IP Library Granted Patent US 11,070,674
Granted Patent B2
US 11,070,674 · App. 16/915,119 · Granted Jul 20, 2021

Techniques for benchmarking pairing strategies in a contact center system

Inventor: Zia Chishti (Washington, DC)
Assignee: AFINITI, LTD.
H04M3/5232H04M3/5141H04M3/5233H04M3/5235H04M2201/18H04M2201/36
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 11,070,674
App. No.
16/915,119
Granted
Jul 20, 2021
Kind
B2
Abstract

Techniques for benchmarking pairing strategies in a contact center system are disclosed. In one embodiment, the techniques may be realized as a method for benchmarking pairing strategies in a contact center system comprising: determining for each contact of a plurality of contacts, an associated plurality of historical contact assignments; determining, for each contact, an associated outcome value; partitioning, for each contact, the associated plurality of historical assignments into a first associated subset assigned using a first pairing strategy and a second associated subset assigned using a second pairing strategy; determining, for each contact, a first portion of the associated outcome value attributable to the first associated subset and a second portion of the associated outcome value attributable to the second associated subset; outputting a difference in performance between the first and second pairing strategies according to the first and second associated portions of the associated outcome value for each contact.

Claims (63)

1. A method comprising:

collecting first performance information for a first pairing strategy;

collecting second performance information for a second paring strategy, wherein the performance information indicates that the first pairing strategy has performed better than the second pairing strategy;

based on a random number, selecting, by at least one computer processor communicatively coupled to and configured to operate in a contact center system, a pairing strategy from a set of pairing strategies comprising the first pairing strategy and the second pairing strategy;

after selecting the first pairing strategy or the second paring strategy based on the random number, pairing, by the at least one computer processor, a contact to an agent in the contact center system using the selected pairing strategy; and

instructing a switch in the contact center system to connect the contact with the agent.

2. The method of claim 1 , wherein the random number is generated by a pseudorandom number generator.

3. The method of claim 2 , wherein a seed for the pseudorandom number generator is based on an identifier or part of the identifier of the contact.

4. The method of claim 2 , wherein a seed for the pseudorandom number generator is based on a phone number or part of the phone number of the contact.

5. The method of claim 2 , wherein a seed for the pseudorandom number generator is based on an arrival time of the contact.

6. The method of claim 1 , further comprising:

based on a second random number, selecting a pairing strategy from the set of pairing strategies comprising the first pairing strategy and the second pairing strategy;

after selecting the pairing strategy based on the second random number, pairing a second contact to an agent in the contact center system using the pairing strategy selected based on the second random number; and

instructing the switch in the contact center system to connect the second contact with the agent.

7. The method of claim 1 , wherein selecting the pairing strategy from the set of pairing strategies is independent of an agent utilization measurement of the contact center system.

8. The method of claim 1 , wherein at least one of the pairing strategies included in the set of pairing strategies is a behavioral pairing strategy.

9. A system comprising:

a data store for storing first performance information for a first pairing strategy and second performance information for a second paring strategy, wherein the performance information indicates that the first pairing strategy has performed better than the second pairing strategy;

at least one computer processor communicatively coupled to and configured to operate in a contact center system, wherein the at least one computer processor is further configured to:

based on a random number, select a pairing strategy from a set of pairing strategies comprising the first pairing strategy and the second pairing strategy;

after selecting the first pairing strategy or the second paring strategy based on the random number, pair a contact to an agent in the contact center system using the selected pairing strategy; and

instruct a switch in the contact center system to connect the contact with the agent.

10. The system of claim 9 , wherein the random number is generated by a pseudorandom number generator.

11. The system of claim 10 , wherein a seed for the pseudorandom number generator is based on an identifier or part of the identifier of the contact.

12. The system of claim 10 , wherein a seed for the pseudorandom number generator is based on a phone number or part of the phone number of the contact.

13. The system of claim 10 , wherein a seed for the pseudorandom number generator is based on an arrival time of the contact.

14. The system of claim 9 , wherein the at least one computer processor is further configured to:

based on a second random number, select a pairing strategy from the set of pairing strategies comprising the first pairing strategy and the second pairing strategy;

after selecting the pairing strategy based on the second random number, pair a second contact to an agent in the contact center system using the pairing strategy selected based on the second random number; and

instruct the switch in the contact center system to connect the second contact with the agent.

15. The system of claim 9 , wherein selecting the pairing strategy from the set of pairing strategies is independent of an agent utilization measurement of the contact center system.

16. The system of claim 9 , wherein at least one of the pairing strategies included in the set of pairing strategies is a behavioral pairing strategy.

