Using a speech analytics system to control recording contact center calls in various contexts

• US 9,154,623 B1
• Filed: 11/25/2013
• Issued: 10/06/2015
• Est. Priority Date: 11/25/2013
• Status: Active Grant

• Current Assignee: Alvaria Cayman
• Original Assignee: Noble Systems Corporation
• Inventors: Ouimette, Jason P., Koster, Karl H.
• Primary Examiner(s): BEZUAYEHU, SOLOMON G
• Application Number:
  US14/088,763
• Time in Patent Office: 680 Days
• Field of Search: 379/85, 379 8801- 8828, 455/415
• US Class Current: 1/1
• CPC Class Codes: H04M 2201/40 using speech recognition speech recognition per se G10L15/00
• CPC Class Codes: H04M 2203/2038 Call context notifications
• CPC Class Codes: H04M 2203/403 Agent or workforce training
• CPC Class Codes: H04M 3/42221 Conversation recording systems at the subscriber's set H04M1/656
• CPC Class Codes: H04M 3/42348 Location-based services which utilize the location information of a target
• CPC Class Codes: H04M 3/51 Centralised call answering arrangements requiring operator intervention , e.g. call or contact centers for telemarketing
• CPC Class Codes: H04M 3/5166 in combination with interactive voice response systems or voice portals, e.g. as front-ends
• CPC Class Codes: H04M 3/5175 Call or contact centers supervision arrangements
• CPC Class Codes: H04M 3/5183 Call or contact centers with computer-telephony arrangements

Abstract

An architecture and process flow for a system that processes event notifications from a speech analytics system for the purpose of controlling the recording of calls in a contact center for various contexts. Based on the regulatory context of the call, call recording may require requesting and receiving consent from the remote party to record the call. A speech analytics system operating in conjunction with an event handler module and a call recording application specific module can facilitate automatically recording the call and minimize agent intervention. The application specific module may provide icons and text on the agent'"'"'s display to remind or inform the agent of the context and various conditions. The application specific module may also control various recording equipment.

Claims

1. A method for automatically recording audio of a call in a contact center, comprising:

establishing the call by the contact center between a human agent and a remote party using a call handler;

providing audio of the call from the call handler to a speech analytics module (“

SAM”

) using two audio streams, wherein a first audio stream conveys speech of the human agent and a second audio stream conveys speech of the remote party;

receiving a call-related event notification at a call recording application specific module (“

CR-ASM”

), wherein the call-related event notification indicates establishment of the call and is provided to the CR-ASM by either the call handler or the SAM;

generating a call instance data structure in response to receiving the call-related event notification;

analyzing by the SAM the speech of the first stream to detect a request from the human agent to obtain authorization from the remote party to record the call;

providing a first one or more speech-related event notifications from the SAM to an event handler module indicating the first audio stream comprises the request from the human agent to obtain authorization from the remote party to record the call;

providing the first one or more speech-related event notifications from the event handler module to the CR-ASM;

modifying the call instance data structure by the CR-ASM in response to receiving the first one or more speech-related event notification;

analyzing by the SAM the speech of the second stream to detect consent provided from the remote party to record the call;

providing a second one or more speech-related event notifications by the SAM to the event handler module indicating the second audio stream comprises consent to record the call;

providing the second one or more speech-related event notifications from the event handler module to the CR-ASM; and

causing by the CR-ASM recording of the audio of the call in response to receiving the second one or more speech-related event notifications.

2. The method of claim 1, wherein a first computing system comprises the SAM, a second computing system comprises the call handler, and a third computing system comprises both the event handler module and the CR-ASM.

3. The method of claim 1 further comprising:

modifying the call instance data structure by the CR-ASM in response to receiving the second one or more speech-related event notifications.

4. The method of claim 3 further comprising;

storing at least a portion of the call instance data structure that is modified in response to receiving the second one or more speech-related event notifications in a database.

5. The method of claim 1 further comprising:

starting a timer after detecting the request to obtain authorization from the remote party to record the call, and terminating the timer after detecting the consent to record the call.

6. The method of claim 1 further comprising:

displaying a visual indicator on a computer used by the human agent indicating that the human agent should prompt the remote party for the consent to record the call.

