System for handling a plurality of streaming voice signals for determination of responsive action thereto

• US 8,676,588 B2
• Filed: 05/22/2009
• Issued: 03/18/2014
• Est. Priority Date: 05/23/2008
• Status: Active Grant

• Current Assignee: Accenture Global Services Limited (Accenture PLC)
• Original Assignee: Accenture Global Services Limited (Accenture PLC)
• Inventors: Ryan, Thomas J., Janan, Biji K.
• Primary Examiner(s): Desir, Pierre-Louis
• Assistant Examiner(s): KOVACEK, DAVID M
• Application Number:
  US12/470,592
• Publication Number:
  US 20090292531A1
• Time in Patent Office: 1,761 Days
• Field of Search: 704200-201, 704231-257, 704270-2701, 704/271, 704/275, 704E15001-E1505, 704E21001-E2102, 379 671- 87, 379 8801- 8827, 37914201-14218, 37920101-21802
• US Class Current: 704/270.1
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: H04M 2201/18 Comparators
• CPC Class Codes: H04M 2201/36 Memories
• CPC Class Codes: H04M 2201/40 using speech recognition speech recognition per se G10L15/00
• CPC Class Codes: H04M 2203/301 Management of recordings
• CPC Class Codes: H04M 3/2281 Call monitoring, e.g. for law enforcement purposes; Call tracing; Detection or prevention of malicious calls
• CPC Class Codes: H04M 3/42221 Conversation recording systems at the subscriber's set H04M1/656
• CPC Class Codes: H04M 3/51 Centralised call answering arrangements requiring operator intervention , e.g. call or contact centers for telemarketing

Abstract

Streaming voice signals, such as might be received at a contact center or similar operation, are analyzed to detect the occurrence of one or more unprompted, predetermined utterances. The predetermined utterances preferably constitute a vocabulary of words and/or phrases having particular meaning within the context in which they are uttered. Detection of one or more of the predetermined utterances during a call causes a determination of response-determinative significance of the detected utterance(s). Based on the response-determinative significance of the detected utterance(s), a responsive action may be further determined. Additionally, long term storage of the call corresponding to the detected utterance may also be initiated. Conversely, calls in which no predetermined utterances are detected may be deleted from short term storage. In this manner, the present invention simplifies the storage requirements for contact centers and provides the opportunity to improve caller experiences by providing shorter reaction times to potentially problematic situations.

Claims

1. A system for use in processing a plurality of calls coming into a contact center, each of the plurality of calls comprising a streaming voice signal, the system comprising:

an interceptor operable to receive the plurality of calls;

a recognizer, operably coupled to the interceptor, operable to continuously analyze a call between a caller and a human agent of the plurality of calls to detect, within the streaming voice signal, occurrence of an unprompted predetermined utterance having response-determinative significance to provide a detected utterance; and

a treatment processor, operably coupled to the recognizer, operable to determine a responsive action based on the response-determinative significance corresponding to the detected utterance and at least one of historical data and a configuration of the contact center, and further operable to perform the responsive action for the caller without action from the human agent; and

wherein the detected utterance indicates that assistance from a third-party, other than the human agent, is needed.

2. The system of claim 1, wherein the interceptor is further operable to identify and extract the streaming voice signal corresponding to each of the plurality of calls from network traffic routed to the call center.

3. The system of claim 1, wherein the interceptor is further operable to:

temporarily store, in short term storage, each call of the plurality of calls;

move, from the short term storage to long term storage, those calls of the plurality of calls for which a save indication is received from the recognizer; and

delete, from the short term storage, those calls of the plurality of calls for which a delete indication is received from the recognizer.

4. The system of claim 3, wherein the recognizer is further operable to:

provide, to the interceptor, the save indication in response to the detected utterance.

5. The system of claim 1, wherein the recognizer is further operable to:

provide, to the treatment processor, the response-determinative significance corresponding to the detected utterance.

6. The system of claim 1, wherein the treatment processor is further operable to provide an indication to modify at least one response of the human agent to a caller initiating the call as the responsive action.

7. The system of claim 1, wherein the treatment processor is further operable to redirect the call to a third party as the responsive action.

8. The system of claim 1, wherein the treatment processor is further operable to request a third party to monitor the call substantially in real time as the responsive action.

9. The system of claim 1, wherein the treatment processor is further operable to initiate a specific response sequence for a caller initiating the call as the responsive action.

10. The system of claim 1, wherein the treatment processor is further operable to initiate a follow-up call to a caller initiating the call subsequent to termination of the call.

11. The system of claim 1, wherein the treatment processor is further operable to:

receive electronic inputs from the caller; and

determine the responsive action based on the electronic inputs and the response-determinative significance of the detected utterance.

12. The system of claim 1, wherein the treatment processor is further operable to:

receive the detected utterance from the recognizer; and

determine the responsive action based on the detected utterance and the response-determinative significance of the detected utterance.

13. The system of claim 1 wherein the streaming voice signal includes voice responses provided by the human agent.

14. The system of claim 1 wherein the predetermined utterance indicates that the caller is a displeased customer.

15. The system of claim 1 wherein the predetermined utterance indicates that the caller requires emergency services.

16. The system of claim 1 wherein the responsive action is further based on a second response-determinative significance corresponding to a second detected utterance recognized during the call.

17. The system of claim 16 wherein the responsive action is to store information regarding the call when the response-determinative significance and the second response-determinative significance are conflicting.

18. In a contact center receiving a plurality of calls, each of the plurality of calls comprising a streaming voice signal, a method for processing the plurality of calls, comprising:

continuously analyzing, by a recognizer, a call between a caller and a human agent of the plurality of calls to detect occurrence of an unprompted predetermined utterance having response-determinative significance to provide a detected utterance; and

determining, by a treatment processor operably coupled to the recognizer, a responsive action based on the response-determinative significance corresponding to the detected utterance and at least one of historical data and a configuration of the contact center;

performing, by the treatment processor, the responsive action for the caller without action from the human agent; and

wherein the detected utterance indicates that assistance from a third-party, other than the human agent, is needed.

19. The method of claim 18, further comprising:

temporarily storing, by an interceptor operably coupled to the recognizer, the plurality of calls.

20. The method of claim 19, further comprising:

moving, by interceptor, storage of the call from short term storage to long term storage based on detection of the detected utterance.

21. The method of claim 18, wherein the responsive action is providing an indication to modify at least one response of the human agent to a caller associated with the call.

22. The method of claim 18, wherein the responsive action is providing an indication to redirect the call to a third party.

23. The method of claim 18, wherein the responsive action is providing an indication to request a third party to monitor the call substantially in real time.

24. The method of claim 18, wherein the responsive action is providing an indication to initiate a specific response sequence for a caller associated with the call.

25. The method of claim 18, wherein the responsive action is providing an indication to initiate a follow-up call to a caller associated with the call subsequent to termination of the call.

26. The method of claim 18, further comprising:

receiving, by the treatment processor, electronic inputs from the caller; and

determining the responsive action based on the electronic inputs and the response-determinative significance of the detected utterance.

27. The method of claim 18, further comprising:

determining the responsive action based on the detected utterance and the response-determinative significance of the detected utterance.