Singing accompaniment recommendation method and server

A recommendation method and server technology, applied in the direction of instruments, special data processing applications, electrical digital data processing, etc., can solve problems such as low accuracy and fuzzy classification of recommendation results, and achieve the effect of improving accuracy

Active Publication Date: 2018-04-17
北京小唱科技有限公司
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] The present invention provides a singing accompaniment recommendation method and server to solve the problem of fuzzy classification

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
  • Singing accompaniment recommendation method and server
  • Singing accompaniment recommendation method and server
  • Singing accompaniment recommendation method and server

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0028] refer to figure 1 , shows a flow chart of a method for recommending singing accompaniment in Embodiment 1 of the present invention. The method for recommending singing accompaniment in the embodiment of the present invention includes the following steps:

[0029] Step 101: The server obtains the user's singing behavior data and the identification information of the artist who has been sung.

[0030] The user's singing behavior data includes the artists that the user has sung, and the number of times the user has sung the songs of these artists.

[0031] Step 102: Based on the user's singing data, establish a vector space corresponding to the artist IDs, and perform clustering on the artist IDs to obtain a clustering result.

[0032] For example, artist A is sung by users a, b, and c for 0, 1, and 3 times respectively. If the sample size is a, b, and c, each value in the vector is 0, 3, and 4; 0 means no singing, 3 means singing, and 4 means singing many times. Then t...

Embodiment 2

[0039] refer to figure 2 , shows a flow chart of a method for recommending singing accompaniment in Embodiment 2 of the present invention. The method for recommending singing accompaniment in the embodiment of the present invention includes the following steps:

[0040] Step 201: The server obtains the user's singing behavior data and the identification information of the artist who has been sung.

[0041] Step 202: Based on the user's singing data, establish a vector space corresponding to the artist IDs, and perform clustering on the artist IDs to obtain a clustering result.

[0042] A preferred clustering method is:

[0043] S1: Extract the user's singing behavior data that satisfies the conditions from the acquired user's singing behavior data;

[0044] The singing behavior data of users who meet the conditions are the historical data of songs sung by users who normally log in and use mobile applications within a certain period of time. The remaining data is the data g...

Embodiment 3

[0067] refer to image 3 , shows a schematic structural diagram of a server of the present invention. The server shown in this embodiment includes.

[0068] The obtaining module 301 is used to obtain the user's singing behavior data and the identification information of the artist who has been sung.

[0069] The clustering module 302 is used to establish a vector space corresponding to artist IDs according to user singing data, and perform clustering on artist IDs to obtain a clustering result.

[0070] The filtering module 303 is configured to filter the clustering results to obtain the filtering results.

[0071] The recommendation module 304 is configured to recommend singing accompaniments according to the filtering results.

[0072] Through the server provided by the embodiment of the present invention, the vector space corresponding to the artist can be established through the user's singing behavior, and the artist can be clustered and the clustering results can be s...

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 provides a singing accompaniment recommendation method and a server. The method is applied in a network platform song requesting system formed by the server and a plurality of users, andcomprises the following steps of: obtaining user singing behavior data and sung artiest identification information by the server; establishing vector spaces corresponding to artist identifiers according to the user singing behavior data, clustering the artist identifiers according to the vector spaces so as to obtain a clustering result; filtering the clustering result to obtain a filter result;and carrying out singing accompaniment recommendation according to the filter result. Through the singing accompaniment recommendation method provided by the invention, the accuracy of music classification during music recommendation can be improved.

Description

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

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
Owner 北京小唱科技有限公司
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2023 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap