Method and apparatus for recording/replaying application execution with recorded voice recognition utterances
View Patent ↗A diagnostic tool for speech recognition applications is provided, which enables a administrator to collect multiple recorded speech sessions. The administrator can then search for various failure points common to one or more of the recorded sessions in order to get a list of all sessions that have the same failure points. The invention allows the administrator to playback the session or replay any portion of the session to see the flow of the application and the recorded utterances. The invention provides the administrator with information about how to maximize the efficiency of the application which enables the administrator to edit the application to avoid future failure points.
1. A method of increasing an efficiency of a speech recognition application comprising:
receiving, by a speech recognition application, a call identification (CallID) associated with a respective one of a plurality of sessions;
recording, on a storage device: said session of the plurality of sessions, and the CallID of said session;
shutting off a recording of said session during time when confidential information is expected to be received;
detecting, by the speech recognition application, an event, wherein the event comprises a communication failure of one session of said plurality of sessions;
determining, by the speech recognition application, that a quantity of detected events that share a common attribute exceeds a predetermined threshold;
grouping said recorded sessions determined to have said common attribute; and
providing access to at least two of said grouped recorded sessions for review.
2. A method according to claim 1 , wherein a recorded session includes an application flow and a recorded utterance.
3. A method according to claim 2 wherein the recorded utterance is muted during a confidential session.
4. A method according to claim 1 , further including playing back said recorded session, wherein playing back said recorded session includes displaying the application flow as said application executes.
5. A method according to claim 4 , wherein playing back said recorded session further includes displaying at least one recorded prompt.
6. A method according to claim 4 further comprising:
determining a cause for speech sessions containing said common attribute; and editing the application to remove the cause of said attribute.
7. A method according to claim 1 wherein said common attribute is a rejection.
8. A method according to claim 1 wherein said common attribute is an opt-out of the application.
9. A method according to claim 8 wherein said opt-out was a result of no-speech.
10. A method according to claim 1 , wherein said recording is performed with a wire tap.
11. A method according to claim 1 , further including:
receiving a request to perform a self-analysis; and
in response to the request to perform a self-analysis:
recording multiple sessions; and
searching the recorded sessions for inputs that exceed a predetermined criterion.
12. A method of increasing an efficiency of a speech recognition application comprising:
receiving, by a speech recognition application, a call identification (CallID) associated with a respective one of a plurality of sessions that contain a common attribute;
recording, on a storage device: said session of the plurality of sessions, and the CallID of said session;
shutting off a recording of said session during time when confidential information is expected to be received;
detecting, by the speech recognition application, an event, wherein the event comprises a communication failure of one session of said plurality of sessions;
determining, by the speech recognition application, that a quantity of detected events that share a common attribute exceeds a predetermined threshold;
grouping said recorded sessions determined to have said common attribute; and
providing access to at least two of said grouped recorded sessions for review.
13. A method according to claim 12 , wherein a recorded session includes an application flow and a recorded utterance.
14. A method according to claim 13 wherein the recorded utterance is muted during a confidential session.
15. A method according to claim 12 , further including playing back said recorded session, wherein playing back said recorded session includes displaying the application flow as said application executes.
16. A method according to claim 15 , wherein playing back said recorded session further includes displaying at least one recorded prompt.
17. A method according to claim 15 further comprising:
determining a cause for speech sessions containing said common attribute; and
editing the application to remove the cause of said attribute.
18. A method according to claim 12 wherein said common attribute is a rejection.
19. A method according to claim 12 wherein said common attribute is an opt-out of the application.
20. A method according to claim 19 wherein said opt-out was a result of no-speech.
21. A method according to claim 12 , wherein said recording is performed with a wire tap.
22. A method according to claim 12 , further including:
receiving a request to perform a self-analysis; and
in response to the request to perform a self-analysis:
recording multiple sessions; and
searching the recorded sessions for inputs that exceed a predetermined criterion.
23. A diagnostic tool to increase an efficiency of a speech recognition application comprising:
receiving means for receiving a call identification (CallID) associated with a respective one of a plurality of sessions;
recording means for recording, on a storage device:
said session of the plurality of sessions, and the CallID of said session;
control means for shutting off a recording of said session during time when confidential information is expected to be received;
detecting means for detecting an event, wherein the event comprises a communication failure of one session of said plurality of sessions;
determining means for determining that a quantity of detected events that share a common attribute exceeds a predetermined threshold, wherein the common attribute comprises a communication failure indicator of the recorded sessions;
grouping means in communication with the diagnostic means for grouping said recorded sessions determined to have said common attribute; and
access means in communication with the grouping means for providing access to at least two of said grouped recorded sessions for review.
24. A diagnostic tool according to claim 23 , wherein a recorded session includes an application flow and a recorded utterance.
25. A diagnostic tool according to claim 24 wherein the recorded utterance is muted during a confidential session.
26. A diagnostic tool according to claim 23 , further including a means for playing back said recorded session, wherein playing back said recorded session includes a display means for displaying the application flow as said application executes.
