Reviewing call checkpoints in agent call recordings in a contact center

• US 9,674,358 B1
• Filed: 09/02/2015
• Issued: 06/06/2017
• Est. Priority Date: 12/17/2014
• Status: Active Grant

• Current Assignee: Alvaria Cayman
• Original Assignee: Noble Systems Corporation
• Inventors: Daddi, Rajesh S., Koster, Karl H.
• Primary Examiner(s): Patel, Hemant
• Application Number:
  US14/842,884
• Time in Patent Office: 643 Days
• Field of Search: 348 1401- 1416, 370259-271, 370351-357, 379 671- 8828, 37920101, 37920201-20701, 37926501-2661, 704270-278, 709201-207, 709217-248
• CPC Class Codes: G06Q 10/06398 Performance of employee with respect to a job function
• CPC Class Codes: H04M 2203/402 Agent or workforce management
• CPC Class Codes: H04M 3/2218 Call detail recording
• CPC Class Codes: H04M 3/42221 Conversation recording systems at the subscriber's set H04M1/656
• CPC Class Codes: H04M 3/5133 Operator terminal details
• CPC Class Codes: H04M 3/5175 Call or contact centers supervision arrangements

Abstract

A real-time speech analytics system (“RSTA 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 RTSA 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 associated with the agent are displayed. 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 playing audio associated with a call recording of a call involving an agent and a party on the call, wherein the call is processed by a call handler in a contact center, the system comprising:

a real-time speech analytics (“

RTSA”

) system configured to report an event message of a keyword detected by speech of the agent during the call;

a checkpoint and alert reporting module comprising a processor configured to;

receive the event message from the RTSA system during the call and associate the event message with a particular checkpoint, and

store timing information based on the event message in association with the particular checkpoint and the call recording in a memory; and

a workstation comprising a computer display and an audio interface,

wherein the workstation is configured to display a plurality of checkpoint widgets on a time-line representing passage of time of the call recording,

wherein each checkpoint widget is displayed overlaid on the time-line and is displayed with a corresponding text-based identifier,

wherein the plurality of checkpoint widgets comprises a particular checkpoint widget corresponding to the particular checkpoint, the particular checkpoint widget comprising a status indicator reflecting the keyword was detected by the RTSA system at the particular checkpoint, and

wherein the processor of the checkpoint and alert reporting module is further configured to;

receive a first request from the workstation identifying the call recording;

cause the workstation to present the plurality of checkpoint widgets on the time-line;

receive a second request from the workstation identifying the particular checkpoint widget of the call recording, wherein the second request requests playback of audio associated with the call recording; and

cause a portion of the audio of the call recording associated with the particular checkpoint widget to be reproduced by the workstation over the audio interface in response to receiving the second request.

2. The system of claim 1, wherein the first request from the workstation identifying the call recording also identifies the agent.

3. The system of claim 1, wherein the portion of the audio of the call recording associated with the particular checkpoint widget to be reproduced over the audio interface of the workstation begins at a predefined amount of time prior to the particular checkpoint.

4. The system of claim 1, wherein the checkpoint and alert reporting module is further configured to cause the workstation to display a warning icon reflecting an absence of detection of corresponding keywords at another checkpoint widget.

5. The system of claim 1, wherein a second checkpoint widget visually comprises a second status indicator indicating absence of detected speech.

6. The system of claim 1, wherein the call handler comprises the checkpoint and alert reporting module, and wherein the call handler establishes a first call leg to the RTSA system, a second call leg to the workstation, and a third call leg to the party.

7. The system of claim 1, wherein one control of a set of controls selects another checkpoint widget for controlling the audio of the call recording.

8. The system of claim 1, wherein a user may control the audio of the call recording using a set of controls presented by the computer display.

9. The system of claim 8, further comprising:

a file store stored in the memory comprising audio of calls involving the agent, including the audio from the call recording.

