Language translation and work assignment optimization in a customer support environment

• US 10,346,544 B2
• Filed: 11/20/2017
• Issued: 07/09/2019
• Est. Priority Date: 10/24/2014
• Status: Active Grant

• Current Assignee: Kyndryl Incorporated
• Original Assignee: International Business Machines Corporation
• Inventors: Brophy, Gary R., Koski, Dennis D., Mueller, Todd A., Schmidt, Jeffrey A.
• Primary Examiner(s): Roberts, Shaun
• Application Number:
  US15/817,567
• Publication Number:
  US 20180075021A1
• Time in Patent Office: 596 Days
• Field of Search: 704 2- 8
• CPC Class Codes: G06F 40/40 Processing or translation of natural language natural language analysis G06F40/20; semantic analysis G06F40/30
• CPC Class Codes: G06F 40/47 Machine-assisted translation, e.g. using translation memory
• CPC Class Codes: G06F 40/51 Translation evaluation
• CPC Class Codes: G06F 40/58 Use of machine translation, e.g. for multi-lingual retrieval, for server-side translation for client devices or for real-time translation
• CPC Class Codes: G06Q 10/063112 Skill-based matching of a person or a group to a task
• CPC Class Codes: H04M 2242/12 Language recognition, selection or translation arrangements
• CPC Class Codes: H04M 3/5233 Operator skill based call distribution
• CPC Class Codes: H04M 3/5238 with waiting time or load prediction arrangements

Abstract

Approaches presented herein enable assignment of translated work to an agent in a 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 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 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.

Claims

1. A method for assigning work in a support environment, the method comprising the computer-implemented steps of:

translating automatically a communication received in a first language into a second language using a machine translation, the translation having a confidence of translation score on a scale based on the machine translation;

obtaining a set of agents, each agent of the set of agents having;

an associated first confidence factor on a scale in the first language based upon a score on a scale for maintaining the first language original to the communication and a technical support proficiency of the agent in the first language score on a scale, and an associated second confidence factor on a scale in the second language based upon the confidence of translation score on a scale of the machine translation and a technical support proficiency of the agent in the second language score on a scale;

generating a threshold confidence factor curve that has a rate of decrease over a wait time period of the communication and that keeps the communication in a queue for a time period; and

assigning, at an end of the time period, the communication in a designated language to one of the set of agents based on an associated confidence factor of the assigned agent being greater than the threshold confidence factor curve at the end of the time period, wherein the designated language is the first language in the case that the associated confidence factor of the assigned agent is the first confidence factor and the designated language is the second language in the case that the associated confidence factor of the assigned agent is the second confidence factor, and wherein the assigned agent resolves a technical issue in the communication in the same designated language.

2. The method of claim 1, further comprising the computer-implemented step of determining, in response to the received communication, whether an agent having a required proficiency in the first language is available to service the communication.

3. The method of claim 1, further comprising the computer-implemented steps of:

weighting the first and second associated confidence factors against a wait time of the communication on the threshold confidence factor curve; and

assigning the communication to the one of the set of agents based on the weighting.

4. The method of claim 1, further comprising the computer-implemented step of placing the communication in a queue in the case that none of the set of agents has an associated confidence factor greater than the threshold confidence factor curve at the time, wherein the threshold confidence factor curve is periodically updated based on a time the communication has remained in the queue.

5. The method of claim 1, further comprising the computer-implemented step of assigning the communication to the one of the set of agents only in the case that a rule optimizing agent availability and risk of constrained resources is satisfied.

6. The method of claim 1, wherein the technical support proficiency is based on one or more of:

a skill set, a language set, a user-defined constraint, and a physical or logical location of the agent.

7. The method of claim 1, wherein the confidence of translation is based on one or more of:

a type of work, a severity of a problem, a problem description, a problem complexity, a customer identity, a customer information, a product information, a component information, an additional skill of an agent required, a language required, a contract term and condition, and a criteria of responses required.

