Data processing method and device

Abstract

The embodiment of the invention discloses a data processing method and a data processing device. The data processing method comprises the following steps: acquiring an audio set of target songs in a song databank, wherein the audio set comprises a plurality of audio data; calculating the distance of every two audio data in the audio set, and adding the distances between any one piece of audio data and different audio data in the audio set so as to obtain distance sums of the audio data; acquiring first N target audio data which are sequenced according to the distance sums from small to large in the audio set, wherein N is a positive integer; according to the distance between every two audio data in the target audio data, calculating the data divergence of the target songs; according to the calculated data divergence of the target songs, confirming difficulty coefficients of the target songs. By adopting the embodiment of the invention, the difficulty coefficients of the songs can be efficiently confirmed, and intelligence and automation of the difficulty coefficients of the songs can be achieved.

Description

Technical field [0001] The present invention relates to the technical field of data processing, in particular to a data processing method and device. Background technique [0002] There are many different styles and categories of songs. Due to the different melody or the characteristics of the singer's voice, the difficulty of singing varies from song to song. The National K Song System provides a scoring system while singing songs for users. However, due to the different difficulty of different songs, in order to achieve a horizontal comparison of different songs, each song needs to be marked with difficulty coefficients so that users can choose to sing and achieve different singing The song can be compared horizontally. The difficulty coefficients of songs in the prior art are all manually labeled. However, using this method not only has high cost and low timeliness, but also produces difficulty coefficients given by different people for the same song due to different artifici...

AI Technical Summary

Problems solved by technology

In the prior art, the difficulty coefficient of songs is manually marked. However, this method is not only costly and time-sensitive, but also produces difficulty coefficients given by different people for the same song due to different artificial subjective judgment standards. inconsistencies

For the above problems, no effective solution has been proposed

Images