SYSTEM AND METHOD FOR AUTOMATIC QUALITY MANAGEMENT IN A CONTACT CENTER ENVIRONMENT

• US 20180091653A1
• Filed: 09/22/2017
• Published: 03/29/2018
• Est. Priority Date: 09/23/2016
• Status: Active Grant

• Current Assignee: Genesys Telecommunications Laboratories Incorporated (Genesys Cloud Services Incorporated)
• Original Assignee: Interactive Intelligence Group Incorporated (Genesys Cloud Services Incorporated)
• Inventors: Miller, Derek M., Brennan, Taylor
• Granted Patent: US 10,652,391 B2
• Time in Patent Office: Days
• CPC Class Codes: G06F 7/02 Comparing digital values G06F7/06, G06F7/22, G06F7/38 take precedence
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 5/04 Inference or reasoning models
• CPC Class Codes: G06Q 10/06398 Performance of employee with respect to a job function
• CPC Class Codes: G06Q 50/2057 Career enhancement or continuing education service
• CPC Class Codes: H04M 2201/18 Comparators
• CPC Class Codes: H04M 2203/402 Agent or workforce management
• CPC Class Codes: H04M 2203/403 Agent or workforce training
• CPC Class Codes: H04M 3/2281 Call monitoring, e.g. for law enforcement purposes; Call tracing; Detection or prevention of malicious calls
• CPC Class Codes: H04M 3/42221 Conversation recording systems at the subscriber's set H04M1/656
• CPC Class Codes: H04M 3/5175 Call or contact centers supervision arrangements

Abstract

A method for automatically managing a recorded interaction between a customer and an agent of a contact center includes: extracting, by a processor, features from the recorded interaction; computing, by the processor, a score of the recorded interaction by supplying the features to a prediction model; detecting, by the processor, a condition based on the score; matching, by the processor, the condition with an action; and transmitting, by the processor, a command to control a component of the contact center to perform the action.

Claims

1. A method for automatically managing a recorded interaction between a customer and an agent of a contact center, the method comprising:

extracting, by a processor, features from the recorded interaction;

computing, by the processor, a score of the recorded interaction by supplying the features to a prediction model;

detecting, by the processor, a condition based on the score;

matching, by the processor, the condition with an action; and

transmitting, by the processor, a command to control a component of the contact center to perform the action.

2. The method of claim 1, wherein the recorded interaction comprises content and metadata, and

wherein the features comprise at least one of:

keywords detected in the content of the recorded interaction;

one or more topics in the content of the recorded interaction;

a length of the recorded interaction;

a number of agent transfers during the recorded interaction; and

a net promoter score associated with the recorded interaction.

3. The method of claim 1, wherein the prediction model is trained by:

extracting, by the processor, a plurality of historical interaction features from a plurality of historical interactions;

receiving, by the processor, a plurality of manual evaluations, each of the manual evaluations corresponding to one of the plurality of historical interactions, and each of the manual evaluations comprising a score; and

training, by the processor, the prediction model in accordance with a relationship between the historical interaction features of the historical interactions and the scores of corresponding ones of the manual evaluations.

4. The method of claim 1, wherein the condition is satisfied when the score is within a threshold range corresponding to compliance with agent performance standards, and

wherein the component of the contact center is a call recording server.

5. The method of claim 4, wherein the command is configured to control the call recording server to delete the recorded interaction.

6. The method of claim 4, wherein the command is configured to control the call recording server to set an expiration date on the recorded interaction.

7. The method of claim 1, wherein the condition is satisfied when the score is within a threshold range corresponding to not in compliance with agent performance standards, and

wherein the component of the contact center is a quality management server.

8. The method of claim 7, wherein the command is configured to control the quality management server to send an alert to a human supervisor.

9. The method of claim 7, wherein the command is configured to control the quality management server to assign an evaluation task to a human supervisor.

10. A system for automatically managing a recorded interaction between a customer and an agent of a contact center comprises:

a processor; and

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

extract features from the recorded interaction;

compute a score of the recorded interaction by supplying the features to a prediction model;

detect a condition based on the score;

match the condition with an action; and

transmit a command to control a component of the contact center to perform the action.

11. The system of claim 10, wherein the recorded interaction comprises content and metadata, and

wherein the features comprise at least one of:

keywords detected in the content of the recorded interaction;

one or more topics in the content of the recorded interaction;

a length of the recorded interaction;

a number of agent transfers during the recorded interaction; and

a net promoter score associated with the recorded interaction.

12. The system of claim 10, wherein the prediction model is trained by:

extracting a plurality of historical interaction features from a plurality of historical interactions;

receiving a plurality of manual evaluations, each of the manual evaluations corresponding to one of the plurality of historical interactions, and each of the manual evaluations comprising a score; and

training the prediction model in accordance with a relationship between the historical interaction features of the historical interactions and the scores of corresponding ones of the manual evaluations.

13. The system of claim 10, wherein the condition is satisfied when the score is within a threshold range corresponding to compliance with agent performance standards, and

wherein the component of the contact center is a call recording server.

14. The system claim 13, wherein the command is configured to control the call recording server to delete the recorded interaction.

15. The system of claim 13, wherein the command is configured to control a call recording server to set an expiration date on the recorded interaction.

16. The system of claim 10, wherein the condition is satisfied when the score is within a threshold range corresponding to not in compliance with agent performance standards, and

wherein the component of the contact center is a quality management server.

17. The system of claim 16, wherein the command is configured to control the quality management server to send an alert to a human supervisor.

18. The system of claim 16, wherein the command is configured to control the quality management server to assign an evaluation task to a human supervisor to perform a manual evaluation of the recorded interaction.

19. A system for automatically managing a recorded interaction between a customer and an agent of a contact center, the system comprising:

means for extracting features from the recorded interaction;

means for computing a score of the recorded interaction by supplying the features to a prediction model;

means for detecting a condition based on the score;

means for matching the condition with an action; and

means for transmitting a command to control a component of the contact center to perform the action.

20. The system of claim 19, wherein the recorded interaction comprises content and metadata, and

wherein the features comprise at least one of:

keywords detected in the content of the recorded interaction;

one or more topics in the content of the recorded interaction;

a length of the recorded interaction;

a number of agent transfers during the recorded interaction; and

a net promoter score associated with the recorded interaction.