Techniques for estimating expected performance in a task assignment system

• US 10,116,795 B1
• Filed: 07/13/2017
• Issued: 10/30/2018
• Est. Priority Date: 07/10/2017
• Status: Active Grant

• Current Assignee: Afiniti Ltd
• Original Assignee: Afiniti Europe Technologies Limited (Afiniti Ltd)
• Inventors: Chishti, Zia, Kan, Ittai, Khatri, Vikash
• Primary Examiner(s): Al Aubaidi, Rasha
• Application Number:
  US15/648,788
• Time in Patent Office: 474 Days
• Field of Search: 37926501-26502, 37926505-26506, 37926601-26602
• CPC Class Codes: G06Q 10/06311 Scheduling, planning or task assignment for a person or group
• CPC Class Codes: H04M 2203/401 Performance feedback
• CPC Class Codes: H04M 2203/402 Agent or workforce management
• CPC Class Codes: H04M 3/5175 Call or contact centers supervision arrangements
• CPC Class Codes: H04M 3/5232 Call distribution algorithms

Abstract

Techniques for estimating expected performance of a task assignment strategy in a task assignment system are disclosed. In one particular embodiment, the techniques may be realized as a method comprising receiving, by at least one computer processor communicatively coupled to a task assignment system, a plurality of historical agent task assignments; determining, by the at least one computer processor, a sample of the plurality based on a strategy for pairing agents with tasks; determining, by the at least one computer processor, an expected performance of the strategy based on the sample; outputting, by the at least one computer processor, the expected performance; and optimizing, by the at least one computer processor, the performance of the task assignment system based on the expected performance.

Claims

1. A method comprising:

receiving, by at least one computer processor communicatively coupled to and configured to perform task assignment operations in a task assignment system, a first plurality of historical agent-task assignments;

determining, by the at least one computer processor, a closeness of fit for each of the first plurality of historical agent-task assignments to a preferred task assignment strategy for validating the preferred task assignment strategy;

determining, by the at least one computer processor, a threshold closeness of fit for each of the first plurality of historical agent-task assignments to the preferred task assignment strategy;

determining, by the at least one computer processor, an expected performance of the task assignment system using the preferred task assignment strategy based on a subset of the first plurality of historical agent-task assignments that are within the threshold closeness of fit;

outputting, by the at least one computer processor, the expected performance for use in pairing agents with tasks in the task assignment system based upon the preferred task assignment strategy; and

establishing, by the at least one computer processor, in a switch of the task assignment system, a connection between an agent and a task based upon the expected performance to realize a first amount of performance gain for the task assignment system attributable to the preferred task assignment strategy, wherein actual performance of the task assignment system is optimized by using the validated preferred task assignment strategy based on the expected performance.

2. The method of claim 1, further comprising:

determining, by the at least one computer processor, a plurality of thresholds of closeness of fit to the preferred task assignment strategy.

3. The method of claim 2, further comprising:

determining, by the at least one computer processor, a correlation of performance of the preferred task assignment strategy to varying degrees of achievement of the preferred task assignment strategy.

4. The method of claim 3, wherein the expected performance is also based on the correlation of performance.

5. The method of claim 4, further comprising:

receiving, by the least one computer processor, a second plurality of historical agent-task assignments generated using the preferred task assignment strategy; and

analyzing, by the at least one computer processor, the correlation of performance based on the second plurality of historical agent-task assignments.

6. The method of claim 5, wherein the second plurality of historical agent-task assignments covers a second date range different from a first date range of the first plurality of historical agent-task assignments.

7. The method of claim 5, wherein each of the second plurality of historical agent-task assignments was paired using the preferred task assignment strategy, and wherein each of the first plurality of historical agent-task assignments was paired using a different task assignment strategy.

8. The method of claim 5, wherein the second plurality of historical agent-task assignments includes some of the historical agent-task assignments from the first plurality of historical agent-task assignments.

9. The method of claim 5, wherein each of the second plurality of historical agent-task assignments is different from each of the first plurality of historical agent-task assignments.

10. The method of claim 1, wherein the task assignment system is a contact center system, and wherein the preferred task assignment strategy assigns contacts to contact center agents.

11. The method of claim 1, wherein the plurality of historical agent-task assignments is a holdout set of a superset of historical agent-task assignments.

12. The method of claim 1, wherein the subset of the plurality of historical agent-task assignments that are within the threshold closeness of fit is a sample of the holdout set.