17. An article of manufacture 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 communicatively coupled to and configured to operate in a contact center system and thereby cause the at least one computer processor to operate so as to:

based on a random number, select a pairing strategy from a set of pairing strategies comprising a first pairing strategy and a second pairing strategy, wherein performance information indicates that the first pairing strategy has performed better than the second pairing strategy;

after selecting the first pairing strategy or the second paring strategy based on the random number, pair a contact to an agent in the contact center system using the selected pairing strategy; and

instruct a switch in the contact center system to connect the contact with the agent.

18. The article of manufacture of claim 17 , wherein the random number is generated by a pseudorandom number generator.

19. The article of manufacture of claim 18 , wherein a seed for the pseudorandom number generator is based on an identifier or part of the identifier of the contact.

20. The article of manufacture of claim 18 , wherein a seed for the pseudorandom number generator is based on a phone number or part of the phone number of the contact.

21. The article of manufacture of claim 18 , wherein a seed for the pseudorandom number generator is based on an arrival time of the contact.

22. The article of manufacture of claim 17 , wherein the at least one computer processor is further caused to operate so as to:

select a second pairing strategy of the plurality of pairing strategies based on a second random number; and

pair a second contact to the agent in the contact center system using the second pairing strategy.

23. The article of manufacture of claim 17 , wherein selecting the pairing strategy from the set of pairing strategies is independent of an agent utilization measurement of the contact center system.

24. The article of manufacture of claim 17 , wherein at least one of the pairing strategies included in the set of pairing strategies is a behavioral pairing strategy.

25. The system of claim 16 , wherein

the behavioral pairing strategy uses an artificial intelligence (AI) model in a process for pairing contacts with agents, and

the system is configured to update the AI model using additional performance information for the selected pairing strategy that was obtained after the switch in the contact center system was instructed to connect the contact with the agent.

26. A method comprising:

collecting first performance information for a first pairing strategy;

collecting second performance information for a second paring strategy, wherein the performance information indicates that the first pairing strategy has performed better than the second pairing strategy;

based on a first random number, selecting, by at least one computer processor communicatively coupled to and configured to operate in a contact center system, a pairing strategy from a set of pairing strategies comprising the first pairing strategy and the second pairing strategy;

after selecting the first pairing strategy or the second paring strategy based on the random number, pairing a first contact with a first agent using the selected pairing strategy;

after pairing the first contact with the first agent using the selected pairing strategy, instructing a switch in the contact center system to connect the first contact with the first agent;

after pairing the first contact with the first agent using the selected pairing strategy, based on a second random number, pairing a second contact with a second agent using a pairing strategy different than the pairing strategy selected based on the first random number; and

after pairing the second contact with the second agent, instructing the switch in the contact center system to connect the second contact with the second agent.

27. The method of claim 26 , wherein the set of pairing strategies consists of the first pairing strategy and the second pairing strategy.

28. The method of claim 1 , wherein the set of pairing strategies consists of the first pairing strategy and the second pairing strategy.

29. The system of claim 9 , wherein the set of pairing strategies consists of the first pairing strategy and the second pairing strategy.

30. The article of manufacture of claim 17 , wherein the set of pairing strategies consists of the first pairing strategy and the second pairing strategy.

Assignments (7)
RELEASE AND TERMINATION OF PATENT SECURITY AGREEMENT Recorded Apr 16, 2025
From: VCP CAPITAL MARKETS, LLC
To: AFINITI, LTD.
Reel/Frame 070866/0614 →
PATENT ASSIGNMENT AGREEMENT Recorded Jan 3, 2025
From: AFINITI, LTD.
To: AFINITI AI HOLDINGS LLC
Reel/Frame 069816/0656 →
PATENT SECURITY AGREEMENT Recorded Jan 3, 2025
From: AFINITI AI LIMITED
To: ALTER DOMUS (US) LLC
Reel/Frame 069816/0858 →
PATENT ASSIGNMENT AGREEMENT Recorded Jan 3, 2025
From: AFINITI AI HOLDINGS LLC
To: AFINITI AI LIMITED
Reel/Frame 069817/0001 →
PATENT SECURITY AGREEMENT Recorded Aug 26, 2024
From: AFINITI, LTD.
To: VCP CAPITAL MARKETS, LLC
Reel/Frame 068793/0261 →
CORRECTIVE ASSIGNMENT TO CORRECT THE TYPOGRAPHICAL ERRORS ON PAGE ONE OF THE ASSIGNMENT PREVIOUSLY RECORDED AT REEL: 054204 FRAME: 0387. ASSIGNOR(S) HEREBY CONFIRMS THE ASSIGNMENT. Recorded Nov 24, 2020
From: AFINITI EUROPE TECHNOLOGIES LIMITED
To: AFINITI, LTD.
Reel/Frame 054700/0324 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Oct 8, 2020
From: AFINITI EUROPE TECHNOLOGIES LIMITED
To: AFINITI, LTD.
Reel/Frame 054204/0387 →
Cited By (2)
US 12,445,558 US 12,665,970