Contact center autopilot algorithms

• US 6,856,680 B2
• Filed: 09/24/2001
• Issued: 02/15/2005
• Est. Priority Date: 09/24/2001
• Status: Expired due to Term

• Current Assignee: Firstpoint Contact Technologies, LLC (Alvaria Incorporated)
• Original Assignee: Rockwell Electronics Commerce Technologies LLC
• Inventors: Fertig, Ken, Reddy, Sudhakar, Mengshoel, Ole J.
• Primary Examiner(s): Hong, Harry S.
• Application Number:
  US09/961,875
• Publication Number:
  US 20030095652A1
• Time in Patent Office: 1,240 Days
• Field of Search: 379/265.01, 379/265.02, 379/265.03, 379/265.04, 379/265.05, 379/265.06, 379/265.07, 379/265.08, 379/265.1, 379/265.11, 379/265.12, 379/265.13, 379/265.14, 705/8, 705/9, 705/10
• US Class Current: 379/265.06
• CPC Class Codes: H04M 3/5233 Operator skill based call distribution

Abstract

A method and apparatus are provided for dynamically reassigning agents among call types in a call distribution system having a plurality of agents assigned to a plurality of call types. The method includes the steps of detecting a deficiency in agent responsibility assigned to a call type of the plurality of call types based upon a measured service parameter and corresponding target service parameter and determining an agent allocation among the plurality of call types best suited to correct the deficiency.

Claims

1. A method of dynamically reassigning agent responsibility among call types in a call distribution system having a plurality of agents assigned to a plurality of call types, such method comprising the steps of:

detecting a deficiency in agent responsibility assigned to a call type of the plurality of call types based upon a measured service parameter and corresponding target service parameter;

creating a plurality of alternative agent allocation scenarios based upon a search process; and

determining an agent allocation among the plurality of call types best suited to correct the deficiency from among the created plurality of alternative agent allocation scenarios.

2. The method of dynamically reassigning agent responsibility among call types as in claim 1 wherein the step of determining the agent allocation among the plurality of call types best suited to correct the deficiency further comprises predicting a performance of each of a plurality of agent reallocation scenarios.

3. The method of dynamically reassigning agent responsibility among call types as in claim 2 wherein the step of predicting the performance of each of the plurality of agent reallocation scenarios further comprises using a single queue Erlang model to approximate the agent allocation best suited to correct the deficiency.

4. The method of dynamically reassigning agent responsibility among call types as in claim 1 wherein the step of detecting a deficiency further comprises measuring a service parameter for at least some call types of the plurality of call types.

5. The method of dynamically reassigning agent responsibility among call types as in claim 4 wherein the step of detecting a deficiency further comprises comparing the measured service parameter with the target service parameter.

6. The method of dynamically reassigning agent responsibility among call types as in claim 5 wherein the step of determining an agent allocation among the plurality of call types best suited to correct the deficiency further comprises estimating a service parameter of each of the plurality of call types for each of a plurality of alternative agent reallocation scenarios.

7. The method of dynamically reassigning agent responsibility among call types as in claim 6 wherein the step of estimating the service parameter for each of the plurality of call types further comprises calculating a combined utility among the estimated service parameter for each of the plurality of alternative agent reallocation scenarios.

8. The method of dynamically reassigning agent responsibility among call types as in claim 1 wherein the step of detecting a deficiency further comprises measuring an average speed of answer for at least some call types of the plurality of call types.

9. The method of dynamically reassigning agent responsibility among call types as in claim 8 wherein the step of detecting a deficiency further comprises comparing the measured average speed of answer with a threshold value.

10. The method of dynamically reassigning agent responsibility among call types as in claim 9 wherein the step of determining an agent allocation among the plurality of call types best suited to correct the deficiency further comprises estimating an average speed of answer of each of the plurality of call types for each of a plurality of alternative agent reallocation scenarios.

11. The method of dynamically reassigning agent responsibility among call types as in claim 10 wherein the step of estimating the service parameter for each of the plurality of call types further comprises calculating a combined utility among the estimated average speed of answer for each of the plurality of alternative agent reallocation scenarios.

12. The method of dynamically reassigning agent responsibility among call types as in claim 1 wherein the step of detecting a deficiency further comprises measuring a call abandonment rate for at least some call types of the plurality of call types.

13. The method of dynamically reassigning agent responsibility among call types as in claim 12 wherein the step of detecting a deficiency further comprises comparing the measured abandonment rate with a threshold value.