7. A system for controlling recording of calls comprising:

a processor configured to;

receive a call-related event notification indicating establishment of a call between a human agent and a remote party, wherein a call leg of the call is established between a call handler and a speech analytics module (“

SAM”

), and wherein the call leg comprises a first audio stream conveying speech of the human agent and a second audio stream conveying speech of the remote party;

generate a call instance data structure in response to the call-related event notification;

receive a first speech-related event notification from an event handler module configured to receive a first corresponding notification from the SAM indicating detection of the speech in the first audio stream of the human agent requesting the remote party for consent to record the call;

modify the call instance data structure reflecting the human agent prompting the remote party for consent to record the call;

receive a second speech-related event notification from the event handler module configured to receive a second corresponding notification from the SAM indicating detection in the speech in the second audio stream of the remote party providing consent to record the call; and

cause audio of the call from both the human agent and the remote party on the call to be recorded after processing the second speech-related event notification.

8. The system of claim 7, further comprising:

the SAM, wherein the SAM is configured to receive the first audio stream and the second audio stream, and wherein the SAM is further configured to provide the first speech-related event notification and the second speech-related event notification to the processor.

9. The system of claim 7, wherein the processor is further configured to:

provide a visual icon for display on a computer used by the human agent prior to receiving the first speech-related event notification, wherein the visual icon serves to indicate to the human agent that verbal consent to record the call should be requested from the remote party.

10. The system of claim 9, wherein the processor is further configured to:

determine that recording the call is allowable prior to providing the visual icon based in part on a geographic location of the remote party.

11. The system of claim 10, wherein the processor is further configured to:

store at least a portion of contents of the call instance data structure in response to receiving a second call-related event notification indicating the call has ended.

12. The system of claim 10, further comprising:

the call handler, wherein the call handler is configured to provide the call-related event notification to the processor contemporaneously with establishing the call leg to the SAM.

13. A non-transitory computer readable medium storing instructions that when executed by a processor cause the processor to:

process a first event notification comprising a call-related event notification indicating establishment of a call between a human agent and a remote party involving a call handler, wherein a call leg of the call is established between the call handler and a speech analytics module (“

SAM”

), and wherein the call leg comprises a first audio stream conveying speech of the human agent and a second audio stream conveying speech of the remote party;

generate a call instance data structure in response to the first event notification;

process a second event notification comprising a first speech-related event notification received from an event handler module configured to receive a first corresponding first notification from the SAM, the second event notification indicating detection of the speech of the human agent in the first audio stream comprising a request to obtain authorization from the remote party to record the call;

modify the call instance data structure reflecting the human agent requested the remote party for consent to record the call;

process a third event notification comprising a second speech-related event notification received from the event handler module configured to receive a second corresponding notification from the SAM, the third event notification indicating detection of the speech in the second audio stream of the remote party providing consent to record the call; and

cause audio of the call from both the human agent and the remote party to be recorded in response to processing the third event notification.

14. The non-transitory computer readable medium of claim 13, wherein the instructions further cause the processor to:

provide a visual icon for display on a computer used by the human agent prior to processing the second event notification, wherein the visual icon indicates to the human agent that verbal consent to record the call should be requested from the remote party.

15. The non-transitory computer readable medium of claim 14, wherein the instructions further cause the processor to:

determine that recording the call is allowable prior to providing the visual icon based in part on a geographic location of the remote party.

16. The non-transitory computer readable medium of claim 13, wherein the instructions further cause the processor to:

process a fourth event notification comprising another call-related event notification indicating the call between the human agent and the remote party has terminated.

17. The non-transitory computer readable medium of claim 16, wherein the instructions further cause the processor to:

store at least a portion of contents of the call instance data structure in response to processing the fourth event notification.

18. The non-transitory computer readable medium of claim 13, wherein the instructions further cause the processor to:

start a timer in response to receiving the second event notification; and

stop the timer in response to receiving the third event notification.

19. The non-transitory computer readable medium of claim 13, wherein the instructions further cause the processor to:

provide a visual icon for display on a computer used by the human agent prior to indicating the call is being recorded.