METHOD FOR COMBINING VOICE SIGNALS TO FORM A CONTINUOUS CONVERSATION IN PERFORMING A VOICE SEARCH

• US 20140244686A1
• Filed: 03/15/2013
• Published: 08/28/2014
• Est. Priority Date: 02/22/2013
• Status: Active Grant

• Current Assignee: DIRECTV, LLC (AT&T, Inc.)
• Original Assignee: The DIRECTV Group, Inc. (AT&T, Inc.)
• Inventors: Tran, Huy Q., Chaudhry, Kapil, Lam, An T., Zarnev, Vlad, Kuriki, Douglas T., Tran, Todd T., Homan, David K., Yan, Michael E.
• Granted Patent: US 9,414,004 B2
• Time in Patent Office: Days
• US Class Current: 707/775
• CPC Class Codes: G06F 16/3325 Reformulation based on results of preceding query
• CPC Class Codes: G06F 16/3329 Natural language query formulation or dialogue systems
• CPC Class Codes: G06F 16/632 Query formulation
• CPC Class Codes: G06F 16/90332 Natural language query formulation or dialogue systems
• CPC Class Codes: G06F 3/0482 Interaction with lists of selectable items, e.g. menus
• CPC Class Codes: G06F 3/04842 Selection of displayed objects or displayed text elements G06F3/0482 takes precedence
• CPC Class Codes: G06F 3/0488 using a touch-screen or digitiser, e.g. input of commands through traced gestures
• CPC Class Codes: G06F 3/165 Management of the audio stream, e.g. setting of volume, audio stream path
• CPC Class Codes: G06F 3/167 Audio in a user interface, e.g. using voice commands for navigating, audio feedback
• CPC Class Codes: G06F 40/40 Processing or translation of natural language natural language analysis G06F40/20; semantic analysis G06F40/30
• CPC Class Codes: G08C 17/02 using a radio link
• CPC Class Codes: G08C 2201/31 Voice input
• CPC Class Codes: G10L 15/063 Training
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: G10L 15/30 Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
• CPC Class Codes: G10L 2015/0638 Interactive procedures
• CPC Class Codes: H04N 21/2221 being a cable television head-end CATV in broadcast systems H04H20/78
• CPC Class Codes: H04N 21/41265 having a remote control device for bidirectional communication between the remote control device and client device unidirectional remote control device H04N21/42204
• CPC Class Codes: H04N 21/4147 PVR [Personal Video Recorder] H04N5/76 takes precedence ; arrangements for broadcast with accumulation-type receivers H04H20/40
• CPC Class Codes: H04N 21/42203 : sound input device, e.g. microphone
• CPC Class Codes: H04N 21/42204 : User interfaces specially adapted for controlling a client device through a remote control device; Remote control devices therefor constructive details of casings for the remote control device H01H9/0235; user interfaces for controlling a tuning device of a television receiver through a remote control H03J9/00; remote control of peripheral devices connected to a television receiver through the remote control device of the television receiver H04B1/205
• CPC Class Codes: H04N 21/42209 : for displaying non-command information, e.g. electronic program guide [EPG], e-mail, messages or a second television channel
• CPC Class Codes: H04N 21/4222 : Remote control device emulator integrated into a non-television apparatus, e.g. a PDA, media center or smart toy remote control device for a television receiver integrated into a mobile phone H04M1/72415
• CPC Class Codes: H04N 21/42222 : Additional components integrated in the remote control device, e.g. timer, speaker, sensors for detecting position, direction or movement of the remote control, microphone or battery charging device
• CPC Class Codes: H04N 21/42224 : Touch pad or touch panel provided on the remote control
• CPC Class Codes: H04N 21/4334 : Recording operations recording of a television signal H04N5/76; arrangements for recording or accumulating broadcast information or broadcast-related information H04H60/27
• CPC Class Codes: H04N 21/4394 : involving operations for analysing the audio stream, e.g. detecting features or characteristics in audio streams arrangements characterised by components specially adapted for monitoring, identification or recognition of audio in broadcast systems H04H60/58
• CPC Class Codes: H04N 21/4398 : involving reformatting operations of audio signals details of audio signal transcoding G10L19/173
• CPC Class Codes: H04N 21/4415 : using biometric characteristics of the user, e.g. by voice recognition or fingerprint scanning cryptography using biological data H04L9/3231; authentication in networks using biometric H04L63/0861
• CPC Class Codes: H04N 21/4583 : Automatically resolving scheduling conflicts, e.g. when a recording by reservation has been programmed for two programs in the same time slot
• CPC Class Codes: H04N 21/47211 : for requesting pay-per-view content payment schemes payment architectures or payment protocols G06Q20/00, G07F
• CPC Class Codes: H04N 21/47214 : for content reservation or setting reminders; for requesting event notification, e.g. of sport results or stock market stock exchange data over packet-switching network H04L12/1804; push services over packet-switching network H04L12/1859; notification of incoming messages in packet switching networks H04L51/224
• CPC Class Codes: H04N 21/4722 : for requesting additional data associated with the content
• CPC Class Codes: H04N 21/475 : End-user interface for inputting end-user data, e.g. personal identification number [PIN], preference data
• CPC Class Codes: H04N 21/4753 : for user identification, e.g. by entering a PIN or password cryptographic authentication protocols H04L9/32; networks authentication protocols H04L63/08
• CPC Class Codes: H04N 21/4828 : for searching program descriptors retrieval of video data G06F16/739
• CPC Class Codes: H04N 21/4882 : for displaying messages, e.g. warnings, reminders arrangements for providing short real-time information to substation in data switching networks H04L12/1895
• CPC Class Codes: H04N 21/6143 : involving transmission via a satellite
• CPC Class Codes: H04N 21/6175 : involving transmission via Internet broadcast-related systems characterised by the transmission system being the Internet H04H60/82

