Selective mapping of callers in a call center routing system
View Patent ↗Systems and methods are disclosed for routing callers to agents in a contact center, along with an intelligent routing system. An exemplary method includes mapping a first portion (or fraction) of callers to agents according to a performance and/or pattern matching algorithm based on comparing caller data associated with the callers and agent data associated with the agents. The method further includes mapping a second portion of the callers (e.g., the remaining portion or fraction of all callers) to agents differently than the first portion of the callers (e.g., mapping based on queue order or performance based), which may provide a control group for monitoring or analyzing the effect of the pattern matching algorithm. The method may further include displaying the effect of the routing on at least one outcome variable, which may include revenue generation, cost, customer satisfaction, first call resolution, cancellation, or other variable outputs from the pattern matching algorithm of the system.
1. A method for routing callers to agents in a call-center routing environment, the method comprising:
mapping, by the one or more computers, a first portion of a set of callers to agents in a set of agents according to a pattern matching algorithm to increase a potential for a first outcome variable based at least in part on comparing caller data associated with callers in the first portion of the callers and agent data associated with agents in the set of agents and past call history data, wherein the caller data comprises demographic data and/or psychographic data associated with callers in the set of callers, and wherein the agent data comprises demographic data and/or psychographic data associated with the agents in the set of agents;
mapping, by the one or more computers, a second portion of the set of callers to agents in the set of agents according to a different mapping method than the first portion;
estimating, by the one or more computers, the first outcome variable for each caller in the first portion of the callers and the first outcome variable for each caller in the second portion of the callers;
generating, by the one or more computers, first graphical data for a visual display of the first outcome variable by time obtained for the first portion of the callers and the first outcome variable by time obtained for the second portion of the callers;
generating, by the one or more computers, data for a graphical user element for adjusting a size of the first portion of the set of callers relative to a size of the second portion of the set of callers; and
routing, by the one or more computers, one of the callers from one of the portions to one of the agents based at least in part on the estimated first outcome variables.
2. The method of claim 1 , further comprising:
mapping, by the one or more computers, the first portion of the set of callers to agents in the set of agents according to the pattern matching algorithm to increase a potential for a second outcome variable, based at least in part on comparing the caller data associated with the callers in the first portion of the callers and the agent data associated with the agents in the set of agents and past call history data;
estimating, by the one or more computers, the second outcome variable obtained for each caller in the first portion of the callers and the second outcome variable obtained for each caller in the second portion of callers; and
generating, by the one or more computers, second graphical data for the visual display of the second outcome variable by time for each of the first portion of the callers and the second outcome variable by time for each of the second portion of callers.
3. The method of claim 2 , further comprising:
weighting, by the one or more computers, one of the first outcome variable or the second outcome variable;
for multiple caller-agent pairs, adding the weighted outcome variable to the other of the outcome variables to obtain a sum for the respective caller-agent pair; and
wherein routing of one of the callers from one of the portions to one of the agents is based at least in part on the sum for the respective caller-agent pair.
4. The method of claim 1 , wherein mapping the second portion of callers comprises mapping the callers according to a performance based order of the agents.
5. The method of claim 1 , wherein mapping the second portion of callers comprises mapping the callers to agents based on an automatic call distribution queue order.
6. The method of claim 1 , wherein the first outcome variable comprises one selected from the group of cost, revenue, and customer satisfaction.
7. The method of claim 1 , wherein the pattern matching algorithm comprises a neural network algorithm.
8. A system for routing callers to agents in a call-center routing environment, comprising:
one or more computers configured to:
map, by the one or more computers, a first portion of a set of callers to agents in a set of agents according to a pattern matching algorithm to increase a potential for a first outcome variable based at least in part on comparing caller data associated with callers in the first portion of the callers and agent data associated with agents in the set of agents and past call history data, wherein the caller data comprises demographic data and/or psychographic data associated with callers in the set of callers, and wherein the agent data comprises demographic data and/or psychographic data associated with the agents in the set of agents;
map, by the one or more computers, a second portion of the set of callers to agents in the set of agents according to a different mapping method than the first portion;
estimate, by the one or more computers, the first outcome variable for each caller in the first portion of the callers and the first outcome variable for each caller in the second portion of the callers;
generate, by the one or more computers, first graphical data for a visual display of the first outcome variable by time obtained for the first portion of the callers and the first outcome variable by time obtained for the second portion of the callers;
generate, by the one or more computers, data for a graphical user element for adjusting a size of the first portion of the set of callers relative to a size of the second portion of the set of callers; and
route, by the one or more computers, one of the callers from one of the portions to one of the agents based at least in part on the estimated first outcome variables.
