Techniques for behavioral pairing in a contact center system
Techniques for behavioral pairing in a contact center system are disclosed. In one particular embodiment, the techniques may be realized as a method for pairing in a contact center including ordering one or more contacts, ordering one or more agents, comparing a first difference in ordering between a first contact and a first agent in a first pair with a second difference in ordering between a second contact and a second agent in a second pair, and selecting the first pair or the second pair for connection based on the comparing, wherein the first contact and the second contact are different or the first agent and the second agent are different.
1. A method comprising:
determining, by at least one computer processor communicatively coupled to and configured to operate in a contact center system, a set of agents available to be connected to a contact, the set of agents comprising a first agent, a second agent, and a third agent; and
selecting, by the at least one computer processor, according to a pairing strategy, the first agent for pairing to the contact to optimize a performance metric;
wherein the first agent has a worst expected performance among the set of agents for the contact according to the performance metric;
wherein the first agent has been lagging the least in a fairness metric, wherein the fairness metric is based on a measurement of utilization of an agent over time;
wherein the third agent has been lagging the most in the fairness metric;
wherein unavailability of the first agent would cause the pairing strategy to select the second agent instead of the third agent; and
wherein the first agent has not previously interacted with the contact.
2. The method of claim 1 , wherein the pairing strategy is a behavioral pairing strategy.
3. The method of claim 1 , wherein the pairing strategy is a diagonal pairing strategy.
4. The method of claim 1 , wherein the pairing strategy targets a balanced agent utilization.
5. The method of claim 1 , wherein the pairing strategy targets an expected improvement to overall performance of the contact center system.
6. The method of claim 1 , wherein the first agent has the worst expected performance among the set of agents for a contact type of the contact.
7. The method of claim 1 , wherein the worst expected performance for the first agent is subsequently updated based on an outcome of an interaction between the first agent and the contact.
8. A system comprising:
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:
determine a set of agents available to be connected to a contact, the set of agents comprising a first agent, a second agent, and a third agent; and
select, according to a pairing strategy, the first agent for pairing to the contact to optimize a performance metric;
wherein the first agent has a worst expected performance among the set of agents for the contact according to the performance metric;
wherein the first agent has been lagging the least in a fairness metric, wherein the fairness metric is based on a measurement of utilization of an agent over time;
wherein the third agent has been lagging the most in the fairness metric;
wherein unavailability of the first agent would cause the pairing strategy to select the second agent instead of the third agent; and
wherein the first agent has not previously interacted with the contact.
9. The system of claim 8 , wherein the pairing strategy is a behavioral pairing strategy.
10. The system of claim 8 , wherein the pairing strategy is a diagonal pairing strategy.
11. The system of claim 8 , wherein the pairing strategy targets a balanced agent utilization.
12. The system of claim 8 , wherein the pairing strategy targets an expected improvement to overall performance of the contact center system.
13. The system of claim 8 , wherein the first agent has the worst expected performance among the set of agents for a contact type of the contact.
14. The system of claim 8 , wherein the worst expected performance for the first agent is subsequently updated based on an outcome of an interaction between the first agent and the contact.
15. 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:
determine a set of agents available to be connected to a contact, the set of agents comprising a first agent, a second agent, and a third agent; and
select, according to a pairing strategy, the first agent for pairing to the contact to optimize a performance metric;
wherein the first agent has a worst expected performance among the set of agents for the contact according to the performance metric;
wherein the first agent has been lagging the least in a fairness metric, wherein the fairness metric is based on a measurement of utilization of an agent over time;
wherein the third agent has been lagging the most in the fairness metric;
wherein unavailability of the first agent would cause the pairing strategy to select the second agent instead of the third agent; and
wherein the first agent has not previously interacted with the contact.
16. The article of manufacture of claim 15 , wherein the pairing strategy is a behavioral pairing strategy.
17. The article of manufacture of claim 15 , wherein the pairing strategy is a diagonal pairing strategy.
18. The article of manufacture of claim 15 , wherein the pairing strategy targets a balanced agent utilization.
19. The article of manufacture of claim 15 , wherein the pairing strategy targets an expected improvement to overall performance of the contact center system.
20. The article of manufacture of claim 15 , wherein the first agent has the worst expected performance among the set of agents for a contact type of the contact.
21. The article of manufacture of claim 15 , wherein the worst expected performance for the first agent is subsequently updated based on an outcome of an interaction between the first agent and the contact.
22. The method of claim 1 , wherein the fairness metric is agent waiting time, wherein the first agent has been waiting the least among the set of agents, and wherein the third agent has been waiting the longest among the set of agents.
23. The method of claim 1 , wherein the fairness metric is agent occupancy, wherein the first agent has been occupied the most among the set of agents, and wherein the third agent has been occupied the least among the set of agents.
24. The system of claim 8 , wherein the fairness metric is agent waiting time, wherein the first agent has been waiting the least among the set of agents, and wherein the third agent has been waiting the longest among the set of agents.
25. The system of claim 8 , wherein the fairness metric is agent occupancy, wherein the first agent has been occupied the most among the set of agents, and wherein the third agent has been occupied the least among the set of agents.
26. The article of manufacture of claim 15 , wherein the fairness metric is agent waiting time, wherein the first agent has been waiting the least among the set of agents, and wherein the third agent has been waiting the longest among the set of agents.
27. The article of manufacture of claim 15 , wherein the fairness metric is agent occupancy, wherein the first agent has been occupied the most among the set of agents, and wherein the third agent has been occupied the least among the set of agents.