System, Method And Program Product For Analyses Based On Agent-Customer Interactions And Concurrent System Activity By Agents

• US 20110197206A1
• Filed: 02/11/2010
• Published: 08/11/2011
• Est. Priority Date: 02/11/2010
• Status: Abandoned Application

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Visweswariah, Karthik, Wright, Gary J., Rzasa, Maureen E., Dorai, Chitra, Joshi, Shailesh, Deshmukh, Om D., Verma, Ashish, Zeng, Sai
• Application Number:
  US12/704,002
• Publication Number:
  US 20110197206A1
• Time in Patent Office: Days
• US Class Current: 719/317
• CPC Class Codes: G06Q 10/06 Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling

Abstract

A method includes deriving first information from a number of agent-customer interactions in a customer service system, and determining concurrent system activity by the agents in the customer service system, the concurrent system activity occurring at least partially concurrently with the number of agent-customer interactions. The method further includes combining the determined first information and the determined concurrent system activity to determine second information related to one or more of the number of agent-customer interactions, and outputting the second information. Apparatus and program products are also disclosed.

Claims

1. A method, comprising:

deriving first information from a plurality of agent-customer interactions in a customer service system;

determining concurrent system activity by the agents in the customer service system, the concurrent system activity occurring at least partially concurrently with the plurality of agent-customer interactions;

combining the determined first information and the determined concurrent system activity to determine second information related to at least one of the plurality of agent-customer interactions; and

outputting the second information.

2. The method of claim 1, wherein deriving first information further comprises performing segmentation on at least one of calls or chats to derive a plurality of phases associated with the at least one of the calls or chats.

3. The method of claim 2, wherein deriving first information further comprises performing segmentation on calls and deriving speaker turn information, the speaker turn information indicating which speaker of the agent or the customer was speaking during a particular time period.

4. The method of claim 3, wherein performing segmentation further comprises assigning a turn taken by one of the agent or customer and associated with an agent-customer interaction to multiple phases with different probabilities.

5. The method of claim 2, wherein performing segmentation further comprises using information from data that is hand marked as to phase in order to perform segmentation on the at least one of calls or chats to determine the plurality of phases.

6. The method of claim 5, wherein determining second information further comprises determining the second information using information from call aggregates.

7. The method of claim 5, wherein determining second information further comprises combining likely answer phrases with the segmentation, the concurrent system activity, and the information from call aggregates in order to provide at least one answer to at least one question input by a user, the at least one answer being second information.

8. The method of claim 5, wherein deriving first information further comprises performing segmentation on calls and deriving speaker turn information, the speaker turn information indicating which speaker of the agent or the customer was speaking during a particular time period.

9. The method of claim 8, wherein deriving the first information further comprises deriving prosodic features, lexical features, automatic speech recognition-based features, and channel-specific features.

10. The method of claim 1, wherein outputting the second information further comprises outputting data suitable for displaying the second information in at least one of a scorecard, chart, report, histogram, or pie chart.

11. The method of claim 10, further comprising displaying the at least one of the scorecard, chart, report, histogram, or pie chart.

12. The method of claim 1, wherein the first information comprises call type and call phases and the concurrent system activity comprises form filling, reading frequently asked questions, and performing research.

13. An apparatus comprising:

at least one processor;

at least one memory coupled to the at least one processor and comprising program code,

the at least one processor, in response to executing the program code, configured to cause the apparatus to perform the following;

deriving first information derived from a plurality of agent-customer interactions in a customer service system;

determining concurrent system activity by the agents in the customer service system, the concurrent system activity occurring at least partially concurrently with the plurality of agent-customer interactions;

combining the determined first information and the determined concurrent system activity to determine second information related to at least one of the plurality of agent-customer interactions; and

outputting the second information.

14. The apparatus of claim 13, wherein deriving first information further comprises performing segmentation on at least one of calls or chats to derive a plurality of phases associated with the at least one of the calls or chats.

15. The apparatus of claim 14, wherein deriving first information further comprises performing segmentation on calls and deriving speaker turn information, the speaker turn information indicating which speaker of the agent or the customer was speaking during a particular time period.

16. The apparatus of claim 15, wherein performing segmentation further comprises assigning a turn taken by one of the agent or customer and associated with an agent-customer interaction to multiple phases with different probabilities.

17. The apparatus of claim 14, wherein performing segmentation further comprises using information from data that is hand marked as to phase in order to perform segmentation on the at least one of calls or chats to determine the plurality of phases.

18. The apparatus of claim 17, wherein determining second information further comprises determining the second information using information from call aggregates.

19. The apparatus of claim 17, wherein determining second information further comprises combining likely answer phrases with the segmentation, the concurrent system activity, and the information from call aggregates in order to provide at least one answer to at least one question input by a user, the at least one answer being second information.

20. The apparatus of claim 17, wherein deriving first information further comprises performing segmentation on calls and deriving speaker turn information, the speaker turn information indicating which speaker of the agent or the customer was speaking during a particular time period.

21. The apparatus of claim 20, wherein deriving the first information further comprises deriving prosodic features, lexical features, automatic speech recognition-based features, and channel-specific features.

22. The apparatus of claim 13, wherein outputting the second information further comprises outputting data suitable for displaying the second information in at least one of a scorecard, chart, report, histogram, or pie chart.

23. The apparatus of claim 22, further comprising displaying the at least one of the scorecard, chart, report, histogram, or pie chart.

24. The apparatus of claim 13, wherein the first information comprises call type and call phases and the concurrent system activity comprises form filling, reading frequently asked questions, and performing research.

25. A computer readable medium tangibly embodying a program of machine-readable instructions executable by a digital processing apparatus to cause the digital processing apparatus to perform operations comprising:

deriving first information from a plurality of agent-customer interactions in a customer service system;

determining concurrent system activity by the agents in the customer service system, the concurrent system activity occurring at least partially concurrently with the plurality of agent-customer interactions;

combining the determined first information and the determined concurrent system activity to determine second information related to at least one of the plurality of agent-customer interactions; and

outputting the second information.