9. The system of claim 8 , wherein the one or more computers are further configured to:
map, by the one or more computers, the first portion of the set of callers to agents in the set of agents according to the pattern matching algorithm to increase a potential for a second outcome variable, based at least in part on comparing the caller data associated with the callers in the first portion of the callers and the agent data associated with the agents in the set of agents and past call history data;
estimate, by the one or more computers, the second outcome variable obtained for each caller in the first portion of the callers and the second outcome variable obtained for each caller in the second portion of callers; and
generate, by the one or more computers, second graphical data for the visual display of the second outcome variable by time for each of the first portion of the callers and the second outcome variable by time for each of the second portion of callers.
10. The system of claim 9 , wherein the one or more computers are further configured to:
weight, by the one or more computers, one of the first outcome variable or the second outcome variable;
for multiple caller-agent pairs, add the weighted outcome variable to the other of the outcome variables to obtain a sum for the respective caller-agent pair; and
wherein routing of one of the callers from one of the portions to one of the agents is based at least in part on the sum for the respective caller-agent pair.
11. The system of claim 8 , wherein the different mapping method comprises mapping the callers to the agents according to a performance based order of the agents.
12. The system of claim 8 , wherein the different mapping method comprises mapping the callers to the agents based on an automatic call distribution queue order.
13. The system of claim 8 , wherein the first outcome variable comprises one selected from the group of cost, revenue, and customer satisfaction.
14. The system of claim 8 , wherein the pattern matching algorithm comprises a neural network algorithm.
15. A non-transitory computer readable storage medium comprising computer readable instructions for carrying out, when executed by one or more computers, the method:
mapping, by the one or more computers, a first portion of a set of callers to agents in a set of agents according to a pattern matching algorithm to increase a potential for a first outcome variable based at least in part on comparing caller data associated with callers in the first portion of the callers and agent data associated with agents in the set of agents and past call history data, wherein the caller data comprises demographic data and/or psychographic data associated with callers in the set of callers, and wherein the agent data comprises demographic data and/or psychographic data associated with the agents in the set of agents;
mapping, by the one or more computers, a second portion of the set of callers to agents in the set of agents according to a different mapping method than the first portion;
estimating, by the one or more computers, the first outcome variable for each caller in the first portion of the callers and the first outcome variable for each caller in the second portion of the callers;
generating, by the one or more computers, first graphical data for a visual display of the first outcome variable by time obtained for the first portion of the callers and the first outcome variable by time obtained for the second portion of the callers;
generating, by the one or more computers, data for a graphical user element for adjusting a size of the first portion of the set of callers relative to a size of the second portion of the set of callers; and
routing, by the one or more computers, one of the callers from one of the portions to one of the agents based at least in part on the estimated first outcome variables.
16. The non-transitory computer readable storage medium of claim 15 , further comprising:
mapping, by the one or more computers, the first portion of the set of callers to agents in the set of agents according to the pattern matching algorithm to increase a potential for a second outcome variable, based at least in part on comparing the caller data associated with the callers in the first portion of the callers and the agent data associated with the agents in the set of agents and past call history data;
estimating, by the one or more computers, the second outcome variable obtained for each caller in the first portion of the callers and the second outcome variable obtained for each caller in the second portion of callers; and
generating, by the one or more computers, second graphical data for the visual display of the second outcome variable by time for each of the first portion of the callers and the second outcome variable by time for each of the second portion of callers.
17. The non-transitory computer readable storage medium of claim 16 , further comprising:
weighting, by the one or more computers, one of the first outcome variable or the second outcome variable;
for multiple caller-agent pairs, adding the weighted outcome variable to the other of the outcome variables to obtain a sum for the respective caller-agent pair; and
wherein routing of one of the callers from one of the portions to one of the agents is based at least in part on the sum for the respective caller-agent pair.
18. The non-transitory computer readable storage medium of claim 15 , wherein mapping the second portion of callers comprises mapping the callers according to a performance based order of the agents.
19. The non-transitory computer readable storage medium of claim 15 , wherein mapping the second portion of callers comprises mapping the callers to agents based on an automatic call distribution queue order.
20. The non-transitory computer readable storage medium of claim 15 , wherein the first outcome variable comprises one selected from the group of cost, revenue, and customer satisfaction.