ADAPTIVE PATTERN RECOGNITION BASED CONTROLLER APPARATUS AND METHOD AND HUMAN-FACTORED INTERFACE THEREORE

• US 20120017232A1
• Filed: 09/23/2011
• Published: 01/19/2012
• Est. Priority Date: 12/23/1991
• Status: Active Grant

• Current Assignee: Linda Irene Hoffberg, Steven Mark Hoffberg
• Original Assignee: Linda Irene Hoffberg, Steven Mark Hoffberg
• Inventors: Hoffberg, Linda Irene, Hoffberg, Steven M.
• Granted Patent: US 8,352,400 B2
• Time in Patent Office: Days
• US Class Current: 725/13
• CPC Class Codes: F24F 11/30 for purposes related to the operation of the system, e.g. for safety or monitoring
• CPC Class Codes: F24F 11/62 characterised by the type of control or by internal processing, e.g. using fuzzy logic, adaptive control or estimation of values
• CPC Class Codes: F24F 2120/10 Occupancy
• CPC Class Codes: G05B 2219/2642 Domotique, domestic, home control, automation, smart house
• CPC Class Codes: G06F 7/023 adaptive, e.g. self learning
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 5/048 Fuzzy inferencing
• CPC Class Codes: G06N 7/06 Simulation on general purpose computers

Abstract

A system and method of predicting items likely to appeal to a user, based on data received from a remote site. One or more local systems are provided, along with a remote system, said local systems communicating with said remote system over a network connection. Each local system maintains a set of characterized items. A local processor predicts an appeal of an item to a user based on the comparison with the set of characterized items with, e.g., user preferences. The user may interact through graphical user interface. At least one user-preference predictive algorithm may be employed to present items predicted to appeal to the user.

Claims

1. A distributed system for predicting items likely to appeal to a user, based on data received from a remote site, comprising:

a plurality of local systems;

a remote system, said local systems communicating with said remote system over a network connection;

each local system maintaining a set of characterized items; and

a local processor for predicting an appeal for an item based on the comparison with the set of characterized items.

2. The system of claim 1, wherein said items comprise items of media content.

3. The system of claim 2, wherein said items comprise any of network television is programming, cable television programming, films, pay-per-view television programming and video.

4. The system of claim 1, said system being a component of a network-based video recording system.

5. A method of predicting items of media content most likely to appeal to a user and presenting said predictions in a graphical user interface, wherein said predictions are based on expressed user preferences, comprising:

providing an interactive user interface for receiving user preference information;

predicting a user appeal of an item of media content according to at least one user-preference predictive algorithm; and

displaying items predicted to appeal to the user in said graphical user interface.

6. The method of claim 5, further comprising the steps of providing a content-based adaptive modeling algorithm for describing the media content.

7. The method of claim 5, further comprising the step of evaluating features of the media content.

8. The method of claim 5, further comprising employing Bayesian logic to predict the appeal of media content to a user.

9. The method of claim 5, wherein said media content comprises at least one type of programming selected from the group consisting of network television programming, cable television programming, network television programming, pay-per-view television programming, movies and public-access television programming.

10. The method of claim 5, wherein preferences are expressed explicitly by the user.

11. The method of claim 5, wherein preferences are expressed implicitly by the user.

12. The method of claim 5, wherein preferences are expressed as a set of distinct factors relating to said media content.

13. The method of claim 5, wherein said at least one predictive algorithm comprises a plurality of predictive algorithms, a result of a respective predictive algorithm being selectively employed to provide a prediction.

14. The method of claim 5, wherein at least one predictive algorithm is based on an analysis of a pattern of user behavior over a course of time through experience of a plurality of media content.

15. The method of claim 5, wherein at least one predictive algorithm allows the user to provide feedback relating to at least one media program.

16. The method of claim 5, wherein at least one predictive algorithm allows the user to provide feedback relating to at least prediction.

17. The method of claim 5, wherein at least one predictive algorithm employs Bayesian logic.

18. A method for selecting content most likely to appeal to a user, wherein said selections represent predictions based on user preferences and context, comprising:

providing an interactive user interface configured to define a context, and to receive preference information from a user based on the interaction;

predicting an appeal of an item of content to a user based on at least one user-preference predictive algorithm; and

presenting context-appropriate items predicted to appeal to the user in said interactive user interface.

19. The method according to claim 18, wherein the content comprises multimedia, the preference information is received at least implicitly, and the context-appropriate items comprise a plurality of ranked items selected based on said predicting and the context.

20. The method according to claim 18, wherein said presenting comprises forming a markup language object, the further comprising receiving a selection of a presented context-appropriate item by the user as an activation of a hyperlink to the selected item, and retrieving the selected item.