Enhancing work force management with speech analytics

• US 10,116,799 B2
• Filed: 06/30/2014
• Issued: 10/30/2018
• Est. Priority Date: 06/30/2014
• Status: Active Grant

• Current Assignee: Genesys Telecommunications Laboratories Incorporated (Genesys Cloud Services Incorporated)
• Original Assignee: Genesys Telecommunications Laboratories Incorporated (Genesys Cloud Services Incorporated)
• Inventors: Konig, Yochai, Ristock, Herbert Willi Artur, Konig, David
• Primary Examiner(s): Shah, Antim G
• Application Number:
  US14/320,237
• Publication Number:
  US 20150381807A1
• Time in Patent Office: 1,583 Days
• Field of Search: 37926503, 37926505, 37926506, 37926512, 37926608
• CPC Class Codes: G06Q 10/063112 Skill-based matching of a person or a group to a task
• CPC Class Codes: H04M 2203/402 Agent or workforce management
• CPC Class Codes: H04M 3/5233 Operator skill based call distribution

Abstract

A method for generating an agent work schedule includes: analyzing, on a processor, a plurality of recorded interactions with a plurality of contact center agents to classify the recorded interactions based on a first plurality of interaction reasons and a plurality interaction resolution statuses; analyzing, on the processor, the classified recorded interactions to compute agent effectiveness of an agent of the plurality of agents, wherein the agent effectiveness corresponds to an interaction reason of the first interaction reasons; forecasting, on the processor, a demand of the contact center agents for a first time period for handling interactions classified with the interaction reason; and generating, on the processor, the agent work schedule for the first time period based on the forecasted demand and the computed agent effectiveness.

Claims

1. A method for generating an agent work schedule, the method comprising:

performing, by a speech or text analytics module hosted on a processor, analytics on a plurality of recorded interactions with a plurality of contact center agents;

detecting, based on the analytics, specific utterances in the recorded interactions;

classifying, on the processor, the recorded interactions into a first plurality of interaction reasons and a first plurality of interaction resolution statuses, wherein the classifying is based on the detected specific utterances;

computing, on the processor, based on the classifying of the recorded interactions, a first agent effectiveness of a first agent and a second agent effectiveness of a second agent of the plurality of agents, wherein the first agent effectiveness and the second agent effectiveness correspond to an interaction reason of the first interaction reasons, the first agent effectiveness being higher than the second agent effectiveness;

forecasting, on the processor, a demand of the contact center agents for a first time period for handling interactions classified with the interaction reason;

generating, on the processor, the agent work schedule for the first time period based on the forecasted demand and the first agent effectiveness and the second agent effectiveness, wherein the agent work schedule includes a first number of agents scheduled to work during the first time period that is larger than a second number of agents scheduled to work during the first time period, the first number of agents including the first agent with the first agent effectiveness, and the second number of agents including the second agent with the second agent effectiveness;

detecting an interaction having the interaction reason during the first time period;

routing, by an electronic switch, the detected interaction to a particular agent selected from the first and second number of agents;

analyzing, on the processor, a second plurality of recorded interactions, the analyzing including classifying the second plurality of recorded interactions into a second plurality of interaction reasons and a second plurality of interaction resolution statuses; and

forecasting, on the processor, a demand of the contact center agents for a second time period for handling the second interaction reasons without forecasting a demand for handling an obsolete interaction reason included in the first plurality of interactions reasons, the second time period being different from the first time period.

2. The method of claim 1, wherein the first agent effectiveness and the second agent effectiveness each comprise an average interaction handling time.

3. The method of claim 2, wherein the agent work schedule is further generated based on an average tare time.

4. The method of claim 1, wherein the analyzing the classified recorded interactions to compute the agent effectiveness of the first and second agents comprises:

identifying, on the processor, from among the plurality of recorded interactions, a subset of recorded interactions in which the first agent or the second agent participated and which were classified with the interaction reason;

identifying, on the processor, from among the subset of recorded interactions, a plurality of unresolved interactions in which an interaction resolution status of the interaction resolution statuses associated with the subset of recorded interactions is set as unresolved; and

computing, on the processor, the first agent effectiveness and the second agent effectiveness with respect to the interaction reason based on a number of unresolved recorded interactions for each agent and a number of interactions for each agent in the subset of recorded interactions.

5. The method of claim 1, further comprising updating, on the processor, the computed first agent effectiveness and the computed second agent effectiveness by analyzing the second plurality of recorded interactions.

6. The method of claim 5, wherein the second interaction reasons comprise at least one new interaction reason different from each of the first interaction reasons.

7. The method of claim 6, wherein the analyzing the classified recorded interactions to compute agent effectiveness of the first and second agents comprises:

identifying, on the processor, from among the plurality of recorded interactions, a subset of recorded interactions in which the first agent or the second agent participated and which were classified with the at least one new interaction reason;

identifying, on the processor, from among the subset of recorded interactions, a plurality of unresolved interactions in which an interaction resolution status of the interaction resolution statuses associated with the subset of recorded interactions is set as unresolved; and

computing, on the processor, the first agent effectiveness and the second agent effectiveness with respect to the at least one new interaction reason based on a number of unresolved recorded interactions for each agent and a number of interactions for each agent in the subset of recorded interactions.

