Advanced quality management and recording solutions for walk-in environments

• US 20050015286A1
• Filed: 04/26/2004
• Published: 01/20/2005
• Est. Priority Date: 09/06/2001
• Status: Active Grant

• Current Assignee: Nice Ltd
• Original Assignee: Nice Systems Limited (Nice Ltd)
• Inventors: Goldenberg, Yoel, Freedman, Ilan, Rudnik, Eyal
• Granted Patent: US 7,728,870 B2
• Time in Patent Office: Days
• US Class Current: 705/7
• CPC Class Codes: H04N 5/765 Interface circuits between an apparatus for recording and another apparatus
• CPC Class Codes: H04N 5/9201 involving the multiplexing of an additional signal and the video signal

Abstract

A system and method for capturing, logging and retrieval of face-to-face interactions characterizing walk-in environments. The system comprising a device for capturing and storing one or more face to face interactions captured in the presence of the parties to the interaction, and a database for storing data and metadata information associated with the face-to-face interactions captured.

Claims

1. An apparatus for capturing, storing and retrieving face-to-face interactions in walk-in environments for the purpose of further analysis, the apparatus comprising:

a device for capturing and storing at least one face to face interaction captured in the presence of the parties to the interaction; and

a database for storing data and metadata information associated with the face-to-face interaction captured.

2. The apparatus of claim 1 wherein the device for capturing the at least one interaction comprises the elements of:

at least one microphone for obtaining interaction audio and for generating signals representative of the interaction audio and for relaying the signals representative of the interaction audio to a telephone line;

a device connected between the at least one microphone and the telephone line for gain and impedance matching and for detecting an on-hook state and an off-hook state of a telephone handset associated with the telephone line; and

a voice capture and storage unit connected to the telephone line for capturing voice represented by the analog signals and for storing the captured voice.

3. The apparatus of claim 2 wherein the voice capture and storage unit further comprises a voice operated switch for minimizing interference when no interaction recording is taking place and for triggering energy-driven voice recording.

4. The apparatus of claim 2 further comprises:

a digital unit connected between the microphone and the telephone line for converting analog signals representative of the interaction audio to digital signals and for transmitting the converted digital signals to the telephone line in a pre-defined time slot when an associated telephone handset is in on-hook state, and for discarding the converted digital signals or mixing the converted digital signals with digital signals from the telephone handset when the associated telephone handset is in off-hook state.

5. The apparatus of claim 1 wherein the device for capturing and storing comprises:

an at least one camera having pan-tilt-zoom adjustment actuators and controlled by a camera selector mechanism and linked to an on-line pant-tilt-zoom adjustment control mechanism, installed in pre-defined locations configured to provide visual covering of an at least one physical service location holding a potentially recordable interaction;

a list of an at least one physical service location associated with the at least one camera; and

a camera selector mechanism for determining the status of the at least one camera and for selecting an at least one camera to cover the at least one physical service location.

6. The apparatus of claim 5 further comprising an at least one pan-tilt-zoom parameter associated with the at least one physical service location for providing an at least one pan-tilt-zoom adjustment parameter value.

7. The apparatus of claim 6 wherein the pan-tilt-zoom parameter comprises the spatial definition of the at least one physical service location.

8. The apparatus of claim 6 wherein the pan-tilt-zoom adjustment parameter comprises the movement required to change the camera'"'"'s position, tilt or pan to allow capture of the at least one physical service location.

9. The apparatus of claim 5 wherein the camera selector de-assigns the at least one camera from the at least one physical service location.

10. The apparatus of claim 5 further comprising an at least one microphone for detecting audio signals at least one physical service location holding a potentially recordable interaction.

11. The apparatus of claim 10 wherein based on an analysis of the audio signals captured by the at least one microphone the camera selector assigns or de-assigns the at least one camera from the at least one physical service location.

12. The apparatus of claim 1 wherein the device for capturing and storing comprises a frequency division multiplexing unit for receiving signals representing interaction data from an least one interaction input device and for multiplexing the input signals and for transmitting the multiplexed signals to a capture and storage unit.

