公开(公告)号：US20190188323A1

公开(公告)日：2019-06-20

申请号：US15844032

申请日：2017-12-15

Applicant: Microsoft Technology Licensing, LLC

Inventor： Souvik Ghosh ,  Timothy Paul Jurka ,  Sergei Tolmanov ,  Yijie Wang

IPC: G06F17/30 ,  G06F15/18 ,  G06Q50/00 ,  H04L29/08

CPC classification number: G06F16/9535 ,  G06N20/00 ,  G06Q50/01 ,  H04L67/306

Abstract: In an example, a plurality of potential feed objects are obtained. An identification of a user performing a navigation command in a user interface is also obtained, the navigation command causing a feed to be displayed or updated. The identification of the user and the plurality of potential feed objects are fed to a machine learned feed object ranking model, the feed object ranking model having been trained via a machine learning algorithm to calculate a score for each of the potential feed objects, the score being based on a combination of a likelihood that the user will perform an interaction, via the user interface, on the potential feed object, likelihoods that the user's interaction will cause one or more downstream events by other users, and a value of the one or more downstream events to a social networking service. The plurality of feed objects are ranked by their scores.

公开(公告)号：US11514115B2

公开(公告)日：2022-11-29

申请号：US15844032

申请日：2017-12-15

Applicant: Microsoft Technology Licensing, LLC

Inventor： Souvik Ghosh ,  Timothy Paul Jurka ,  Sergei Tolmanov ,  Yijie Wang

IPC: G06F16/9535 ,  H04L67/306 ,  G06Q50/00 ,  G06N20/00 ,  H04L67/50

Abstract: In an example, a plurality of potential feed objects are obtained. An identification of a user performing a navigation command in a user interface is also obtained, the navigation command causing a feed to be displayed or updated. The identification of the user and the plurality of potential feed objects are fed to a machine learned feed object ranking model, the feed object ranking model having been trained via a machine learning algorithm to calculate a score for each of the potential feed objects, the score being based on a combination of a likelihood that the user will perform an interaction, via the user interface, on the potential feed object, likelihoods that the user's interaction will cause one or more downstream events by other users, and a value of the one or more downstream events to a social networking service. The plurality of feed objects are ranked by their scores.

公开(公告)号：US11151661B2

公开(公告)日：2021-10-19

申请号：US15966583

申请日：2018-04-30

Applicant: Microsoft Technology Licensing, LLC

Inventor： Yijie Wang ,  Souvik Ghosh ,  Timothy Paul Jurka ,  Shaunak Chatterjee ,  Wei Xue ,  Bonnie Barrilleaux

IPC: G06Q50/00 ,  G06F17/18 ,  G06N20/00 ,  G06F16/435 ,  G06F3/0482

Abstract: A plurality of potential feed objects and corresponding identifications of actors who performed a user interface action that caused a corresponding potential feed object to be generated are obtained. The plurality of potential feed objects and corresponding actor identifications are then fed into a machine learned feed object ranking model, with the machine learned feed object ranking model having been trained via a machine learning algorithm to calculate a score for each of the potential feed objects. The score is based on a combination of a likelihood that the user will perform an interaction, via the user interface, on the potential feed object, likelihood that the user's interaction will cause one or more downstream events by other users, and likelihood that a response from a viewer will cause the actor corresponding to the potential feed object to perform an additional user interface action to generate another potential feed object.

公开(公告)号：US20190333162A1

公开(公告)日：2019-10-31

申请号：US15966583

申请日：2018-04-30

Applicant: Microsoft Technology Licensing LLC

Inventor： Yijie Wang ,  Souvik Ghosh ,  Timothy Paul Jurka ,  Shaunak Chatterjee ,  Wei Xue ,  Bonnie Barrilleaux

IPC: G06Q50/00 ,  G06F17/30 ,  G06F3/0482 ,  G06F15/18 ,  G06F17/18

Abstract: A plurality of potential feed objects and corresponding identifications of actors who performed a user interface action that caused a corresponding potential feed object to be generated are obtained. The plurality of potential feed objects and corresponding actor identifications are then fed into a machine learned feed object ranking model, with the machine learned feed object ranking model having been trained via a machine learning algorithm to calculate a score for each of the potential feed objects. The score is based on a combination of a likelihood that the user will perform an interaction, via the user interface, on the potential feed object, likelihood that the user's interaction will cause one or more downstream events by other users, and likelihood that a response from a viewer will cause the actor corresponding to the potential feed object to perform an additional user interface action to generate another potential feed object.

公开(公告)号：US10949480B2

公开(公告)日：2021-03-16

申请号：US15900219

申请日：2018-02-20

Applicant: Microsoft Technology Licensing, LLC

Inventor： Boyi Chen ,  Yijie Wang ,  Timothy Paul Jurka ,  Ying Xuan

IPC: G06F16/9535 ,  G06Q50/00 ,  G06N20/00 ,  G06F16/2457

Abstract: In an example embodiment, a GLMix model is utilized that models viewers and actors of feed items. This allows for random effects of individual viewers and actors to be taken into account without introducing biases. Additionally, in an example embodiment, predictions/recommendations are made more accurate by using three models, which are then combined, instead of a single GLMix model. Each of these models has different granularities and dimensions. A global model may model the similarity between user attributes (e.g., from the member profile or activity history) and item attributes. A per-viewer model may model user attributes and activity history of actors on feed items. A per-actor model may model user attributes and activity history of the viewers of feed items. The per-actor model may therefore, rely on information regarding how and what type of viewers interacted with items acted on by the particular actor.

公开(公告)号：US20190258741A1

公开(公告)日：2019-08-22

申请号：US15900219

申请日：2018-02-20

Applicant: Microsoft Technology Licensing, LLC

Inventor： Boyi Chen ,  Yijie Wang ,  Timothy Paul Jurka ,  Ying Xuan

IPC: G06F17/30 ,  G06N99/00 ,  G06Q50/00

Abstract: In an example embodiment, a GLMix model is utilized that models viewers and actors of feed items. This allows for random effects of individual viewers and actors to be taken into account without introducing biases. Additionally, in an example embodiment, predictions/recommendations are made more accurate by using three models, which are then combined, instead of a single GLMix model. Each of these models has different granularities and dimensions. A global model may model the similarity between user attributes (e.g., from the member profile or activity history) and item attributes. A per-viewer model may model user attributes and activity history of actors on feed items. A per-actor model may model user attributes and activity history of the viewers of feed items. The per-actor model may therefore, rely on information regarding how and what type of viewers interacted with items acted on by the particular actor.