User interest group dividing method and system based on multilayer potential features

A technology of user interest and feature analysis, applied in the field of user interest grouping based on multi-layer latent features, can solve problems such as control within a certain range, decreased accuracy of results, and large differences in emotional interpretation of music, etc., to achieve rich feature dimensions , the effect of reducing the effect of sparseness

Active Publication Date: 2017-05-10
天翼爱音乐文化科技有限公司
View PDF4 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, there is a very important prerequisite for using this process: the characteristics of the item should be clear; such as: movies, electrical appliances, daily commodities, food; but if it involves emotional items, such as: music, such characteristics will be subjective by humans Judgment, everyone’s emotional interpretation of music is quite different, which is likely to cause inaccurate classification; and the amount of item data needs to be controlled within a certain range; if the amount of item data is too large, due to labor costs and importance, the accuracy of the results will decrease serious

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
  • User interest group dividing method and system based on multilayer potential features
  • User interest group dividing method and system based on multilayer potential features
  • User interest group dividing method and system based on multilayer potential features

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0026] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present invention, and do not limit the protection scope of the present invention.

[0027] figure 1 A flow chart showing a user interest grouping method based on multi-layer latent features, including steps:

[0028] S100, read the user play log from the log system;

[0029] Specifically, the user's playing log is read from the music playing log system in the music server. The play log records various information about each user's clicking and playing of songs on the client, including the name of the song to be played, the duration of playing a single song, information on searching for songs, information on searching for singers, song columns, and use...

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 user interest group dividing method and system based on multilayer potential features. The method comprises the steps of reading a user playing log from a log system; conducting column feature analysis, track feature analysis, and lyric feature analysis according to the user playing log; determining a feature model according to a column feature analysis result, a track feature analysis result, and a lyric feature analysis result; conducting a clustering analysis on the feature model to obtain a cluster central value; conducting user group dividing according to the cluster central value. According to the user interest group dividing method and system based on the multilayer potential features, group dividing of users can be accurately conducted, so that music which corresponds to interests of the users of various kinds is accurately recommended.

Description

technical field [0001] The invention relates to the field of music aggregation processing, in particular to a user interest grouping method based on multi-layer latent features. Background technique [0002] With the rapid development of the Internet industry in recent years, the rapid expansion of massive music resources has made it extremely difficult for users to choose music. Therefore, how to quickly and effectively recommend suitable music to users has become a key issue for music software to quickly occupy the market. [0003] With the development of big data technology, before recommending music to users, different users will be grouped, so as to recommend corresponding music information to different types of users. The general user interest grouping is to extract the characteristics of the items, and then map the characteristics of the items to the users according to the user's browsing, collection and purchase of items, and quantify the characteristics through the...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06F17/30
CPCG06F16/635G06F16/685
Inventor 潘志锋朱映波陈国言骆延楠陈君炫曾荣
Owner 天翼爱音乐文化科技有限公司
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.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap