IP Library Granted Patent US 11,893,904
Granted Patent B2
US 11,893,904 · App. 17/475,005 · Granted Feb 6, 2024

Utilizing conversational artificial intelligence to train agents

Inventors: Dan Stoops (Daly City, CA); Cliff Bell (Daly City, CA); Merijn Te Booij (Daly City, CA)
Assignee: Genesys Cloud Services, Inc.
G09B5/04H04L51/02H04M3/5175H04M3/5183
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 11,893,904
App. No.
17/475,005
Granted
Feb 6, 2024
Kind
B2
Abstract

A system for utilizing conversational artificial intelligence (AI) to train contact center agents according to an embodiment includes at least one processor and at least one memory comprising a plurality of instructions stored therein that, in response to execution by the at least one processor, causes the system to place a virtual call from an automated training system to an agent device of an agent, connect the virtual call to a chatbot in response to establishing a communication connection with the agent device, transmit one or more statements from the chatbot, receive, from the agent device, one or more agent responses of the agent corresponding to the one or more statements, and analyze the one or more agent responses to determine one or more training characteristics associated with AI-based contact center training of the agent.

Claims (27)

1. A system for utilizing conversational artificial intelligence (AI) to train contact center agents, the system comprising:

at least one processor; and

at least one memory comprising a plurality of instructions stored therein that, in response to execution by the at least one processor, causes the system to:

place a virtual call from an automated training system to an agent device of an agent;

connect the virtual call to a chatbot in response to establishing a communication connection with the agent device;

transmit one or more statements from the chatbot;

receive, from the agent device, one or more agent responses of the agent corresponding to the one or more statements; and

analyze the one or more agent responses to determine one or more training characteristics associated with AI-based contact center training of the agent, wherein to analyze the one or more agent responses comprises to (i) determine a duration of each of the one or more agent responses, (ii) determine an accuracy of each of the one or more agent responses, and (iii) evaluate a language efficiency of each of the one or more agent responses in response to a determination, based on the determined duration and the determined accuracy, that the corresponding agent response is both timely and accurate, and wherein to evaluate the language efficiency of a corresponding agent response comprises to identify more efficient language to be used by the agent to convey a same intent as the corresponding agent response.

2. The system of claim 1 , wherein to analyze the one or more agent responses comprises to analyze a sequence of statements from the chatbot and corresponding agent responses of the agent.

3. The system of claim 1 , wherein to determine the accuracy of each of the one or more agent responses comprises to compare each of the one or more agent responses to a set of predefined response elements evaluated by the chatbot.

4. The system of claim 1 , wherein to analyze the one or more agent responses comprises to evaluate agent fatigue of the agent as a training session between the agent and the chatbot progresses from a first agent response of the one or more agent responses to a second subsequent agent response of the one or more agent responses; and

wherein the plurality of instructions further causes the system to pace placement of at least one subsequent virtual call from the automated training system to the agent device based on the evaluation of agent fatigue.

5. The system of claim 1 , wherein to place the virtual call from the automated training system comprises to place the virtual call from a cloud-based system including the automated training system to an agent device of a contact center system.

6. The system of claim 1 , wherein to transmit the one or more statements from the chatbot comprises to generate audio via a text-to-speech conversion.

7. The system of claim 1 , wherein the automated training system comprises an interactive voice response system.

8. A method of utilizing conversational artificial intelligence (AI) to train contact center agents, the method comprising:

placing, by a computing system, a virtual call from an automated training system to an agent device of an agent;

connecting, by the computing system, the virtual call to a chatbot in response to establishing a communication connection with the agent device;

transmitting, by the computing system, one or more statements from the chatbot;

receiving, by the computing system and from the agent device, one or more agent responses of the agent corresponding to the one or more statements; and

analyzing, by the computing system, the one or more agent responses to determine one or more training characteristics associated with AI-based contact center training of the agent, wherein analyzing the one or more agent responses comprises (i) determining a duration of each of the one or more agent responses, (ii) determining an accuracy of each of the one or more agent responses, and (iii) evaluating a language efficiency of each of the one or more agent responses in response to determining, based on the determined duration and the determined accuracy, that the corresponding agent response is both timely and accurate, and wherein evaluating the language efficiency of a corresponding agent response comprises identifying more efficient language to be used by the agent to convey a same intent as the corresponding agent response.

9. The method of claim 1 , wherein analyzing the one or more agent responses comprises analyzing a sequence of statements from the chatbot and corresponding agent responses of the agent.

10. The method of claim 8 , wherein determining the accuracy of each of the one or more agent responses comprises comparing each of the one or more agent responses to a set of predefined response elements evaluated by the chatbot.

11. The method of claim 1 , wherein analyzing the one or more agent responses comprises evaluating agent fatigue of the agent as a training session between the agent and the chatbot progresses from a first agent response of the one or more agent responses to a second subsequent agent response of the one or more agent responses.

12. The method of claim 1 , wherein placing the virtual call from the automated training system comprises placing the virtual call from a cloud-based system including the automated training system to an agent device of a contact center system.

13. The method of claim 1 , wherein transmitting the one or more statements from the chatbot comprises generating audio via a text-to-speech conversion.

14. The method of claim 1 , wherein the automated training system comprises an interactive voice response system.

Assignments (3)
NOTICE OF SUCCESSION OF SECURITY INTERESTS AT REEL/FRAME 059470/0398 Recorded Feb 3, 2025
From: BANK OF AMERICA, N.A., AS RESIGNING AGENT
To: GOLDMAN SACHS BANK USA, AS SUCCESSOR AGENT
Reel/Frame 070097/0393 →
SECURITY AGREEMENT Recorded Mar 18, 2022
From: GENESYS CLOUD SERVICES, INC.; GENESYS TELECOMMUNICATIONS LABORATORIES, INC.
To: BANK OF AMERICA, N.A.
Reel/Frame 059470/0398 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Oct 6, 2021
From: STOOPS, DAN; BELL, CLIFF; TE BOOIJ, MERIJN
To: GENESYS CLOUD SERVICES, INC.
Reel/Frame 057715/0824 →