Automated agent behavior recommendations for call quality improvement

Patent metadata

Field	Value
Publication number	US-11647116-B2
Application number	US-202117537842-A
Country	US
Kind code	B2
Filing date	Nov 30, 2021
Priority date	Sep 30, 2020
Publication date	May 9, 2023
Grant date	May 9, 2023

Abstract

Disclosed herein is a method for automated agent behavior recommendations for call quality improvement. The method performed at a server includes receiving a first data record and a second data record of a plurality of data records, each comprising communication between a first party and a second party and determining a first communication originated from the first party. The method includes determining a category for each section of the plurality of sections of the first communication, and a plurality of behavior distances between different categories associated with the plurality of sections. The method includes augmenting first metadata of the first data record and second metadata of the second data record to include associated behavior distances and determining an average performance ranking of the first party to generate a recommendation to increase the average performance ranking of the first party above a preconfigured threshold.

First claim

What is claimed is:

1. A method, comprising:
receiving, at a server, a first data record and a second data record comprising communication between a first party and a second party;
determining, at the server, a plurality of behavior distances in the communication between the first party and the second party;
augmenting, by the server, first metadata of the first data record and second metadata of the second data record to include associated behavior distances;
determining, at the server, an average performance ranking of the first party based on an analysis of the first metadata and the second metadata; and
generating, at the server, one or more recommendations for the first party to increase the average performance ranking of the first party above a preconfigured threshold.

2. The method of claim 1 , wherein the communication is audio communication and the method further comprises generating, by the server, a transcription of the audio communication including timestamps.

3. The method of claim 1 , wherein the first data record or the second data record comprises start times and end times of an event from a set of events comprising spoken or written communication between the first party and the second party.

4. The method of claim 1 , further comprising:
determining, by the server, availability of a communication channel for the first party in the first data record or the second data record;
in response to determining that the communication channel for the first party is unavailable in the first data record or the second data record, classifying, by the server, each spoken or written word of a plurality of spoken or written words exchanged between the first party and the second party, wherein the plurality of spoken or written words are exchanged over a plurality of communication channels;
determining, by the server, a channel of the plurality of communication channels over which a number of spoken or written words identifying the first party based on a predetermined set of words exceeding a predetermined threshold value; and
separating, by the server, a first communication originated from the first party from a second communication originated from the second party based on the determined channel.

5. The method of claim 1 , wherein the communication comprises a salutation by the first party, an acknowledgement by the first party, an inquiry by the first party, a validation by the first party, or advice by the first party.

6. The method of claim 1 , wherein determining the average performance ranking further comprises:
analyzing, by the server, the first metadata and the second metadata based on a policy associated with a set of organizational guidelines.

7. The method of claim 1 , further comprising:
facilitating, by the server, training material for the first party, wherein the training material corresponds to the one or more recommendations generated for the first party to increase the average performance ranking of the first party above the preconfigured threshold.

8. The method of claim 1 , wherein the processor is further configured to:
facilitate training material for the first party, wherein the training material corresponds to the one or more recommendations generated for the first party to increase the average performance ranking of the first party above the preconfigured threshold.

9. A system, comprising:
a memory; and
a processor coupled to the memory, wherein the processor is configured to:
receive a first data record and a second data record comprising communication between a first party and a second party;
determine a plurality of behavior distances in the communication between the first party and the second party;
augment first metadata of the first data record and second metadata of the second data record to include associated behavior distances;
determine an average performance ranking of the first party based on an analysis of the first metadata and the second metadata; and
generate one or more recommendations for the first party to increase the average performance ranking of the first party above a preconfigured threshold.

10. The system of claim 9 , wherein the communication is audio communication and wherein the processor is further configured to generate a transcription of the audio communication including timestamps.

11. The system of claim 9 , wherein the first data record or the second data record comprises start times and end times of an event from a set of events comprising spoken or written communication between the first party and the second party.

12. The system of claim 9 , wherein the processor is further configured to:
determine availability of a communication channel for the first party in the first data record or the second data record;
in response to determining that the communication channel for the first party is unavailable in the first data record or the second data record, classify each spoken or written word of a plurality of spoken or written words exchanged between the first party and the second party, wherein the plurality of spoken or written words are exchanged over a plurality of communication channels;
determine a channel of the plurality of communication channels over which a number of spoken or written words identify the first party based on a predetermined set of words exceeding a predetermined threshold value; and
separate a first communication originated from the first party from a second communication originated from the second party based on the determined channel.

13. The system of claim 9 , wherein the communication comprises a salutation by the first party, an acknowledgement by the first party, an inquiry by the first party, a validation by the first party, or advice by the first party.

14. The system of claim 9 , wherein when determining the average performance ranking the processor is further configured to:
analyze the first metadata and the second metadata based on a policy associated with a set of organizational guidelines.

15. A non-transitory computer-readable medium having instructions stored thereon that, when executed by at least one computing device of an application server, cause the at least one computing device to perform operations comprising:
receive a first data record and a second data record comprising communication between a first party and a second party;
determine a plurality of behavior distances in the communication between the first party and the second party;
augment first metadata of the first data record and second metadata of the second data record to include associated behavior distances;
determine an average performance ranking of the first party based on an analysis of the first metadata and the second metadata; and
generate one or more recommendations for the first party to increase the average performance ranking of the first party above a preconfigured threshold.

16. The non-transitory computer-readable medium of claim 15 , wherein the communication is audio communication and the operations further comprise generate a transcription of the audio communication including timestamps.

17. The non-transitory computer-readable medium of claim 15 , wherein the first data record or the second data record comprises start times and end times of an event from a set of events comprising spoken or written communication between the first party and the second party.

18. The non-transitory computer-readable medium of claim 15 , wherein the operations further comprise:
determining availability of a communication channel for the first party in

Assignees

• Capital One Services Llc

Inventors

• Shukla Nagendra
• Bricker Joel
• Abbott Brian
• Hardwick Bradley
• Dickert Sean

Classifications

• H04M2203/403

  Agent or workforce training · CPC title

• H04M3/5175 Primary

  Call or contact centers supervision arrangements · CPC title

• G10L15/22

  Procedures used during a speech recognition process, e.g. man-machine dialogue · CPC title

• H04M2203/401

  Performance feedback · CPC title

• G10L15/30

  Distributed recognition, e.g. in client-server systems, for mobile phones or network applications · CPC title