Analysis of the temporal evolution of emotions in an audio interaction in a service delivery environment

• US 8,417,524 B2
• Filed: 02/11/2010
• Issued: 04/09/2013
• Est. Priority Date: 02/11/2010
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Deshmukh, Om D., Dorai, Chitra, Joshi, Shailesh, Rzasa, Maureen E., Verma, Ashish, Visweswariah, Karthik, Wright, Gary J., Zeng, Sai
• Primary Examiner(s): GUERRA-ERAZO, EDGAR X
• Application Number:
  US12/704,172
• Publication Number:
  US 20110196677A1
• Time in Patent Office: 1,153 Days
• Field of Search: 704/207, 704/208, 704/210, 704/214, 704/215, 704/231, 704/246, 704/275, 704/235, 704/257, 704/270, 704/270.1, 704/243
• US Class Current: 704/243
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 2015/227 of the speaker; Human-factor methodology

Abstract

Analyzing an audio interaction is provided. At least one change in an emotion of a speaker in an audio interaction and at least one aspect of the audio interaction are identified. The at least one change in an emotion is analyzed in conjunction with the at least one aspect to determine a relationship between the at least one change in an emotion and the at least one aspect, and a result of the analysis is provided.

Claims

1. A method for analyzing an audio interaction, the method comprising:

identifying, by a computer, a change in an emotion of a speaker in an audio interaction;

identifying, by the computer, aspects of the audio interaction;

analyzing, by the computer, the change in the emotion of the speaker in conjunction with the aspects of the audio interaction;

determining, by the computer, a relationship between the change in the emotion of the speaker and the aspects of the audio interaction based on the computer analyzing the change in the emotion of the speaker in conjunction with the aspects;

identifying, by the computer, an emotion-influencing aspect of the audio interaction that caused the change in the emotion of the speaker based on the computer determining the relationship between the change in the emotion of the speaker and the aspects of the audio interaction; and

providing, by the computer, the emotion-influencing aspect identified in the audio interaction that caused the change in the emotion of the speaker.

2. The method of claim 1, wherein the speaker comprises a current speaker, further comprising:

identifying, by the computer, the current speaker in the audio interaction.

3. The method of claim 2, wherein identifying the current speaker in the audio interaction, comprises:

detecting, by the computer, a change in the speaker by detecting channel-specific non-speech features in the audio interaction.

4. The method of claim 1, wherein the identifying of the change in the emotion of the speaker in the audio interaction comprises identifying, by the computer, an interaction history of the speaker that includes a number of repeat calls made by the speaker obtained by analysis of system logs.

5. The method of claim 1, wherein the audio interaction is a telephone conversation.

6. The method of claim 1, wherein the audio interaction comprises an audio interaction between an agent in a contact center of an enterprise and a consumer.

7. The method of claim 6 further comprising:

collating, by the computer, the audio interaction with a plurality of further audio interactions between the agent and a plurality of consumers to improve efficiency of the agent.

8. The method of claim 6 further comprising:

analyzing, by the computer, a co-location of emotion changes and aspects over a plurality of audio interactions to propose best practices and to evaluate performance of agents in the contact center.

9. A computer program product stored in a computer readable storage device having computer usable program code embodied therein that is executable by a computer for analyzing an audio interaction, the computer program product comprising:

computer usable program code for identifying a change in an emotion of a speaker in an audio interaction;

computer usable program code for identifying aspects of the audio interaction;

computer usable program code for analyzing the change in the emotion of the speaker in conjunction with the aspects of the audio interaction;

computer usable program code for determining a relationship between the change in the emotion of the speaker and the aspects of the audio interaction based on the analyzing of the change in the emotion of the speaker in conjunction with the aspects;

computer usable program code for identifying an emotion-influencing aspect of the audio interaction that caused the change in the emotion of the speaker based on the determining of the relationship between the change in the emotion of the speaker and the aspects of the audio interaction; and

computer usable program code for providing the emotion-influencing aspect identified in the audio interaction that caused the change in the emotion of the speaker.

10. The computer program product of claim 9, wherein the speaker comprises a current speaker, further comprising:

computer usable program code for identifying the current speaker in the audio interaction.

11. The computer program product of claim 10, wherein the computer usable program code for identifying the current speaker in the audio interaction, comprises:

computer usable program code for detecting a change in the speaker by detecting channel-specific non-speech features in the audio interaction.

12. The computer program product of claim 9, wherein the computer usable program code for identifying the change in the emotion of the speaker in the audio interaction comprises computer usable program code for identifying an interaction history of the speaker that includes a number of repeat calls made by the speaker obtained by analysis of system logs.

13. The computer program product of claim 9, wherein the audio interaction is a telephone conversation between an agent in a contact center of an enterprise and a consumer.

14. The computer program product of claim 13, and further comprising:

computer usable program code for collating the audio interaction with a plurality of further audio interactions between the agent and a plurality of consumers to improve efficiency of the agent.

15. A computer system for analyzing an audio interaction, the computer system comprising:

a storage device storing instructions, and

a processor for executing the instructions to;

identify a change in an emotion of a speaker in an audio interaction;

identify aspects of the audio interaction;

analyze the change in the emotion of the speaker in conjunction with the aspects of the audio interaction;

determine a relationship between the change in the emotion of the speaker and the aspects of the audio interaction based on analyzing the change in the emotion of the speaker in conjunction with the aspects;

identify an emotion-influencing aspect of the audio interaction that caused the change in the emotion of the speaker based on determining the relationship between the change in the emotion of the speaker and the aspects of the audio interaction; and

provide the emotion-influencing aspect identified in the audio interaction that caused the change in the emotion of the speaker.

16. The computer system of claim 15, wherein the speaker comprises a current speaker, the processor further executing the instructions to identify the current speaker in the audio interaction.

17. The computer system of claim 16, wherein the processor executing the instructions to identify the current speaker, comprises the processor executing the instructions to detect a change in the speaker by detecting channel-specific non-speech features in the audio interaction.

18. The computer system of claim 15, wherein the processor executing the instructions to identify the change in the emotion of the speaker in the audio interaction comprises the processor executing the instructions to identify an interaction history of the speaker that includes a number of repeat calls made by the speaker obtained by analysis of system logs.

19. The computer system of claim 15, wherein the audio interaction is a telephone conversation between an agent in a contact center of an enterprise and a consumer.