DETECTING TRENDS FROM IMAGES UPLOADED TO A SOCIAL NETWORK

• US 20150058079A1
• Filed: 08/26/2013
• Published: 02/26/2015
• Est. Priority Date: 08/26/2013
• Status: Abandoned Application

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: FREUND, Martin Brandt, Xie, Yuanying
• Application Number:
  US14/010,428
• Publication Number:
  US 20150058079A1
• Time in Patent Office: Days
• US Class Current: 705/7.31
• CPC Class Codes: G06Q 30/0202 Market predictions or forecasting for commercial activities
• CPC Class Codes: G06Q 50/01 Social networking

Abstract

A system and method is disclosed for detecting marketable subjects within digital images uploaded to the social network. Software associated with a social network detects a marketable subject in a plurality of images provided to a social stream by a group of users who share a relationship in the social network. A popularity of the marketable subject within the group of users is determined based on the detecting, and a current trend is identified for the group of users based on the popularity and a relevant time period for the images. A vendor related to the marketable subject may be notified that the current trend applies to one or more of the group of users.

Claims

1. A computer-implemented method, comprising:

detecting a marketable subject in a plurality of images provided to a social stream by a group of users who share a relationship in a social network;

determining, based on the detecting, a popularity of the marketable subject within the group of users;

identifying, for the group of users, a current trend based on the popularity and a relevant time period for the images; and

notifying a vendor related to the marketable subject that the current trend applies to one or more of the group of users.

2. The computer-implemented method of claim 1, wherein the marketable subject is a brand identity, style of clothing, or business establishment.

3. The computer-implemented method of claim 1, further comprising:

determining, for each image, an instance in time for the marketable subject, the current trend being identified when a threshold number of the images include an instance in time within the relevant time period.

4. The computer-implemented method of claim 1, further comprising:

determining user interests based on information provided by the users to the social network; and

determining the relationship based on an interest common to each of the users.

5. The computer-implemented method of claim 1, wherein the relationship is between a user of the group who is actively using the social network and the remaining users in the group.

6. The computer-implemented method of claim 1, wherein the marketable subject is detected in a provided image by image recognition.

7. The computer-implemented method of claim 1, wherein the marketable subject is detected from meta data embedded in a respective image.

8. The computer-implemented method of claim 1, further comprising:

determining a level of relevancy of the marketable subject to the one or more users, wherein the vender is notified when the level of relevancy satisfies a predetermined threshold.

9. The computer-implemented method of claim 8, further comprising:

setting a value of an offering related to the marketable subject based on the level of relevancy; and

providing the value of the offering to the vendor.

10. The computer-implemented method of claim 1, further comprising:

providing a prototype user for a respective user of the group, the prototype user being associated with a plurality of different apparel pieces; and

associating a different brand with each different apparel piece based on an identified trend for the associated brand within the group;

wherein the marketable subject comprises one of the different apparel pieces.

11. The computer-implemented method of claim 1, further comprising:

determining that the current trend comprises a change in an initial trend, the vendor being notified in response to the change.

12. The computer-implemented method of claim 11, further comprising:

sending an offering to at least one of the group of users in response to the change.

13. A machine-readable medium having instructions stored thereon that, when executed, cause a machine to perform a method, the method comprising:

detecting a plurality of marketable subjects in a plurality of images uploaded to a social network, the images uploaded by a group of users who share a relationship in the social network;

identifying, for the group of users, a current trend associated with a detected marketable subject based on a threshold number of instances of the detected marketable subject associated with the group; and

notifying a vendor related to the detected marketable subject that the current trend applies to one or more of the group of users.

14. The machine-readable medium of claim 13, wherein the marketable subject is a brand identity, style of clothing, or business establishment.

15. The machine-readable medium of claim 13, wherein the current trend is identified based on a threshold number of the group of users uploading respective images that depict the detected marketable subject.

16. The machine-readable medium of claim 15, wherein the current trend is identified based on the respective images being uploaded within a predetermined time period.

17. The machine-readable medium of claim 13, wherein the relationship comprises a social connection mutually made between a respective pair of users.

18. The machine-readable medium of claim 13, the method further comprising:

determining a common interest for the group of users based on one or more activities of each of the users in the social network, wherein the relationship shared by the group of users is based on the common interest.

19. The machine-readable medium of claim 13, the method further comprising:

determining one or more interests of a respective user based on information provided to the social network from the user; and

determining that the current trend is relevant to the user based on a relationship between the marketable subject and the provided information,

wherein the vendor is notified that the current trend applies to users to whom the current trend is determined to be relevant.

20. A system, comprising:

one or more processors; and

a memory including instructions that, when executed by the one or more processors, cause the one or more processors to facilitate the steps of;

detecting a marketable subject in a plurality of images provided to a social stream by a group of users who share a relationship in a social network;

determining, based on the detecting, a popularity of the marketable subject within the group of users;

identifying, for the group of users, a current trend based on the popularity and a relevant time period for the images; and

notifying a vendor related to the marketable subject that the current trend applies to one or more of the group of users.