METHOD AND SYSTEM FOR DISCOVERY OF USER UNKNOWN INTERESTS

• US 20140280548A1
• Filed: 03/15/2013
• Published: 09/18/2014
• Est. Priority Date: 03/15/2013
• Status: Active Grant

• Current Assignee: R2 Solutions LLC (Acacia Research Corporation)
• Original Assignee: Yahoo! Inc. (Apollo Global Management, Inc.)
• Inventors: Langlois, Jean-Marc, Gaffney, Scott, Teo, Choon Hui, Liu, Nathan
• Granted Patent: US 9,270,767 B2
• Time in Patent Office: Days
• US Class Current: 709/204
• 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

Abstract

A method and system for exploring a list of user interests beyond the currently known user interests by defining a distance metrics in the interest space is disclosed. The new method and system target for exploration, items of interests which are close in proximity to the current set of user interests, thereby greatly improving the chance that one of the exploration items will be liked by the user.

Claims

1. A method for identifying content for a user, the method implemented on a machine having at least one processor, storage, and a communication interface connected to a network, the method comprising:

retrieving information related to a user, wherein the information indicates one or more interests of the user;

identifying at least one interest of the user based on the information;

determining one or more supplemental interests with respect to each of the identified at least one interest of the user, where the one or more supplemental interests do not overlap with the one or more interests of the user; and

identifying supplemental content associated with the one or more supplemental interests with respect to each of the identified at least one interest of the user, wherein

the supplemental content associated with the one or more supplemental interests is used to discover unknown interest of the user.

2. The method of claim 1, further comprising:

identifying relatedness between each piece of content in the supplemental content and its corresponding supplemental interest;

ranking each piece of content in the supplemental content based on the relatedness;

selecting at least some pieces of content in the supplemental content based on the ranking; and

outputting the selected content from the supplemental content.

3. The method of claim 1 further comprising:

randomly obtaining content; and

adding the randomly obtained content to the supplemental content.

4. The method of claim 2 further comprising filtering the ranked content in the supplemental content based on a criteria.

9. The method of claim 1, wherein step of determining comprises:

estimating a metric for each of a plurality of candidate supplemental interests; and

selecting the one or more supplemental interests based on their respective metrics with respect to a threshold.

10. The method of claim 9, wherein the metric includes at least one of:

a distance between two interests in a content taxonomy;

a co-occurrence of two interests in a collection of content;

a co-occurrence of two interests in a set of user profiles;

a co-occurrence of two interests in a set of user sessions; and

any combination thereof.

11. The method of claim 1, wherein the unknown interest of the user is discovered based on interaction between the user and the supplemental content.

5. A system for identifying unknown user content, the system comprising:

a retrieval unit for retrieving information related to a user, wherein the information indicates one or more interests of the user;

an interest analyzer for identifying at least one interest of the user based on the information;

a supplemental interest identifier for determining one or more supplemental interests with respect to each of the identified at least one interest of the user, where the one or more supplemental interests do not overlap with the one or more interests of the user; and

a supplemental content identifier for identifying supplemental content associated with the one or more supplemental interests with respect to each of the identified at least one interest of the user, wherein

the supplemental content associated with the one or more supplemental interests is used to discover unknown interest of the user.

6. The system of claim 5, further comprising:

a supplemental weighting unit for identifying relatedness between each piece of content in the supplemental content and its corresponding supplemental interest;

a ranking unit for ranking each piece of content in the supplemental content based on the relatedness;

a selector for selecting at least some pieces of content in the supplemental content based on the ranking; and

an output for outputting the selected content from the supplemental content.

12. The system of claim 5, further comprising a random content selector configured for:

randomly obtaining content; and

adding the randomly obtained content to the supplemental content.

13. The system of claim 5, wherein the supplemental interest identifier is further configured for:

estimating a metric for each of a plurality of candidate supplemental interests; and

selecting the one or more supplemental interests based on their respective metrics with respect to a threshold.

14. The system of claim 13, wherein the metric includes at least one of:

a distance between two interests in a content taxonomy;

a co-occurrence of two interests in a collection of content;

a co-occurrence of two interests in a set of user profiles;

a co-occurrence of two interests in a set of user sessions; and

any combination thereof.

15. The system of claim 5, wherein the unknown interest of the user is discovered based on interaction between the user and the supplemental content.

16. The system of claim 6, wherein the ranked content in the supplemental content is filtered based on a criteria.

7. A non-transitory machine readable medium having recorded thereon information for identifying unknown user interest, wherein the information, when read by a machine, causes the machine to perform the steps of:

retrieving information related to a user, wherein the information indicates one or more interests of the user;

identifying at least one interest of the user based on the information;

determining one or more supplemental interests with respect to each of the identified at least one interest of the user, where the one or more supplemental interests do not overlap with the one or more interests of the user; and

identifying supplemental content associated with the one or more supplemental interests with respect to each of the identified at least one interest of the user, wherein

the supplemental content associated with the one or more supplemental interests is used to discover unknown interest of the user.

8. The medium of claim 7, wherein the information, when read by the machine, further causes the machine to perform the steps of:

identifying relatedness between each piece of content in the supplemental content and its corresponding supplemental interest;

ranking each piece of content in the supplemental content based on the relatedness;

selecting at least some pieces of content in the supplemental content based on the ranking; and

outputting the selected content from the supplemental content.

17. The medium of claim 7, wherein the information, when read by the machine, further causes the machine to perform the steps of:

randomly obtaining content; and

adding the randomly obtained content to the supplemental content.

18. The medium of claim 7, wherein step of determining comprises:

estimating a metric for each of a plurality of candidate supplemental interests; and

selecting the one or more supplemental interests based on their respective metrics with respect to a threshold.

19. The medium of claim 18, wherein the metric includes at least one of:

a distance between two interests in a content taxonomy;

a co-occurrence of two interests in a collection of content;

a co-occurrence of two interests in a set of user profiles;

a co-occurrence of two interests in a set of user sessions; and

any combination thereof.

20. The medium of claim 7, wherein the unknown interest of the user is discovered based on interaction between the user and the supplemental content.