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

• US 8,751,222 B2
• Filed: 05/22/2009
• Issued: 06/10/2014
• Est. Priority Date: 05/23/2008
• Status: Active Grant

• Current Assignee: Accenture Global Services Limited (Accenture PLC)
• Original Assignee: Accenture GmbH (Accenture PLC)
• Inventors: Ryan, Thomas J., Janan, Biji K.
• Primary Examiner(s): MCFADDEN, SUSAN IRIS
• Application Number:
  US12/470,614
• Publication Number:
  US 20090292532A1
• Time in Patent Office: 1,845 Days
• Field of Search: 704/214, 704/270.1, 379/88.04
• US Class Current: 704/214
• CPC Class Codes: G10L 2015/088 Word spotting
• CPC Class Codes: H04M 3/42221 Conversation recording systems at the subscriber's set H04M1/656
• 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. In an apparatus comprising at least one processing device, a method for processing a plurality of streaming voice signals, the method comprising:

continuously analyzing, by a voice recognition component, a streaming voice signal of the plurality of streaming voice signals to detect occurrence of an unprompted predetermined utterance made by a caller to a human agent to provide a detected utterance;

determining, by a significance determination component operably connected to the voice recognition component, response-determinative significance of the detected utterance; and

providing, by the significance determination component, at least an indication of the response-determinative significance to the human agent in order for the agent to determine how best to respond to the caller,

wherein a responsive action is determined based on the response-determinative significance of the detected utterance.

2. The method of claim 1, wherein the detected utterance is significant with regard to a business relationship.

3. The method of claim 1, wherein the detected utterance is significant with regard to an emergency condition.

4. The method of claim 1, further comprising:

providing, by the significance determination component in response to the detected utterance, an indication that the streaming voice signal should be stored in long-term storage.

5. The method of claim 1, further comprising:

prior to analyzing the streaming voice signal, converting, by a conversion component operably connected to the voice recognition component, the streaming voice signal into an analyzable form.

6. The method of claim 5, wherein converting the streaming voice signal into the analyzable form further comprises extracting voice data from network packets.

7. The method of claim 5, wherein converting the streaming voice signal into the analyzable form further comprises decrypting the streaming voice signal.

8. The method of claim 5, wherein converting the streaming voice signal into the analyzable form further comprises decompressing the streaming voice signal.

9. The method of claim 1, wherein providing at least the indication of the response-determinative significance further comprises providing the detected utterance and the response-determinative significance thereof.

10. An apparatus for processing a plurality of streaming voice signals comprising:

at least one processor; and

at least one storage device operably connected to the at least one processor and having stored thereon executable instructions that, when executed by the at least one processor, cause the apparatus to;

continuously analyze a streaming voice signal of the plurality of streaming voice signals to detect occurrence of an unprompted predetermined utterance made by a caller to a human agent to provide a detected utterance;

determine response-determinative significance of the detected utterance; and

provide at least an indication of the response-determinative significance to the human agent in order for the agent to determine how best to response to the caller,

wherein a responsive action is determined based on the response-determinative significance of the detected utterance.

11. The apparatus of claim 10, wherein the detected utterance is significant with regard to a business relationship.

12. The apparatus of claim 10, wherein the detected utterance is significant with regard to an emergency condition.

13. The apparatus of claim 10, the at least one storage device further comprising executable instructions that, when executed by the at least one processor, cause the apparatus to:

provide, in response to the detected utterance, an indication that the streaming voice signal should be stored in long-term storage.

14. The apparatus of claim 10, the at least one storage device further comprising executable instructions that, when executed by the at least one processor, cause the apparatus to:

prior to analyzing the streaming voice signal, convert the streaming voice signal into an analyzable form.

15. The apparatus of claim 14, wherein the executable instructions that cause the apparatus to convert the streaming voice signal into the analyzable form further comprise executable instructions that cause the apparatus to extract voice data from network packets.

16. The apparatus of claim 14, wherein the executable instructions that cause the apparatus to convert the streaming voice signal into the analyzable form further comprise executable instructions that cause the apparatus to decrypt the streaming voice signal.

17. The apparatus of claim 14, wherein the executable instructions that cause the apparatus to convert the streaming voice signal into the analyzable form further comprise executable instructions that cause the apparatus to decompress the streaming voice signal.

18. The apparatus of claim 10, wherein the executable instructions that cause the apparatus to provide at least the indication of the response-determinative significance further comprise executable instructions that cause the apparatus to provide the detected utterance and the response-determinative significance thereof.

19. An apparatus for processing a plurality of streaming voice signals comprising:

a voice recognition component operable to detect occurrence of an unprompted predetermined utterance made by a caller to a human agent in a streaming voice signal of the plurality of streaming voice signals to provide a detected utterance; and

a significance determination component, operably connected to the voice recognition component, operable to determine response-determinative significance of the detected utterance and provide at least an indication of the response-determinative significance to the human agent in order for the agent to determine how best to respond to the caller,

wherein a responsive action is determined based on the response-determinative significance of the detected utterance.

20. The apparatus of claim 19, further comprising, operably connected to the voice recognition component, a conversion component operable to convert the streaming voice signal into an analyzable form.

21. The apparatus of claim 20, wherein the conversion component comprises a network packet extraction component.

22. The apparatus of claim 20, wherein the conversion component comprises a decryption component.

23. The apparatus of claim 20, wherein the conversion component comprises a decompression component.

24. The apparatus of claim 19, wherein the significance determination component is further operable to provide, in response to the detected utterance, an indication that the streaming voice signal should be stored in long-term storage.