13. The apparatus of claim 12 further comprises a computing device having at least one input channel for receiving interaction video from an at least one camera and for relaying the interaction video from the at least one camera to a processor unit.

14. The apparatus of claim 12 further comprises a computing device having at least one input channel for receiving interaction video from an at least one camera and for relaying the interaction video from the at least one cameras to a processor unit.

15. The apparatus of claim 12 further comprises an at least one voice sampler data device associated with an at least one interaction participant for identifying the at least one interaction participant by comparing the captured voice of the at least one participant with the at least one voice sampler data.

16. The apparatus of claim 12 further comprises a volume detector device located at an interaction location and for detecting the presence of an interaction participant and the absence of an interaction participant.

17. The apparatus of claim 9 wherein detecting the presence or the absence of an interaction participant provides interaction beginning determination and interaction termination determination.

18. The apparatus of claim 1 wherein the device for capturing and storing comprises an audio content analyzer applied to a recording plurality of interactions for segmenting the recording plurality of interactions into separate at least one interaction or segment.

19. The apparatus of claim 18 wherein the audio content analyzer identifies at least one verbal phrase or word characteristic to the beginning portion of an interaction or segment, said verbal phrase or word is defined as the beginning of the interaction or segment.

20. The apparatus of claim 18 wherein the audio content analyzer identifies at least one verbal phrase or word characteristic to the ending portion of an interaction or segment, said verbal phrase or word is defined as the termination point of the interaction or segment.

21. The apparatus of claim 1 wherein the device for capturing and storing comprises:

an audio content analyzer applied to a recording of an interaction for identifying the interaction participants;

an audio processing unit connected to the interaction input device for generating a digital representation of the voices of the interaction participants; and

an audio filtering unit applied to the recording of the interaction for eliminating the ambient noise from the interaction recording.

22. The apparatus of claim 1 wherein the device for capturing and storing comprises:

a first audio input device associated with a customer service representative for capturing a first interaction audio data generated during a face-to-face interaction;

a second audio input device associated with a customer for capturing a second interaction audio data generated during a face-to-face interaction; and

a computing device for receiving the interaction audio data captured by the first and second audio input devices, and for identifying the interaction participants by comparing the first and second interaction audio data generated during a face-to-face interaction with previously stored audio files.

23. The apparatus of claim 22 wherein the computing device further comprises an audio processor for generating a representation for the audio relayed from the first and second audio input devices to be compared with previous audio files representative of the audio files generated previously by the participants.

24. The apparatus of claim 1 wherein the device for capturing and storing comprises:

at least one camera installed at an interaction location having pan-tilt-zoom movement capabilities and linked to a pan-tilt-zoom adjustment controller for providing visual covering of the interaction area and for locating an object in the interaction location space and for tracking an object in the interaction location space; and

an at least one microphone installed at the interaction location for audio covering of the interaction area.

25. The apparatus of claim 24 further comprises an at least one microphones installed at the interaction location for cooperatively providing audio covering for the interaction location area.

26. The apparatus of claim 24 wherein at least one camera installed at an interaction location are connected to an object location and microphone controller unit for directing said cameras to a predetermined service location.

27. The apparatus of claim 26 wherein the object location and microphone controller unit comprises a visual object locator and movement monitor for locating an object within the service location and for tracking said object within the service location and for controlling the capture of audio and video of an interaction associated with said object.

28. The apparatus of claim 26 wherein the object location and microphone controller unit comprises a service location file, a camera location file and a microphone location file.

29. The apparatus of claim 26 wherein the object location and microphone controller unit comprises a camera controller for controlling said cameras, a microphone controller for controlling said microphone, and a microphone selector to select a microphone located adjacent or within the service location.

30. A method for metadata gathering in walk-in environments, the method comprising:

determining the beginning and ending of an interaction associated with a face-to-face interaction; and

generating and storing data or metadata information associated with the face-to-face interaction captured.