14. The method of dynamically reassigning agent responsibility among call types as in claim 13 wherein the step of determining an agent allocation among the plurality of call types best suited to correct the deficiency further comprises estimating an abandonment rate of each of the plurality of call types for each of a plurality of alternative agent reallocation scenarios.

15. The method of dynamically reassigning agent responsibility among call types as in claim 14 wherein the step of estimating the service parameter for each of the plurality of call types further comprises calculating a combined utility among the estimated abandonment rates for each of the plurality of alternative agent reallocation scenarios.

16. The method of dynamically reassigning agent responsibility among call types as in claim 1 wherein the step of determining the agent allocation further comprises reallocating a fractional portion of an agent'"'"'s time from a first call type to a second call type of the plurality of call types.

17. The method of dynamically reassigning agent responsibility among call types as in claim lwherein the step of determining an agent allocation best suited to correct the deficiency further comprises identifying an agent allocation scenario providing a largest relative number of calls handled per time period.

18. An apparatus for dynamically reassigning agent responsibility among call types in a call distribution system having a plurality of agents assigned to a plurality of call types, such apparatus comprising:

means for detecting a deficiency in agent responsibility assigned to a call type of the plurality of call types based upon a measured service parameter and corresponding target service parameter;

means for creating a plurality of alternative agent allocation scenarios based upon a search process; and

means for determining an agent allocation among the plurality of call types best suited to correct the deficiency from among the plurality of alternative agent allocation scenarios provided by the means for creating.

19. The apparatus for dynamically reassigning agent responsibility among call types as in claim 18 wherein the means for determining the agent allocation among the plurality of call types best suited to correct the deficiency further comprises means for predicting a performance of each of a plurality of agent reallocation scenarios.

20. The apparatus for dynamically reassigning agent responsibility among call types as in claim 19 wherein the means for predicting the performance of each of the plurality of agent reallocation scenarios further comprises means for using a single queue Erlang model to approximate the agent allocation best suited to correct the deficiency.

21. The apparatus for dynamically reassigning agent responsibility among call types as in claim 18 wherein the means for detecting a deficiency further comprises means for measuring a service parameter for at least some call types of the plurality of call types.

22. The apparatus for dynamically reassigning agent responsibility among call types as in claim 21 wherein the means for detecting a deficiency further comprises means for comparing the measured service parameter with the target service parameter.

23. The apparatus for dynamically reassigning agent responsibility among call types as in claim 22 wherein the means for determining an agent allocation among the plurality of call types best suited to correct the deficiency further comprises means for estimating a service parameter of each of the plurality of call types for each of a plurality of alternative agent reallocation scenarios.

24. The apparatus for dynamically reassigning agent responsibility among call types as in claim 23 wherein the means for estimating the service parameter for each of the plurality of call types further comprises means for calculating a combined utility among the estimated service parameter for each of the plurality of alternative agent reallocation scenarios.

25. The apparatus for dynamically reassigning agent responsibility among call types as in claim 18 wherein the means for detecting a deficiency further comprises means for measuring an average speed of answer for at least some call types of the plurality of call types.

26. The apparatus for dynamically reassigning agent responsibility among call types as in claim 25 wherein the means for detecting a deficiency further comprises means for comparing the measured average speed of answer with a threshold value.

27. The apparatus for dynamically reassigning agent responsibility among call types as in claim 26 wherein the means for determining an agent allocation among the plurality of call types best suited to correct the deficiency further comprises means for estimating an average speed of answer of each of the plurality of call types for each of a plurality of alternative agent reallocation scenarios.

28. The apparatus for dynamically reassigning agent responsibility among call types as in claim 27 wherein the means for estimating the service parameter for each of the plurality of call types further comprises means for calculating a combined utility among the estimated average speed of answer for each of the plurality of alternative agent reallocation scenarios.

29. The apparatus for dynamically reassigning agent responsibility among call types as in claim 18 wherein the means for detecting a deficiency further comprises means for measuring a call abandonment rate for at least some call types of the plurality of call types.

30. The apparatus for dynamically reassigning agent responsibility among call types as in claim 29 wherein the means for detecting a deficiency further comprises means for comparing the measured abandonment rate with a threshold value.

31. The apparatus for dynamically reassigning agent responsibility among call types as in claim 30 wherein the means for determining an agent allocation among the plurality of call types best suited to correct the deficiency further comprises means for estimating an abandonment rate of each of the plurality of call types for each of a plurality of alternative agent reallocation scenarios.