13. A system comprising:

at least one computer processor communicatively coupled to and configured to perform task assignment operations in a task assignment system, wherein the at least one computer processor is further configured to;

receive a first plurality of historical agent-task assignments;

determine a closeness of fit for each of the first plurality of historical agent-task assignments to a preferred task assignment strategy for validating the preferred task assignment strategy;

determine a threshold closeness of fit for each of the first plurality of historical agent-task assignments to the preferred task assignment strategy;

determine an expected performance of the task assignment system using the preferred task assignment strategy based on a subset of the first plurality of historical agent-task assignments that are within the threshold closeness of fit;

output the expected performance for use in pairing agents with tasks in the task assignment system based upon the preferred task assignment strategy; and

establish, in a switch of the task assignment system, a connection between an agent and a task based upon the expected performance to realize a first amount of performance gain for the task assignment system attributable to the preferred task assignment strategy, wherein actual performance of the task assignment system is optimized by using the validated preferred task assignment strategy based on the expected performance.

14. The system of claim 13, wherein the at least one computer processor is further configured to:

determine a plurality of thresholds of closeness of fit to the preferred task assignment strategy.

15. The system of claim 14, wherein the at least one computer processor is further configured to:

determine a correlation of performance of the preferred task assignment strategy to varying degrees of achievement of the preferred task assignment strategy.

16. The system of claim 15, wherein the expected performance is also based on the correlation of performance.

17. The system of claim 16, wherein the at least one computer processor is further configured to:

receive a second plurality of historical agent-task assignments generated using the preferred task assignment strategy; and

analyze the correlation of performance based on the second plurality of historical agent-task assignments.

18. The system of claim 17, wherein the second plurality of historical agent-task assignments covers a second date range different from a first date range of the first plurality of historical agent-task assignments.

19. The system of claim 17, wherein each of the second plurality of historical agent-task assignments was paired using the preferred task assignment strategy, and wherein each of the first plurality of historical agent-task assignments was paired using a different task assignment strategy.

20. The system of claim 17, wherein the second plurality of historical agent-task assignments includes some of the historical agent-task assignments from the first plurality of historical agent-task assignments.

21. The system of claim 17, wherein each of the second plurality of historical agent-task assignments is different from each of the first plurality of historical agent-task assignments.

22. The system of claim 13, wherein the task assignment system is a contact center system, and wherein the preferred task assignment strategy assigns contacts to contact center agents.

23. The system of claim 13, wherein the plurality of historical agent-task assignments is a holdout set of a superset of historical agent-task assignments.

24. The system of claim 13, wherein the subset of the plurality of historical agent-task assignments that are within the threshold closeness of fit is a sample of the holdout set.

25. An article of manufacture comprising:

a non-transitory processor readable medium; and

instructions stored on the medium;

wherein the instructions are configured to be readable from the medium by at least one computer processor communicatively coupled to and configured to perform task assignment operations in a task assignment system and thereby cause the at least one computer processor to operate so as to;

receive a first plurality of historical agent-task assignments;

determine a closeness of fit for each of the first plurality of historical agent-task assignments to a preferred task assignment strategy for validating the preferred task assignment strategy;

determine a threshold closeness of fit for each of the first plurality of historical agent-task assignments to the preferred task assignment strategy;

determine an expected performance of the task assignment system using the preferred task assignment strategy based on a subset of the first plurality of historical agent-task assignments that are within the threshold closeness of fit;

output the expected performance for use in pairing agents with tasks in the task assignment system based upon the preferred task assignment strategy; and

establish, in a switch of the task assignment system, a connection between an agent and a task based upon the expected performance to realize a first amount of performance gain for the task assignment system attributable to the preferred task assignment strategy, wherein actual performance of the task assignment system is optimized by using the validated preferred task assignment strategy based on the expected performance.

26. The article of manufacture of claim 25, wherein the at least one computer processor is further caused to operate so as to:

determine a plurality of thresholds of closeness of fit to the preferred task assignment strategy.

27. The article of manufacture of claim 26, wherein the at least one computer processor is further caused to operate so as to:

determine a correlation of performance of the preferred task assignment strategy to varying degrees of achievement of the preferred task assignment strategy.

28. The article of manufacture of claim 27, wherein the expected performance is also based on the correlation of performance.

29. The article of manufacture of claim 28, wherein the at least one computer processor is further caused to operate so as to:

receive a second plurality of historical agent-task assignments generated using the preferred task assignment strategy; and

analyze the correlation of performance based on the second plurality of historical agent-task assignments.

30. The article of manufacture of claim 25, wherein the task assignment system is a contact center system, and wherein the preferred task assignment strategy assigns contacts to contact center agents.