Methods for presenting online advertising at a social network site based on user interests

• US 9,275,170 B2
• Filed: 11/22/2013
• Issued: 03/01/2016
• Est. Priority Date: 09/22/2006
• Status: Active Grant

• Current Assignee: John Nicholas and Kristin Gross
• Original Assignee: John Nicholas and Kristin Gross
• Inventors: Gross, John Nicholas
• Primary Examiner(s): Hoang, Son T
• Application Number:
  US14/087,369
• Publication Number:
  US 20140089103A1
• Time in Patent Office: 830 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

An advertising system generates customized advertising for social network members. The ads results are personalized based on members'"'"' explicit and implicit interests derived from user actions, content selections, etc.

Claims

1. A method utilizing a computing system for presenting advertising content to a user at a social networking website, wherein the method comprises:

(a) collecting and processing, by the computing system, ratings data provided explicitly by a first member of a social network within an electronic interface at the social network website including;

i) ratings specified by the first member for first items and/or topics of interest to the first member; and

ii) ratings specified by the first member for one or more first webpages, wherein the ratings indicate a high level of interest of the first member in the first items and/or topics and the one or more first webpages;

(b)(1) using a natural language classifier running on the computing system;

(i) mapping the first items and/or topics of interest and the one or more first webpages rated by the first member to a first set of words and/or phrases, and

(ii) identifying a second set of items and/or topics that is also logically linked by the natural language classifier to the first set of words and/or phrases based on a correlation derived from an analysis of a text corpus associated with the second set of items and/or topics;

(b)(2) predicting at least a selected subset of items and/or topics of the second set of items and/or topics that would be of interest to the first member using a recommendation system;

(c) generating and storing first member profile data within the computing system based on the ratings data, the first member profile data including information relating to both of the first items and/or topics and the at least selected subset of items and/or topics;

(d) presenting advertisements by the computing system to the first member within the electronic interface at the social network site based on a correlation between keywords specified for the advertisements and the information for both the first items and/or topics and the at least selected subset of items and/or topics associated with the first member profile data.

2. The method of claim 1, wherein at least some of the advertisements are presented based on search results based on the user'"'"'s actions made in step (d) prior to a search query concerning content related to the first topics.

3. The method of claim 1, wherein the ratings data comprise at least a binary value.

4. The method of claim 1, wherein the ratings data further identify endorsement or inclination towards an item by the first member.

5. The method of claim 1, wherein additional implicit ratings are determined for the first member, wherein the implicit ratings are based on actions taken by the first member at the social network website.

6. The method of claim 1, wherein additional explicit ratings are determined for the first member, wherein the explicit ratings are based on actions or selections made by the first member at a separate website different from the social network website.

7. The method of claim 1, wherein the explicit ratings data include designations of one or more friends of the first member, wherein the one or more friends are also members of the social network.

8. The method of claim 1, wherein portions of content of the advertisements are derived from content provided by content sources rated by the first member.

9. The method of claim 1, wherein each of the items comprises an image, music file, video file, movie, restaurant, brand name, or article.

10. The method of claim 1, wherein the first member ratings data include content post ratings including ratings for particular non-human content sources.

11. The method of claim 1, wherein the explicit ratings including ratings made by the first member for previously viewed advertisements.

12. The method of claim 1, wherein the ratings data being further derived from content posted by the first member at a webpage.

13. The method of claim 1, wherein the ratings data being further derived from content reviewed by the first member within an ongoing data feed.

14. The method of claim 1, wherein the advertisements are presented along with recommendations generated by the recommendation system specifically for the first member, including content created or liked by other members designated as friends by the first member.

15. The method of claim 1, wherein the advertisements are presented and matched to items presented in a search result list provided in response to a query made by the first member.

16. The method of claim 1, wherein the advertisements are presented along with recommendations of social network members selected for the first member.

17. The method of claim 1, wherein the advertisements are presented to a self-selected group of members of the social network based on a common interest of group of members.

18. A method utilizing a computing system for presenting advertising content to a user at a social networking site, wherein the method comprises:

(a) processing content provided explicitly by a first member of a social network within an electronic interface at the social network website to identify first member interest data;

(b) processing first ratings data provided explicitly by the first member within the electronic interface at the social network website including;

i) ratings for content posted by other members of the social network;

ii) ratings for items endorsed by the first member;

iii) ratings for topics endorsed by the first member; and

iv) ratings for webpages endorsed by the first member;

(c)(1) using natural language classifier running on the computing system, mapping a first set of words and/or phrases in content provided explicitly by the first member and a second set of words or phrases associated with the content posted by the other members of the social network, wherein the ratings of the items, the topics, and the webpages indicate a high level of interest of the first member in one or more predefined concepts and/or topics;

(c)(2) predicting at least a selected subset of the one or more predefined concepts and/or topics that would be of interest to the first member using a recommendation system;

d) generating and storing first member profile data within the computing system based on the first member interest data and the first ratings data, the first member profile data including at least an indication of the at least selected subset of the one or more predefined concepts and/or topics; and

(e) presenting advertisements by the computing system to the first member within the electronic interface at the social network site based on a correlation between keywords for the advertisements and the at least selected subset of the one or more predefined concepts or topics of the first member profile data.