Methods and systems for selecting content for a personalized video

Patent metadata

Field	Value
Publication number	US-10237602-B2
Application number	US-201615365827-A
Country	US
Kind code	B2
Filing date	Nov 30, 2016
Priority date	Nov 30, 2016
Publication date	Mar 19, 2019
Grant date	Mar 19, 2019

Abstract

A method of generating a personalized video for a user of a social networking service. For a plurality of images associated with the user, respective first metrics are determined for respective images of the plurality of images based on one or more predefined image-content criteria, a first set of images is selected from the plurality of images based at least in part on the respective first metrics, and the personalized video is populated with the first set of images. The method further includes providing the personalized video to the user for viewing.

First claim

What is claimed is:

1. A method, comprising:
at a server system having one or more processors and memory storing instructions for execution by the one or more processors:
generating a personalized video for a user of a social networking service, comprising, for a plurality of images associated with the user:
determining, by the server system, respective first metrics for respective images of the plurality of images based on image recognition processing of the plurality of images and one or more predefined image-content criteria;
selecting, by the server system, a first set of images from the plurality of images based at least in part on the respective first metrics, wherein selecting the first set of images from the plurality of images includes:
selecting a first image showing a location according to the first metric of the first image; and
in response to selecting the first image:
 identifying a second image showing the location; and
 modifying the first metric for the second image relative to the first metrics for other unselected images not showing the location, thereby reducing a probability the second image is selected; and

populating the personalized video with the first set of images; and

providing the personalized video to the user for viewing.

2. The method of claim 1 , further comprising, at the server system, determining respective second metrics for the respective images of the plurality of images based on feedback for the respective images provided by users of the social networking service;
wherein selecting the first set of images is further based, at least in part, on the second metrics.

3. The method of claim 2 , wherein the feedback for determining the second metrics comprises:
likes, comments, and shares of the respective images by users of the social networking service; and
a degree of interaction between the user and other users of the social networking service providing feedback on the respective image.

4. The method of claim 2 , wherein selecting the first set of images comprises:
ranking the plurality of images using the respective first metrics and the respective second metrics; and
choosing images for the first set of images from the plurality of images in accordance with the ranking.

5. The method of claim 1 , wherein:
selecting the first set of images comprises selecting a group image that comprises the user and a plurality of other users of the social networking service; and
populating the personalized video comprises including the group image in a slide at a designated position in the personalized video.

6. The method of claim 5 , wherein:
the slide at the designated position is a final image slide in the personalized video; and
the plurality of other users is at least four other users.

7. The method of claim 1 , further comprising specifying a number of image slots available in the personalized video;
wherein a number of images in the first set of images equals the number of image slots available in the personalized video.

8. The method of claim 1 , wherein selecting the first set of images comprises:
selecting a profile picture of the user; and
selecting one or more profile pictures of contacts of the user.

9. The method of claim 8 , wherein populating the personalized video comprises:
including the profile picture of the user as an initial image slide in the personalized video; and
including the one or more profile pictures of the contacts of the user in image slides following the initial image slide in the personalized video.

10. The method of claim 1 , wherein the one or more predefined image-content criteria comprise at least one of whether an image includes people and a portion of an image occupied by one or more people.

11. The method of claim 1 , wherein the one or more predefined image-content criteria comprise a degree to which a subject of an image is obstructed.

12. The method of claim 1 , wherein the one or more predefined image-content criteria comprise a criterion favoring photographs over synthetic images.

13. The method of claim 1 , wherein the one or more predefined image-content criteria comprise whether an image is a portrait.

14. The method of claim 1 , wherein selecting the first set of further images comprises:
selecting a third image showing one or more contacts of the user according to the first metric of third image; and
in response to selecting the third image:
identifying a fourth image showing one or more contacts of the user; and
modifying the first metric for the fourth image relative to the first metrics of other unselected images not showing any of the one or more contacts of the user, thereby reducing a probability the fourth image is selected.

15. The method of claim 1 , wherein selecting the first set of images further comprises:
selecting a third image having a timestamp falling within a first period of time according to the first metric of the third image; and
in response to selecting the third image:
identifying a fourth image having a timestamp falling within the first period of time; and
modifying the first metric for the fourth image relative to the first metrics of other unselected images having timestamps falling within the first period of time, thereby reducing a probability the fourth image is selected.

16. The method of claim 1 , wherein selecting the first set of images comprises selecting images from the first set of images showing respective numbers of people below a threshold number of people.

17. The method of claim 1 , wherein:
selecting the first set of images comprises selecting at least one image having one or more comments; and
populating the personalized video with the first set of images comprises overlaying at least one of the one or more comments on the selected image.

18. A server system, comprising:
one or more processors; and
memory storing one or more programs for execution by the one or more processors, the one or more programs including instructions for:
generating a personalized video for a user of a social networking service, comprising, for a plurality of images associated with the user:
determining, by the server system, respective first metrics for respective images of the plurality of images based on image recognition processing of the plurality of images and one or more predefined image-content criteria;
selecting, by the server system, a first set of images from the plurality of images based at least in part on the respective first metrics, wherein selecting the first set of images from the plurality of images includes:
selecting a first image showing a location according to the first metric of the first image; and
in response to selecting the first image:
 identifying a second image showing the location; and
 modifying the first metric for the second image relative to the first metrics for other unselected images not showing the location, thereby reducing a probability the second image is selected; and

populating the personalized video with the first set of images; and

providing the personalized video to the user for viewing.

19. A non-transitory computer-readable storage medium, storing one or more programs configured for execution by one or more processors of a server system, the one or more programs including instructions for:
generating a personalized video for a user of a social networking service, comprising, for a plurality of images associated with the user:
determining, by the server system, respective first metrics for respective images of t

Assignees

• Facebook Inc

Inventors

• Lin Boyan
• Lai Peter Tuchen
• Lu Jia
• Wu Shu
• Cui Can

Classifications

• H04N21/8153

  comprising still images, e.g. texture, background image · CPC title

• H04N21/4312

  involving specific graphical features, e.g. screen layout, special fonts or colors, blinking icons, highlights or animations · CPC title

• H04N21/44213

  Monitoring of end-user related data (arrangements for monitoring the users' behaviour or opinions in broadcast systems H04H60/33) · CPC title

• G11B27/031

  Electronic editing of digitised analogue information signals, e.g. audio or video signals · CPC title

• H04N21/2668 Primary

  Creating a channel for a dedicated end-user group, e.g. insertion of targeted commercials based on end-user profiles {(information retrieval from the Internet by querying with filtering and personalisation G06F16/9535; arrangements for replacing or switching information during the broadcast H04H20/10; push services over packet-switching network H04L12/1859; adaptation of message content in packet-switching networks H04L51/063)} · CPC title