Abstract

A system and method for operating the same includes a conversation manager that receives a receiving a first search request and, after receiving the first search request, receives a second search request. The system also includes a classifier module within the conversation manager classifying the first search request relative to the second search request as related or not related. A context merger module within the classifier module combines the first search request and the second search request to form a merged search request. A search module performs a second search based on the merged search request.

Claims

1. A method comprising:

receiving a first search request;

after receiving the first search request, receiving a second search request;

classifying the first search request relative to the second search request as related or not related;

when the first search request is related to the second search request in response to classifying, combining the first search request and the second search request to form a merged search request; and

performing a second search based on the merged search request.

2. The method as recited in claim 1 further comprising after receiving the first search request, performing a first search for content to obtain first search results.

3. The method as recited in claim 2 further comprising displaying the first search results on a display at a requesting device.

4. The method as recited in claim 2 further comprising displaying the first search results on a display at a mobile device.

5. The method as recited in claim 2 further comprising after the first search generating a first context object.

6. The method as recited in claim 5 wherein generating the first context object comprises generating the first context object from intent objects identified from the first search request.

7. The method as recited in claim 6 wherein the intent objects comprise at least one of media type, genre, channel, content rating, date, episode, title and team.

8. The method as recited in claim 5 further comprising generating a first context token from the context object.

9. The method as recited in claim 5 further comprising generating a first encrypted context token from the context object.

10. The method as recited in claim 9 further comprising communicating the first encrypted context token and the second search request to a conversation manager.

11. The method as recited in claim 10 further comprising decrypting the first encrypted context token in the conversation manager to form the context object having first intents therein and wherein the second search request comprises second intents.

12. The method as recited in claim 11 wherein classifying comprises classifying the first intents relative to the second intents.

13. The method as recited in claim 12 wherein combining the first search request and the second search request comprises combining the first intents and the second intents to form a second context object comprising the first intents and the second intents.

14. The method as recited in claim 12 further comprising when the first search is not related to the second search, generating a second context object including the second intents.

15. The method as recited in claim 12 wherein classifying the first search request and the second search request comprises classifying the first search request relative to the second search request using a support vector machine.

16. The method as recited in claim 12 further comprising adjusting classifying in response to a qualifier word in the second search request.

17. The method as recited in claim 16 wherein adjusting comprises adjusting classifying in response to a connector word in the second search request.

18. The method as recited in claim 16 wherein adjusting comprises adjusting classifying in response to a switching word in the second search request.

19. The method as recited in claim 16 wherein adjusting comprises adjusting classifying in response to a reference or key word in the second search request.

20. A system comprising:

conversation manager receiving a receiving a first search request and, after receiving the first search request, receiving a second search request;

a classifier module within the conversation manager classifying the first search request relative to the second search request as related or not related;

a context merger module within the classifier module combining the first search request and the second search request to form a merged search request; and

a search module performing a second search based on the merged search request.

21. The system as recited in claim 20 wherein the search module performs a first search for content to obtain first search results after receiving the first search request.

22. The system as recited in claim 21 further comprising a requesting device displaying the first search results on a display.

23. The system as recited in claim 21 further comprising a mobile device displaying the first search results on a display.

24. The system as recited in claim 21 further comprising a context object generator generating a first context object after the first search.

25. The system as recited in claim 24 wherein the context object generator comprises generating intent objects from the first search request.

26. The system as recited in claim 25 wherein the intent objects comprise at least one of media type, genre, channel, content rating, date, episode, title and team.

27. The system as recited in claim 24 further comprising a context token encoder generating a first context token from the context object.

28. The system as recited in claim 24 further comprising a context token encoder generating a first encrypted context token from the context object and a requesting device receiving the first encrypted context.

29. The system as recited in claim 28 wherein the requesting device communicates the first encrypted context token and the second search request to the conversation manager.

30. The system as recited in claim 29 further comprising a context token decoder decrypting the first encrypted context token to form the context object having first intents therein and wherein the second search request comprises second intents.

31. The system as recited in claim 30 wherein the classifier module classifies the first intents relative to the second intents.

32. The system as recited in claim 31 wherein the context merger module combines the first intents and the second intents to form the merged search request.

33. The system as recited in claim 31 wherein the context object generates a second context object having the second intents and not the first intents.

34. The system as recited in claim 31 wherein the classifier module comprises a support vector machine.

35. The system as recited in claim 31 wherein the classifier module adjusts classifying in response to a qualifier word in the second search request.

36. The system as recited in claim 31 wherein the classifier module adjusts classifying in response to a connector word in the second search request.

37. The system as recited in claim 31 wherein the classifier module adjusts classifying in response to a switching word in the second search request.

38. The system as recited in claim 31 wherein the classifier module adjusts classifying in response to a reference or key word in the second search request.