System and method for optimizing contact center resource groups

• US 10,158,757 B2
• Filed: 07/29/2016
• Issued: 12/18/2018
• Est. Priority Date: 07/29/2016
• Status: Active Grant

• Current Assignee: Genesys Telecommunications Laboratories Incorporated (Genesys Cloud Services Incorporated)
• Original Assignee: Genesys Telecommunications Laboratories Incorporated (Genesys Cloud Services Incorporated)
• Inventors: te Booij, Merijn, Gopalla, Kentis, Ristock, Herbert Willi Artur
• Primary Examiner(s): Hoque, Nafiz E
• Application Number:
  US15/224,298
• Publication Number:
  US 20180034966A1
• Time in Patent Office: 872 Days
• CPC Class Codes: H04M 2203/402 Agent or workforce management
• CPC Class Codes: H04M 3/5175 Call or contact centers supervision arrangements
• CPC Class Codes: H04M 3/5232 Call distribution algorithms

Abstract

A method for automatically generating a grouping of resources of a customer contact center includes: identifying, by a processor, one or more resource groups, each of the resource groups including a plurality of customer contact center resources; predicting, by the processor, for each of the one or more resource groups, a predicted performance metric of the resource group in accordance with the one or more customer contact center resources of the resource group; identifying, by the processor, a particular resource group of the one or more resource groups having a corresponding predicted performance satisfying a threshold performance among the one or more resource groups; and outputting, by the processor, the particular resource group.

Claims

1. A method for automatically generating a grouping of resources of a customer contact center, the method comprising:

identifying, by a processor, one or more resource groups, each of the resource groups comprising a plurality of customer contact center resources, wherein the resource group comprises one or more agents;

predicting, by the processor, for each of the one or more resource groups, a predicted performance metric of the resource group in accordance with the one or more customer contact center resources of the resource group, the predicting the predicted performance metric of the resource group comprising;

retrieving, by the processor, a plurality of predictors of agent performance, each predictor corresponding to one of the agents of the customer contact center;

predicting, by the processor, a predicted performance metric of each agent in the resource group based on the plurality of predictors of agent performance; and

computing, by the processor, the predicted performance metric of the resource group in the customer contact center in accordance with the predicted performance metric of each agent in the resource group;

identifying, by the processor, a particular resource group of the one or more resource groups having a corresponding predicted performance satisfying a threshold performance among the one or more resource groups; and

outputting, by the processor, the particular resource group,

wherein a predictor of the plurality of predictors of agent performance is generated by;

retrieving one or more historical performance metrics of an agent corresponding to the predictor;

retrieving historical social network data corresponding to the agent;

correlating the one or more historical performance metrics of the agent with the historical social network data of the agent; and

computing a plurality of parameters controlling a relationship between the historical social network data of the agent and the one or more historical performance metrics of the agent.

2. The method of claim 1, wherein the historical social network data comprises at least one of:

voice communication logs between the agent and one or more other agents of the customer contact center;

chat communication logs between the agent and one or more other agents of the customer contact center; and

team assignment data.

3. The method of claim 1, wherein each of the plurality of predictors of agent performance comprises a linear regression model between the one or more customer contact center resources of the resource group and a performance metric.

4. The method of claim 1, wherein each of the plurality of predictors of agent performance comprises a neural network having input features comprising the one or more customer contact center resources of the resource group and a performance metric as an output.

5. The method of claim 1, wherein the predicted performance metric comprises at least one of average handle time, average hold time, first call resolution rate, abandonment rate, net promoter score, conversion rate, and agent mood.

6. The method of claim 1, wherein the one or more customer contact center resources of the resource group comprise at least one of:

a printer;

an agent;

a manager;

a subject matter expert;

a telecommunications resource;

a server; and

telephony equipment.

