Treatment processing of a plurality of streaming voice signals for determination of a responsive action thereto

• US 9,444,939 B2
• Filed: 05/22/2009
• Issued: 09/13/2016
• 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:
  US12/470,626
• Publication Number:
  US 20090292533A1
• Time in Patent Office: 2,671 Days
• Field of Search: 704231-257, 704/270, 704/270.1, 704/271, 704/275, 704E17001-E17016, 704E15001-E1505, 381/110, 379 671- 8828, 37926501-26601, 379/258
• US Class Current: 1/1
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 2015/088 Word spotting
• CPC Class Codes: H04M 3/493 Interactive information services, e.g. directory enquiries ; Arrangements therefor, e.g. interactive voice response [IVR] systems or voice portals
• CPC Class Codes: H04M 3/5183 Call or contact centers with computer-telephony arrangements

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 method comprising:

receiving, by a device and during a communication between a first person and a second person, a first plurality of voice signals from the first person and a second plurality of voice signals from the second person;

temporarily storing, by the device, based on intercepting the communication, and in a first storage, at least a portion of the first plurality of voice signals and at least a portion of the second plurality of voice signals;

detecting, by the device and based on the first plurality of voice signals and the second plurality of voice signals, portions of utterances included in the first plurality of voice signals or the second plurality of voice signals;

combining, by the device, the portions of utterances to generate multiple utterances;

determining, by the device and based on the multiple utterances, that particular utterances, of the multiple utterances, include significances,

the significances of the particular utterances corresponding to indications of why the particular utterances are important in a given context, and providing information about a subsequent decision concerning how to respond, and

determining that the particular utterances include significances including;

analyzing information that associates a plurality of utterances with a corresponding significance; and

determining, based on analyzing the information, that each of the particular utterances matches an utterance of the plurality of utterances;

determining, by the device, and based on the significances of the particular utterances, if a responsive action is appropriate,

the responsive action being based on a nature of the communication, based on types of the particular utterances, and corresponding to a particular action to carry out,

the responsive action being appropriate when a threshold number of the particular utterances is satisfied;

removing, automatically by the device and without user input, when the responsive action is not appropriate and prior to termination of the communication, the at least the portion of the first plurality of voice signals and the at least the portion of the second plurality of voice signals from the first storage;

moving, automatically, by the device and without user input, when the responsive action is appropriate and prior to the termination of the communication, the at least the portion of the first plurality of voice signals and the at least the portion of the second plurality of voice signals from the first storage to a second storage,

the second storage being different than the first storage; and

processing, by the device and when the responsive action is appropriate, the communication,

where processing the communication includes deploying the responsive action, prior to the termination of the communication, by;

displaying an indication of the responsive action to the second person, where the indication directs the second person to request that a third party monitor the communication substantially in real time, and

redirecting the communication to the third party.

2. The method of claim 1, where the communication is a call to a contact center.

3. The method of claim 1, where the responsive action is deployed by displaying an indication to modify at least one response of the second person to the first person.

4. The method of claim 1, where the responsive action is deployed by displaying an indication to initiate a specific response sequence for the second person.

5. The method of claim 1, where the responsive action is deployed by displaying an indication to initiate a follow-up communication to the first person subsequent to the termination of the communication.

6. The method of claim 1, where analyzing the information, associated with the plurality of utterances, includes:

using statistical analysis techniques to one of;

analyze one or more portions of the first plurality of voice signals, or

analyze one or more portions of the second plurality of voice signals.

7. An apparatus comprising:

a memory to store instructions; and

at least one processor to execute the instructions to;

receive, during a communication between a first person and a second person, a first plurality of voice signals from the first person and a second plurality of voice signals from the second person;

temporarily store, based on intercepting the communication and in a first storage, at least a portion of the first plurality of voice signals and at least a portion of the second plurality of voice signals;

detect, based on the first plurality of voice signals and the second plurality of voice signals, portions of utterances included in the first plurality of voice signals or the second plurality of voice signals;

combine the portions of utterances to generate multiple utterances;

determine, based on the multiple utterances, that particular utterances, of the multiple utterances, include significances,

the significances of the particular utterances corresponding to indications of why the particular utterances are important in a given context, and providing information about a subsequent decision concerning how to respond, and

the at least one processor, when determining that the particular utterances include significances, is to;

analyze information that associates a plurality of utterances with a corresponding significance; and

determine, based on analyzing the information, that each of the particular utterances matches an utterance of the plurality of utterances;

determine, based on the significances of the particular utterances, if a responsive action is appropriate,

the responsive action being based on a nature of the communication, based on types of the particular utterances, and corresponding to a particular action to carry out,

the responsive action being appropriate when a threshold number of the particular utterances is satisfied;

remove, automatically and without user input, when the responsive action is not appropriate and prior to termination of the communication, the at least the portion of the first plurality of voice signals and the at least the portion of the second plurality of voice signals from the first storage;

move, automatically and without the user input, when the responsive action is appropriate and prior to the termination of the communication, the at least the portion of the first plurality of voice signals and the at least the portion of the second plurality of voice signals from the first storage to a second storage,

the second storage being different than the first storage; and

process, when the responsive action is appropriate, the communication,

the at least one processor, when processing the communication, is to deploy the responsive action, prior to the termination of the communication, by;

displaying an indication of the responsive action to the second person, where the indication directs the second person to request that a third party monitor the communication substantially in real time, and

redirecting the communication to the third party.

