method comprises the steps: acquiring a generation identifier of a to-be-generated target note and a target feature vector generated based on the generation identifier; reading generation indication information of the target note from the target feature vector; when determining that the generation mode of the target note is a first mode according to the generation indication information, acquiring one or more associated feature vectors of the target feature vector; according to any associated feature vector in the one or more associated feature vectors and the target feature vector, determining a recurrence probability of the associated identifier corresponding to any associated feature vector; and according to the recurrence probability of the correlation identifier corresponding to each correlation feature vector, selecting the correlation identifier of which the recurrence probability meets a probability threshold value from the correlation identifiers corresponding to the correlation feature vectors as a generated target note, and generating a note sequence with a sequence structure so as to generate structural music.

Description

technical field [0001] The present application relates to the field of computer technology, and in particular to a method for generating musical notes, related equipment, storage media and program products. Background technique [0002] With the improvement of living standards, listening to music has become an important way for people to relax and entertain, and it is obvious that beautiful music can effectively relieve negative emotions and help people to build mental health to a certain extent. Thanks to the rapid development of computer science and technology, music can no longer rely entirely on artificial creation, that is to say, people can use computer equipment to automatically generate music. At present, computer equipment usually uses a recurrent neural network or attention mechanism as the basic structure, and then uses this computer equipment to determine new notes from the note vocabulary based on each note in the generated note sequence, and generate Each note...

AI Technical Summary

Problems solved by technology

At present, computer equipment usually uses a recurrent neural network or attention mechanism as the basic structure, and then uses this computer equipment to determine new notes from the note vocabulary based on each note in the generated note sequence, and generate Each note of , it is impossible to construct a sequence of notes with a sequence structure

Images