Systems and Methods for Human Intelligence Personal Assistance

• US 20110191681A1
• Filed: 02/02/2011
• Published: 08/04/2011
• Est. Priority Date: 02/02/2010
• Status: Abandoned Application

• Current Assignee: 4D Retail Technology Corp.
• Original Assignee: 4D Retail Technology Corp.
• Inventors: Stark, Dean
• Application Number:
  US13/019,974
• Publication Number:
  US 20110191681A1
• Time in Patent Office: Days
• US Class Current: 715/716
• CPC Class Codes: G06Q 10/10 Office automation; Time management
• CPC Class Codes: G06Q 30/01 Customer relationship services
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising

Abstract

A human intelligence personal assistance system and method is disclosed. A user interacts with an audio and video image of a person. Inputs from the user request performance of one or more tasks including passive requests activated by mere motion detection. Thus the user may actively request tasks such as email review or passively trigger tasks such as sales assistance. Depending upon the complexity of the task, either a human operator or a computer may assist the user. The audio and video image communicates with the user in synchronization with downloaded results.

Claims

1. A computer-implemented method for human intelligence personal assistance, comprising:

presenting a moving video image to a user;

receiving, via a computing device, an input from the user requesting an execution of at least one task;

determining whether the execution should be performed by zero or more operators in conjunction with zero or more computers wherein there is at least one operator or at least one computer;

performing, via a finding of the determining, the execution producing results; and

outputting to the user the results wherein the results are conveyed to the user in synchronization with the moving video image.

2. The computer-implemented method of claim 1, wherein the performing the at least one task comprises:

breaking down the at least one task into at least one piece for an implementation;

concluding whether the implementation should be performed by zero or more operators in conjunction with zero or more computers wherein there is at least one operator or at least one computer;

performing, via a decision of the concluding, the implementation; and

re-joining an outcome of the performing the implementation back into the results.

3. The computer-implemented method of claim 1, wherein the moving video image is an image of a human, the results comprise audio output, and the synchronization comprises synchronization of the audio output with a lip movement of the image of the human.

4. The computer-implemented method of claim 1, wherein the moving video image is computer generated.

5. The computer-implemented method of claim 1, wherein the input comprises at least one selected from the group consisting of motion detection, voice, video, keyboard, touchscreen, mouse, and stylus.

6. The computer-implemented method of claim 1, wherein the one or more computers are networked with zero or more additional computers.

7. The computer-implemented method of claim 1, wherein the one or more computers are in communication with a server.

8. The computer-implemented method of claim 1, wherein the performing comprises generating one or more of the group consisting of voice to text, text to voice, text to text, voice to voice, video to video, translation of the input, translation of the results, computer to computer text, computer to computer voice, and computer to computer video.

9. The computer-implemented method of claim 1, wherein the computing device performs at least one of parsing the input and filtering the input.

10. A computer-implemented human intelligence personal assistance system, comprising:

a display configured to present a moving video image to a user,

a computing device configured to receive an input from the user requesting an execution of at least one task;

means for determining whether the execution should be performed by zero or more operators in conjunction with zero or more computers wherein there is at least one operator or at least one computer;

means for performing, via a finding of the determining, the execution producing results; and

means for outputting to the user the results wherein the results are conveyed to the user in synchronization with the moving video image.

11. The computer-implemented system of claim 10, wherein the means for performing the at least one task comprises:

means for breaking down the at least one task into at least one piece for an implementation;

means for concluding whether the implementation should be performed by zero or more operators in conjunction with zero or more computers wherein there is at least one operator or at least one computer;

means for performing, via a decision of the concluding, the implementation; and

means for re-joining an outcome of the performing the implementation back into the results.

12. The computer-implemented system of claim 10, wherein the moving video image is an image of a human, the results comprise audio output, and the synchronization comprises synchronization of the audio output with a lip movement of the image of the human.

13. The computer-implemented system of claim 10, wherein the moving video image is computer generated.

14. The computer-implemented system of claim 10, wherein the input comprises at least one member selected from the group consisting of motion detection, voice, video, keyboard, touchscreen, mouse, and stylus.

15. The computer-implemented system of claim 10, wherein the one or more computers are networked with zero or more additional computers.

16. The computer-implemented system of claim 10, wherein the one or more computers are in communication with a server.

17. The computer-implemented system of claim 10, wherein the means for performing comprises means for generating one or more members of the group consisting of voice to text, text to voice, text to text, voice to voice, video to video, translation of the input, translation of the results, computer to computer text, computer to computer voice, and computer to computer video.

18. The computer-implemented system of claim 10, wherein the computing device is configured to perform at least one of parsing the input and filtering the input.