Abstract: A methods for routing callers to agents in a contact center, along with an intelligent routing system. One or more agents are graded on achieving an optimal interaction, such as increasing revenue, decreasing cost, or increasing customer satisfaction. Callers are then preferentially routed to a graded agent to obtain an increased chance at obtaining a chosen optimal interaction. In a more advanced embodiment, caller and agent demographic and psychographic characteristics can also be determined and used in a pattern matching algorithm to preferentially route a caller with certain characteristics to an agent with certain characteristics to increase the chance of an optimal interaction.

Abstract: Systems and methods are disclosed for estimating and assigning agent performance characteristics in a call routing center. Performance characteristics (e.g., sales rate, customer satisfaction, duration of call, etc.) may be assigned to an agent when the agent has made few calls relative to other agents or otherwise has a large error in their measure of one or more performance characteristics used for matching callers to agents (e.g., via a performance based or pattern matching routing method). A method includes identifying agents of a plurality of agents having a number of calls fewer than a predetermined number of calls (or an error in the performance characteristic exceeding a threshold), assigning a performance characteristic to the identified agents (that is different than the agent's actual performance characteristic), and routing a caller to one of the plurality of agents based on the performance characteristics of the plurality of agents.

Abstract: 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.

Abstract: Systems and methods are disclosed for routing callers to agents in a contact center. Exemplary methods and systems include using one of a plurality of different methods or computer models for matching callers to agents, the method or model selected based on a type of phone or phone number associated with a caller (e.g., residential, business, or mobile). The models may include queue routing, performance based matching, adaptive pattern matching algorithms, or the like. In one example, similar adaptive models may be used for two or more different types of phones, but trained differently, e.g., based on data and outcomes for the particular type of phone. Different models for routing callers to agents may perform differently for different types of phones. Further, training correlation or adaptive pattern matching algorithms based on different types of phones may improve performance compared to a single algorithm for all types of phones.

Abstract: Systems and methods are disclosed for preprocessing caller-agent pairs in a contact routing center, along with an intelligent routing system. A method includes determining at least one agent data for each agent of a set of agents, determining at least one caller data for each caller of a set of callers, and determining a score for each possible caller-agent pair of the set of agents and the set of callers using the agent data and the caller data in a pattern matching algorithm. The scores for each possible caller-agent pair may then be stored, e.g., in a look-up table, for retrieval, where matching a caller of the set of callers to an agent of the set of agents is based on the previously determined or calculated scores. For example, the caller-agent pair having the best score of all potential caller-agent pairs may be connected.

Abstract: Methods and systems are provided for routing callers to agents in a call-center routing environment. An exemplary method includes identifying caller data for a caller in a queue of callers, and jumping or moving the caller to a different position within the queue based on the caller data. The caller data may include one or both of demographic data and psychographic data. The caller can be jumped forward or backward in the queue relative to at least one other caller. Jumping the caller may further be based on comparing the caller data with agent data via a pattern matching algorithm and/or computer model for predicting a caller-agent pair outcome. Additionally, if a caller is held beyond a hold threshold (e.g., a time, “cost” function, or the like) the caller may be routed to the next available agent.

Abstract: Methods and systems are disclosed for routing callers to agents in a contact center, along with an intelligent routing system. A method for routing callers includes routing a caller, if agents are available, to an agent based on a pattern matching algorithm (which may include performance based matching, pattern matching based on agent and caller data, computer models for predicting outcomes of agent-caller pairs, and so on). Further, if no agents are available for the incoming caller, the method includes holding the caller in a shadow queue, e.g., a set of callers. When an agent becomes available the method includes scanning all of the callers in the shadow queue and matching the agent to the best matching caller within shadow queue.

Abstract: Apparatus and methods are disclosed for routing callers to agents in a contact center. Exemplary methods and system include using one of a plurality of different computer models for matching callers to agents, the model selected based on a degree and/or type of caller data available. The models may include queue routing, performance based matching, adaptive pattern matching algorithms, or other computer models for matching callers to agents. In one example, similar adaptive models may be used for two or more different degrees/types of caller data, but are trained differently, e.g., based on the degree/type of caller data. Different models for routing callers to agents may perform differently for different degrees/types of caller data. Further, training correlation or adaptive pattern matching algorithms based on different degrees/types of caller data may improve their respective performance compared to a single algorithm for all degrees/types of caller data.