32. The apparatus for dynamically reassigning agent responsibility among call types as in claim 31 wherein the means for estimating the service parameter for each of the plurality of call types further comprises means for calculating a combined utility among the estimated abandonment rates for each of the plurality of alternative agent reallocation scenarios.

33. The apparatus for dynamically reassigning agent responsibility among call types as in claim 19 wherein the means for predicting the agent allocation further comprises means for reallocating a fractional portion of an agent'"'"'s time from a first call type to a second call type of the plurality of call types.

34. The apparatus for dynamically reassigning agent responsibility among call types as in claim 19 wherein the means for predicting an agent allocation best suited to correct the deficiency further comprises means for identifying an agent allocation scenario providing a largest relative number of calls handled per time period.

35. An apparatus for dynamically reassigning agent responsibility among call types in a call distribution system having a plurality of agents assigned to a plurality of call types, such apparatus comprising:

a statistics processor adapted to detect a deficiency in agent responsibility assigned to a call type of the plurality of call types based upon a measured service parameter and corresponding target service parameter;

a matrix generator adapted to create a plurality of alternative agent allocation scenarios based upon a search process; and

an autopilot for determining an agent allocation among the plurality of call types best suited to correct the deficiency from the plurality of alternative agent allocation scenarios provided by the matrix generator.

36. The apparatus for dynamically reassigning agent responsibility among call types as in claim 35 wherein the autopilot for determining the agent allocation among the plurality of call types best suited to correct the deficiency further comprises a performance predictor adapted to predict a performance of each of a plurality of agent reallocation scenarios.

37. The apparatus for dynamically reassigning agent responsibility among call types as in claim 35 wherein the autopilot further comprises means for using a single queue Erlang model adapted to approximate the agent allocation best suited to correct the deficiency.

38. The apparatus for dynamically reassigning agent responsibility among call types as in claim 35 wherein the statistics processor detecting a deficiency further comprises a service level processor adapted to measure a service parameter for at least some call types of the plurality of call types.

39. The apparatus for dynamically reassigning agent responsibility among call types as in claim 38 further comprising a comparator adapted to compare the measured service parameter with the target service parameter.

40. The apparatus for dynamically reassigning agent responsibility among call types as in claim 39 wherein the autopilot further comprises a performance predictor adapted to estimate a service parameter of each of the plurality of call types for each of a plurality of alternative agent reallocation scenarios.

41. The apparatus for dynamically reassigning agent responsibility among call types as in claim 40 wherein the autopilot further comprises a utility processor adapted to calculate a combined utility among the estimated service parameter for each of the plurality of alternative agent reallocation scenarios.

42. The apparatus for dynamically reassigning agent responsibility among call types as in claim 35 wherein the statistics processor further comprises an average speed of answer processor adapted to measure an average speed of answer for at least some call types of the plurality of call types.

43. The apparatus for dynamically reassigning agent responsibility among call types as in claim 42 further comprising a comparator adapted to compare the measured average speed of answer with a threshold value.

44. The apparatus for dynamically reassigning agent responsibility among call types as in claim 43 wherein the autopilot further comprises a performance predictor adapted to estimate an average speed of answer of each of the plurality of call types for each of a plurality of alternative agent reallocation scenarios.

45. The apparatus for dynamically reassigning agent responsibility among call types as in claim 44 wherein performance predictor further comprises a utility processor adapted to calculate a combined utility among the estimated average speed of answer for each of the plurality of alternative agent reallocation scenarios.

46. The apparatus for dynamically reassigning agent responsibility among call types as in claim 35 wherein the statistical processor further comprises an abandonment processor adapted to measure a call abandonment rate for at least some call types of the plurality of call types.

47. The apparatus for dynamically reassigning agent responsibility among call types as in claim 46 further comprising a comparator adapted to compare the measured abandonment rate with a threshold value.

48. The apparatus for dynamically reassigning agent responsibility among call types as in claim 47 wherein the autopilot further comprises a performance predictor adapted to estimate an abandonment rate of each of the plurality of call types for each of a plurality of alternative agent reallocation scenarios.

49. The apparatus for dynamically reassigning agent responsibility among call types as in claim 48 further comprising a utility processor adapted to calculate a combined utility among the estimated abandonment rates for each of the plurality of alternative agent reallocation scenarios.

50. The apparatus for dynamically reassigning agent responsibility among call types as in claim 35 wherein the autopilot further comprises a target matrix adapted for reallocation of a fractional portion of an agent'"'"'s time from a first call type to a second call type of the plurality of call types.