System for determining changes in the relative interest of subjects

• US 20050102267A1
• Filed: 12/17/2004
• Published: 05/12/2005
• Est. Priority Date: 07/20/1999
• Status: Active Grant

• Current Assignee: Thomson Reuters Enterprise Centre GmbH (The Woodbridge Co. Ltd.)
• Original Assignee: West Services
• Inventors: O'Reilly, Daniel F.X., Gasbarro, Pasco, Moss, John L.
• Granted Patent: US 7,809,738 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/951 Indexing; Web crawling techniques
• CPC Class Codes: G06F 16/953 Querying, e.g. by the use of web search engines
• CPC Class Codes: Y10S 707/99933 Query processing, i.e. searching
• CPC Class Codes: Y10S 707/99937 Sorting

Abstract

A system for determining changes in the interest of a subject over a time period. The system measures the volume of news articles for a subject over a time period and makes a comparison to a previous volume of news articles for the same subject over a previous time period.

Claims

1. A method for determining changes in the count of news articles related to a subject over a recent time period, the method comprising:

measuring a count of news articles for the subject over the recent time period;

comparing the count of news articles for the subject over the recent time period to a count of news articles for the subject for a previous time period; and

signaling when the comparison yields a difference greater than a predetermined amount.

2. The method of claim 1 further comprising storing in a database the count of news articles for the subject over the recent time period.

3. The method of claim 1 further comprising receiving news articles from at least one news source.

4. The method of claim 3 further comprising storing the news articles in a computer server.

5. The method of claim 1 wherein measuring the count of news articles further comprises querying the server.

6. The method of claim 5 wherein querying the server comprises the use of a pre-programmed query engine.

7. The method of claim 1 wherein the subjects comprise one or more from the group comprising company names, stock ticker symbols, people, products, and other topics of interest.

8. The method of claim 1 further comprising purging news articles stored in the computer server.

9. The method of claim 8 wherein the purging is conducted on the basis of the time period that the news articles were stored.

10. The method of claim 8 wherein purging is conducted on the basis of the subject matter of the news articles.

11. The method of claim 1 further comprising tagging the news articles by analyzing and coding the articles.

12. The method of claim 11 wherein the tagging is automated.

13. The method of claim 1 further comprising calculating a frequency of news articles for the subject over the recent time period from the count of news articles for the subject over the recent time period.

14. The method of claim 1 further comprising determining a reconfiguration factor for permitting comparisons of data collected with dissimilar numbers of news sources.

15. The method of claim 14 wherein determining the reconfiguration factor further comprises dividing the frequency of news articles for all subjects of a recent server configuration by the frequency of news articles for all subjects of a previous server configuration.

16. The method of claim 14 wherein determining the reconfiguration factor further comprises dividing the count of news articles for all subjects over the recent time period by the count of news articles for all subjects over at least one prior time period of equal duration.

17. The method of claim 1 further comprising analyzing previous counts for a period of seasonality.

18. The method of claim 17 further comprising storing the period of seasonality.

19. The method of claim 17 further comprising comparing the counts and frequencies of the recent time period to the counts and frequencies of the previous time period using the period of seasonality.

20. The method of claim 1 further comprising calculating a weighted average of the count of news articles of the recent time period and of the count of news articles of the previous time period.

21. The method of claim 20 wherein calculating the weighted average of the given time period includes finding the logarithmic values of the frequency of news articles related to the subject for a selected time period including the recent time period and for a previous time period not including the recent time period, and comparing the logarithmic values.

22. The method of claim 20 further comprising calculating the logarithmic value of a first time period including both the recent time period and a portion of the previous time period, and calculating the logarithmic value of a second time period including both the portion of the previous time period of the first time period and a previous period of equal duration to the recent period, and comparing the logarithmic values of the first and second time periods as rolling averages.

23. The method of claim 20 further comprising calculating the logarithmic value of a first time period including both the recent time period and a portion of the immediately previous time period, and calculating the logarithmic value of a second time period including both the portion of the immediately previous time period and a portion of the previous period of unequal duration to the recent period, and comparing the logarithmic values of the first and second time periods.

24. The method of claim 2 further comprising assessing the counts and frequencies stored in the database to construct historical statistics.

25. The method of claim 2 further comprising assessing the counts and frequencies stored in the database to construct forecast scenarios.

26. The method of claim 1 further comprising determining changes in the count of news articles related to multiple subjects over a given time period.

27. The method of claim 1 further comprising determining changes in interest of multiple subjects over multiple time periods.

28. A system for determining changes in the count of news articles related to a subject over a recent time period, the system comprising:

means for measuring a count of news articles for the subject over the recent time period;

means for comparing the count of news articles for the subject over the recent time period against a count of news articles for the subject for a previous time period; and

means for signaling when the comparison yields a difference greater than a predetermined amount.