Social search system and method

• US 9,507,878 B2
• Filed: 11/22/2013
• Issued: 11/29/2016
• Est. Priority Date: 09/22/2006
• Status: Active Grant

• Current Assignee: John Nicholas and Kristin Gross Trust
• Original Assignee: John Nicholas and Kristin Gross Trust
• Inventors: Gross, John Nicholas
• Primary Examiner(s): Richardson, James E
• Application Number:
  US14/087,400
• Publication Number:
  US 20140081943A1
• Time in Patent Office: 1,103 Days
• Field of Search: 707/705
• US Class Current: 1/1
• CPC Class Codes: G06F 16/24578 using ranking
• CPC Class Codes: G06F 16/335 Filtering based on additional data, e.g. user or group profiles filtering in web context G06F16/9535, G06F16/9536
• CPC Class Codes: G06F 16/90324 using system suggestions
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 30/0255 based on user history
• CPC Class Codes: G06Q 30/0256 User search
• CPC Class Codes: G06Q 30/0269 based on user profile or attribute
• CPC Class Codes: G06Q 30/0273 Determination of fees for advertising
• CPC Class Codes: G06Q 50/01 Social networking

Abstract

A search system generates customized search results for social network members. The results are responsive to queries and are personalized based on members'"'"' explicit and implicit interests derived from user actions, content selections, etc.

Claims

1. A method of presenting personalized search results to a user at a social networking site with a computing system comprising:

(a) presenting first content to a first member of a social network at the social network site, including postings by other members, within a graphical interface, which first content is automatically determined by the computing system for said first member with a content recommendation engine based in part on;

i) first interest information identified explicitly by said first member, and

ii) second interest information determined implicitly from actions taken by said first member;

wherein said first content is presented by said content recommendation engine automatically at the social networking site as output predicted and customized for said first member;

(b) collecting and processing first ratings data for said first member with the computing system at the social network site for said first content including a first rating for a first item included in the first content;

(d) automatically mapping said first item to a first set of one or more corresponding item topics with an automated classifier, such that the automated classifier at least considers potential 1;

1, 1;

N and N;

1 item to item topic mappings, where N>

1, in selecting the first set of corresponding item topics, said mapping including generating a classification database of items and item topics, wherein in considering potential N;

1 mappings, said automated classifier associates said first item with N semantically equivalent items and maps the N semantically equivalent items to a single item topic in selecting the first set of corresponding item topics

receiving and processing a first query at the social networking site from said first member of said social network directed to a first subject;

wherein said first query is processed by a search engine at the social network site that is separate from said content recommendation engine;

(e) associating said first subject with a first item topic by mapping keywords in said first query to one or more matching item topics in said classification database using a search classifier that performs said mapping the first topic being selected from among the one or more matching topics;

(f) correlating said first subject identified from said first query to said first item with the computing system based on said first rating and said mapping of said first item to said first set of one or more corresponding item topics; and

(g) based on results of step (f) customizing and presenting a set of search result listings to said first member responsive to said first topic, such that said set of search result listings include content related to said first item.

2. The method of claim 1, further including a step:

providing an advertisement related to said first content source and/or said first item along with said set of search result listings.

3. The method of claim 1, wherein said set of search result listings includes at least one listing identifying another second member.

4. The method of claim 1, wherein said set of search result listings includes at least one listing identifying content or items rated by a second member of said social network identified as a friend of said first member.

5. The method of claim 1, wherein said mapping keywords to matching topics comprises using natural language processing.

6. The method of claim 5, wherein said mapping keywords to matching topics is done on a 1:

1 basis, such that each keyword is associated with a single matching topic.

7. The method of claim 5, wherein said mapping keywords to matching topics is done on a 1:

N basis, such that each keyword is associated with one or more matching topics.

8. The method of claim 5, wherein said mapping keywords to matching topics is done on an N:

1 basis, such that multiple keywords are associated with a single matching topic.

9. The method of claim 5, wherein said mapping keywords to matching topics considers semantic equivalents of said keywords.

10. A method of presenting personalized search results to a user at a social networking site with a computing system comprising:

(a) presenting first content to a first member of a social network at the social network site including postings by other members within a graphical interface, which first content is automatically determined by the computing system for said first member with a content recommendation engine based in part on;

(i) first interest information identified explicitly by said first member, and

(ii) second interest information determined implicitly from actions taken by said first member;

wherein said first content is presented by said content recommendation engine automatically at the social networking site as output customized for said first member; and

(b) collecting and processing first ratings data for said first member with the computing system at the social network site including a first rating for a first item included in the first content;

(c) automatically mapping said first item to a first set of one or more corresponding item topics with an automated classifier, such that the automated classifier at least considers potential 1;

1, 1;

N and N;

1 item to item topic mappings, where N>

1, in selecting the first set of corresponding item topics, said mapping including generating a classification database of items and item topics, wherein in considering potential N;

1 mappings, said automated classifier associates said first item with N semantically equivalent items and maps the N semantically equivalent items to a single item topic in selecting the first set of corresponding item topics;

(d) receiving and processing a first query at the social networking site from said first member of said social network requesting items;

wherein said first query is processed by a search engine at the social network site that is separate from said content recommendation engine;

(e) determining, using the computing system, that the items of the first query are associated with a first item topic by mapping keywords in said first query to corresponding item topics in said classification database;

(f) correlating said first item topic identified from said first query with a set of related item topics selected from of said first set of one or more corresponding item topics associated with the first item with the computing system based at least in part on said mapping of said first item to said first set of one or more corresponding item topics; and

(g) based on results of step (f) generating and presenting a set of customized search result listings to said first member in response to said first query, such that said customized set of search result listings includes first content directed to said first item topic and second content directed to the set of related item topics.

11. The method of claim 10, further including a step:

providing an advertisement related to said first content source and/or said first item along with said set of search result listings.

12. The method of claim 10, wherein said set of search result listings includes at least one listing identifying another second member.

13. The method of claim 10, wherein said set of search result listings includes at least one listing identifying content or items rated by a second member of said social network identified as a friend of said first member.

14. The method of claim 10, wherein said mapping keywords to matching topics comprises using natural language processing.

15. The method of claim 14, wherein said mapping keywords to matching topics is done on a 1:

1 basis, such that each keyword is associated with a single matching topic.

16. The method of claim 14, wherein said mapping keywords to matching topics is done on a 1:

N basis, such that each keyword is associated with one or more matching topics.

17. The method of claim 14, wherein said mapping keywords to matching topics is done on an N:

1 basis, such that multiple keywords are associated with a single matching topic.

18. The method of claim 14, wherein said mapping keywords to matching topics considers semantic equivalents of said keywords.

19. The method of claim 10, further comprising training the automated classifier using a training corpus.