Computer-Vision Content Detection for Sponsored Stories

• US 20130044959A1
• Filed: 08/18/2011
• Published: 02/21/2013
• Est. Priority Date: 08/18/2011
• Status: Active Grant

• Current Assignee: Meta Platforms, Inc. (f/k/a Facebook, Inc.)
• Original Assignee: Meta Platforms, Inc. (f/k/a Facebook, Inc.)
• Inventors: Mitchell, Justin, Odio, Samuel, Garcia, David Harry
• Granted Patent: US 9,135,631 B2
• Time in Patent Office: Days
• US Class Current: 382/217
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 50/01 Social networking
• CPC Class Codes: H04L 67/52 specially adapted for the location of the user terminal
• CPC Class Codes: H04L 67/535 Tracking the activity of the user network monitoring arrangements H04L43/00; recording of computer activity G06F11/34

Abstract

Methods, apparatuses and systems directed to sponsored story generation from an photo upload in an organic activity stream in a social networking site. A social networking system may apply computer image algorithms to detect image objects in user-uploaded images and videos, and promote them as sponsored stories.

Claims

1. A method comprising, by one or more computing systems:

receiving sponsor specifications designating one or more concept nodes in a social network;

monitoring an organic activity stream for the upload of one or more multimedia objects containing one or more image objects associated with the one or more concept nodes;

upon finding a matching multimedia object, exporting the matching multimedia object to a sponsored story system.

2. The method of claim 1, wherein monitoring the organic activity stream comprises:

upon receiving a multimedia object comprising one or more images from an uploading user, wherein the uploading user is represented by a node on a social network;

applying one or more object image recognition algorithms to the multimedia object;

comparing at least a portion of the multimedia object to a plurality of stored images in a database, each of the plurality of stored images associated with a concept node on the social network;

based on the comparison, identifying one or more image objects in the multimedia object associated with one or more concept nodes; and

attaching meta-data identifying the one or more concept nodes to the multimedia object.

3. The method of claim 2, wherein the multimedia object comprises an image.

4. The method of claim 2, wherein the multimedia object comprises a video, and wherein comparing at least a portion of the multimedia object comprises:

extracting one or more frames from the video; and

comparing the extracted one or more frames to the plurality of stored images in the database.

5. The method of claim 1, wherein the organic activity stream is a news feed of the collective actions of all the users of a social network.

6. The method of claim 2, wherein the sponsor specification includes a visual specification, and further comprising:

formatting the matching multimedia object into a sponsored story in accordance with the sponsor specification.

7. The method of claim 6, further comprising displaying the sponsored story to all users of the social network connected to the uploading user.

8. The method of claim 6, further comprising displaying the sponsored story to a portion the users of the social network connected to the uploading user.

9. The method of claim 8, wherein the portion of the users is determined by an ad selection algorithm.

10. A non-transitory, computer-readable media comprising instructions operable, when executed, to:

receive sponsor specifications designating one or more concept nodes in a social network;

monitor an organic activity stream for the upload of one or more multimedia objects containing one or more image objects associated with the one or more concept nodes;

upon finding a matching multimedia object, export the matching multimedia object to a sponsored story system.

11. The media of claim 10, wherein monitoring the organic activity stream comprises:

upon receiving a multimedia object comprising one or more images from an uploading user, wherein the uploading user is represented by a node on a social network;

applying one or more object image recognition algorithms to the multimedia object;

comparing at least a portion of the multimedia object to a plurality of stored images in a database, each of the plurality of stored images associated with a concept node on the social network;

based on the comparison, identifying one or more image objects in the multimedia object associated with one or more concept nodes; and

attaching meta-data identifying the one or more concept nodes to the multimedia object.

12. The media of claim 11, wherein the multimedia object comprises an image.

13. The media of claim 11, wherein the multimedia object comprises a video, and wherein comparing at least a portion of the multimedia object comprises:

extracting one or more frames from the video; and

comparing the extracted one or more frames to the plurality of stored images in the database.

14. The media of claim 11, wherein the organic activity stream is a news feed of the collective actions of all the users of a social network.

15. The media of claim 11, wherein the sponsor specification includes a visual specification, and the instructions are further operable, when executed, to:

format the matching multimedia object into a sponsored story in accordance with the sponsor specification.

16. The media of claim 15, wherein the instructions are further operable, when executed, to display the sponsored story to all users of the social network connected to the uploading user.

17. The media of claim 15, wherein the instructions are further operable, when executed, to display the sponsored story to a portion the users of the social network connected to the uploading user.

18. The media of claim 17, wherein the portion of the users is selected by an ad selection algorithm.

19. An apparatus comprising:

one or more processors;

one or more non-transitory, computer-readable media comprising instructions, the instructions operable, when executed, to;

receive sponsor specifications designating one or more concept nodes in a social network;

monitor an organic activity stream for the upload of one or more multimedia objects containing one or more image objects associated with the one or more concept nodes;

upon finding a matching multimedia object, export the matching multimedia object to a sponsored story system.

20. The apparatus of claim 19, wherein monitoring the organic activity stream comprises:

upon receiving a multimedia object comprising one or more images from an uploading user, wherein the uploading user is represented by a node on a social network;

applying one or more object image recognition algorithms to the multimedia object;

comparing at least a portion of the multimedia object to a plurality of stored images in a database, each of the plurality of stored images associated with a concept node on the social network;

based on the comparison, identifying one or more image objects in the multimedia object associated with one or more concept nodes; and

attaching meta-data identifying the one or more concept nodes to the multimedia object.