Techniques for benchmarking pairing strategies in a contact center system

• US 10,110,745 B2
• Filed: 06/26/2017
• Issued: 10/23/2018
• Est. Priority Date: 08/30/2016
• Status: Active Grant

• Current Assignee: Afiniti Ltd
• Original Assignee: Afiniti Europe Technologies Limited (Afiniti Ltd)
• Inventors: Rizvi, Syed Meesum Raza
• Primary Examiner(s): Nguyen, Quynh
• Application Number:
  US15/633,162
• Publication Number:
  US 20180063330A1
• Time in Patent Office: 484 Days
• Field of Search: 37926502, 37926511, 37926512
• CPC Class Codes: G06F 17/18 for evaluating statistical data , e.g. average values, frequency distributions, probability functions, regression analysis forecasting specially adapted for a specific administrative, business or logistic context G06Q10/04
• CPC Class Codes: G06Q 10/0639 Performance analysis of employees; Performance analysis of enterprise or organisation operations
• CPC Class Codes: G06Q 10/06398 Performance of employee with respect to a job function
• CPC Class Codes: H04M 2203/551 Call history recording a computer conference H04L12/1831
• CPC Class Codes: H04M 2203/556 Statistical analysis and interpretation
• CPC Class Codes: H04M 3/5141 Details of processing calls and other types of contacts in an unified manner unified messaging in packet-switching networks H04L51/56
• CPC Class Codes: H04M 3/5232 Call distribution algorithms
• CPC Class Codes: H04M 3/5233 Operator skill based call distribution

Abstract

Techniques for benchmarking pairing strategies in a contact center system are disclosed. In one particular embodiment, the techniques may be realized as a method for benchmarking pairing strategies in a contact center system including determining results for a first plurality of contact-agent interactions, determining results for a second plurality of contact-agent interactions, and determining combined results across the first and second pluralities of contact-agent interactions corrected for a Yule-Simpson effect.

Claims

1. A method for benchmarking pairing strategies in a contact center system comprising:

cycling, by at least one computer processor communicatively coupled to and configured to perform benchmarking operations in the contact center system, among at least two pairing strategies in the contact center system, wherein the cycling comprises alternatively applying a first contact-agent pairing strategy and at least one second contact-agent pairing strategy in the contact center system to pair contacts with agents according to the respective pairing strategy being applied for connection in the contact center system;

for each of a plurality of contact-agent interactions in the contact center system, recording, by the at least one computer processor, a result of the contact-agent interaction, a pairing strategy indicator of which of the at least two pairing strategies was used for pairing the contact-agent interaction, and an interaction type indicator of which of a plurality of contact-agent interaction types is associated with the contact-agent interaction;

for each of the at least two pairing strategies, combining, by the at least one computer processor, results for the plurality of contact-agent interactions paired using a same pairing strategy of the at least two pairing strategies, corrected for a Yule-Simpson effect, and based on the recorded result, the pairing strategy indicator, and the interaction type indicator;

determining, by the at least one computer processor, a difference in performance between the at least two pairing strategies corrected for the Yule-Simpson effect, wherein the difference in performance is a performance gain attributable to utilizing the first pairing strategy of the at least two pairing strategies to optimize performance of the contact center system compared to the at least one second of the at least two pairing strategies; and

outputting, by the at least one computer processor, the difference in performance between the at least two pairing strategies corrected for the Yule-Simpson effect for benchmarking at least the first pairing strategy of the at least two pairing strategies with respect to the at least one second of the at least two pairing strategies.

2. The method of claim 1, wherein the first pairing strategy is a behavioral pairing strategy.

3. The method of claim 1, further comprising:

determining, by the at least one computer processor, a second difference in performance between the at least two pairing strategies uncorrected for the Yule-Simpson effect, wherein the second performance difference incorrectly demonstrates that optimizing performance of the contact center system could be realized using the at least one second of the at least two pairing strategies instead of the first pairing strategy.

4. The method of claim 1, wherein each interaction type indicator indicates which of a plurality of skills is associated with each of the plurality of contact-agent interactions.

5. The method of claim 1, wherein each interaction type indicator indicates which of a plurality of time periods is associated with each of the plurality of contact-agent interactions.

6. The method of claim 1, wherein the at least two pairing strategies alternate more frequently than once per day.

7. The method of claim 1, wherein the Yule-Simpson effect was a result of an underlying partitioning of contact-agent interactions indicated by each of the interaction type indicators according to at least one of:

a plurality of time periods,

a plurality of agent skills,

a plurality of contact-agent assignment strategies (pairing strategies),

a plurality of contact center sites,

a plurality of contact center switches, and

a plurality of benchmarking schedules.