31. The method of claim 30 further comprises the steps of:

obtaining interaction audio by an at least one microphone;

generating signals representing the interaction audio;

feeding the signals representing the interaction audio to a telephone line;

detecting an on-hook state and an off-hook state of a telephone handset associated with the telephone line by an active unit installed between the at least one microphone and the telephone line; and

relaying the signals from the active unit through the telephone line to a voice capture and storage unit.

32. The method of claim 30 wherein the voice capturing and voice storage is triggered by a voice operated switch associated with the voice capturing and storage unit.

33. The method of claim 30 further comprises the steps of:

converting the analog signals representing interaction audio to digital signals by a digital unit connected between the at least one microphone and the telephone line;

transmitting the converted digital signals to the telephone line in a pre-defined time slot;

when the telephone handset associated with the telephone line in an on-hook state.

34. The method of claim 33 further comprises the step of discarding the converted digital signals or mixing the converted digital signals with digital signals from the telephone handset when the telephone handset associated with the telephone line is in an off-hook state.

35. The method of claim 30 further comprises the steps of:

obtaining a list of physical service positions associated with an at least one camera;

selecting an at least one not in use and not out of order camera for the required record-on-demand task;

loading pan-tilt-zoom parameters pertaining to the physical service position; and

re-directing the spatially the view of the camera to the physical service position by the operation of the pan-tilt-zoom adjustment actuators.

36. The method of claim 35 further comprises the steps of:

locating and selecting an in-use camera suitable for the performance of the recording-on-demand; and

re-directing the view of the located camera toward the required physical service position through the operation of the pan-tilt-zoom actuators.

37. The method of claim 30 further comprises the steps of:

relaying signals representing interaction data from an at least one interaction input device to a frequency division multiplexing unit; and

multiplexing the signals representing interaction data into a combined signal wherein signals associated with a specific interaction input device are characterized by being modulated into a pre-defined frequency band.

38. The method of claim 37 further comprises the step of relaying signals representing interaction video from at least one camera via at least one input channel into a processing unit.

39. The method of claim 30 further comprises the steps of:

searching a pre-recorded voice sample bank for the presence of a pre-recorded voice sample matching the interaction participant voice sample;

matching the pre-recorded voice sample to the interaction participant voice sample; and

obtaining the details of the interaction participant associated with the pre-recorded voice sample.

40. The method of claim 39 further comprises the step of sampling interaction audio obtained by at least one microphone to obtain an interaction participant voice sample.

41. The method of claim 39 wherein the voice sample bank is generated dynamically during the performance of an interaction consequent to the extraction of interaction audio associated with the interaction participant and by the integration of interaction participant-specific customer relationship management information.

42. The method of claim 30 further comprises the steps of:

detecting the presence and the absence of an interaction participant at a service location; and

submitting a command to begin an interaction recording in accordance with the presence or absence of the interaction participant.

43. The method of claim 30 further comprises the steps of:

receiving a captured stream of interaction audio;

identifying verbal phrases or words where the phrases and the words are characterized by the location thereof in the beginning portion of an interaction;

identifying verbal phrases or words where the phrases and the words are characterized by the location thereof in the terminating portion of an interaction;

segmenting the recorded stream of the interaction audio into distinct separate identifiable interactions based on the characteristics of the identified verbal phrases.

44. The method of claim 30 further comprises the step of:

identifying an interaction participant by determining who is the customer service representative from a previously provided voice file and the customer as the non-customer service representation or from the content of the interaction;

generating a digital representation of the voice of the interaction participant; and

eliminating ambient noise from the interaction recording consequent to the selective separation of the identified interaction participant voice.

45. The method claim 30 further comprises the steps of:

locating an object in an interaction location space by an at least one camera;

tracking the located object in the interaction location space by the at least one camera; and

generating microphone activation commands for an at least one microphone based on the tracked object location data provided by the at least one camera.