Suggesting profile images for a social network

• US 9,424,491 B1
• Filed: 10/13/2014
• Issued: 08/23/2016
• Est. Priority Date: 10/05/2011
• Status: Expired due to Fees

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Kirkham, Stephen, Bilinski, Brandon
• Primary Examiner(s): Bali, Vikkram
• Application Number:
  US14/512,978
• Time in Patent Office: 680 Days
• Field of Search: None
• US Class Current: 1/1
• CPC Class Codes: G06F 16/5866 using information manually generated, e.g. tags, keywords, comments, manually generated location and time information
• CPC Class Codes: G06F 18/22 Matching criteria, e.g. proximity measures
• CPC Class Codes: G06F 18/24 Classification techniques

Abstract

A system and method for generating an ordered set of suggested profile images. The profile image application includes a scorer, a recognition engine, a trend analyzer, a suggestion module and a user interface engine. The scorer scores user images based on metadata, such as the number of people tagged in the image and the recency of the image. The recognition engine identifies people and objects in the image. The trend analyzer identifies trends. The suggestion module generates the ordered set of suggested profile images based at least in part on the score. The user interface engine generates a user interface that includes the ordered set of suggested profile images.

Claims

1. A method comprising:

receiving a first image and a second image, the first image and the second image associated with a first user;

identifying, with one or more processors, metadata associated with the first image and metadata associated with the second image;

scoring, with the one or more processors, the first image based at least in part on the metadata associated with the first image and the second image based at least in part on the metadata associated with the second image by assigning different scores to the first image and the second image when the metadata associated with the first image indicates that the first user was identified from the first image by the first user and the metadata associated with the second image indicates that the first user and a second user were identified from the second image;

generating, with the one or more processors, an ordered set of suggested profile images including the first image and the second image and an order of the ordered set of suggested profile images based at least in part on the scoring of the first image and the second image; and

providing the ordered set of suggested profile images to the first user.

2. The method of claim 1, wherein the metadata includes at least one of a tag of the first user, a tag of other people and a timestamp.

3. The method of claim 2, wherein an image where the first user and other people are tagged is later in the order of the ordered set of suggested profile images than an image where the first user is tagged.

4. The method of claim 2, wherein a less recent image is scored such that the less recent image is later in the order of the ordered set of suggested profile images based at least in part on the timestamp.

5. The method of claim 1, wherein the first image and the second image include at least one of a user-uploaded image and an image from a third-party application.

6. The method of claim 1, further comprising:

receiving a selected profile image from the ordered set of suggested profile images;

updating a user profile associated with the first user to include the selected profile image, wherein receiving the selected profile image constitutes a user preference from the first user; and

adjusting the scoring to reflect the user preference.

7. The method of claim 2, further comprising performing image recognition on the first image and the second image to determine whether the first user was properly tagged.

8. The method of claim 2, further comprising performing image recognition to determine whether one or more of the first image and the second image include a person that is not tagged.

9. The method of claim 1, further comprising:

performing image recognition on one or more of the first image and the second image in a social network to identify at least one of a person and an object;

identifying a trend based at least in part on the at least one of the person and the object; and

wherein the scoring is based at least in part on the trend.

10. The method of claim 1, wherein a user profile associated with the first user lacks a profile image.

11. A system comprising:

a scorer stored on a memory and executable by one or more processors, the scorer receiving a first image and a second image, the first image and second image associated with a first user, identifying metadata associated with the first image and metadata associated with the second image, and scoring the first image based at least in part on the metadata associated with the first image and the second image based at least in part on the metadata associated with the second image by assigning different scores to the first image and the second image when the metadata associated with the first image indicates that the first user was identified from the first image by the first user and the metadata associated with the second image indicates that the first user and a second user were identified from the second image;

a suggestion module stored on the memory and executable by the one or more processors, the suggestion module generating an ordered set of suggested profile images including the first image and the second image and an order of the ordered set of suggested profile images based at least in part on the scoring of the first image and the second image; and

a user interface engine stored on the memory and executable by the one or more processors, the user interface engine providing the ordered set of suggested profile images for display to the first user.

12. The system of claim 11, wherein the metadata includes at least one of a tag of the first user, a tag of other people and a timestamp.

13. The system of claim 12, wherein the scorer generates a score for an image where the first user and other people are tagged such that the image is ordered later than an image where the first user is tagged in the ordered set of suggested profile images.

14. The system of claim 12, wherein the scorer generates a score for a less recent image such that the less recent image is later in the order of the set of suggested profile images based at least in part on the timestamp.

15. The system of claim 11, wherein the first image and the second image are at least one of a user-uploaded image and an image from a third-party application.

16. The system of claim 11, further comprising:

a social network application stored on the memory and executable by the one or more processors, the social network application receiving a selected profile image from the ordered set of suggested profile images and updating a user profile associated with the first user to include the selected profile image,

wherein receiving the selected profile constitutes a user preference, and

wherein the scorer adjusts the scoring to reflect the user preference.

17. The system of claim 12, further comprising a recognition engine coupled to the scorer, the recognition engine for performing image recognition on the first image and the second image to determine whether the first user was properly tagged.

18. The system of claim 12, further comprising a recognition engine coupled to the scorer, the recognition engine for performing image recognition to determine whether one or more of the first image and the second image include a person that is not tagged.

19. The system of claim 11, further comprising:

a recognition engine coupled to the scorer, the recognition engine for performing image recognition on the first image and the second image in a social network to identify at least one of a person and an object;

a trend analyzer coupled to the recognition engine and the scorer, the trend analyzer for identifying a trend based at least in part on the at least one of the person and the object; and

wherein the scoring is based at least in part on the trend.

20. A computer program product comprising a non-transitory computer useable medium including a computer readable program, wherein the computer readable program when executed on a computer causes the computer to:

receive a first image and a second image, the first image and the second image associated with a first user;

identify metadata associated with the first image and metadata associated with the second image;

score the first image based at least in part on the metadata associated with the first image and the second image based at least in part on the metadata associated with the second image by assigning different scores to the first image and the second image when the metadata associated with the first image indicates that the first user was identified from the first image by the first user and the metadata associated with the second image indicates that the first user and a second user were identified from the second image;

generate an ordered set of suggested profile images including the first image and the second image and an order of the ordered set of suggested profile images based at least in part on the scoring of the first image and the second image; and

generate a user interface for displaying the ordered set of suggested profile images to the first user.