Handling a telephone call by voice analytics in a computer-telephony integration system

• US 8,600,756 B2
• Filed: 06/19/2009
• Issued: 12/03/2013
• Est. Priority Date: 06/20/2008
• Status: Active Grant

• Current Assignee: Vonage Business Limited (Telefonaktiebolaget LM Ericsson)
• Original Assignee: NewVoiceMedia Limited (Telefonaktiebolaget LM Ericsson)
• Inventors: Pickering, Richard, Moussalli, Joseph, Unitt, Ashley
• Primary Examiner(s): Lerner, Martin
• Application Number:
  US12/999,899
• Publication Number:
  US 20110125498A1
• Time in Patent Office: 1,628 Days
• Field of Search: 704/246, 704/270.1, 704/275, 379/88.01, 379/88.02, 379/88.2, 379/88.21, 379/207.13, 379/207.15, 379/265.06, 379/265.07, 379/266.07
• US Class Current: 704/270.1
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 15/30 Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
• CPC Class Codes: G10L 17/00 Speaker identification or verification techniques
• CPC Class Codes: H04M 2201/41 using speaker recognition speaker recognition per se G10L17/00
• CPC Class Codes: H04M 2203/357 Autocues for dialog assistance
• CPC Class Codes: H04M 3/42068 where the identifier is used to access a profile
• 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
• CPC Class Codes: H04M 3/5183 Call or contact centers with computer-telephony arrangements

Abstract

The invention provides a computer-implemented method of handling a telephone call, comprising monitoring a conversation between an agent and a customer on a telephone line as part of the telephone call to extract the audio signal therefrom. Real-time voice analytics are performed on the extracted audio signal while the telephone call is in progress. The results from the voice analytics are then passed to a computer-telephony integration system responsible for the call for use by the computer-telephony integration system for determining future handling of the call.

Claims

1. A computer-implemented method of handling a telephone call, the method comprising:

monitoring a conversation between an agent and a customer on a telephone line as part of said telephone call to extract the audio signal therefrom;

performing real-time voice analytics on the extracted audio signal while the telephone call is in progress, and passing results from the voice analytics to a computer-telephony integration system responsible for the call, wherein the computer-telephony system is located in a telephony carrier service provider equipment (SPE) environment located remotely from a customer service center where a plurality of agents that serve customers for an enterprise are located, and wherein the computer-telephony system provides a bridge for the telephone call between the agent and the customer, wherein the audio signal is extracted at the bridge, and wherein the real-time voice analytics is performed by a speech analytics server computer located in the service provider environment proximate to the bridge; and

using the results by the computer-telephony integration system for determining future handling of the call in respect of compliance testing in order to confirm that the agent has made one or more predetermined statements relating to a transaction during the telephone conversation; and

if the voice analytics system does not confirm that the agent has made said the one or more predetermined statements, automatically preventing by the computer-telephony integration system the agent from completing the transaction with the caller.

2. The method of claim 1, wherein the computer-telephony system provides a bridge for the telephone call between the agent and the customer, and wherein said audio signal is extracted at said bridge.

3. The method of claim 1, wherein the computer-telephony system is implemented on a cloud computing service.

4. The method of claim 1, wherein the agent represents an interactive voice response unit.

5. The method of claim 1, wherein if the voice analytics system does not confirm that the agent has made said one or more predetermined statements, the application flow for the call is modified to help ensure that the one or more one predetermined statements are made while the telephone call is still in progress.

6. The method of claim 1, wherein the modification of the application flow includes transferring the caller to an interactive voice response system to make the one or more predetermined statements automatically.

7. The method of claim 1, further comprising allowing the transaction to complete after modification of the application flow and the one or more predetermined statements have been made.

8. The method of claim 1, further comprising:

receiving an incoming telephone call at a computer-telephony system and obtaining a calling line identification associated with the call, wherein the monitored conversation between an agent and a customer on a telephone line is part of said telephone call; and

using said results by the computer-telephony integration system for authenticating a party on the call by a combination of the voice analytics results and the calling line identification.

9. The method of claim 8, wherein the speaker authentication is performed against a stored template for the customer which is identified based on the calling line ID.

10. The method of claim 1, wherein the voice analytics are only performed on the audio signal from one of the agent or the customer.

11. The method of claim 1, further comprising the agent entering text data into the computer telephony integration system during the call.

12. The method of claim 11, wherein the entered text data is passed to the voice analytics system to assist with the analysis of the telephone conversation.

13. The method of claim 12, wherein the voice analytics system is used to confirm that the agent has entered the correct text into the computer-telephony integration server based on what is said during the telephone conversation.

14. The method of claim 1, wherein voice analytics system is in the network in said SPE environment.

15. A non-transitory computer-readable storage medium containing a computer program comprising instructions for a computer-telephony integration system to handle a telephone call according to the following method:

monitoring a conversation between an agent and a customer on a telephone line as part of said telephone call to extract the audio signal therefrom;

performing real-time voice analytics on the extracted audio signal while the telephone call is in progress, and passing results from the voice analytics to a computer-telephony integration system responsible for the call, wherein the computer-telephony system is located in a telephony carrier service provider equipment (SPE) environment located remotely from a customer service center where a plurality of agents that serve customers for an enterprise are located, and wherein the computer-telephony system provides a bridge for the telephone call between the agent and the customer, wherein the audio signal is extracted at the bridge, and wherein the real-time voice analytics is performed by a speech analytics server computer located in the service provider environment proximate to the bridge; and

using said results by the computer-telephony integration system for determining future handling of the call in respect of compliance testing and to confirm that the agent has made one or more predetermined statements relating to a transaction during the telephone conversation, wherein if the voice analytics system does not confirm that the agent has made said one or more predetermined statements, the computer-telephony integration system is configured to prevent the agent from completing the transaction with the caller.

16. A computer-telephony integration system for handling a telephone call in an SPE environment within a telephone network, the system comprising:

a line connection for monitoring a conversation between an agent and a customer on a telephone line as part of said telephone call to extract the audio signal therefrom;

a voice analytics system located in the SPE environment for performing real-time voice analytics on the extracted audio signal while the telephone call is in progress, and for passing results from the voice analytics to a computer- telephony integration server responsible for the call; and

a computer-telephony integration server located in the SPE environment for receiving the results from the voice analytics system and using said results for determining future handling of the call in respect of compliance testing and to confirm that the agent has made one or more predetermined statements relating to a transaction during the telephone conversation, wherein if the voice analytics system does not confirm that the agent has made said one or more predetermined statements, the computer-telephony integration system is configured to prevent the agent from completing the transaction with the caller.

17. The computer-telephony integration system of claim 16, wherein the line connection is configured to obtain a calling line identification associated with the call, and wherein the computer-telephony integration system is configured to authenticate the customer on the call by a combination of the results from the voice analytics system and the calling line identification.