27. A diagnostic tool according to claim 26 , wherein playing back said recorded session further includes a display means for displaying at least one recorded prompt.
28. A diagnostic tool according to claim 23 wherein said common attribute is a rejection.
29. A diagnostic tool according to claim 23 wherein said common attribute is an opt-out of the application.
30. A diagnostic tool according to claim 29 wherein said opt-out was a result of no-speech.
31. A diagnostic tool according to claim 23 , wherein said recording means includes a wire tap.
32. A diagnostic tool according to claim 23 further comprising: diagnostic means for determining a cause for speech sessions containing said common attribute; and editing means for editing the application to remove the cause of said attribute.
33. A diagnostic tool according to claim 23 , further including:
receiving means for receiving a request to perform a self-analysis; and recording means for recording multiple sessions in response to the request to perform a self-analysis; and
searching means for searching the recorded sessions for inputs that exceed a predetermined criterion.
34. A diagnostic tool to increase an efficiency of a speech recognition application comprising:
receiving means for receiving a call identification (CallID) associated with a respective one of a plurality of sessions that contain a common attribute;
recording means for recording, on a storage device:
said session of the plurality of sessions, and the CallID of said session;
control means for shutting off a recording of said session during time when confidential information is expected to be received;
detecting means for detecting an event, wherein the event comprises a communication failure of one session of said plurality of sessions;
determining means for determining that a quantity of detected events that share a common attribute exceeds a predetermined threshold, wherein the common attribute comprises a communication failure indicator of the recorded sessions;
grouping means in communication with the diagnostic means for grouping said recorded sessions determined to have said common attribute; and
access means in communication with the grouping means for providing access to at least two of said grouped recorded sessions for review.
35. A diagnostic tool according to claim 34 , wherein a recorded session includes an application flow and a recorded utterance.
36. A diagnostic tool according to claim 35 wherein the recorded utterance is muted during a confidential session.
37. A diagnostic tool according to claim 34 , further including a means for playing back said recorded session, wherein playing back said recorded session includes a display means for displaying the application flow as said application executes.
38. A diagnostic tool according to claim 37 , wherein playing back said recorded session further includes a display means for displaying at least one recorded prompt.
39. A diagnostic tool according to claim 34 wherein said common attribute is a rejection.
40. A diagnostic tool according to claim 34 wherein said common attribute is an opt-out of the application.
41. A diagnostic tool according to claim 40 wherein said opt-out was a result of no-speech.
42. A diagnostic tool according to claim 34 , wherein said recording means includes a wire tap.
43. A diagnostic tool according to claim 34 further comprising:
diagnostic means for determining a cause for speech sessions containing said common attribute; and editing means for editing the application to remove the cause of said attribute.
44. A diagnostic tool according to claim 34 , further including:
receiving means for receiving a request to perform a self-analysis; and
recording means for recording multiple sessions in response to the request to perform a self-analysis; and
searching means for searching the recorded sessions for inputs that exceed a predetermined criterion.
45. A diagnostic tool to increase an efficiency of a speech recognition application comprising:
receiving module for receiving a call identification (CallID) associated with a respective one of a plurality of sessions;
recording module for recording, on a storage device: said session of the plurality of sessions, and the CallID of said session;
control module for shutting off a recording of said session during time when confidential information is expected to be received;
detecting module for detecting an event, wherein the event comprises a communication failure of one session of said plurality of sessions;
determining module for determining that a quantity of detected events that share a common attribute exceeds a predetermined threshold, wherein the common attribute comprises a communication failure indicator of the recorded sessions;
grouping module in communication with the diagnostic module for grouping said recorded sessions determined to have said common attribute; and
access module in communication with the grouping module for providing access to at least two of said grouped recorded sessions for review.
46. A diagnostic tool according to claim 45 , further including a module for playing back said recorded session, wherein playing back said recorded session includes a display module for displaying the application flow as said application executes.
47. A diagnostic tool according to claim 46 , wherein playing back said recorded session further includes a display module for displaying at least one recorded prompt.
48. A diagnostic tool according to claim 45 wherein said common attribute is a rejection.
49. A diagnostic tool according to claim 45 wherein said common attribute is an opt-out of the application.
50. A diagnostic tool according to claim 45 wherein said opt-out was a result of no-speech.
51. A diagnostic tool according to claim 45 , wherein said recording module includes a wire tap.
52. A diagnostic tool according to claim 45 further comprising: diagnostic module for determining a cause for speech sessions containing said common attribute; and editing module for editing the application to remove the cause of said attribute.
53. A diagnostic tool according to claim 45 , further including: a receiver to receive a request to perform a self-analysis; and
a recorder in communication with the receiver to record multiple sessions in response to the request to perform a self-analysis; and
a processor to access the recorded multiple sessions, the processor configured to search the recorded sessions for inputs that exceed a predetermined criterion.