Image record trend identification for user profiles

• US 7,836,093 B2
• Filed: 12/11/2007
• Issued: 11/16/2010
• Est. Priority Date: 12/11/2007
• Status: Active Grant

• Current Assignee: Apple Inc.
• Original Assignee: Eastman Kodak Company
• Inventors: McIntyre, Dale F., Gobeyn, Kevin M., Scalise, Anthony, Delong, Kevin R., Poetker, Robert B.
• Primary Examiner(s): Ehichioya; Fred I
• Application Number:
  US11/953,908
• Publication Number:
  US 20090150330A1
• Time in Patent Office: 1,071 Days
• Field of Search: 707/100, 707/733, 707/734, 707/784, 707/802, 707/E17.059, 707/E17.06, 705/14.66, 705/27
• US Class Current: 707/802
• CPC Class Codes: G06Q 30/0269 based on user profile or attribute
• CPC Class Codes: G11B 27/28 by using information signals recorded by the same method as the main recording G11B27/22 takes precedence
• CPC Class Codes: H04H 60/46 for recognising users' preferences
• CPC Class Codes: H04H 60/48 for recognising items expressed in broadcast information
• CPC Class Codes: H04H 60/59 of video recognising characters or patterns in general G06F18/00, G06V20/00
• CPC Class Codes: H04N 1/32112 in a separate computer file, document page or paper sheet, e.g. a fax cover sheet H04N1/32122 takes precedence
• CPC Class Codes: H04N 1/32128 attached to the image data, e.g. file header, transmitted message header, information on the same page or in the same computer file as the image for information embedded in the image H04N1/32144
• CPC Class Codes: H04N 21/44008 involving operations for analysing video streams, e.g. detecting features or characteristics in the video stream arrangements characterised by components specially adapted for monitoring, identification or recognition of video in broadcast systems H04H60/59
• CPC Class Codes: H04N 21/4667 Processing of monitored end-user data, e.g. trend analysis based on the log file of viewer selections
• CPC Class Codes: H04N 21/4826 using recommendation lists, e.g. of programs or channels sorted out according to their score
• CPC Class Codes: H04N 2201/3205 of identification information, e.g. name or ID code H04N2201/3209 takes precedence
• CPC Class Codes: H04N 2201/3214 of a date
• CPC Class Codes: H04N 2201/3215 of a time or duration
• CPC Class Codes: H04N 2201/3252 Image capture parameters, e.g. resolution, illumination conditions, orientation of the image capture device H04N2201/3256 and subgroups take precedence
• CPC Class Codes: H04N 2201/3253 Position information, e.g. geographical position at time of capture, GPS data

Abstract

Systems and methods for generating user profiles based at least upon an analysis of image content from digital image records are provided. The image content analysis is performed to identify trends that are used to identify user subject interests. The user subject interests may be incorporated into a user profile that is stored in a processor-accessible memory system.

Claims

1. A method implemented at least in part by a data processing system, the method for generating a user profile for a particular user, and the method comprising the steps of:

automatically identifying one or more trends based at least upon an analysis of image content from a plurality of digital image records associated with the particular user, wherein each trend represents commonality between multiple digital image records and the commonality relates at least to one of the following;

events, or location,

identifying a plurality of the particular user'"'"'s subject interests based at least upon an analysis of the trends;

generating a user profile associated with the particular user based at least upon the particular user'"'"'s subject interests; and

storing the particular user profile in a processor-accessible memory system.

2. The method of claim 1, wherein each of the trends involve a commonality detected based at least upon an analysis of the image content from at least some of the plurality of digital image records.

3. The method of claim 2, wherein the step of identifying one or more trends only identifies trends that meet a commonality threshold.

4. The method of claim 3, wherein the commonality threshold indicates that a commonality must be detected (a) among at least X of the plurality of digital image records, wherein X is an integer, or (b) among a particular percentage of the plurality of digital image records.

5. The method of claim 1, wherein at least one of the trends involves a combination of multiple commonalities.

6. The method of claim 1, wherein at least one of the trends relates to multiple digital image records that are deemed to have captured a reoccurring event.

7. The method of claim 1, wherein the analysis of image content includes a scene classification process, an object detection process, an audio analysis process, a text-from-image extraction process, or an event clustering process.

8. The method of claim 1, further comprising the step of identifying the particular user'"'"'s preferences based at least upon an analysis of the trends, wherein the user preferences link at least two of the user subject interests together, and wherein the particular user profile is further generated or updated based at least upon the user preferences.

9. The method of claim 8, wherein one of the particular user subject interests is a particular activity and another of the user subject interests is a particular person, and wherein one of the user preferences links the particular activity with the particular person.

10. The method of claim 1, further comprising the step of identifying a level-of-interest for at least some of the particular user subject interests based at least upon an analysis of the trends, wherein the particular user'"'"'s profile is further generated or updated based at least upon the levels of interest.

11. The method of claim 10, wherein the analysis of the trends for purposes of identifying the level-of-interest involves consideration of a number of digital image records involved in at least one of the trends with respect to a number of digital image records in the plurality of digital image records.

12. The method of claim 10, wherein the analysis of the trends for purposes of identifying the level-of-interest involves consideration of a recency of digital image records involved in at least one of the trends.

13. The method of claim 10, wherein the analysis of the trends for purposes of identifying the level-of-interest involves an analysis of a particular trend comprising two commonalities, and wherein the analysis of the particular trend involves a consideration of a number of different instances of a first of the two commonalities, wherein each of the different instances has associated therewith a set of digital image records deemed to represent at least the corresponding instance and a second of the two commonalities.

14. The method of claim 13, wherein each of the two commonalities relates to one or more events, one or more objects, one or more locations, or time.

15. The method of claim 1, further comprising the steps of:

generating an invitation for the user to interact with a particular user subject interest based at least upon an analysis of the particular user'"'"'s profile; and

storing the invitation in a processor-accessible memory system.

16. The method of claim 1, wherein at least one of the particular user'"'"'s subject interests is identified based at least upon an analysis of at least two of the trends.