Call routing methods and systems based on multiple variable standardized scoring
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 combining multiple output variables of a pattern matching algorithm (for matching callers and agents) into a single metric for use in the routing system. The pattern matching algorithm may include a neural network architecture, where the exemplary method combines output variables from multiple neural networks. The method may include determining a Z-score of the variable outputs and determining a linear combination of the determined Z-scores for a desired output. Callers may be routed to agents via the pattern matching algorithm to maximize the output value or score of the linear combination. The output variables may include revenue generation, cost, customer satisfaction performance, 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 the acts of:
comparing, by one or more computers, caller data for each caller of a set of callers to agent data for each agent of a set of agents as well as past agent-caller output data via a pattern matching algorithm to obtain output values for multiple agent-caller pairs for each of two or more output variables;
determining, by the one or more computers, a Z-score for each of the multiple agent-caller pairs for each of the two or more output variables obtained from the pattern matching algorithm;
determining, by the one or more computers, a linear combination of the Z-scores of the two or more output variables for each of the multiple agent-caller pairs; and
routing, by a router, one of the callers from the set of callers to one of the agents from the set of agents based at least in part on the highest linear combination of the Z-scores, to maximize the linear combination of the Z-scores for the one of the callers based on available agent-caller pairs; and further comprising
adjusting, by the one or more computers, in a call routing center the linear combination of the Z-scores in real time, wherein the linear combination of the Z-scores includes a relative weighting of the two or more output variables, in real time,
wherein at least one of the two or more output variables is selected from a group of revenue generation, cost, and customer satisfaction.
2. The method of claim 1 , wherein the routing of the one of the callers to the one of the agents is further based on a waiting time of the one of the callers.
3. A system for routing callers to agents in a call-center routing environment, comprising:
one or more computers configured to
comparing, by the one or more computers, caller data for each caller of a set of callers to agent data for each agent of a set of agents as well as past agent-caller output data via a pattern matching algorithm to obtain output values for multiple agent-caller pairs for each of two or more output variables;
determining, by the one or more computers, a Z-score for each of the multiple agent-caller pairs for each of the two or more output variables obtained from the pattern matching algorithm;
determining, by the one or more computers, a linear combination of the Z-scores of the two or more output variables for each of the multiple agent-caller pairs; and
routing, by a router, one of the callers from the set of callers to one of the agents from the set of agents based at least in part on the highest linear combination of the Z-scores, to maximize the linear combination of the Z-scores for the one of the callers based on available agent-caller pairs; and further comprising
adjusting, by the one or more computers, in a call routing center the linear combination of the Z-scores in real time, wherein the linear combination of the Z-scores includes a relative weighting of the two or more output variables, in real time,
wherein at least one of the two or more output variables is selected from a group of revenue generation, cost, and customer satisfaction.
4. The system of claim 3 , wherein the routing of the one of the callers to the one of the agents is further based on a waiting time of the one of the callers.
5. A non-transitory computer readable storage medium comprising program instructions for routing callers to agents in a call-center routing environment, that when executed by one or more computers, performs the steps:
comparing, by the one or more computers, caller data for each caller of a set of callers to agent data for each agent of a set of agents as well as past agent-caller output data via a pattern matching algorithm to obtain output values for multiple agent-caller pairs for each of two or more output variables;
determining, by the one or more computers, a Z-score for each of the multiple agent-caller pairs for each of the two or more output variables obtained from the pattern matching algorithm;
determining, by the one or more computers, a linear combination of the Z-scores of the two or more output variables for each of the multiple agent-caller pairs; and
routing, one of the callers from the set of callers to one of the agents from the set of agents based at least in part on the highest linear combination of the Z-scores, to maximize the linear combination of the Z-scores for the one of the callers based on available agent-caller pairs; and further comprising
adjusting, by the one or more computers, in a call routing center the linear combination of the Z-scores in real time, wherein the linear combination of the Z-scores includes a relative weighting of the two or more output variables, in real time,
wherein at least one of the two or more output variables is selected from a group of revenue generation, cost, and customer satisfaction.
6. The non-transitory computer readable storage medium of claim 5 , wherein the routing of the one of the callers to the one of the agents is further based on a waiting time of the one of the callers.