System and methods for creating and evaluating content and predicting responses to content

• US 20030055759A1
• Filed: 06/05/2002
• Published: 03/20/2003
• Est. Priority Date: 01/13/2000
• Status: Active Grant

• Current Assignee: Apple Inc.
• Original Assignee: Erinmedia
• Inventors: Vinson, Michael J., Foster, Frank S. IV, Conkwright, G. Colby
• Granted Patent: US 7,383,243 B2
• Time in Patent Office: Days
• US Class Current: 705/35
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 30/0201 Market modelling; Market analysis; Collecting market data
• CPC Class Codes: G06Q 30/0204 Market segmentation
• CPC Class Codes: G06Q 30/0205 Location or geographical consideration
• CPC Class Codes: G06Q 30/0242 Determining effectiveness of advertisements
• CPC Class Codes: G06Q 30/0254 based on statistics
• CPC Class Codes: G06Q 30/0255 based on user history
• 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 30/0277 Online advertisement
• CPC Class Codes: G06Q 40/00 Finance; Insurance; Tax strategies; Processing of corporate or income taxes
• CPC Class Codes: Y10S 707/99931 Database or file accessing

Abstract

A method of creating new content based on previously experienced content and content ratings, in which content attributes are obtained and analyzed against set-top box events collected as the content is experienced. Analysis includes determining effects of various content attributes on content ratings, content attribute order on content ratings, and determining a preferred content attribute set and content attribute presentation order. Also taught is a system and method of predicting future events given a proposed dataset, in which past events are monitored and correlated with a proposed dataset sharing at least one attribute with, and having a substantially similar structure to, the past events, and the results of the correlation are reported as a prediction of future events. The invention further includes a method of predicting behaviors of non-sampled demographic specifications based on sampled demographic specifications of a given level, in which past behavior is monitored and correlated with demographic characteristics.

Claims

1. A method of creating new content based on previously experienced content and content ratings, comprising:

obtaining content attributes from embedded content information or from external sources;

recording set-top box events as content is experienced;

correlating set-top box events to content attributes; and

,

analyzing such correlations over time to determine the effect of content attributes on content ratings.

2. The content creation method of claim 1, further comprising:

analyzing the effect of content attribute order on content ratings.

3. The content creation method of claim 1, further comprising:

determining a preferred content attribute set and content attribute presentation order.

4. The method of claim 1 in which the content attributes include times at which various content attributes are presented to a set-top box.

5. The method of claim 1 in which the set-top box events are recorded in a privacy compliant manner.

6. A method of creating new content based on previously experienced content and content ratings, comprising:

obtaining content attributes from embedded content information or from external sources, including times at which various content attributes are presented to a set-top box;

recording set-top box events as content is experienced;

correlating set-top box events to content attributes;

analyzing such correlations over time to determine the effect of content attributes on content ratings;

analyzing the effect of content attribute order on content ratings; and

determining a preferred content attribute set and content attribute presentation order.

7. The method of claim 6 in which the set-top box events are recorded in a privacy compliant manner.

8. A method of creating new content based on previously experienced content and content ratings, where such new content is directed toward a demographic group, comprising:

obtaining content attributes from embedded content information or from external sources;

recording set-top box events as content is experienced;

correlating set-top box events to content attributes;

correlating set-top box events and content attributes to demographic characteristics;

analyzing such correlations over time to determine the effect of content attributes on content ratings for a given demographic group;

analyzing the effect of content attribute order on content ratings for a given demographic group; and

determining a preferred content attribute set and content attribute presentation order for a given demographic group.

9. The method of claim 8, in which the set-top box events are recorded in a privacy-compliant manner.

10. A system for predicting future events based on a proposed dataset, consisting of:

a dataset of past events;

a known dataset sharing at least one attribute with the dataset of past events, and with substantially similar attributes to the proposed dataset;

a means of correlating the dataset of past events with the known dataset to form a new dataset; and

,

a means of correlating the new dataset to the proposed dataset.

11. The system of claim 10, where the dataset of past events consists of set-top box event data.

12. The system of claim 11, in which the data collected in the past event dataset is collected in a privacy compliant manner.

