Method and system for identifying a party answering a telephone call based on simultaneous activity

• US 20050276390A1
• Filed: 06/10/2004
• Published: 12/15/2005
• Est. Priority Date: 06/10/2004
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Varolii Corporation (Microsoft Corporation)
• Inventors: Sikora, Scott Edward, Munguia, Rudolfo Xavier, Bishara, Michael Jason, Selig, William John
• Granted Patent: US 7,184,521 B2
• Time in Patent Office: Days
• US Class Current: 379/80
• CPC Class Codes: H04M 1/65 Recording arrangements for recording a message from the calling party in the exchange H04M3/50
• CPC Class Codes: H04M 2203/2027 Live party detection
• CPC Class Codes: H04M 3/493 Interactive information services, e.g. directory enquiries ; Arrangements therefor, e.g. interactive voice response [IVR] systems or voice portals
• CPC Class Codes: H04M 3/5158 in combination with automated outdialling systems devices for signalling identity of wanted subscriber H04M1/26

Abstract

A method and system for identifying whether a communicating party is a person or an automated device is provided. The identification system determines whether a person or an automated device is currently providing audio of the communication. When the identification is to be determined, the identification system outputs an audio signal to the party. The identification system monitors the input audio signal from the party to determine whether a person or an automated device is providing the input audio. The identification system makes this determination based on whether there is simultaneous sound on the input audio signal and the output audio signal. The greater the amount of simultaneous sound, the greater the likelihood that the party is an automated device.

Claims

1. A method for detecting whether an automated device is currently providing audio on a telephone call, the method comprising:

outputting an audio signal to the telephone call;

inputting an audio signal from the telephone call;

determining an amount of time during which the input audio signal and output audio signal are both active; and

when the determined amount exceeds a threshold amount, indicating that an automated device is providing the audio.

2. The method of claim 1 wherein when the determined amount does not exceed the threshold amount, indicating that a person is providing the audio.

3. The method of claim 1 wherein the automated device provides a recorded voice as the audio.

4. The method of claim 1 wherein the input audio signal is active when a human audible sound is being represented.

5. The method of claim 1 wherein the detecting occurs over an identification interval and the determining occurs at evaluation intervals within the identification interval.

6. The method of claim 5 wherein when the determined amount of time during which the input audio signal and output audio signal are both active cannot exceed the threshold amount, indicating that an automated device is not providing the audio.

7. The method of claim 5 wherein when the determined amount of time during which the input audio signal and output audio signal are both active cannot exceed the threshold amount, indicating that a person is providing the audio.

8. The method of claim 1 wherein the input audio signal is filtered to remove spikes.

9. The method of claim 1 wherein the determining applies a hysteresis effect to the input audio signal.

10. The method of claim 1 wherein the output audio signal is sampled to determine when the output audio signal is active.

11. The method of claim 1 including receiving an indication of when the output audio signal is active without having to sample the output audio signal.

12. The method of claim 1 including when it is indicated that an automated device is providing audio, performing recognition of the input audio signal.

13. The method of claim 12 wherein the recognized input audio signal is used to determine whether a telephone number has changed.

14. The method of claim 12 wherein the recognized input audio signal is used to determine whether a party other than an intended party has provided the audio signal of the automated device.

15. The method of claim 1 including when the telephone call is terminated by the called party, identifying the time of termination so that it can be correlated with what was currently being output on the output audio signal.

16. The method of claim 1 including using different thresholds for residential and business telephones.

17. An automated method for detecting whether a recorded voice or a live voice is currently providing audio of a telephone call, the method comprising:

outputting an audio signal to the telephone call;

inputting an audio signal from the telephone call; and

determining whether a recorded voice or a live voice is providing the audio of the telephone call based on amount of overlap of sound on the output audio signal and input audio signal.

18. The method of claim 17 wherein the amount of overlap represents times during which sound is simultaneously on the input audio signal and output audio signal.

19. The method of claim 17 wherein when the amount of overlap exceeds a threshold amount, indicating that a recorded voice is providing the audio.

20. The method of claim 17 wherein when the amount of overlap does not exceed the threshold amount, indicating that a live voice is providing the audio.

21. The method of claim 17 wherein the overlap is weighted differently depending on timing of the overlap.

22. The method of claim 17 wherein the detecting occurs over an identification interval and the determining occurs at evaluation intervals within the identification interval.

23. The method of claim 22 wherein when the amount of overlap cannot exceed a threshold amount based on amount of overlap possible during the identification interval, indicating that a live voice is providing the audio.

24. The method of claim 17 wherein the input audio signal is filtered to remove spikes.

25. The method of claim 17 wherein the determining applies a hysteresis effect to the input audio signal.

26. The method of claim 17 wherein the output audio signal is sampled to determine when the output audio signal represents sound.

27. The method of claim 17 including receiving an indication of when the output audio signal represents sound without having to sample the output audio signal.

28. The method of claim 17 including when it is detected that a recorded voice is providing the audio, performing recognition of the input audio signal.

29. The method of claim 17 including:

when it is determined that a live voice is providing the audio, placing another telephone call to an agent; and

when that other telephone call answers, connecting the telephone calls so that the agent can talk to a person providing the live voice.

30. The method of claim 29 wherein the connecting is via a Two-B Channel Transfer.

31. The method of claim 29 wherein the telephone calls are not connected through a device that placed the telephone calls.

32. The method of claim 17 including when the telephone call is terminated by a person providing the live voice, identifying the time of termination so that it can be correlated with what was currently being output on the output audio signal.

33. The method of claim 17 including using different overlap thresholds indicating whether the audio is being provided by a live voice or a recorded voice for residential and business telephones.

34. The method of claim 17 wherein a live voice is detected as a result of a person who stops speaking upon hearing the output audio signal.

35. A system for identifying a party answering a telephone call, comprising:

a telephone line having an input line and an output line;

a first component that monitors the input line to detect when the telephone call has been answered and, when answered, outputs an audio signal to the output line; and

a second component that monitors the input line to determine when sound is simultaneously being input on the input line and output on the output line, the amount of simultaneity indicating whether a person or an automated device has answered the telephone call.

36. The system of claim 35 wherein the first component is a voice response unit and the second component is a call progress activity unit.

37. The system of claim 35 wherein the telephone line is connected to both the first component and the second component.

38. The system of claim 35 wherein the second component monitors the output line to determine when sound is being output.

39. The system of claim 35 wherein when the determined amount of simultaneity exceeds a threshold, indicating that an automated device has answered the telephone call.

40. The system of claim 39 wherein when the determined amount of simultaneity does not exceed the threshold, indicating that a person has answered the telephone call.

41. The system of claim 39 wherein the simultaneity contributes differently to exceeding the threshold depending on timing.

42. The system of claim 35 wherein the identifying occurs over an identification interval and the determining occurs at evaluation intervals within the identification interval.

43. The system of claim 42 wherein when the determined amount of simultaneity cannot exceed a threshold based on amount of simultaneity possible during the identification interval, indicating that a person has answered the telephone call.

44. The system of claim 35 wherein when it is determined that a person has answered the telephone call, the first component places another telephone call and, when that other call answers, connects the telephone calls.

45. The system of claim 44 wherein the connection is via a Two-B Channel Transfer.

46. The system of claim 44 wherein the telephone calls are not connected through the telephone line.