Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Online music recommendation method and device

A recommendation method and recommendation device technology, applied in the Internet field, can solve problems such as insufficient scoring, redundant operations by users, and high operating thresholds, and achieve the effects of standardized calculation results, stable analysis results, and low operating thresholds

Active Publication Date: 2016-09-14
GUANGZHOU KUGOU COMP TECH CO LTD
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, the first method has a high user operation threshold and requires users to do redundant operations; the scoring is not detailed enough, and users only have 5 levels to score; the timeliness and sensitivity are not strong, and will not decay with time, and the songs they liked in the past do not represent the present. Will like it, the display score cannot distinguish the songs that the current user likes
In the second method, the analysis of listening to songs is not detailed enough, and users’ preferences cannot be distinguished based on specific operations, such as listening time and scenes. The accuracy is not high; individual songs will affect the judgment of users’ preferences for all songs.
For example, if a user listens to a song many times, the score of the song will be too high, and the user's other songs will be judged inaccurately, and the user's preference cannot be obtained; convenient classification statistics

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
  • Online music recommendation method and device
  • Online music recommendation method and device
  • Online music recommendation method and device

Examples

Experimental program
Comparison scheme
Effect test

no. 1 example

[0021] figure 1 It is a schematic flowchart of the online music recommendation method according to the first embodiment of the present invention. Please refer to figure 1 , the online music recommendation method in the embodiment of the present invention includes:

[0022] Step S11: Record various user operation records of the user in each unit time period, and two adjacent unit time periods do not overlap each other.

[0023] The length of the unit time period can be set according to actual needs. For example, it can be set to one day, that is to say, the user's daily operation flow can be recorded. Of course, the unit time period can also be set from 6:00 to 24:00 every day , the present invention is not limited thereto. The user's operation flow refers to the single operation of the user on music products such as qq music (such as listening, liking, favorite, setting as background music, etc.) can be described by a string of text, such a sequence of text strings The dat...

no. 2 example

[0035] figure 2 It is a schematic flowchart of an online music recommendation method according to the second embodiment of the present invention. Please refer to figure 2 , the online music recommendation method in the embodiment of the present invention includes:

[0036] Step S21: Record various user operation records of the user in each unit time period, and two adjacent unit time periods do not overlap each other. This step is the same as the corresponding step in the first embodiment, and will not be repeated here.

[0037] Step S22: Set the first score and attenuation coefficient corresponding to each operation of each song by the user in each unit time period according to the types or attributes of the various operations in the recorded various user operation logs. This step is the same as the corresponding step in the first embodiment, and will not be repeated here.

[0038] Step S23: Collect the first scores of all operations performed by the user on each song w...

no. 3 example

[0049] image 3 It is a schematic flowchart of an online music recommendation method according to the third embodiment of the present invention. Please refer to image 3 , the online music recommendation method in the embodiment of the present invention includes:

[0050] Step S31: Record various user operation records of the user in each unit time period, and two adjacent unit time periods do not overlap each other. This step is the same as the corresponding step in the first embodiment, and will not be repeated here.

[0051] Step S32: Set the first score and attenuation coefficient corresponding to each operation of each song by the user in each unit time period according to the types or attributes of the various operations in the recorded various user operation streams. This step is the same as the corresponding step in the first embodiment, and will not be repeated here.

[0052] Step S33: Collect the first scores of all operations performed by the user on each song w...

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 relates to an online music recommendation method and device. The online music recommendation method comprises recording a plurality of user operation assemblies in every unit time period of a user and enabling every two unit time periods to be not overlapped; setting a first score and an attenuation coefficient which are corresponding to every user operation performed on every song in every unit time period according to types or attributes of a plurality of operations in the plurality of recorded user operation assemblies; collecting first scores of user operations performed on every song in continuous n unit time periods, attenuating the first scores by time according to the corresponding attenuation coefficient and obtaining user standard operation scores of every song in the continuous n unit time periods according to the attenuated first scores; recommending songs to clients according to the user standard operation scores in the continuous n unit time periods. The online music recommendation method and device enables a user not to perform unnecessary operations and is good in timeliness and sensitiveness.

Description

technical field [0001] The invention relates to the technical field of the Internet, in particular to an online music recommendation method and device. Background technique [0002] Music personalized recommendation is one of the most popular applications in the field of personalized recommendation. The music personalized recommendation system is usually based on the user's music operation flow to score the songs operated by the user to predict the user's favorite songs and recommend them. [0003] There are currently two technical solutions widely used in the method of scoring songs operated by users: the first one is to display the scoring mode: the user marks the song with a score of 1-5 (5 points indicate the favorite), so that the user can find out what the user likes. Songs; the second is simple implicit scoring: through the user's operations such as listening to songs, simply record the corresponding scores for the corresponding operations, and get the user's final s...

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 Patents(China)
IPC IPC(8): G06F17/30
CPCG06F16/635
Inventor 刘黎春王翔朱静涛范成涛周斌李深远陈剑锋覃春霞黄斯亮孙娟金虎光李丹陈湜艾志兵
Owner GUANGZHOU KUGOU COMP TECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com