13. The system of claim 11, in which the known dataset consists of sales figures.

14. The system of claim 11, where the known dataset consists of content attributes and content presentation data.

15. The system of claim 14, where the proposed dataset consists of a set of content attributes for proposed content.

16. A method of predicting future events given a proposed dataset, comprising:

monitoring past events;

correlating the past events with a dataset sharing at least one attribute with the past events, and with a substantially similar structure to the proposed dataset, the results of such are stored in an array;

correlating the array with the proposed dataset; and

reporting the results of the array/proposed dataset correlations as a prediction of future events.

17. The method of claim 16, in which the past events include set-top box events.

18. The method of claim 16, in which the past events are collected in a privacy compliant manner.

19. The method of claim 17, in which the proposed dataset substantially consists of proposed content attributes.

20. The method of claim 19, in which the dataset includes previously presented content attributes.

21. The method of claim 20, in which the dataset consists of sales figures.

22. A system of predicting future events for a given demographic segment, comprising:

a dataset of past events;

a demographic dataset sharing at least one attribute with the dataset of past events;

a means of correlating the dataset of past events with the demographic dataset and storing the result in an array;

a known dataset sharing at least one attribute with the demographic dataset, and with substantially similar attributes to the proposed dataset;

a means of correlating the array with the known dataset to form a new dataset; and

,

a means of correlating the new dataset to a proposed dataset.

23. The system of claim 22 in which the past events are collected in a privacy compliant manner.

24. The system of claim 22 in which the dataset of past events corresponds to set-top box data.

25. The system of claim 22 in which the demographic dataset shares a zip code or other geographic identifier with the set-top box data.

26. The system of claim 22 in which the known dataset shares a zip code or other geographic identifier with the array.

27. The system of claim 22 in which the proposed dataset is comprised of proposed content and attributes corresponding thereto.

28. A system of predicting future events for a given demographic segment, comprising:

a dataset of past set-top box events, collected in a privacy compliant manner;

a demographic dataset sharing at least one attribute with the dataset of past set-top box events, such as a zip code or other geographic identifier;

a means of correlating the dataset of past events with the demographic dataset and storing the result in an array;

a known dataset sharing at least one attribute, such as a zip code or other geographic identifier, with the demographic dataset and with substantially similar attributes to the proposed dataset;

a means of correlating the array with the known dataset to form a new dataset; and

,

a means of correlating the new dataset with a proposed dataset comprised of proposed content and attributes corresponding thereto.

29. A method of predicting future events for a given demographic based on a proposed dataset, comprising:

monitoring past events;

correlating the past events with a demographic dataset and storing the result in an array;

correlating the array with a dataset sharing at least one attribute with the array, and with a substantially similar structure to the proposed dataset, the results of such are stored in an additional dataset;

correlating the additional dataset with the proposed dataset; and

reporting the results of such correlations as a prediction of future events.

30. The method of claim 29, in which the past events are monitored in a privacy compliant manner.

31. The method of claim 29, in which the past events include set-top box events.

32. The method of claim 31, in which the demographic dataset and the set-top box event dataset both contain zip code attributes.

33. The method of claim 29, in which the proposed dataset substantially comprising proposed content attributes.

34. The method of claim 29, in which the past events include attributes of any content being experienced at the time of an event.

35. A method of predicting future events for a given demographic based on a proposed dataset, comprising:

monitoring past events, including set-top box events, a zip code associated with a set-top box, and attributes of content presented by the set-top box at the time the event occurs, in a privacy compliant manner;

correlating the past events with a demographic dataset which includes at least one zip code, and storing the result in an array;

correlating the array with a dataset sharing at least one attribute with the array, and with a substantially similar structure to the proposed dataset, the results of such are stored in an additional dataset;

correlating the additional dataset with a proposed dataset, substantially comprised of proposed content attributes; and

reporting the results of such correlations as a prediction of future events.

36. A method of predicting behaviors of non-sampled demographic specifications based on sampled demographic specifications of a given level comprising:

monitoring past behavior and correlating the behavior with demographic characteristics monitored;

breaking a non-sampled demographic specification into sub-specifications for which sample data has been collected;

establishing the statistical effects of various rules on each sub-specification and those characterizations comprising them; and

statistically predicting non-sample behaviors based on such effects.

37. The method claim 36, further comprising:

observing correlations between behaviors of sampled demographic specifications or sub-specifications and behaviors of non-sampled demographic specifications; and

,

inferring behaviors of the non-sampled demographic specifications from such correlations, such that predicted or observed sampled demographic specification behaviors may be reported as non-sampled demographic specification behaviors within a determinable level of accuracy.