7. A system comprising:

a processor; and

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

identify one or more resource groups, each of the resource groups comprising a plurality of customer contact center resources, each of the resource groups comprising one or more agents;

predict, for each of the one or more resource groups, a predicted performance metric of the resource group in accordance with the one or more customer contact center resources of the resource group by;

retrieving a plurality of predictors of agent performance, each predictor corresponding to one of the agents of the customer contact center;

predicting a predicted performance metric of each agent in the resource group based on the plurality of predictors of agent performance; and

computing the predicted performance metric of the resource group in the customer contact center in accordance with the predicted performance metric of each agent in the resource group;

identify a particular resource group of the one or more resource groups having a corresponding predicted performance satisfying a threshold performance among the one or more resource groups; and

output the particular resource group,

wherein the memory further stores instructions that, when executed by the processor, cause the processor to generate a predictor of the plurality of predictors by;

retrieving one or more historical performance metrics of an agent corresponding to the predictor;

retrieving historical social network data corresponding to the agent;

correlating the one or more historical performance metrics of the agent with the historical social network data of the agent; and

computing a plurality of parameters controlling a relationship between the historical social network data of the agent and the one or more historical performance metrics of the agent.

8. The system of claim 7, wherein the historical social network data comprises at least one of:

voice communication logs between the agent and one or more other agents of the customer contact center;

chat communication logs between the agent and one or more other agents of the customer contact center; and

team assignment data.

9. The system of claim 7, wherein each of the plurality of predictors of agent performance comprises a linear regression model between the one or more customer contact center resources of the resource group and a performance metric.

10. The system of claim 7, wherein each of the plurality of predictors of agent performance comprises a neural network having input features comprising the one or more customer contact center resources of the resource group and a performance metric as an output.

11. The system of claim 7, wherein the predicted performance metric comprises at least one of average handle time, average hold time, first call resolution rate, abandonment rate, net promoter score, conversion rate, and agent mood.

12. The system of claim 7, wherein the one or more customer contact center resources of the resource group comprise at least one of:

a printer;

an agent;

a manager;

a subject matter expert;

a telecommunications resource;

a server; and

telephony equipment.

13. A system comprising:

means for identifying one or more resource groups, each of the resource groups comprising a plurality of customer contact center resources, each of the resource groups comprising one or more agents;

means for predicting, for each of the one or more resource groups, a predicted performance metric of the resource group in accordance with the one or more customer contact center resources of the resource group, the means for predicting being configured to;

retrieve a plurality of predictors of agent performance, each predictor corresponding to one of the agents of the customer contact center;

predict a predicted performance metric of each agent in the resource group based on the plurality of predictors of agent performance; and

compute the predicted performance metric of the resource group in the customer contact center in accordance with the predicted performance metric of each agent in the resource group;

means for identifying a particular resource group of the one or more resource groups having a corresponding predicted performance satisfying a threshold performance among the one or more resource groups; and

means for outputting the particular resource group,

wherein a predictor of the plurality of predictors of agent performance is generated by;

retrieving one or more historical performance metrics of an agent corresponding to the predictor;

retrieving historical social network data corresponding to the agent;

correlating the one or more historical performance metrics of the agent with the historical social network data of the agent; and

computing a plurality of parameters controlling a relationship between the historical social network data of the agent and the one or more historical performance metrics of the agent.

14. The system of claim 13, wherein the historical social network data comprises at least one of:

voice communication logs between the agent and one or more other agents of the customer contact center;

chat communication logs between the agent and one or more other agents of the customer contact center; and

team assignment data.

15. The system of claim 13, wherein each of the plurality of models of agent performance comprises a linear regression model between the one or more customer contact center resources of the resource group and a performance metric.

16. The system of claim 13, wherein each of the plurality of predictors of agent performance comprises a neural network having input features comprising the one or more customer contact center resources of the resource group and a performance metric as an output.

17. The system of claim 13, wherein the predicted performance metric comprises at least one of average handle time, average hold time, first call resolution rate, abandonment rate, net promoter score, conversion rate, and agent mood.

18. The system of claim 13, wherein the one or more customer contact center resources of the resource group comprise at least one of:

a printer;

an agent;

a manager;

a subject matter expert;

a telecommunications resource;

a server; and

telephony equipment.