Processes for generating content sharing recommendations based on image content analysis

• US 9,405,964 B1
• Filed: 09/09/2013
• Issued: 08/02/2016
• Est. Priority Date: 09/09/2013
• Status: Active Grant

• Current Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Original Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Inventors: Suchland, Jonathan Edward, Jafarzadeh, Ario, Denman, Scott Michael, Choudhary, Mihir Kumar, Cavalcanti, Daniel Hafner, Slimp, Joshua Jacob
• Primary Examiner(s): Le, Vu
• Assistant Examiner(s): Woldemariam, Aklilu
• Application Number:
  US14/022,070
• Time in Patent Office: 1,058 Days
• Field of Search: 370/203, 382/100, 382/115, 382/118, 382/299, 715/700, 715/727, 715/747, 715/804
• US Class Current: 1/1
• CPC Class Codes: G06F 18/00 Pattern recognition
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 50/01 Social networking
• CPC Class Codes: G06V 40/172 Classification, e.g. identification
• CPC Class Codes: H04N 1/00 Scanning, transmission or reproduction of documents or the like, e.g. facsimile transmission; Details thereof

Abstract

Processes are disclosed for generating share recommendations for sharing content based at least in part on associated metadata of the content (e.g., geo-location of the content, the date/time of the content, subject matter of the content, etc.). A quick share system may track an individual'"'"'s share history, including people with whom the individual has shared content, the date/time the content was shared, the geo-location of the individual when the content was shared, etc. Share recommendations indicating one or more suggested people with whom the individual may wish to share content may be generated for the individual, based at least in part on some of a current time/date, the individual'"'"'s current location, the content metadata, the individual'"'"'s share history. Share recommendations may also be based in part on an event associated with the content, user feedback data for shared content, and content analysis such as image analysis for digital images.

Claims

1. A system for providing share recommendations for a user, the system comprising:

a computing system comprising one or more processors, the computing system programmed with executable program instructions to at least;

access a digital photograph stored on a user computing device of a sharing user;

identify a photographed subject of the digital photograph by analyzing image data of the digital photograph, wherein the photographed subject is a person and is identified by application of a facial recognition process to the image data;

select a contact of the sharing user as a potential share recipient of the digital photograph, wherein the contact is a person other than the photographed subject;

determine a share potential of the digital photograph with respect to the selected contact at least partly by (a) determining whether an association exists between the photographed subject and the selected contact, and (b) determining whether a geo-location of the digital photograph corresponds to a geolocation associated with the selected contact; and

output to the sharing user, via a user interface of the user computing device, a recommendation of the selected contact as a share recipient of the digital photograph, the recommendation based on the determined share potential.

2. The system of claim 1, wherein the association is a social network connection between the photographed subject and the contact.

3. The system of claim 1, wherein the user interface includes functionality for the sharing user to accept the recommendation and to send the digital photograph to the selected contact.

4. The system of claim 1, wherein the computing system is further programmed to select, based on information regarding communication channels to which the selected contact has access, a recommended communication channel for sharing the digital photograph with the selected contact.

5. The system of claim 1, wherein the computing system is further programmed to select, based on information associated with the selected contact, a communication channel by which the digital photograph is to be sent to the contact, and wherein the communication channel is selected from a group comprising at least an email, a text or SMS message, an application, a web service or a physical delivery of a physical copy of the digital photograph.

14. The system of claim 1, wherein the computing system is programmed to output the recommendation by displaying a representation of the selected contact via a user interface display that provides functionality for designating one or more recipients to whom to send the digital photograph.

6. A computer-implemented method for generating share recommendations for a user, the computer-implemented method comprising:

accessing a digital image stored on a user computing device;

identifying a subject of the digital image by analyzing image content of the digital image, wherein the subject is an individual or a location;

identifying a potential share recipient of the digital image, the potential share recipient being a person other than the identified subject;

determining a share potential of the digital image to be shared with respect to the potential share recipient, wherein determining the share potential comprises (a) determining whether an association exists between the subject and the potential share recipient, and (b) determining whether a geo-location of the digital image corresponds to a geolocation associated with the potential share recipient; and

generating a share recommendation to share the digital image with the potential share recipient based at least in part on the determined share potential,

wherein the method is performed programmatically by a computing system that comprises one or more processors.

7. The computer-implemented method of claim 6, wherein the share recommendation is generated automatically in response to determining that a location associated with the potential share recipient is the subject of the digital image.

8. The computer-implemented method of claim 6, wherein the share recommendation comprises a communication channel by which the digital image is to be sent to the potential share recipient.

9. The computer-implemented method of claim 8, wherein the communication channel is selected from a group comprising at least an email, a text message, an application, a web service or a physical delivery of a physical copy of the digital image.

10. The computer-implemented method of claim 6, wherein the share potential is determined based at least in part on a matching of a geo-location of the digital image to a geo-location associated with the potential share recipient.

11. The computer-implemented method of claim 6, further comprising:

generating caption text for the digital image based at least in part on content data for the digital image, and wherein the share recommendation includes the caption text to be shared with the digital image.

12. The computer-implemented method of claim 6, further comprising:

accessing a user profile for a sharing user, wherein the user profile includes a current location and a share history of the sharing user including a list of past share recipients, and wherein the share potential is determined based at least in part on a comparison of the current location to past locations from which the sharing user shared content items with the past share recipients.

13. The computer-implemented method of claim 12, wherein the share recommendation is generated based at least partly on an automated determination that the potential share recipient is on the list of past share recipients.

15. Non-transitory computer storage having stored thereon an executable computer program that instructs a computing system comprising one or more processors to perform an automated process that comprises:

detecting, by analyzing image data of a digital photograph associated with a user, a photographed subject of the digital photograph, wherein the photographed subject is a person or a location;

identifying, based on user profile data associated with contacts of the user, a contact that is a potential share recipient of the digital photograph, the contact being a person other than the photographed subject;

determining a share potential of the digital photograph with respect to the contact, wherein determining the share potential comprises (a) determining whether an association exists between the photographed subject and the contact, and (b) determining whether a geo-location of the digital photograph corresponds to a geolocation associated with the contact; and

recommending said contact to the user, via a user interface for sharing photographs, as a share recipient of the digital photograph based at least partly on the determined share potential.

16. The non-transitory computer storage of claim 15, wherein detecting the photographed subject comprises applying a facial recognition algorithm to the digital photograph.

17. The non-transitory computer storage of claim 15, wherein the automated process further comprises recommending to the user, based on data associated with the contact, a communication channel for sharing the digital photograph with the contact.