Music recommendation method and system based on knowledge graph

A technology of knowledge graph and recommendation method, applied in the field of music recommendation method and system based on knowledge graph, to achieve the effect of reducing loss, improving information utilization problem, and improving the effect of entity recommendation

Inactive Publication Date: 2021-06-25
QILU UNIV OF TECH
View PDF5 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

As various auxiliary data become more and more abundant in music recommendation, resulting in the heterogeneity and complexity of auxiliary data, it is still challenging to effectively utilize the contextual information in auxiliary information in music recommendation.

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 recommendation method and system based on knowledge graph
  • Music recommendation method and system based on knowledge graph
  • Music recommendation method and system based on knowledge graph

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0094] as attached figure 1 As shown, the music recommendation method based on the knowledge map of the present invention, the method is specifically as follows:

[0095] S1. Construct a music recommendation knowledge map: use the original music data set to construct a music recommendation knowledge map, obtain the user's potential interest and use it to stimulate the dissemination of user preferences on the music knowledge entity set;

[0096]The data set selected in this embodiment is the Last.FM data set, and the Last.FM data set contains music records from 2000 users. The hyperparameter settings of each data set in the ST_RippleNet model are shown in the following table:

[0097]

[0098] S2. Construct the ST_RippleNet model: By integrating heterogeneous data from various sources in the music recommendation knowledge map, introducing low-dimensional vectors and using triple-layer attention mechanisms to build the ST_RippleNet model, and then making full use of the know...

Embodiment 2

[0160] The music recommendation system based on knowledge graph of the present invention, the system includes,

[0161] The map construction unit is used to build a music recommendation knowledge map, using the original music data set to construct a music recommendation knowledge map, to obtain the user's potential interests and to stimulate the dissemination of user preferences on the music knowledge entity set;

[0162] The model construction unit is used to build the ST_RippleNet model. By integrating multiple sources of heterogeneous data in the music recommendation knowledge map, introducing low-dimensional vectors and using triple-layer attention mechanisms to build the ST_RippleNet model, and then making full use of music recommendation knowledge Atlas knowledge information;

[0163] A model optimization unit for optimizing the ST_RippleNet model using the RMSProp optimizer;

[0164] The function improvement unit is used to improve the loss function and reduce the loss...

Embodiment 3

[0180] The embodiment of the present invention also provides a computer-readable storage medium, in which a plurality of instructions are stored, and the instructions are loaded by a processor, so that the processor executes the music recommendation method based on knowledge graph in any embodiment of the present invention. Specifically, a system or device equipped with a storage medium may be provided, on which a software program code for realizing the functions of any of the above embodiments is stored, and the computer (or CPU or MPU of the system or device) ) to read and execute the program code stored in the storage medium.

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 recommendation method and system based on a knowledge graph, belongs to the field of knowledge graphs and content recommendation, and aims to solve the technical problem of how to improve the accuracy of music recommendation by using context information in auxiliary information. According to the technical scheme, the method specifically comprises the following steps: constructing a music recommendation knowledge graph: constructing the music recommendation knowledge graph by utilizing an original music data set, obtaining potential interests of a user, and stimulating the propagation of user preferences on a music knowledge entity set according to the potential interests; constructing an ST_RippleNet model: constructing the ST_RippleNet model by integrating various source heterogeneous data in the music recommendation knowledge graph, introducing a low-dimensional vector and adopting a triple multilayer attention mechanism, so as to make full use of knowledge information of the music recommendation knowledge graph; carrying out model optimization, wherein an RMSProp optimizer is used for carrying out optimization on the ST_RippleNet model; and constructing a loss function of the ST_RippleNet model, wherein the loss function is improved, and the loss of the ST_RippleNet model in the recommendation process is reduced.

Description

technical field [0001] The present invention relates to the technical field of knowledge graph and content recommendation, in particular to a music recommendation method and system based on knowledge graph. Background technique [0002] With the development of science and technology, various music software for people's leisure and entertainment has gradually emerged, such as QQ Music, Kuwo Music, Kugou Music and NetEase Cloud Music. Music software will provide music suitable for users according to user preferences, such as happy , sad, fashion, dj and other music types. On the other hand, online music platforms will recommend music to users based on the types of music they have listened to in the past or their hobbies, which is not only the needs of users, but also the demand of technological progress. [0003] In the current online music platform, music recommendation plays a vital role in allowing users to pay attention to personalized content, and users also expect perso...

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): G06F16/635G06F16/68G06F16/36
CPCG06F16/635G06F16/68G06F16/367
Inventor 成金勇杨志胜徐颖
Owner QILU UNIV OF TECH
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