公开(公告)号：US20190007720A1

公开(公告)日：2019-01-03

申请号：US15637617

申请日：2017-06-29

Applicant: Facebook, Inc.

Inventor： Aditya Palnitkar ,  Saurabh Gupta ,  Yash Gupta

IPC: H04N21/25 ,  G06F17/30

CPC classification number: H04N21/252 ,  G06F16/735 ,  G06F16/9535 ,  H04N21/44204 ,  H04N21/44222

Abstract: An online system that recommends content to a user obtains a content item and receives limited interaction with the content item when it is obtained. The online system also maintains embeddings for various users based on interactions by the users with content presented to the users. Viewing users to whom the content item is presented and who performed one or more interactions with the content item are identified. Based on embeddings for the viewing users, the online system generates a content embedding for the content item. When the online system identifies a candidate user, the online system determines a similarity between the content embedding and an embedding of the viewing user and determines whether to recommend the content item to the candidate user based on the comparison.

公开(公告)号：US20180329928A1

公开(公告)日：2018-11-15

申请号：US15595745

申请日：2017-05-15

Applicant: Facebook, Inc.

Inventor： Saurabh Gupta ,  Aditya Palnitkar ,  Yash Gupta

IPC: G06F17/30

CPC classification number: G06F16/5866 ,  G06F16/437 ,  G06F16/70 ,  G06F16/735 ,  G06F16/738 ,  G06F16/907 ,  G06F16/9535 ,  G06F16/9537 ,  G06K9/00711 ,  G06Q30/02 ,  G06Q50/01

Abstract: An online system generates personalized video heat map for a target user, which visually indicates segments of a video likely to be of interest to the target user. The online system divides the video into the segments and identifies actions performed by users other than the target user on each of the segments. The online system determines embedding vectors describing each segment as represented by the identified actions performed on the segment and also determines an embedding vector describing the target user. Based on those embedding vectors, a personalized score for the segment is determined using a trained model. The online system uses the personalized score for each segment of the video to generate the personalized heat map. The personalized heat map can be provided to the target user along with the video.

公开(公告)号：US10715850B2

公开(公告)日：2020-07-14

申请号：US15637617

申请日：2017-06-29

Applicant: Facebook, Inc.

Inventor： Aditya Palnitkar ,  Saurabh Gupta ,  Yash Gupta

IPC: G06F15/16 ,  H04N21/25 ,  G06F16/735 ,  G06F16/9535 ,  H04N21/442

Abstract: An online system that recommends content to a user obtains a content item and receives limited interaction with the content item when it is obtained. The online system also maintains embeddings for various users based on interactions by the users with content presented to the users. Viewing users to whom the content item is presented and who performed one or more interactions with the content item are identified. Based on embeddings for the viewing users, the online system generates a content embedding for the content item. When the online system identifies a candidate user, the online system determines a similarity between the content embedding and an embedding of the viewing user and determines whether to recommend the content item to the candidate user based on the comparison.

公开(公告)号：US10409859B2

公开(公告)日：2019-09-10

申请号：US15595745

申请日：2017-05-15

Applicant: Facebook, Inc.

Inventor： Saurabh Gupta ,  Aditya Palnitkar ,  Yash Gupta

IPC: G06F16/58 ,  G06F16/70 ,  G06K9/00 ,  G06F16/435 ,  G06F16/907 ,  G06F16/9535 ,  G06F16/9537 ,  G06Q50/00 ,  G06Q30/02

Abstract: An online system generates personalized video heat map for a target user, which visually indicates segments of a video likely to be of interest to the target user. The online system divides the video into the segments and identifies actions performed by users other than the target user on each of the segments. The online system determines embedding vectors describing each segment as represented by the identified actions performed on the segment and also determines an embedding vector describing the target user. Based on those embedding vectors, a personalized score for the segment is determined using a trained model. The online system uses the personalized score for each segment of the video to generate the personalized heat map. The personalized heat map can be provided to the target user along with the video.