METHOD FOR PREDICTING NEWS CONTENT

• US 20130159116A1
• Filed: 02/14/2013
• Published: 06/20/2013
• Est. Priority Date: 08/14/2007
• Status: Active Grant

• Current Assignee: John N. Gross
• Original Assignee: John N. Gross
• Inventors: Gross, John Nicholas
• Granted Patent: US 8,775,406 B2
• Time in Patent Office: Days
• US Class Current: 705/14.71
• 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

A news and/or search engine system predicts events and stories based on existing events, stories, etc., extracted from a knowledge domain. These predictions can be used for a number of different purposes, including locating new content and actual event outcomes.

Claims

1. A method of predicting content of a news story with a computing system comprising:

a) identifying a first event described in first content published in a knowledge domain including one or more social network domains, news content domains, blog domains and/or message board domains;

b) automatically determining a plurality of different alternative predicted states for said first event, based on a comparison of characteristics of said first event to characteristics of prior events of a same type;

c) automatically generating queries to said knowledge domain and/or at least one search engine to locate published new content associated with said plurality of different predicted states;

d) presenting search results or news stories to a user with the computing system which includes at least some of said new published content when such is identified at step (c).

2. The method of claim 1 including a step:

automatically determining which of said plurality of different alternative predicted states has actually occurred with the computing system based on analyzing a substance of said new content.

3. The method of claim 2 wherein said determining is based on identifying predicted text and/or phrases relating to said plurality of different alternative predicted states in said new content.

4. The method of claim 1 wherein said comparison step (b) uses templates or patterns for said type of event which are derived from online published content describing said prior events.

5. The method of claim 1 including a step of generating a set of future sources to be consulted for said new content based on predicted changes in a state of said first event.

6. The method of claim 1 wherein step (c) is performed repeatedly after step (b) to identify a first instance of said published new content.

7. The method of claim 1 wherein step (c) is performed repeatedly at a target time specified as a completion time for said first event.

8. The method of claim 1 wherein queries in step (c) are adjusted automatically as a state of said first event progresses.

9. The method of claim 1 wherein the computing system in step (d) further presents a status update for said first event in a social network page for said user.

10. The method of claim 1 wherein a set of sources for said knowledge domain and a frequency of polling can be specified for steps (c) and/or (d).

11. The method of claim 1 further including a step of presenting advertising within said interface based on a temporal sequence identified for said user in reviewing search results for said first topic news content.

12. The method of claim 1 further including a step of conducting an advertising auction which employs pricing for advertisements presented with said search results based on a temporal sequence identified for said user in reviewing said search results for said first topic news content.

13. The method of claim 1 further including a step of presenting advertising within said interface based on an expected mental state of said user predicted based on a state of an event identified in said first topic news content.

14. The method of claim 1 further including a step of conducting an advertising auction which employs pricing for advertisements presented with said search results based on a prediction of an expected time for said user to complete reviewing said search results.

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

adjusting an advertising auction pricing for keywords based on a prediction of content associated with said plurality of different alternative predicted states.

16. The method of claim 1 wherein said results at step (d) are presented as part of search results in response to a query made by the user for said first event.

17. The method of claim 1, further including a step of computing semantic variants and temporal derivatives of said first content and storing such for future evaluations of documents containing said new content.

18. A method of predicting content of a future unpublished news story with a computing system comprising:

a) identifying a first event described in content published in a knowledge domain including one or more social network domains, news content domains, blog domains and/or message board domains;

b) automatically predicting future content for a plurality of different alternative future unpublished stories for said first event or updates to said first event, based on a comparison of characteristics of said first event to characteristics of prior events of a same type;

wherein said future content is derived from content of prior stories describing said prior events.

19. The method of claim 18 wherein said future content is presented as part of search results in response to a query made by the user for said first event.

20. The method of claim 18 further including a step:

automatically searching for said future content by querying at least one of a social network, message board, blog and/or search engine.

21. The method of claim 18 further including a step:

automatically searching for a numerical outcome associated with said first event by querying at least one of a social network, message board, blog and/or search engine.

22. A method of determining with a computing system an outcome of an event described in a news story comprising:

a) identifying a first event described in content published in a knowledge domain including one or more social network domains, news content domains, blog domains and/or message board domains;

b) automatically determining a plurality of different alternative predicted states for said first event, based on a comparison of characteristics of said first event to characteristics of prior events of a same type;

c) automatically generating queries to said knowledge domain and/or at least one search engine to locate published new content associated with said plurality of different predicted states;

d) automatically determining with the computing system which of said plurality of different alternative predicted states is an actual outcome which has occurred based on analyzing a substance of said new content;

e) presenting said actual outcome as part of a news story and/or a search engine result.

23. The method of claim 22 wherein said first event includes a numerical score or value correlated to a state of said first event, which numerical score or value includes a template that is used to analyze a temporal order of said new content.

24. The method of claim 22 further including a step:

verifying said actual outcome before step (e).

25. The method of claim 24 further including a step of consulting a set of content sources associated with a high reputation or trust score at step (d) for identifying said actual outcome.

26. The method of claim 22 further including a step:

adjusting an advertising auction pricing for keywords based on a prediction of content associated with said plurality of different alternative predicted states.

27. The method of claim 22 further including a step of presenting advertising with said news story and/or search engine result, which advertising includes content correlated to said actual outcome.