8. The method of claim 6, further comprising forecasting, on the processor, a demand of the contact center agents for a second time period for handling interactions classified with the new interaction reason, the second time period being different from the first time period.

9. The method of claim 1, wherein the obsolete interaction reason is different from each of the second interaction reasons.

19. The method of claim 1, wherein the first agent effectiveness and the second agent effectiveness correspond to a sub-category of the interaction reason of the first interaction reasons.

21. The method of claim 1 further comprising:

updating a skill set associated with the first agent based on the first agent effectiveness.

10. A system comprising:

a processor; and

memory storing instructions that, when executed on the processor, cause the processor to;

perform, by a speech or text analytics module hosted on the processor, analytics on a plurality of recorded interactions with a plurality of contact center agents;

detect, based on the analytics, specific utterances in the recorded interactions;

classify the recorded interactions into a first plurality of interaction reasons and a plurality of interaction resolution statuses, wherein the classifying is based on the detected specific utterances;

compute, based on the classifying of the recorded interactions, a first agent effectiveness of a first agent and a second agent effectiveness of a second agent of the plurality of agents, wherein the first agent effectiveness and the second agent effectiveness correspond to an interaction reason of the first interaction reasons, the first agent effectiveness being higher than the second agent effectiveness;

forecast a demand of the contact center agents for a first time period for handling interactions classified with the interaction reason;

generate the agent work schedule for the first time period based on the forecasted demand and the first agent effectiveness and the second agent effectiveness, wherein the agent work schedule includes a first number of agents scheduled to work during the first time period that is larger than a second number of agents scheduled to work during the first time period, the first number of agents including the first agent with the first agent effectiveness, and the second number of agents including the second agent with the second agent effectiveness;

detect an interaction having the interaction reason during the first time period;

transmit a signal for routing the detected interaction reasons;

analyze a second plurality of recorded interactions, wherein the instructions that cause the processor to analyze include instructions that cause the processor to classify the second plurality of recorded interactions into a second plurality of interaction reasons and a second plurality of interaction resolution statuses; and

forecast a demand of the contact center agents for a second time period for handling the second interaction reasons without forecasting a demand for handling an obsolete interaction reason included in the first plurality of interactions reasons, the second time period being different from the first time period; and

an electronic switch coupled to the processor, the electronic switch configured to route the detected interaction to a particular agent selected from the first and second number of agents.

11. The system of claim 10, wherein the memory further stores instructions that, when executed by the processor, cause the processor to determine an interaction handling time, wherein the first agent effectiveness and the second agent effectiveness each comprise an average interaction handling time computed from the interaction handling time.

12. The system of claim 11, wherein the agent work schedule is further generated based on an average tare time.

13. The system of claim 10, wherein the instructions stored in the memory that cause the processor to analyze the classified recorded interactions to compute the agent effectiveness of the first and second agents comprise instructions that, when executed by the processor, cause the processor to:

identify, from among the plurality of recorded interactions, a subset of recorded interactions in which the first agent or the second agent participated and which were classified with the interaction reason;

identify, from among the subset of recorded interactions, a plurality of unresolved interactions in which an interaction resolution status of the interaction resolution statuses associated with the subset of recorded interactions is set as unresolved; and

compute the first agent effectiveness and the second agent effectiveness with respect to the interaction reason based on a number of unresolved recorded interactions for each agent and a number of interactions for each agent in the subset of recorded interactions.

14. The system of claim 10, wherein the memory further stores instructions that, when executed by the processor, cause the processor to update the computed first agent effectiveness and the computed second agent effectiveness by analyzing the second plurality of recorded interactions.

15. The system of claim 14, wherein the second interaction reasons comprise at least one new interaction reason different from each of the first interaction reasons.

16. The system of claim 15, wherein the instructions stored in the memory that cause the processor to compute agent effectiveness of the first and second agents comprise instructions that, when executed by the processor, cause the processor to:

identify, from among the plurality of recorded interactions, a subset of recorded interactions in which the first agent or the second agent participated and which were classified with the at least one new interaction reason;

identify, from among the subset of recorded interactions, a plurality of unresolved interactions in which an interaction resolution status of the interaction resolution statuses associated with the subset of recorded interactions is set as unresolved; and

compute the first agent effectiveness and the second agent effectiveness with respect to the at least one new interaction reason based on a number of unresolved recorded interactions for each agent and a number of interactions for each agent in the subset of recorded interactions.

17. The system of claim 15, wherein the memory further stores instructions that, when executed by the processor, cause the processor to forecast a demand of the contact center agents for a second time period for handling interactions classified with the new interaction reason, the second time period being different from the first time period.

18. The system of claim 14, wherein the obsolete interaction reason is different from each of the second interaction reasons.

20. The system of claim 10, wherein the first agent effectiveness and the second agent effectiveness correspond to a sub-category of the interaction reason of the first interaction reasons.