Temporal based online search and advertising

• US 10,698,886 B2
• Filed: 08/14/2008
• Issued: 06/30/2020
• Est. Priority Date: 08/14/2007
• Status: Active Grant

• Current Assignee: John Nicholas and Kristin Gross Trust U/A/D April 13 2010
• Original Assignee: John Nicholas and Kristin Gross Trust U/A/D
• Inventors: Gross, John Nicholas
• Primary Examiner(s): Mamillapalli, Pavan
• Application Number:
  US12/191,999
• Publication Number:
  US 20090048928A1
• Time in Patent Office: 4,338 Days
• Field of Search: 707725, 707787
• CPC Class Codes: G06F 16/24 Querying
• CPC Class Codes: G06F 16/24578 using ranking
• CPC Class Codes: G06F 16/95 Retrieval from the web
• CPC Class Codes: G06F 16/951 Indexing; Web crawling techniques
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06F 16/9536 Search customisation based on social or collaborative filtering
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06Q 30/00 Commerce
• CPC Class Codes: G06Q 30/0243 Comparative campaigns
• CPC Class Codes: G06Q 30/0251 Targeted advertisements

Abstract

Advertising and search is performed using temporal parameters of stories, events, topics and electronic documents. The contents of a document relating to an event/topic is analyzed to identify temporal components. These components can be compared with corresponding counterparts in other documents to identify a relative temporal order, and to help drive an advertising engine or search engine.

Claims

1. A method of presenting advertising with an online computing system comprising:

a) [i] identifying an electronic document being reviewed by a user within an interface, said electronic document referencing a first event;

[ii] identifying content in said electronic document with the computing system representing at least one first subject and a related first subject status for said first event;

wherein said first subject is assigned to a plurality of subject status values associated with said first event;

b) processing said electronic document with the computing system to determine temporal characteristics of such document including by determining which of said plurality of assigned subject status values is represented by said first related subject status identified for said first subject; and

wherein said temporal characteristics are not any of a creation time alone, a publication time alone, or a combination of a creation time and a publication time alone;

c) presenting advertising with the computing system based at least in part on said temporal characteristics of such document including said first subject status value determined for said first event.

2. The method of claim 1 wherein advertising is presented to said user based on a predicted first subject status determined for said first event.

3. The method of claim 1 wherein advertising is presented to said user based on a temporal sequence identified for said electronic document, which temporal sequence identifies a temporal rank for said electronic document relative to other documents containing content for said first subject and related first subject status previously reviewed by said user.

4. The method of claim 1 wherein said steps are implemented as one or more computer software routines stored in a tangible media and adapted to cause one or more computing systems to perform the operations recited therein.

5. The method of claim 1 wherein an auction for presenting said advertising is based in part on said temporal characteristics of such documents.

6. The method of claim 5, wherein a keyword value is altered in accordance with said temporal characteristics.

7. The method of claim 1 wherein said advertising is configured to have a variable cost which varies in accordance with a current value of said related first subject status.

8. The method of claim 1 wherein said advertising is configured to have a variable cost which varies in accordance with a predicted reviewing time for said user.

9. The method of claim 1 wherein said plurality of

subject status values represent a plurality of sequential corresponding temporal periods.

10. The method of claim 1 including a step:

wherein

advertising is presented to the user based on a current subject status value determined by the computing system, which current subject status value differs from said first subject status value identified in said electronic document.

11. The method of claim 1 further including a step:

presenting advertising with the computing system based on a prediction of a user'"'"'s mental state to reviewing said first subject status identified for said first event.

12. The method of claim 1 wherein said related first

subject status is assigned to a distinct temporal period or distinct outcome for said first event.

13. The method of claim 1 wherein said plurality of

subject status values are derived from an event template generated by the computing system for prior events determined to be similar to said first event.

14. A method of presenting advertising in response to a search query with an online computing system comprising:

a) receiving a search query from a user;

wherein said search query includes keywords correlated to a first event, said first event being associated by the computing system with one or more outcome states;

b) generating a set of search results, including a set of electronic documents, which are responsive to the search query with the online computing system;

c) [i] processing said set of electronic documents with the computing system to determine temporal characteristics of such documents with respect to said first event, including any outcome state identified in content therein;

wherein said temporal characteristics include content characteristics associated with said electronic document but that are not any of a creation time alone, a publication time alone, or a combination of a creation time and a publication time alone;

[ii] ranking said set of electronic documents and presenting selected ones to the user with the computing system which contain content for a most current outcome state of said one or more outcome states;

d) presenting advertising with the computing system based at least in part on said temporal characteristics of such documents including said most current outcome state identified for said first event.

