TECHNIQUES FOR BEHAVIORAL PAIRING IN A CONTACT CENTER SYSTEM

• Main Authors: KLUGERMAN, Michael, Richard, KAN, Ittai, RILEY, Blake, Jay
• Format: Patent
• Language: English; French; German
• Published: 08.01.2020
• Subjects: CALCULATING; COMPUTING; COUNTING; DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FORADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORYOR FORECASTING PURPOSES; PHYSICS; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE,COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTINGPURPOSES, NOT OTHERWISE PROVIDED FOR

A method for behavioral pairing in a contact center system, the method performed by at least one computer processor communicatively coupled to and configured to operate in the contact center system, the method comprising determining a plurality of agents available for connection to a contact, wherein each of the plurality of agents has an expected availability and each of the plurality of agents is associated with a skill of a plurality of skills; determining a plurality of contact types for the contact center system, wherein each of the plurality of contact types has an expected frequency and is associated with a skill requirement of a plurality of skill requirements, each of the plurality of skill requirements associated with a skill of the plurality of skills; generating a first network flow model by grouping the plurality of agents according to the plurality of skills thereby forming a plurality of grouped agents and grouping the plurality of contact types according to the plurality of skill requirements thereby forming a plurality of grouped contact types; adjusting the first network flow model such that the expected availability of the plurality of grouped agents more closely meets the expected frequency of the plurality of grouped contact types in the adjusted first network flow model; generating a second network flow model from the adjusted first network flow model by optimizing an allocation of the expected availability of the plurality of agents to satisfy the expected frequency of the plurality of contact types, the second network flow model comprising a plurality of contact-agent pairings among possible pairings between the plurality of contact types and the plurality of agents; selecting one of the plurality of contact-agent pairings for the contact according to a contact type associated with the contact and a likelihood determined from the first network flow model; and connecting the contact to an agent according to the selected one of the plurality of contact-agent pairings.