10. A non-transitory computer readable medium storing instructions that when executed by a processor in call handler system cause the processor to:

receive an event message from a real-time speech analytics (“

RTSA”

) system associated with a call between an agent in a contact center agent and a remote party, the event message reporting detection of a keyword spoken by the agent;

determine the event message correlates with a particular checkpoint associated with the call;

after completion of the call, receive a first request from a workstation comprising filter information identifying the agent and a time period of calls handled by the agent, wherein the filter information is used to identify a plurality of checkpoint widgets associated with a call recording of the call;

cause the plurality of checkpoint widgets to be displayed on the workstation overlaid on a time-line representing passage of time of the call recording, wherein each checkpoint widget is displayed with a corresponding text-based identifier, and wherein one of the plurality of checkpoint widgets comprises a status indicator reflecting the keyword was detected by the RTSA system at the particular checkpoint,

receive a second request from the workstation requesting a portion of the call recording associated with the particular checkpoint be played; and

cause the portion of audio of the call recording associated with the particular checkpoint to be played using an audio interface of the workstation.

11. The non-transitory computer readable medium of claim 10, wherein the filter information identifying the time period of calls handled by the agent indicates a date, a beginning time on the date, and an ending time on the date.

12. The non-transitory computer readable medium of claim 10, further comprising instructions that when executed cause the processor to:

cause the plurality of checkpoint widgets to be displayed on the workstation with a corresponding compliance score for each of the plurality of checkpoint widgets.

13. The non-transitory computer readable medium of claim 10, further comprising instructions that when executed cause the processor to:

in response to receiving the second request indicating the particular checkpoint, present a user with a window on the workstation displaying controls of an audio player configured to allow the user to control the audio of the call recording.

14. The non-transitory computer readable medium of claim 10, further comprising instructions that when executed cause the processor to:

play the portion of the audio of the call recording at a predefined amount of time prior to the particular checkpoint.

15. The non-transitory computer readable medium of claim 10, further comprising instructions that when executed cause the processor to:

cause the workstation to display a warning icon associated with another checkpoint widget reflecting an absence of detection of corresponding keywords at the another checkpoint widget.

16. A method for playing a portion of audio of a call recording of a call involving an agent in a contact center and a remote party, the method comprising:

receiving at a processor an event message from a real-time speech analytics (“

RTSA”

) system associated with the call, the event message reporting detection of a keyword spoken by the agent;

determining by the processor that the event message correlates with a particular checkpoint associated with the call;

storing timing information by the processor based on the event message in association with the particular checkpoint and the call recording;

receiving at the processor a first request from a workstation comprising filter information identifying the agent and a time period of calls handled by the agent, wherein the filter information is used in part to identify a plurality of checkpoint widgets associated with the call recording;

displaying on the workstation the plurality of checkpoint widgets of the call recording overlaid on a time-line representing passage of time, wherein each checkpoint widget is displayed with a corresponding text-based identifier,

wherein one of the plurality of checkpoint widgets is associated with the particular checkpoint and the one of the plurality of checkpoint widgets comprises a status indicator reflecting the keyword was detected by the RTSA system during the call,

receiving a second request from the workstation requesting a portion of the call recording associated with the particular checkpoint to be played; and

playing the portion of audio of the call recording associated with the particular checkpoint using an audio interface of the workstation.

17. The method of claim 16, wherein causing the plurality of checkpoint widgets to be displayed on the workstation further causes a corresponding compliance score to be displayed with each checkpoint widget.

18. The method of claim 16, wherein the filter information identifying the agent and a time period of calls handled by the agent, comprises a date, beginning time, and ending time.

19. The method of claim 16, wherein the timing information of the audio of the call comprises an offset time from a beginning of the call.

20. The method of claim 16, wherein causing the portion of audio of the call recording associated with the particular checkpoint to be played comprises starting the portion of the audio at a predefined amount of time prior to the particular checkpoint.