Intelligent call routing and call supervision method for call centers

• US 7,844,045 B2
• Filed: 06/16/2004
• Issued: 11/30/2010
• Est. Priority Date: 06/16/2004
• Status: Expired due to Fees

• Current Assignee: Sovereign Peak Ventures, LLC (Dominion Harbor Enterprises, LLC)
• Original Assignee: Panasonic Corporation (Panasonic Holdings Corporation)
• Inventors: Junqua, Jean-Claude, Contolini, Matteo
• Primary Examiner(s): SING, SIMON P
• Application Number:
  US10/869,810
• Publication Number:
  US 20050286705A1
• Time in Patent Office: 2,358 Days
• Field of Search: 37926501-2661
• US Class Current: 379/265.12
• CPC Class Codes: H04M 2203/2061 Language aspects
• CPC Class Codes: H04M 3/5232 Call distribution algorithms

Abstract

A call routing and supervising system includes an input receiving customer speech from a remote location, and a voice characteristics extractor extracting voice characteristics from the customer speech, such as language/dialect/accent, age group, gender, and eigendimension coordinates. A customer service representative selector selects one or more customer service representatives based on profiles of the customer service representatives respective of customers having voice characteristics similar to the extracted voice characteristics. In other aspects, a call monitor automatically analyzes dialogue between the customer and the customer service representative, such as detected interruptions, tracked dialogue turns, and recognized key phrases indicating frustration, polity, and/or resolution characteristics of dialogue. The call monitor records performance of the customer service representative respective of customers having the voice characteristics. Automatic call rerouting and/or real-time instruction of call center personnel can also be accomplished based on analysis results.

Claims

1. A call routing and supervising system, comprising:

an input receiving customer speech of a customer from a remote location;

voice characteristics extractor extracting voice characteristics from the customer speech based on trained models of a plurality of different groups of speakers;

a representative selector selecting one or more from a plurality of human customer service representatives to service the customer based on profiles of the plurality of human customer service representatives and the extracted voice characteristics, wherein the profiles map said plurality of human customer service representatives to said plurality of different groups of speakers; and

the representative selector being a self-tuning selector that adjusts the mapping of one of the plurality of human customer service representatives to said plurality of different groups of speakers based on customer satisfaction indicators extracted from voice characteristics of said customer speech, wherein the customer satisfaction indicators indicate a degree of satisfaction of the customer with the service provided to the customer by the one of the plurality of human customer service representatives.

2. The system of claim 1, further comprising a call monitor performing an automatic analysis of dialogue between the customer and a human customer service representative during interaction between the customer and the human customer service representative.

3. The method of claim 2, wherein said call monitor records performance of the human customer service representative respective of customers having the voice characteristics based on the analysis.

4. The system of claim 2, wherein said call monitor automatically selects predefined instructions based on the analysis and communicates the instructions to the human customer service representative during interaction between the customer and the human customer service representative.

5. The system of claim 4, wherein said human customer service representative selector suggests rerouting the call based on the analysis and selects a new one of plural human customer service representatives.

6. The system of claim 5, wherein said human customer service representative selector selects the new one of plural human customer service representatives based on previous performance of the human customer service representatives respective of customers having voice characteristics similar to the voice characteristics extracted from the customer speech.

7. The system of claim 5, wherein said human customer service representative selector selects the new one of plural human customer service representatives based on a preexisting supervisory relationship between the new human customer service representative and the human customer service representative interacting with the customer during the analysis.

8. The system of claim 2, wherein said call monitor performs the automatic analysis of dialogue by detecting interruptions.

9. The system of claim 2, wherein said call monitor performs the automatic analysis of dialogue by tracking a number of dialogue turns.

10. The system of claim 2, wherein said call monitor performs the automatic analysis of dialogue by recognizing speech content and comparing the speech content to key phrases adapted to detect frustration, polity, and resolution characteristics of the dialogue.

11. The system of claim 2, wherein said call monitor performs the automatic analysis of dialogue by at least once more extracting voice characteristics from the customer speech during the interaction and reassessing a categorization of the customer based on the voice characteristics extracted from the customer speech during the interaction.

12. A call routing and supervising method, comprising:

receiving customer speech from a remote location;

extracting voice characteristics from the customer speech using trained models of a plurality of different groups of speakers;

selecting one or more from a plurality of human customer service representatives based on profiles of the human customer service representatives that map to said plurality of different groups of speakers, wherein the profiles define voice characteristics of speech uttered by each of the plurality of human customer service representatives, wherein speech uttered by the selected one or more customer service representatives have voice characteristics similar to the voice characteristics extracted from the customer speech

extracting customer satisfaction indicators from voice characteristics of said customer speech; and

self-tuning the mapping of said plurality of different groups of speakers to said plurality of human customer service representatives to based on said customer satisfaction indicators.

13. The method of claim 12, further comprising performing an automatic analysis of dialogue between the customer and a human customer service representative during interaction between the customer and the human customer service representative.

14. The method of claim 13, further comprising recording performance of the human customer service representative respective of customers having the voice characteristics based on the analysis.

15. The method of claim 13, further comprising:

automatically selecting predefined instructions based on the analysis; and

communicating the instructions to the human customer service representative during interaction between the customer and the human customer service representative.

16. The method of claim 15, further comprising:

instructing the human customer service representative to reroute the call based on the analysis; and

selecting a new one of plural human customer service representatives.

17. The method of claim 16, wherein selecting the new one of plural human customer service representatives is based on previous performance of the human customer service representatives respective of customers having voice characteristics similar to the voice characteristics extracted from the customer speech.

18. The method of claim 16, wherein selecting the new one of plural human customer service representatives is based on a preexisting supervisory relationship between the new human customer service representative and the human customer service representative interacting with the customer during the analysis.

19. The method of claim 13, wherein performing an automatic analysis of dialogue includes detecting interruptions.

20. The method of claim 13, wherein performing an automatic analysis of dialogue includes tracking a number of dialogue turns.

21. The method of claim 13, wherein performing an automatic analysis of dialogue includes recognizing speech content and comparing the speech content to key phrases adapted to detect frustration, polity, and resolution characteristics of the dialogue.

22. The method of claim 13, wherein performing an automatic analysis of dialogue includes at least once more extracting voice characteristics from the customer speech during the interaction and reassessing a categorization of the customer based on the voice characteristics extracted from the customer speech during the interaction.

23. A call routing and supervising system, comprising:

an input that receives customer speech of a customer at a remote location;

a voice characteristics extractor that extracts voice characteristics from the customer speech based on trained models, wherein a trained model corresponds to a group of speakers from a plurality of different groups of speakers;

a customer categorizer that categorizes the customer into a customer category based on the voice characteristics extracted from the customer speech and the trained models;

a plurality of customer service representative profiles, wherein a customer service representative profile maps a particular customer service representative to a particular customer category;

a customer service selector that selects a customer service representative from a plurality of customer service representatives to service the customer based on the customer group of the customer and the profile of the customer service representative; and

a call supervision component that monitors dialogue between the customer service representative and the customer and extracts customer service indicators indicating a degree of satisfaction of the customer from the voice characteristics extracted from the customer speech; and

a profile updating component that updates the mapping of the customer service representative profile of the customer service representative to the customer category based on the customer service indicators extracted from the dialogue.