Topic based recommender system and method

• US 9,646,109 B2
• Filed: 03/05/2015
• Issued: 05/09/2017
• 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): NGUYEN, PHONG H
• Application Number:
  US14/639,907
• Publication Number:
  US 20150178304A1
• Time in Patent Office: 796 Days
• Field of Search: 707705, 707749, 707758
• 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 recommendation system is used to provide suggestions in environments such as message boards, RSS aggregators, blogs and the like by comparing member interests and creating recommendation items corresponding to categorized topics or other members. In some instances, a natural language can assist in processing content to sort it into the appropriate topic bin. An advertising module cooperates with the system to provide content based ads relevant to the recommended items.

Claims

1. A method of generating automatic recommendations for human readable content sources to a first user with a computing system comprising:

(a) processing a set of first ratings from the first user for a plurality of first content sources with the computing system, each of the first content sources including at least one of a human author, a non-human entity, or a social network contact, to derive a first set of interests for said first user;

(b) establishing a first user profile for the first user based on said step (a), the first user profile containing the ratings and the first set of interests derived for the first user for said one or more first user selected human readable content source entities;

(c) processing a set of second ratings from one or more second users for said first content source, to derive a second set of interests for said second users;

(d) correlating said set of first ratings with said set of second ratings using the computing system to predict a selected set of second users for inclusion as human readable content source entities within said first user profile;

(e) generating an automatic recommendation with a recommender system operating on the computing system or another computing system which identifies to the first user both;

     1) Phone or more of said selected set of second users to said first user; and

     2) one or more of the second set of interests based at least in part on step (c); and

(f) modifying said first user profile upon receiving a confirmation from the first user to include one or more of said selected set of second users and/or one or more of the second set of interests.

2. The method of claim 1, wherein said correlation is determined by one or both of collaborative filtering or corroborative filtering.

3. The method of claim 1, wherein said set of first ratings and said set of second ratings include implicit ratings data which is determined implicitly from actions taken by said first user and said one or more second users in reviewing content presented electronically during an Internet session including at one or more website separate from a website supported by the computing system.

4. The method of claim 1, wherein said set of first ratings and said set of second ratings are recommendations given to authors of message board posts.

5. The method of claim 1, further comprising presenting an advertisement to said first user which contains content predicted based on said correlation.

6. The method of claim 1, further comprising presenting an advertisement along with said recommendation, the advertisement being based on a content of said recommendation.

7. A method of generating automatic recommendations at a website for content to a first user with a computing system comprising:

(a) providing a first database correlating a plurality of first individual data items and rankings for the first user, wherein at least some of said first individual data items represent first user selected second entities;

(b) providing a second database correlating a plurality of topics or concepts to one or more of said plurality of first individual data items as well as to one or more of a plurality of second individual data items, each of said first and second pluralities of first and second individual data items being associated with at least one corresponding topic or concept;

(c) identifying first content presented to the first user with the computing system;

(d) analyzing said first content with the computing system to classify said first content to one or more first topics or first concepts using a natural language engine classifier;

(e) identifying at least one individual data item from said second database corresponding to said first topics or first concepts;

(f) identifying a rating provided by said first user with the computing system for said first content;

(g) generating a ranking for said corresponding at least one individual data item from said rating provided by the first user for said first content;

(h) repeating steps (c) through (g) for other content presented for the first user to generate a plurality of rankings for a plurality of corresponding individual data items in said second database;

(i) comparing rankings for individual data items provided by said first user and one or more second users, including said user selected second entities, to identify correlations between such users and/or individual data items;

(j) generating and presenting an automatic recommendation with a recommender system operating on the computing system for the first user concerning an individual data item based in part on step (i); and

(k) generating and presenting a recommendation with the computing system for the first user to adopt selected ones of said one or more second users based in part on step (i).

8. The method of claim 7, further comprising training said natural language engine with a training corpus.

9. The method of claim 7, wherein said first content includes at least one of:

(1) an advertisement presented to the first user;

(2) a search result list;

or (3) human readable content reviewed on the Internet.

10. The method of claim 7, further comprising customizing a search engine result by the first user concerning one of said topics or concepts based on one or both of said prediction or said recommendation.