公开(公告)号：US11886971B2

公开(公告)日：2024-01-30

申请号：US16541633

申请日：2019-08-15

申请人： Microsoft Technology Licensing, LLC

发明人： Lekshmi Menon ,  Amar Budhiraja ,  Gaurush Hiranandani ,  Prateek Jain ,  Darshatkumar Anandji Shah ,  Ayush Choure ,  Navya Yarrabelly ,  Anurag Mishra ,  Mohammad Luqman ,  Shivangi Dhakad ,  Juhi Dua

IPC分类号： G06N3/04 ,  G06N3/08

CPC分类号： G06N3/04 ,  G06N3/08

摘要： Systems and methods for entity recommendation can make use of rich data by allowing the items to be recommended and the recipients of the recommendation (e.g., users) to be modeled as “complex entities” composed of one or more static sub-entities and/or a dynamic component, and by utilizing information about multiple relationships between the sub-entities as reflected in bipartite graphs. Generating recommendations from such information may involve creating vector representations of the sub-entities based on the bipartite graphs (e.g., using graph-based convolutional networks), and combining these vector representations into representations of the items and users (or other recipients) to be fed into a classifier model.

公开(公告)号：US11184301B2

公开(公告)日：2021-11-23

申请号：US16541818

申请日：2019-08-15

申请人： Microsoft Technology Licensing, LLC

发明人： Lekshmi Menon ,  Amar Budhiraja ,  Gaurush Hiranandani ,  Prateek Jain ,  Darshatkumar Anandji Shah ,  Ayush Choure ,  Navya Yarrabelly ,  Anurag Mishra ,  Mohammad Luqman ,  Shivangi Dhakad ,  Juhi Dua

IPC分类号： G06F15/16 ,  H04L12/58 ,  G06F16/901 ,  G06N3/08

摘要： Systems and methods for entity recommendation can make use of rich data by allowing the items to be recommended and the recipients of the recommendation (e.g., users) to be modeled as “complex entities” composed of one or more static sub-entities and/or a dynamic component, and by utilizing information about multiple relationships between the sub-entities as reflected in bipartite graphs. Generating recommendations from such information may involve creating vector representations of the sub-entities based on the bipartite graphs (e.g., using graph-based convolutional networks), and combining these vector representations into representations of the items and users (or other recipients) to be fed into a classifier model.

公开(公告)号：US20210049442A1

公开(公告)日：2021-02-18

申请号：US16541633

申请日：2019-08-15

申请人： Microsoft Technology Licensing, LLC

发明人： Lekshmi Menon ,  Amar Budhiraja ,  Gaurush Hiranandani ,  Prateek Jain ,  Darshatkumar Anandji Shah ,  Ayush Choure ,  Navya Yarrabelly ,  Anurag Mishra ,  Mohammad Luqman ,  Shivangi Dhakad ,  Juhi Dua

IPC分类号： G06N3/04 ,  G06N3/08

摘要： Systems and methods for entity recommendation can make use of rich data by allowing the items to be recommended and the recipients of the recommendation (e.g., users) to be modeled as “complex entities” composed of one or more static sub-entities and/or a dynamic component, and by utilizing information about multiple relationships between the sub-entities as reflected in bipartite graphs. Generating recommendations from such information may involve creating vector representations of the sub-entities based on the bipartite graphs (e.g., using graph-based convolutional networks), and combining these vector representations into representations of the items and users (or other recipients) to be fed into a classifier model.

公开(公告)号：US20210051121A1

公开(公告)日：2021-02-18

申请号：US16541818

申请日：2019-08-15

申请人： Microsoft Technology Licensing, LLC

发明人： Lekshmi Menon ,  Amar Budhiraja ,  Gaurush Hiranandani ,  Prateek Jain ,  Darshatkumar Anandji Shah ,  Ayush Choure ,  Navya Yarrabelly ,  Anurag Mishra ,  Mohammad Luqman ,  Shivangi Dhakad ,  Juhi Dua

IPC分类号： H04L12/58 ,  G06N3/08 ,  G06F16/901

摘要： Systems and methods for entity recommendation can make use of rich data by allowing the items to be recommended and the recipients of the recommendation (e.g., users) to be modeled as “complex entities” composed of one or more static sub-entities and/or a dynamic component, and by utilizing information about multiple relationships between the sub-entities as reflected in bipartite graphs. Generating recommendations from such information may involve creating vector representations of the sub-entities based on the bipartite graphs (e.g., using graph-based convolutional networks), and combining these vector representations into representations of the items and users (or other recipients) to be fed into a classifier model.