System and method for collaborative image selection

• US 7,321,919 B2
• Filed: 05/23/2006
• Issued: 01/22/2008
• Est. Priority Date: 05/23/2005
• Status: Active Grant

• Current Assignee: Gula Consulting Limited Liability Company (Intellectual Ventures LLC)
• Original Assignee: Picateers Incorporated
• Inventors: Jacobs, Lawrence, Nakhoda, Shehzaad, Liu, Xiang, Zhong, Tie
• Primary Examiner(s): Chang, Jungwon
• Application Number:
  US11/438,948
• Publication Number:
  US 20060271691A1
• Time in Patent Office: 609 Days
• Field of Search: 709/206, 709/203, 709/204, 709/205, 709/224, 705/27, 705/10
• US Class Current: 709/205
• CPC Class Codes: H04L 67/306 User profiles
• CPC Class Codes: H04L 67/535 Tracking the activity of the user network monitoring arrangements H04L43/00; recording of computer activity G06F11/34
• CPC Class Codes: H04N 1/00132 in a digital photofinishing system, i.e. a system where digital photographic images undergo typical photofinishing processing, e.g. printing ordering
• CPC Class Codes: H04N 1/00148 Storage information retrieval G06F16/00
• CPC Class Codes: H04N 1/00172 directly from a still digital camera or from a storage medium mounted in a still digital camera H04N1/0018 takes precedence
• CPC Class Codes: H04N 1/00177 from a user terminal, e.g. personal computer
• CPC Class Codes: H04N 1/00196 Creation of a photo-montage, e.g. photoalbum H04N1/0019 takes precedence
• CPC Class Codes: H04N 1/00244 with a server, e.g. an internet server fax-servers or the like for store and forward H04N1/324

Abstract

A system and method for sharing images and collaborating in the selection of images likely to be interest to a user. Images (e.g., photos) are shared within a community of users, by allowing user to access any unrestricted community image, recommend an image to another user, assemble compilations of any images the user can access, etc. Various metrics regarding user activity are tracked, such as how often an image was viewed, downloaded, recommended, included in a compilation, printed, edited, etc. The metric values may be normalized, and then weighted and combined to produce, for each image, a ranking or rating personalized to an individual user. Ratings of images for a user may be used to order them for electronic presentation, assemble a set of images for an electronic compilation (e.g., an online album) or physical compilation (e.g., a photo book, a yearbook) or for some other purpose.

Claims

1. A method of selecting images for a personalized compilation, the method comprising:

establishing a community of users, wherein a given user may be a member of multiple communities;

storing a set of images submitted to the community by the users;

facilitating sharing of the images between the users;

facilitating a recommendation of a first image to a first user from a second user by;

accepting the recommendation from the second user; and

communicating the recommendation to the first user;

wherein the recommendation does not comprise the first image;

maintaining different electronic compilations derived from the shared images for different users in the community;

automatically ranking a subset of the images to reflect their estimated interest for a third user, wherein the ranking is based on user activities with the images, and wherein the user activities comprise recommendations of the images; and

presenting the subset of images in an order determined by the ranking;

wherein a different subset of images is presented to a different user based on different automatic rankings.

2. The method of claim 1, wherein said ranking comprises, for each image in the subset of images:

calculating values for multiple metrics corresponding to the user activities;

weighting each metric'"'"'s value according to how closely the metric is considered to correlate to a user'"'"'s interest in an image; and

combining the weighted metrics to yield an interest ranking for the image.

3. The method of claim 1, wherein said ranking is further based on relationships between users making recommendations of an image and users receiving the recommendations.

4. The method of claim 1, further comprising:

accepting a user'"'"'s explicit rating of an image in the subset of images, wherein the user activities further include said explicit rating.

5. The method of claim 1, wherein the user activities further comprise selecting an image as a favorite.

6. The method of claim 1, wherein the user activities further comprise including an image in a compilation.

7. The method of claim 1, wherein the user activities further comprise ordering a physical copy of an image.

8. The method of claim 1, wherein the user activities further comprise submitting metadata for an image.

9. The method of claim 1, wherein the user activities further comprise downloading an image.

10. The method of claim 1, wherein the user activities further comprise grouping an image with another image having a different ranking.

