Adaptive pattern recognition based control system and method

• US 6,400,996 B1
• Filed: 02/01/1999
• Issued: 06/04/2002
• Est. Priority Date: 02/01/1999
• Status: Expired due to Term

• Current Assignee: Hoffberg Family Trust 2, Blanding Hovenweep LLC (Intellectual Ventures LLC), STEVEN M. HOFFBERG 2004-1 GRAT
• Original Assignee: Linda I. Hoffberg-Borghesani, Steven Mark Hoffberg
• Inventors: Hoffberg, Steven M., Hoffberg-Borghesani, Linda I.
• Primary Examiner(s): PATEL, RAMESH B
• Application Number:
  US09/241,135
• Time in Patent Office: 1,219 Days
• Field of Search: 700/17, 700/18, 700/19, 700/23, 700/24, 700/25, 700/83, 700/87, 700/86, 370/218, 370/219, 370/220, 370/355, 370/356, 704/318, 704/100, 704/101, 704/102, 704/227, 704/223, 704/224, 345/157, 345/810, 345/835, 345/840, 345/841, 345/741
• US Class Current: 700/83
• CPC Class Codes: G05B 19/0426 Programming the control sequence
• CPC Class Codes: G05B 2219/23021 Gesture programming, camera sees hand, displays it on screen, grasp buttons
• CPC Class Codes: G05B 2219/23026 Recognise user input pattern and present possible intended program
• CPC Class Codes: G06F 18/00 Pattern recognition
• CPC Class Codes: G06F 3/0481 based on specific properties of the displayed interaction object or a metaphor-based environment, e.g. interaction with desktop elements like windows or icons, or assisted by a cursor's changing behaviour or appearance
• CPC Class Codes: G06F 3/0482 Interaction with lists of selectable items, e.g. menus
• CPC Class Codes: G06V 40/103 Static body considered as a whole, e.g. static pedestrian or occupant recognition

Abstract

An adaptive interface for a programmable system, for predicting a desired user function, based on user history, as well as machine internal status and context. The apparatus receives an input from the user and other data. A predicted input is presented for confirmation by the user, and the predictive mechanism is updated based on this feedback. Also provided is a pattern recognition system for a multimedia device, wherein a user input is matched to a video stream on a conceptual basis, allowing inexact programming of a multimedia device. The system analyzes a data stream for correspondence with a data pattern for processing and storage. The data stream is subjected to adaptive pattern recognition to extract features of interest to provide a highly compressed representation that may be efficiently processed to determine correspondence. Applications of the interface and system include a video cassette recorder (VCR), medical device, vehicle control system, audio device, environmental control system, securities trading terminal, and smart house. The system optionally includes an actuator for effecting the environment of operation, allowing closed-loop feedback operation and automated learning.

Claims

1. An apparatus, comprising:

a logical input for receiving a control input and a user attribute relating to a human user;

a memory system, storing said control input and user attribute;

an input for receiving data from a data environment;

means for storing descriptive elements of said received data;

means for determining a preference of the user relating to said received data, based on said stored user attribute and said descriptive elements;

means for processing said received data in dependence on said control input, having an output; and

a data packet network controller adapted for processing received data packets of information addressed to said controller from a data packet network interface, and responding thereto in according to a predetermined protocol, at least one of said control input, said user attribute, said received data, said descriptive elements, said user preference, and said output being communicated through said data packet network interface.

2. The apparatus according to claim 1, wherein:

said apparatus comprises a terminal used by users of a program delivery system for suggesting programs to users;

said logical input comprises means for receiving user specific data to be used in selecting programs;

said memory system comprises means for storing the user specific data; and

said input for receiving data comprises means for receiving program control information containing the program description data in conjunction with program data.

3. The apparatus according to claim 2, wherein said program selection means comprises:

a processor, wherein user programming preferences are generated from the user specific data; and

means for suggesting the selected programs to the user.

4. The apparatus according to claim 1, further comprising a recorder for selectively recording data based on said output of said processing means.

5. The apparatus according to claim 1, further comprising an output generator, presenting information to said user in a menu format.

6. The apparatus according to claim 1, wherein said determining means employs artificial intelligence.

7. The apparatus according to claim 1, wherein said decriptive elements comprise a program guide generated remotely from the apparatus and transmitted in electronically accessible form.

8. The apparatus according to claim 1, wherein said descriptive elements comprise data defined by a human input.

9. The apparatus according to claim 1, wherein said descriptive elements comprise data defined by an automated analysis of said data.

10. The apparatus according to claim 1, wherein:

said user attribute is derived from a history of program delivery to the user data;

said means for determining a user preference comprising;

means for transforming the user history data into preferred program indicators, wherein a program indicator comprises a program category with each program category having a weighted value, said preferred program indicators being persistently stored in said memory system;

means for comparing the stored preferred program indicators with the descriptive elements, wherein each program is assigned a weighted value based on at least one associated program category;

means for prioritizing the programs from highest weighted value programs to lowest weighted value programs;

means for indicating one or more programs meeting a predetermined weight threshold and

means, operably connected to the program selection means, for displaying for suggestion the selected programs to the user.

11. The apparatus according to claim 1, further comprising:

a data selector, for selecting a program from a the data environment;

an encoder, for encoding programs in a digitally compressed format;

a mass storage system control, for storing and retrieving encoded programs;

a decoder, for decompressing retrieved encoded programs; and

an output, for outputting the decompressed programs.

12. A method, comprising the steps of:

receiving data describing an user attribute;

receiving a content data stream, and extracting from the content data stream information describing a plurality of program options;

processing the data describing a user attribute and the information describing a plurality of program options to determine a probable user preference; and

communicating at least one of said user attribute, said content data stream, and said user preference through a data packet network interface.

13. The method according to claim 12, wherein:

said method is used by a terminal for a program delivery system for suggesting programs to users using the program options and the user attribute;

said step of receiving a content data stream, comprises receiving both programs and program control information for selecting programs as the information describing a plurality of program options; and

further comprising the step of;

presenting the program or information describing a program option for the selected programs to the user.

14. The method according to claim 13, wherein said user attribute comprises a semantic description of a preference.

15. The method according to claim 14, wherein said data processing step comprises determining a semantic relationship of said user preference to the information describing a plurality of program options.

16. The method according to claim 13, wherein said information describing a plurality of program options comprises a program guide.

17. The method according to claim 13, wherein said data processing step employs artificial intelligence.

18. The method according to claim 13, wherein said user attribute comprises a demographic profile.

19. The method according to claim 13, wherein said user attribute comprises data relating to a history of use by the user.

20. The method according to claim 13, further comprising the step of transmitting a sequence of identifications to the user being based on a degree of correspondence between user attribute and the plurality of program options.

21. The method according to claim 13, further comprising the step of selectively recording an identified program.

22. The method according to claim 13, further comprising the step of adapting the determined likely user preference based on a response of the user.

23. An Internet appliance, comprising:

a data packet network interface;

a data packet network server, communicating data packets with said data packet network interface;

a logical input for receiving a control input and a user attribute relating to a human user;

a memory, storing said control input and user attribute;

a logical input for receiving data from a data environment;

means for analyzing said received data to extract descriptive elements thereof;

means for determining a preference of the user relating to said received data, based on said stored user attribute and said descriptive elements;

means for processing said received data in dependence on said control input, having an output; and

at least one of said control input, said user attribute, said received data, said descriptive elements, said user preference, and said output being communicated through said data packet network interface.

24. The Internet appliance according to claim 23, wherein said data packet network server comprises an embedded web server.

25. The Internet appliance according to claim 23, wherein said data packet network server adaptively generates a user interface based on said user attribute.