Inferring user preferences from an internet based social interactive construct

• US 9,037,531 B2
• Filed: 07/18/2013
• Issued: 05/19/2015
• Est. Priority Date: 11/02/2007
• Status: Active Grant

• Current Assignee: eBay Inc.
• Original Assignee: eBay Inc.
• Inventors: Pinckney, Thomas, Dixon, Christopher, Gattis, Matthew Ryan
• Primary Examiner(s): Holmes, Michael B
• Application Number:
  US13/945,274
• Publication Number:
  US 20130304691A1
• Time in Patent Office: 670 Days
• Field of Search: 706/62
• US Class Current: 706/62
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 5/04 Inference or reasoning models
• CPC Class Codes: G06N 5/048 Fuzzy inferencing
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 30/0631 Item recommendations
• CPC Class Codes: G06Q 50/01 Social networking

Abstract

In embodiments of the present invention improved capabilities are described for a computer program product embodied in a computer readable medium that, when executing on one or more computers, helps determine an unknown user'"'"'s preferences through the use of internet based social interactive graphical representations on a computer facility by performing the steps of (1) ascertaining preferences of a plurality of users who are part of an internet based social interactive construct, wherein the plurality of users become a plurality of known users; (2) determining the internet based social interactive graphical representation for the plurality of known users; and (3) inferring the preferences of an unknown user present in the internet based social interactive graphical representation of the plurality of known users based on the interrelationships between the unknown user and the plurality of known users within the graphical representation.

Claims

1. A computer-implemented method comprising:

receiving one or more search query terms submitted by a particular user;

retrieving a list of search results based on the search query terms;

accessing user preference profile information identifying one or more preferences of the particular user;

ranking the list of search results, based on the user preference profile information, wherein a first search result describing a product matching the preferences of the particular user is ranked higher in the ranked list in comparison to a second search result describing a second product that does not match the preferences of the particular user; and

providing the ranked list of search results to the particular user.

2. The method of claim 1, further comprising:

identifying the preferences of the particular user; and

generating the user preference profile information identifying the preferences of the particular user.

3. The method of claim 2, wherein the preferences of the particular user are identified based on previous search result selections of the particular user.

4. The method of claim 2, wherein the preferences of the particular user are identified by analyzing user actions of the particular user on an online social network.

5. The method of claim 2, wherein the preferences of the particular user are identified by crawling, from a third party website, information describing the preferences of the particular user.

6. The method of claim 2, wherein the preferences of the particular user are identified from online sources indicating location-based behavior of the particular user.

7. The method of claim 1, wherein the search results describe at least one product.

8. A non-transitory machine-readable storage medium comprising instructions that, when executed by one or more processors of a machine, cause the machine to perform operations comprising:

receiving one or more search query terms submitted by a particular user;

retrieving a list of search results based on the search query terms;

identifying one or more preferences of the particular user;

generating user preference profile information identifying the preferences of the particular user;

accessing the user preference profile information identifying the preferences of the particular user;

ranking the list of search results, based on the user preference profile information; and

providing the ranked list of search results to the particular user.

9. The storage medium of claim 8, wherein a first search result describing a product matching the preferences of the particular user is ranked higher in the ranked list in comparison to a second search result describing a second product that does not match the preferences of the particular user.

10. The storage medium of claim 8, wherein the preferences of the particular user are identified based on previous search result selections of the particular user.

11. The storage medium of claim 8, wherein the preferences of the particular user are identified by analyzing user actions of the particular user on an online social network.

12. The storage medium of claim 8, wherein the preferences of the particular user are identified by crawling, from a third party website, information describing the preferences of the particular user.

13. The storage medium of claim 8, wherein the preferences of the particular user are identified from online sources indicating location-based behavior of the particular user.

14. A system comprising:

a machine including a memory and at least one processor; and

a recommendation module, executable by the machine, configured to;

receive one or more search query terms submitted by a particular user;

retrieve a list of search results based on the search query terms, wherein the search results describe at least one product;

access user preference profile information identifying one or more preferences of the particular user;

rank the list of search results, based on the user preference profile information; and

provide the ranked list of search results to the particular user.

15. The system of claim 14, wherein a first search result describing a product matching the preferences of the particular user is ranked higher in the ranked list in comparison to a second search result describing a second product that does not match the preferences of the particular user.

16. The system of claim 14, wherein the recommendation module is further configured to:

identify the preferences of the particular user; and

generate the user preference profile information identifying the preferences of the particular user.

17. The system of claim 16, wherein the preferences of the particular user are identified based on previous search result selections of the particular user.

18. The system of claim 16, wherein the preferences of the particular user are identified by analyzing user actions of the particular user on an online social network.