Language translation and work assignment optimization in a customer support environment

摘要

Approaches presented herein enable assignment of translated work to an agent in a customer support environment based on a confidence factor that measures accuracy of translation and an agent's language skill. Specifically, agent proficiencies in a set of natural languages are measured and scored. An incoming customer communication is translated into one or more natural languages and each language translation is assigned a translation score based on a confidence of translation. The skill score and translation score are utilized to calculate a confidence factor for each language. In one approach, the customer communication is assigned to an agent that has a confidence factor greater than a predetermined threshold confidence factor. In another approach, the communication is only assigned if a rule optimizing agent availability and risk of constrained resources is satisfied.

主权项

1. A method for assigning work in a customer support environment, the method comprising the computer-implemented steps of:
receiving a customer communication in a first language; detecting a shortage of agents having the first language as a primary language; translating, in response to the shortage of agents, the customer communication into a second language; calculating a translation score based on a confidence in the translation, the confidence in the translation being based on a technical content of the customer communication; obtaining a set of agents, each agent in the set of agents being a person that has a language proficiency in at least one of the first language or the second language and has a language proficiency score associated with the language proficiency, the language proficiency score being based on a measure of an ability of each agent to communicate in the first language or the second language and a technical skill set of each agent associated with a technical area of the customer communication, and each of the first language and the second language being natural languages; calculating, for each agent, an associated confidence factor by combining the language proficiency score for the agent and the translation score; generating a threshold confidence factor curve comprising a first curve, having a first rate of decrease over a first wait time period of the customer communication, and a second curve, having a second rate of decrease over a second, subsequent wait time of the customer communication, the second rate of decrease being greater than the first rate of decrease and the threshold confidence factor curve being based on a priority of the customer communication; and assigning, at a time, the customer communication to one of the set of agents to respond to the customer communication in a selected language based on the associated confidence factor being greater than the threshold confidence factor curve at the time.