8. The apparatus of claim 7, where the communication is a call to a contact center.

9. The apparatus of claim 7, where the responsive action is deployed by displaying an indication to modify at least one response of the second person to the first person.

10. The apparatus of claim 7, where the responsive action is deployed by displaying an indication to initiate a specific response sequence for the second person to make to the first person.

11. The apparatus of claim 7, where the responsive action is deployed by displaying an indication to initiate a follow-up communication to the first person subsequent to the termination of the communication.

12. The apparatus of claim 7, where, upon completing the processing of the communication, the at least one processor is to one of:

determine whether to delete or retain the first plurality of voice signals based on one or more predetermined utterances being detected, or

determine whether to delete or retain the second plurality of voice signals based on one or more other predetermined utterances being detected.

13. A non-transitory computer-readable medium storing instructions, the instructions comprising:

one or more instructions which, when executed by a processor of a device, cause the processor to;

receive, during a communication between a first person and a second person, a first plurality of voice signals from the first person and a second plurality of voice signals from the second person;

temporarily store, based on intercepting the communication and in a first storage, at least a portion of the first plurality of voice signals and at least a portion of the second plurality of voice signals;

detect, based on the first plurality of voice signals and the second plurality of voice signals, portions of utterances included in the first plurality of voice signals or the second plurality of voice signals;

combine the portions of the utterances to generate multiple utterances;

determine, based on the multiple utterances, that particular utterances, of the multiple utterances, include significances,

the significances of the particular utterances corresponding to indications of whether the particular utterances are important in a given context, and providing information about a subsequent decision concerning how to respond, and

the one or more instructions, that cause the processor to determine that the particular utterances include significances, cause the processor to;

analyze information that associates a plurality of utterances with a corresponding significance; and

determine, based on analyzing the information, that each of the particular utterances matches an utterance of the plurality of utterances;

determine, based on the significances of the particular utterances, if a responsive action is appropriate,

the responsive action being based on a nature of the communication, based on types of the particular utterances, and corresponding to a particular action to carry out,

the responsive action being appropriate when a threshold number of the particular utterances is satisfied;

remove, automatically and without user input, when the responsive action is not appropriate and prior to termination of the communication, the at least the portion of the first plurality of voice signals and the at least the portion of the second plurality of voice signals from the first storage;

move, automatically and without the user input, when the responsive action is appropriate and prior to the termination of the communication, the at least the portion of the first plurality of voice signals and the at least the portion of the second plurality of voice signals from the first storage to a second storage,

the second storage being different than the first storage; and

process, when the responsive action is appropriate, the communication,

the one or more instructions, that cause the processor to process the communication, cause the processor to deploy the responsive action, prior to the termination of the communication, by;

displaying an indication of the responsive action to the second person, where the indication directs the second person to request that a third party monitor the communication substantially in real time, and

redirecting the communication to the third party.

14. The non-transitory computer-readable medium of claim 13, where the significances of the particular utterances are further based on:

first information associated with a physical location of the first person, and

second information associated with historical data describing past characteristics of the first person.

15. The non-transitory computer-readable medium of claim 13, where the responsive action is deployed by displaying an indication to modify at least one response of the second person to the first person.

16. The non-transitory computer-readable medium of claim 13, where the responsive action is deployed by displaying an indication to initiate a specific response sequence for the second person to make to the first person.

17. The non-transitory computer-readable medium of claim 13, where the responsive action is deployed by displaying an indication to initiate a follow-up communication to the first person subsequent to the termination of the communication.

18. The non-transitory computer-readable medium of claim 13, further comprising:

one or more instructions which, when executed by the processor, cause the processor to;

use statistical analysis techniques to analyze one or more portions of the first plurality of voice signals, and one or more portions of the second plurality of voice signals.

19. The non-transitory computer-readable medium of claim 13, where the communication is a call to a contact center.

20. The non-transitory computer-readable medium of claim 13, further comprising:

one or more instructions which, when executed by the processor, cause the processor to;

determine whether to delete or retain the first plurality of voice signals based on one or more predetermined utterances being detected; and

determine whether to delete or retain the second plurality of voice signals based on one or more other predetermined utterances being detected.