Music copywriting generation method based on a word shift distance combined with a word vector

A word vector and distance technology, which is applied in the field of personalized music copy generation based on song comment text, can solve the problems of long generation time, small range of copywriting songs, and large labor cost input, so as to improve efficiency, reduce space and convenience. The effect of diverse choices

Active Publication Date: 2019-04-19
WUHAN UNIV
View PDF2 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At the same time, the invention overcomes the defects of long time-consuming generation of traditional music copywriting, large labor cost investmen

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Music copywriting generation method based on a word shift distance combined with a word vector
  • Music copywriting generation method based on a word shift distance combined with a word vector
  • Music copywriting generation method based on a word shift distance combined with a word vector

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0016] In order to facilitate those of ordinary skill in the art to understand and implement the present invention, the present invention will be described in further detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the implementation examples described here are only used to illustrate and explain the present invention, and are not intended to limit this invention.

[0017] The present invention mainly verifies the feasibility and efficiency of the present invention through the collection of music corpus and the realization effect of the algorithm. Since the target experience group of music copywriting is mainly people, the experimental results are reflected by the manual evaluation of 100 recruited experimenters. . The data of the present invention comes from NetEase Cloud Music, which has a large number of songs and tens of thousands of music reviews for each song. A total of 458 songs and 445,163 accompanying comments ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a music copywriting generation method based on a word shift distance combined with a word vector. The method comprises the following steps: firstly, crawling a lyric text and acomment text of a song from a music software website; Performing word segmentation processing on the lyric text and the comment text; Then further using vectorization representation on the words obtained in the word segmentation to obtain vector distribution representation of the words; Calculating word shift distances between the lyric text vectors in the songs and all the comment text vectors,and obtaining a word shift distance sequence of the song comment texts; Setting a boundary value threshold value N of the word shift distance, and sorting the song comment texts with the word shift distance smaller than the boundary value threshold value N according to the word shift distance to serve as screened comment texts; And finally, performing duplicate removal processing on the alternative comment text, deleting sentences which do not conform to the natural grammar rule, and adding attribute information of songs as song music copywriting recommended to the user. The generated music copywriting is small in length, and the efficiency of selecting songs by people is improved.

Description

technical field [0001] The invention belongs to the field of information technology, and relates to a method for generating text summaries for natural language processing, in particular to a song comment text-based personality that combines the advantages of text word vector embedding representation and text similarity calculation based on word shift distance A method for generating music copywriting. Background technique [0002] The continuous development of the Internet era helps people to obtain music through more convenient tools, and people no longer need to buy MP3 devices to listen to music, and it also breaks the geographical restrictions of music dissemination. But the amount of music is growing rapidly at the same time. Hundreds of new songs are added to the global music library every day. It has become a major problem for people to choose the songs they want to listen to. [0003] In order to promote songs, song manufacturers usually add a personalized descripti...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G06F17/22G06F17/27G06F16/63G06F16/951
CPCG06F40/194G06F40/284
Inventor 彭敏王维川胡刚金志欢高望
Owner WUHAN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products