Reviewing call checkpoints in agent call recording in a contact center

• US 10,194,027 B1
• Filed: 04/17/2017
• Issued: 01/29/2019
• Est. Priority Date: 02/26/2015
• Status: Active Grant

• Current Assignee: Alvaria Cayman
• Original Assignee: Noble Systems Corporation
• Inventors: Daddi, Rajesh S., Koster, Karl H.
• Primary Examiner(s): Patel, Hemant S
• Application Number:
  US15/488,586
• Time in Patent Office: 652 Days
• Field of Search: 37926501-2661
• CPC Class Codes: H04M 2201/40 using speech recognition speech recognition per se G10L15/00
• CPC Class Codes: H04M 2203/303 Marking
• CPC Class Codes: H04M 2203/305 Recording playback features, e.g. increased speed
• CPC Class Codes: H04M 3/42221 Conversation recording systems at the subscriber's set H04M1/656
• CPC Class Codes: H04M 3/5175 Call or contact centers supervision arrangements

Abstract

A speech analytics system detects speech during a call involving a contact center agent and a remote party. Upon detecting the speech, an event message is generated by the speech analytic system and transmitted to a checkpoint and alert reporting module, which is configured to generate and update a checkpoint widget displayed to the agent. The checkpoint widget provides visual information regarding the status of the checkpoints encountered during the call. Checkpoint widgets may be stored for each call handled by an agent, and subsequently may be requested for display to a supervisor for reviewing of the agent'"'"'s performance. Upon providing appropriate filter information, the selected widgets may be displayed using a time-line. By selecting a particular checkpoint indicator on a widget, audio from the call associated with that checkpoint is retrieved and streamed to the supervisor, thus allowing auditory review of that portion of the call.

Claims

1. A system for displaying information related to detection of keywords during a call involving an agent and a remote party, the system comprising:

a workstation comprising a computer display; and

a speech analytics sub-system configured to;

detect a first keyword in speech of the call, wherein the first keyword is associated with a first checkpoint of the call;

determine a second keyword was not detected in the speech of the call, wherein the second keyword is associated with a second checkpoint of the call;

receive an input from the workstation selecting the call from among a plurality of calls involving the agent; and

cause a time-line of the call to be displayed on the computer display,

wherein the time-line comprises a plurality of checkpoint widgets associated with the call including the first checkpoint widget and the second checkpoint widget,

wherein a first status indicator of the first checkpoint widget displayed on the time-line reflects the first keyword was detected in the speech of the call, and

a second status indicator of the second checkpoint widget displayed on the time-line reflects the second keyword was not detected in the speech of the call.

2. The system of claim 1, wherein the speech analytics sub-system is further configured to:

store timing information as to when the first keyword was detected in the speech of the call;

receive a second request from the workstation identifying one of the plurality of checkpoint widgets of the call, wherein the second request requests playback of audio associated with the call; and

cause a portion of the audio of the call based on the timing information associated with the one of the plurality of checkpoint widgets of the call to be played by the workstation over an audio interface of the workstation in response to receiving the second request.

3. The system of claim 2, wherein the second request comprises a selection of the one of the plurality of checkpoint widgets by a user using a pointing device.

4. The system of claim 1, wherein the speech analytics sub-system is further configured to:

cause the workstation to display a name of the agent associated with the call along with the time-line of the call.

5. The system of claim 1, wherein the speech analytics sub-system is further configured to:

cause the workstation to display a plurality of time-lines involving the agent including the time-line.

6. The system of claim 1, wherein the second status indicator reflecting the second keyword was not detected in the speech of the call comprises a different color than the first status indicator reflecting the first keyword was detected in the speech of the call.

7. The system of claim 1, wherein the speech analytics sub-system is configured to detect the first keyword in the speech of the call by processing a call recording of the call.

8. A method for displaying information on a computer to a user related to detection of keywords during a call involving an agent of a contact center and a remote party, the method comprising:

detecting a first keyword in speech of the call by a speech analytics sub-system, wherein the first keyword is associated with a first checkpoint of the call;

determining a second keyword was not detected in the speech of the call by the speech analytics sub-system, wherein the second keyword is associated with a second checkpoint of the call; and

displaying on the computer a time-line of the call based on information from the speech analytics sub-system,

wherein the time-line of the call further comprises a plurality of checkpoint widgets associated with the call including the first checkpoint widget and the second checkpoint widget,

wherein a first status indicator of the first checkpoint widget displayed on the time-line reflects the first keyword was detected in the speech of the call, and

a second status indicator of the second checkpoint widget displayed on the time-line reflects the second keyword was not detected in the speech of the call.

9. The method of claim 8, further comprising:

receiving a second request at the speech analytics sub-system identifying one of the plurality of checkpoint widgets of the call, wherein the second request requests playback of audio associated with the call; and

cause a portion of the audio of the call associated with the identified one of the plurality of checkpoint widgets of the call to be played by the computer over an audio interface of the computer.

10. The method of claim 8, further comprising:

displaying on the computer a name of the agent associated with the call along with the time-line of the call.

11. The method of claim 8, further comprising:

displaying a plurality of time-lines corresponding to a plurality of calls on the computer involving the agent along with the time-line of the call.

12. The method of claim 9, wherein the second request comprises a selection of the one of the plurality of checkpoint widgets by a user using a pointing device.

13. The method of claim 8, wherein the second status indicator reflecting the second keyword was not detected in the speech of the call comprises a different color than the first status indicator reflecting the first keyword was detected in the speech of the call.

14. The method of claim 8, wherein the first status indicator of the first checkpoint widget displayed on the time-line reflects the first keyword was detected in the speech of the agent of the call.

15. The method of claim 8, wherein the plurality of checkpoint widgets are displayed in conjunction with associated text representing corresponding keywords associated with the corresponding checkpoint widget.

16. The method of claim 15, wherein detecting the first keyword in the speech of the call by the speech analytics sub-system comprises detecting the first keyword in the speech of a call recording of the call.

17. A method for displaying information on a computer to a user related to detection of keywords during a call involving an agent of a contact center and a remote party, the method comprising:

displaying a time-line of the call, wherein the call is associated with a call recording,

wherein the time-line of the call further comprises a plurality of checkpoint widgets associated with the call including the first checkpoint widget and the second checkpoint widget,

wherein each of the plurality of checkpoint widgets is displayed with text reflecting a corresponding keyword associated with each of the plurality of checkpoint widgets,

wherein a first status indicator of the first checkpoint widget displayed on the time-line reflects the first keyword was detected in the speech of the call, and

a second status indicator of the second checkpoint widget displayed on the time-line reflects the second keyword was not detected in the speech of the call.

18. The method of claim 17, further comprising:

receiving a selection from the user at the computer selecting the first checkpoint widget;

retrieving a portion of the call recording; and

causing the computer to play the portion of the call recording associated with the first checkpoint widget to the user in response to receiving the selection.

20. The method of claim 17, further comprising:

displaying a plurality of time-lines associated with a plurality of calls associated with the agent.

19. The method of 18, further comprising:

displaying a plurality of control icons to the user;

receiving an input from the user selecting a control icon from among the plurality of control icons to play the call recording; and

causing the computer to play the portion of the call in response to receiving the input.