11. The method of claim 1, wherein the user activities further comprise discussing an image between users.

12. The method of claim 1, wherein the third user is one of the first user and the second user.

13. A computer readable medium storing instructions that, when executed by a computer, cause the computer to perform a method of selecting images for a personalized compilation, the method comprising:

establishing a community of users, wherein a given user may be a member of multiple communities;

storing a set of images submitted to the community by the users;

facilitating sharing of the images between the users;

facilitating a recommendation of a first image to a first user from a second user by;

accepting the recommendation from the second user; and

communicating the recommendation to the first user;

wherein the recommendation does not comprise the first image;

maintaining different electronic compilations derived from the shared images for different users in the community;

automatically ranking a subset of the images to reflect their estimated interest for a third user, wherein the ranking is based on user activities with the images, and wherein the user activities comprise recommendations of the images; and

presenting the subset of images in an order determined by the ranking;

wherein a different subset of images is presented to a different user based on different automatic rankings.

14. A computer-implemented method of determining a first user'"'"'s likely interest in a set of images, the method comprising:

for each user in a plurality of users, including the first user, eliciting the user'"'"'s recommendations to other users of images in the set of images;

for each image in the set of images, associating values for multiple metrics, including;

the first user'"'"'s rating of the image, wherein a given user'"'"'s rating of an image indicates whether the given user selected the image as a favorite;

how often the image was recommended to the first user by other users;

how often the image was downloaded by the first user;

an average rating of the image by all users who rated the image;

how long the image was viewed by the first user;

whether the first user viewed an enlarged version of the image;

clarity of the image;

for each image in the set of images, combining the values for the metrics to yield an estimated interest in the image by the first user; and

based on the estimated interests of the images, presenting to the first user an automated layout of multiple images from the set of images.

15. The method of claim 14, wherein said presenting comprises:

presenting to the user the N images in the set of images having the highest estimated interests, wherein N>

0.

16. The method of claim 14, wherein the metrics further include:

an average rating of the image by users who recommended the image to at least one other user; and

how often the image was recommended by any user.

17. The method of claim 14, wherein the metrics further include:

the number of comments made on the image by users.

18. The method of claim 14, wherein the metrics further include:

how often the image was selected as a primary image in a compilation of images from the set of images; and

how often the image was selected to be placed on the cover of a printed compilation of images from the set of images.

19. The method of claim 14, wherein the metrics further include:

how often metadata was submitted for the image.

20. A computer readable medium storing instructions that, when executed by a computer, cause the computer to perform a method of determining a first user'"'"'s likely interest in a set of images, the method comprising:

for each user in a plurality of users, including the first user, eliciting the user'"'"'s recommendations to other users of images in the set of images;

for each image in the set of images, associating values for multiple metrics, including;

the first user'"'"'s rating of the image, wherein a given user'"'"'s rating of an image indicates whether the given user selected the image as a favorite;

how often the image was recommended to the first user by other users;

how often the image was downloaded by the first user;

an average rating of the image by all users who rated the image;

how long the image was viewed by the first user;

whether the first user viewed an enlarged version of the image;

clarity of the image;

for each image in the set of images, combining the values for the metrics to yield an estimated interest in the image by the first user; and

based on the estimated interests of the images, presenting to the first user an automated layout of multiple images from the set of images.

21. A method of selecting images of interest to a user, comprising:

assembling a pool of images available for access by all users in a community of users;

recording user activity regarding the images, wherein a user'"'"'s activity includes one or more of;

viewing a first version of a first image;

viewing a second version of the first image, wherein the second version is of greater size or resolution than the first version;

recommending an image to a related user;

recommending an image to an unrelated user;

explicitly rating an image; and

selecting a subset of the pool of images to form a compilation;

for one or more images not previously accessed by a first user, assigning to the images weights corresponding to;

recommendations of the images to the first user from relatives of the first user;

recommendations of the images to the first user from users not related to the first user;

recommendations of the images between users other than the first user;

explicit ratings assigned to the images by users other than the first user;

quality of the images; and

frequency of access by users other than the first user; and

for each of the one or more images, combining the weights to determine an estimated level of interest in the image by the first user.

22. A method of compiling personalized sets of images for different users, comprising:

assembling a pool of images available for access by a community of users;

recording activity regarding the images, including;

a duration of time a user views an image;

a frequency with which a user views an image;

addition of a caption to an image;

requesting an enlarged view of a viewed image;

recommendation of an image to a single user by multiple other users;

determining possible subjects of one or more images by noting;

which users access said image;

which users, if any, said image is recommended to by the users who access said image;

any relationships between the users who access said image and users to whom they recommend said image; and

for the different users, automatically compiling personalized sets of images likely to be of interest to the users.

23. The method of claim 22, further comprising:

determining whether multiple users have organized separate collections of images with similar titles.