8. A system for assigning work in a support environment, comprising:

a memory medium comprising program instructions;

a bus coupled to the memory medium; and

a processor, for executing the program instructions, coupled to a confidence factor management engine via the bus that when executing the program instructions causes the system to;

translate automatically a communication received in a first language into a second language using a machine translation, the translation having a confidence of translation score on a scale based on the machine translation;

obtain a set of agents, each agent of the set of agents having;

an associated first confidence factor on a scale in the first language based upon a score on a scale for maintaining the first language original to the communication and a technical support proficiency of the agent in the first language score on a scale, and an associated second confidence factor on a scale in the second language based upon the confidence of translation score on a scale of the machine translation and a technical support proficiency of the agent the second language score on a scale;

generate a threshold confidence factor curve that has a rate of decrease over a wait time period of the communication and that keeps the communication in a queue for a time period; and

assign, at an end of the time period, the communication to one of the set of agents based on an associated confidence factor of the assigned agent being greater than the threshold confidence factor curve at the end of the time period, wherein the designated language is the first language in the case that the associated confidence factor of the assigned agent is the first confidence factor and the designated language is the second language in the case that the associated confidence factor of the assigned agent is the second confidence factor.

9. The system of claim 8, the program instructions further causing the system to determine, in response to the received communication, whether an agent having a required proficiency in the first language is available to service the communication.

10. The system of claim 8, the program instructions further causing the system to:

weight the associated confidence factors against a wait time of the communication on the threshold confidence factor curve; and

assign the communication to the one of the set of agents based on the weighting.

11. The system of claim 8, the program instructions further causing the system to place the communication in a queue in the case that none of the set of agents has an associated confidence factor greater than the threshold confidence factor curve at the time, wherein the threshold confidence factor curve is periodically updated based on a time the communication has remained in the queue.

12. The system of claim 8, the program instructions further causing the system to assign the communication to the one of the set of agents only in the case that a rule optimizing agent availability and risk of constrained resources is satisfied.

13. The system of claim 8, wherein the technical support proficiency is based on one or more of:

a skill set, a language set, a user-defined constraint, and a physical or logical location of the agent.

14. The system of claim 8, wherein the confidence of translation is based on one or more of:

a type of work, a severity of a problem, a problem description, a problem complexity, a customer identity, a customer information, a product information, a component information, an additional skill of an agent required, a language required, a contract term and condition, and a criteria of responses required.

15. A computer program product for assigning work in a support environment, the computer program product comprising a computer readable storage device, and program instructions stored on the computer readable storage device, to:

translate automatically a communication received in a first language into a second language using a machine translation, the translation having a confidence of translation score on a scale based on the machine translation;

obtain a set of agents, each agent of the set of agents having;

an associated first confidence factor on a scale in the first language based upon a score on a scale for maintaining the first language original to the communication and a technical support proficiency of the agent in the first language score on a scale, and an associated second confidence factor on a scale in the second language based upon the confidence of translation score on a scale of the machine translation and a technical support proficiency of the agent in the second language score on a scale;

generate a threshold confidence factor curve having a rate of decrease over a wait time period of the communication; and

assign, at a time, the communication in a designated language to one of the set of agents based on an associated confidence factor of the assigned agent being greater than the threshold confidence factor curve at the time, wherein the designated language is the first language in the case that the associated confidence factor of the assigned agent is the first confidence factor and the designated language is the second language in the case that the associated confidence factor of the assigned agent is the second confidence factor, and wherein the assigned agent resolves a technical issue in the communication in the same designated language.

16. The computer program product of claim 15, the computer readable storage device further comprising program instructions to:

weight the associated confidence factors against a wait time of the communication on the threshold confidence factor curve; and

assign the communication to the one of the set of agents based on the weighting.

17. The computer program product of claim 15, the computer readable storage device further comprising program instructions to:

determine, in response to the received communication, whether an agent having a required proficiency in the first language is available to service the communication; and

place the communication in a queue in the case that none of the set of agents has an associated confidence factor greater than the threshold confidence factor curve at the time, wherein the threshold confidence factor curve is periodically updated based on a time the communication has remained in the queue.

18. The computer program product of claim 15, the computer readable storage device further comprising program instructions to assign the communication to the one of the set of agents only in the case that a rule optimizing agent availability and risk of constrained resources is satisfied.

19. The computer program product of claim 15, wherein the technical support proficiency is based on one or more of:

a skill set, a language set, a user-defined constraint, and a physical or logical location of the agent.

20. The computer program product of claim 15, wherein the confidence of translation is based on one or more of:

a type of work, a severity of a problem, a problem description, a problem complexity, a customer identity, a customer information, a product information, a component information, an additional skill of an agent required, a language required, a contract term and condition, and a criteria of responses required.