15. The method of claim 14 wherein an auction by the computing system for presenting said advertising is based in part on matching said keywords to said one or more outcome states.

16. The method of claim 15, wherein a keyword value is altered by the computing system in accordance with said temporal characteristics.

17. The method of claim 14 wherein said advertising is configured by the computing system to have a variable cost which varies in accordance with an identified outcome state identified in one or more documents presented in said search results, or reviewed by a query presenter.

18. The method of claim 14 wherein said advertising is configured by the computing system to have a variable cost which varies in accordance with a predicted reviewing time for a user presenting said query.

19. The method of claim 14 wherein advertising is presented with the computing system to a user presenting said search query based on a predicted outcome state identified for said first event and related to said query and/or said search results.

20. The method of claim 14, wherein said temporal characteristics include but are not limited to a time relationship between word phrases describing said one or more outcome states for said event.

21. The method of claim 14, further including a step:

collecting bids from advertisers to be associated with keyword describing said temporal characteristics.

22. The method of claim 14 wherein said steps are implemented as one or more computer software routines stored in a tangible media and adapted to cause one or more computing systems to perform the operations recited therein.

23. A method of presenting advertising within a news aggregator using an online computing system comprising:

a) identifying a first news story being reviewed by a user within an interface for a website;

wherein said first news story includes keywords correlated by the computing system to a first event, said first event being associated by the computing system with one or more event states;

b) processing said first news story with the computing system to determine temporal characteristics of such story with respect to said first event including any first event state identified in content therein;

wherein said temporal characteristics include characteristics associated with said electronic document but that are not any of a creation time alone, a publication time alone, or a combination of a creation time and a publication time alone;

c) predicting said user'"'"'s expected review time of stories within said website for said first event with the computing system, based on identifying said first event state in said first news story and subsequent event states associated with said first event identified in other news stories not reviewed yet by said first user;

d) adjusting one of at least an advertising auction or an advertising presentation with the computing system based at least in part on the results of steps (b) and/or (c).

24. The method of claim 23 wherein said steps are implemented as one or more computer software routines stored in a tangible media and adapted to cause one or more computing systems to perform the operations recited therein.

25. A method of presenting advertising within a news aggregator using an online computing system comprising:

a) [i] assigning a plurality of predetermined potential outcome event states to a first event with the computing system;

[ii] identifying a news story for the first event being reviewed by a user within an interface;

b) processing said news story to determine temporal characteristics of such story with respect to said first event with the computing system, including determining an event state identified in such news story for such first event;

wherein said temporal characteristics include characteristics associated with said news story but that are not any of a creation time alone, a publication time alone, or a combination of a creation time and a publication time alone;

c) predicting changes in temporal characteristics of said news story with respect to, said first event with the computing system, including a predicted change from said identified event state to a related one of the plurality of predetermined potential outcome event states;

d) adjusting one of at least an advertising auction or an advertising presentation with the computing system based at least in part on the results of steps (b) and/or (c).

26. The method of claim 25 wherein said steps are implemented as one or more computer software routines stored in a tangible media and adapted to cause one or more computing systems to perform the operations recited therein.

27. The method of claim 25 further including a step:

performing a verification check in one or more separate online domains to confirm an existence of said related one of the plurality of predetermined potential outcome event states for said first event.

28. The method of claim 25 further including a step:

generating said predetermined potential outcome event states for said first event by processing a corpus of documents to calculate a causal relationship and progression of related event states.

29. A method of presenting advertising within a search page using an online computing system comprising:

a) assigning a plurality of predetermined potential outcome event states to a first event with the computing system;

b) receiving a query from a user for a news story for the first event;

c) processing said news story to determine temporal characteristics of such story with respect to said first event with the computing system, including determining an event state identified in such news story for such first event;

wherein said temporal characteristics include characteristics associated with said news story but that are not any of a creation time alone, a publication time alone, or a combination of a creation time and a publication time alone;

e) matching said determined event state in said news story for the first event to a selected one of said plurality of predetermined outcome event states;

d) presenting advertising to the user in response to the query with the computing system with one or more advertisements correlated to said selected one of said plurality of predetermined outcome states.

30. The method of claim 29 including a step:

wherein

advertising is presented to the user based on a current event state determined by the computing system, which current event state differs from said determined event state identified in said news story.

31. The method of claim 29 further including a step:

presenting advertising with the computing system based on a prediction of a user'"'"'s mental state to reviewing said determined event state for said first event.

32. The method of claim 29 wherein said determined

event state in said news story is assigned to a distinct temporal period for said first event.

33. The method of claim 29 wherein said plurality of

predetermined event states are derived from an event template generated by the computing system for prior events determined to be similar to said first event.