ON-LINE PRODUCT RELATED RECOMMENDATIONS

• US 20160005097A1
• Filed: 07/07/2014
• Published: 01/07/2016
• Est. Priority Date: 07/07/2014
• Status: Active Grant

• Current Assignee: Yahoo AD Tech LLC
• Original Assignee: Yahoo! Inc. (Apollo Global Management, Inc.)
• Inventors: Hsiao, JenHao, Li, Jia
• Granted Patent: US 11,151,630 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06Q 30/0631 Item recommendations
• CPC Class Codes: G06T 2207/10 Image acquisition modality
• CPC Class Codes: G06T 2207/30196 Human being; Person
• CPC Class Codes: G06T 7/11 Region-based segmentation

Abstract

Example methods, apparatuses, and/or articles of manufacture are disclosed that may be implemented, in whole or in part, using one or more computing devices to facilitate or support one or more processes and/or operations for one or more on-line recommendations, such as product-related recommendations, for example.

Claims

1. A method comprising:

identifying one or more regions of an on-line image to determine a product, or portion thereof, preferred by one or more users based, at least in part, on one or more features of said one or more regions; and

providing an on-line product-related recommendation based, at least in part, on a determination of said product, or said portion thereof, preferred by said one or more users.

2. The method of claim 1, wherein said providing comprises electronically providing said on-line product-related recommendation to said one or more users.

3. The method of claim 2, wherein said one or more regions comprise one or more regions of interest identified based, at least in part, on a saliency map of said on-line image.

4. The method of claim 1, wherein said determination of said product, or said portion thereof, preferred by said one or more users is based, at least in part, on a visual-bag-of-words-type processing of said on-line image.

5. The method of claim 1, wherein said determination of said product, or said portion thereof, preferred by said one or more users comprises a comparison of said one or more regions of said on-line image with one or more visual words of one or more product-related images included in a database.

6. The method of claim 5, wherein said on-line product-related recommendation is based, at least in part, on at least one of the following with respect to said comparison:

a visual product similarity;

a personal visual preference;

a contextual similarity;

or any combination thereof.

7. The method of claim 1, wherein said product, or said portion thereof, is displayed against at least one of the following:

a plain background;

a cluttered background;

or any combination thereof.

8. The method of claim 1, wherein said one or more regions of said on-line image are identified based, at least in part, on at least one of the following:

a color contrast-type measure;

an edge density-type measure;

a superpixel straddling (SS) cues-type measure;

or any combination thereof.

9. The method of claim 1, wherein said on-line image comprises at least one of the following:

an annotated on-line image;

an unannotated on-line image;

or any combination thereof.

10. The method of claim 1, wherein said one or more features comprise at least one of the following:

one or more texture-type features;

one or more color-type features;

or any combination thereof.

11. The method of claim 1, wherein said one or more regions comprise one or more homogenous regions.

12. A method comprising:

electronically recommending an on-line purchase based, at least in part, on an interest of a user inferable from one or more portions of a web document.

13. The method of claim 12, wherein said one or more portions of said web document are indicative of a product preferred by said user for purposes of said on-line purchase.

14. The method of claim 12, wherein said web document comprises a displayable web document.

15. The method of claim 14, wherein said web document comprises at least one of the following:

an annotated web document;

an unannotated web document;

or any combination thereof.

16. The method of claim 12, wherein said electronically recommending an on-line purchase comprises electronically recommending an on-line product.

17. The method of claim 12, wherein said interest of said user is inferable based, at least in part, on one or more machine-learned functions.

18. The method of claim 17, wherein said one or more machine-learned functions are capable of identifying at least one of the following:

a personal visual preference of said user;

a visual similarity of an on-line product;

a contextual similarity of said user and/or an on-line product;

or any combination thereof.

19. An apparatus comprising:

a computing platform, said platform including a capability to;

identify one or more regions of an on-line image to determine a product, or portion thereof, preferred by one or more users based, at least in part, on one or more features of said one or more regions; and

provide an on-line product-related recommendation based, at least in part, on a determination of said product, or said portion thereof, preferred by said one or more users.

20. The apparatus of claim 19, wherein said capability to provide said on-line product-related recommendation comprises a capability to electronically provide said on-line product-related recommendation to said one or more users.