8. A system for benchmarking pairing strategies in a contact center system comprising:

at least one computer processor configured to perform benchmarking operations in the contact center system, wherein the at least one computer processor is configured to;

cycle among at least two pairing strategies in the contact center system, wherein the cycling comprises alternatively applying a first contact-agent pairing strategy and at least one second contact-agent pairing strategy in the contact center system to pair contacts with agents according to the respective pairing strategy being applied for connection in the contact center system;

for each of a plurality of contact-agent interactions in the contact center system, record a result of the contact-agent interaction, a pairing strategy indicator of which of the at least two pairing strategies was used for pairing the contact-agent interaction, and an interaction type indicator of which of a plurality of contact-agent interaction types is associated with the contact-agent interaction;

for each of the at least two pairing strategies, combine results for the plurality of contact-agent interactions paired using a same pairing strategy of the at least two pairing strategies, corrected for a Yule-Simpson effect, and based on the recorded result, the pairing strategy indicator, and the interaction type indicator; and

determine a difference in performance between the at least two pairing strategies corrected for the Yule-Simpson effect, wherein the difference in performance is a performance gain attributable to utilizing the first pairing strategy of the at least two pairing strategies to optimize performance of the contact center system compared to the at least one second of the at least two pairing strategies; and

output the difference in performance between the at least two pairing strategies corrected for the Yule-Simpson effect for benchmarking at least the first pairing strategy of the at least two pairing strategies with respect to the at least one second of the at least two pairing strategies.

9. The system of claim 8, wherein the first pairing strategy is a behavioral pairing strategy.

10. The system of claim 8, further comprising:

determining, by the at least one computer processor, a second difference in performance between the at least two pairing strategies uncorrected for the Yule-Simpson effect, wherein the second performance difference incorrectly demonstrates that optimizing performance of the contact center system could be realized using the at least one second of the at least two pairing strategies instead of the first pairing strategy.

11. The system of claim 8, wherein each interaction type indicator indicates which of a plurality of skills is associated with each of the plurality of contact-agent interactions.

12. The system of claim 8, wherein each interaction type indicator indicates which of a plurality of time periods is associated with each of the plurality of contact-agent interactions.

13. The system of claim 8, wherein the at least two pairing strategies alternate more frequently than once per day.

14. The system of claim 8, wherein the Yule-Simpson effect was a result of an underlying partitioning of contact-agent interactions indicated by each of the interaction type indicators according to at least one of:

a plurality of time periods,

a plurality of agent skills,

a plurality of contact-agent assignment strategies (pairing strategies),

a plurality of contact center sites,

a plurality of contact center switches, and

a plurality of benchmarking schedules.

19. The system of claim 8, wherein the at least two pairing strategies alternate more frequently than once per day.

15. An article of manufacture for benchmarking pairing strategies in a contact center system comprising:

a non-transitory computer 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 configured to operate in the contact center system and thereby cause the at least one computer processor to operate further so as to;

cycle among at least two pairing strategies in the contact center system, wherein the cycling comprises alternatively applying a first contact-agent pairing strategy and at least one second contact-agent pairing strategy in the contact center system to pair contacts with agents according to the respective pairing strategy being applied for connection in the contact center system;

for each of a plurality of contact-agent interactions in the contact center system, record a result of the contact-agent interaction, a pairing strategy indicator of which of the at least two pairing strategies was used for pairing the contact-agent interaction, and an interaction type indicator of which of a plurality of contact-agent interaction types is associated with the contact-agent interaction;

for each of the at least two pairing strategies, combine results for the plurality of contact-agent interactions paired using a same pairing strategy of the at least two pairing strategies, corrected for a Yule-Simpson effect, and based on the recorded result, the pairing strategy indicator, and the interaction type indicator; and

determine a difference in performance between the at least two pairing strategies corrected for the Yule-Simpson effect, wherein the difference in performance is a performance gain attributable to utilizing the first pairing strategy of the at least two pairing strategies to optimize performance of the contact center system compared to the at least one second of the at least two pairing strategies; and

output the difference in performance between the at least two pairing strategies corrected for the Yule-Simpson effect for benchmarking at least the first pairing strategy of the at least two pairing strategies with respect to the at least one second of the at least two pairing strategies.

16. The article of manufacture of claim 15, wherein the first pairing strategy is a behavioral pairing strategy.

17. The article of manufacture of claim 15, further comprising:

determining, by the at least one computer processor, a second difference in performance between the at least two pairing strategies uncorrected for the Yule-Simpson effect, wherein the second performance difference incorrectly demonstrates that optimizing performance of the contact center system could be realized using the at least one second of the at least two pairing strategies instead of the first pairing strategy.

18. The article of manufacture of claim 15, wherein each interaction type indicator indicates which of a plurality of skills is associated with each of the plurality of contact-agent interactions.

20. The article of manufacture of claim 15, wherein the Yule-Simpson effect was a result of an underlying partitioning of contact-agent interactions indicated by each of the interaction type indicators according to at least one of:

a plurality of time periods,

a plurality of agent skills,

a plurality of contact-agent assignment strategies (pairing strategies),

a plurality of contact center sites,

a plurality of contact center switches, and

a plurality of benchmarking schedules.