Research on the graphical convolution neural network based benefits recommendation system strategy
The recommendation system is one of the important methods to realize the intelligent recommendation of massive Internet benefit products.In order to improve the accuracy of personalized benefits recommendation, a deep learning recommendation system based on graph computing method was proposed.Consid...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Beijing Xintong Media Co., Ltd
2023-08-01
|
| Series: | Dianxin kexue |
| Subjects: | |
| Online Access: | http://www.telecomsci.com/zh/article/doi/10.11959/j.issn.1000-0801.2023155/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841530848342441984 |
|---|---|
| author | Tao TAO Zhen LI Jibin WANG Haiyong XU Yong JIANG Zhuo CEHN Runbo ZHANG Qingyuan HU |
| author_facet | Tao TAO Zhen LI Jibin WANG Haiyong XU Yong JIANG Zhuo CEHN Runbo ZHANG Qingyuan HU |
| author_sort | Tao TAO |
| collection | DOAJ |
| description | The recommendation system is one of the important methods to realize the intelligent recommendation of massive Internet benefit products.In order to improve the accuracy of personalized benefits recommendation, a deep learning recommendation system based on graph computing method was proposed.Considering the heterogeneity of multi-source data, a graph representation technology based on deep learning was carried out to construct the multiple relationship graph between users and benefit products.The multiple relationship graph extracted the information of graph structure, and model the heterogeneous graphs for the multi-dimensional features of users and the multiple interaction modes between rights and interests products, which effectively aggregated various interactive information and the multiple feature.A heterogeneous graph convolutional neural network was built to learn the high-dimensional feature vectors for various nodes, and excavate users＇ latent preferences to provide a recommendation link with strong interpretability, which greatly improved the recommendation success rate and generating economic value. |
| format | Article |
| id | doaj-art-a3f0510cce684696b94d76cfab256204 |
| institution | Kabale University |
| issn | 1000-0801 |
| language | zho |
| publishDate | 2023-08-01 |
| publisher | Beijing Xintong Media Co., Ltd |
| record_format | Article |
| series | Dianxin kexue |
| spelling | doaj-art-a3f0510cce684696b94d76cfab2562042025-01-15T02:58:18ZzhoBeijing Xintong Media Co., LtdDianxin kexue1000-08012023-08-01399110159562766Research on the graphical convolution neural network based benefits recommendation system strategyTao TAOZhen LIJibin WANGHaiyong XUYong JIANGZhuo CEHNRunbo ZHANGQingyuan HUThe recommendation system is one of the important methods to realize the intelligent recommendation of massive Internet benefit products.In order to improve the accuracy of personalized benefits recommendation, a deep learning recommendation system based on graph computing method was proposed.Considering the heterogeneity of multi-source data, a graph representation technology based on deep learning was carried out to construct the multiple relationship graph between users and benefit products.The multiple relationship graph extracted the information of graph structure, and model the heterogeneous graphs for the multi-dimensional features of users and the multiple interaction modes between rights and interests products, which effectively aggregated various interactive information and the multiple feature.A heterogeneous graph convolutional neural network was built to learn the high-dimensional feature vectors for various nodes, and excavate users＇ latent preferences to provide a recommendation link with strong interpretability, which greatly improved the recommendation success rate and generating economic value.http://www.telecomsci.com/zh/article/doi/10.11959/j.issn.1000-0801.2023155/heterogeneous graphgraph convolutional neural networkbenefit recommendationmulti-source data |
| spellingShingle | Tao TAO Zhen LI Jibin WANG Haiyong XU Yong JIANG Zhuo CEHN Runbo ZHANG Qingyuan HU Research on the graphical convolution neural network based benefits recommendation system strategy Dianxin kexue heterogeneous graph graph convolutional neural network benefit recommendation multi-source data |
| title | Research on the graphical convolution neural network based benefits recommendation system strategy |
| title_full | Research on the graphical convolution neural network based benefits recommendation system strategy |
| title_fullStr | Research on the graphical convolution neural network based benefits recommendation system strategy |
| title_full_unstemmed | Research on the graphical convolution neural network based benefits recommendation system strategy |
| title_short | Research on the graphical convolution neural network based benefits recommendation system strategy |
| title_sort | research on the graphical convolution neural network based benefits recommendation system strategy |
| topic | heterogeneous graph graph convolutional neural network benefit recommendation multi-source data |
| url | http://www.telecomsci.com/zh/article/doi/10.11959/j.issn.1000-0801.2023155/ |
| work_keys_str_mv | AT taotao researchonthegraphicalconvolutionneuralnetworkbasedbenefitsrecommendationsystemstrategy AT zhenli researchonthegraphicalconvolutionneuralnetworkbasedbenefitsrecommendationsystemstrategy AT jibinwang researchonthegraphicalconvolutionneuralnetworkbasedbenefitsrecommendationsystemstrategy AT haiyongxu researchonthegraphicalconvolutionneuralnetworkbasedbenefitsrecommendationsystemstrategy AT yongjiang researchonthegraphicalconvolutionneuralnetworkbasedbenefitsrecommendationsystemstrategy AT zhuocehn researchonthegraphicalconvolutionneuralnetworkbasedbenefitsrecommendationsystemstrategy AT runbozhang researchonthegraphicalconvolutionneuralnetworkbasedbenefitsrecommendationsystemstrategy AT qingyuanhu researchonthegraphicalconvolutionneuralnetworkbasedbenefitsrecommendationsystemstrategy |