# US 2019/0245975 A1 · Automatic quality management of chat agents via chat bots

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2019/0245975 A1
- Document ID: US20190245975A1
- Status: Published application
- Kind: A1
- Application number: 16/389,745
- Filed: 2019-04-19
- Published: 2019-08-08
- Earliest claimed: 2017-08-15
- Assignees: Genesys Telecommunications Laboratories, Inc.
- Applicants: Genesys Telecommunications Laboratories, Inc.
- Inventors: Yochai Konig; David Konig
- Web page: https://patentgrep.com/patent/US20190245975A1

## CPC

- H04M 3/5175: {Call or contact centers supervision arrangements}
- G06F 40/30: Semantic analysis
- G06Q 10/06398: {Performance of employee with respect to a job function}
- H04L 51/02: using automatic reactions or user delegation, e.g. automatic replies or chatbot-generated messages
- H04M 3/5183: {Call or contact centers with computer-telephony arrangements}
- H04M 7/0045: {where the text-based messaging service is an instant messaging service}
- H04M 2203/401: Performance feedback
- H04M 2203/403: Agent or workforce training
- H04M: TELEPHONIC COMMUNICATION (circuits for controlling other apparatus via a telephone cable and not involving telephone switching apparatus G08)
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)

## Abstract

A method for automated quality management of agents of a contact center includes: selecting, by a processor, a topic for interacting with a human agent of the contact center; identifying, by the processor, a dialog tree associated with the selected topic; and engaging, by the processor, in an automated communication session with the human agent based on the identified dialog tree, wherein the engaging of the automated communication session includes: receiving, by the processor, an agent input; identifying, by the processor, a current node of the dialog tree associated with the agent input; selecting, by the processor, an automated phrase to be output in response to identifying the current node; and outputting, by the processor, the automated phrase.

## Claims

### Claim at position 1

1-20. (canceled)

### Claim 21

A method for automated quality management of agents of a contact center, the method comprising:
identifying, by a processor, a trigger for invoking evaluation of a particular human agent of the contact center;
selecting, by a processor, a topic for interacting with the human agent, wherein the selected topic is based on the identified trigger;
identifying, by the processor, a dialog tree associated with the selected topic;
invoking, by the processor, an automated response module for engaging in an automated communication session with the human agent based on the identified dialog tree, wherein the automated response module is configured to emulate a human customer during the automated communication session;
evaluating, by the processor, the automated communication session with the human agent based on a defined criteria;
determining, by the processor, whether the criteria has been satisfied; and
invoking, by the processor, and action in response to the determination.

### Claim 22 (depends on 21)

The method of claim 21, further comprising:
receiving, by the processor, an agent input from the human agent during the automated communication session;
identifying, by the processor, a current node of the dialog tree based on the agent input;
selecting, by the processor, an automated phrase associated with the identified current node; and
outputting, by the processor, the selected automated phrase as a response to the agent input.

### Claim 23 (depends on 22)

The method of claim 22, wherein the evaluating of the automated communication session further comprises:
identifying, by the processor, a target agent input;
semantically comparing, by the processor, the agent input to the target agent input;
determining, by the processor, whether the agent input is semantically equivalent to the target agent input; and
calculating, by the processor, a performance score for the human agent based on the semantic equivalence of the agent input to the target agent input.

### Claim 24 (depends on 23)

The method of claim 23, wherein the processor determines that the criteria has been satisfied in response to the performance score exceeding a threshold score.

### Claim 25 (depends on 22)

The method of claim 22, wherein the automated phrase is selected from a plurality of phrases provided by human customers during interactions with the agents of the contact center, the plurality of phrases being in response to inputs by the agents of the contact center that correspond to the agent input from the human agent.

### Claim 26 (depends on 25)

The method of claim 25, wherein the selecting of the automated phrase further comprises:
identifying, by the processor, a number of occurrences of each of the plurality of phrases; and
selecting, by the processor, one of the plurality of the phrases based on the identified number of occurrences.

### Claim 27 (depends on 21)

The method of claim 21, wherein the trigger is a particular contact center optimization criterion.

### Claim 28 (depends on 21)

The method of claim 21, wherein the trigger is a particular level of performance of the human agent in handling interactions associated with the topic.

### Claim 29 (depends on 21)

The method of claim 21, wherein the action is invoking, by the processor, a coaching session for the human agent.

### Claim 30 (depends on 21)

The method of claim 21, wherein the action is triggering, by the processor, a reward or promotion for the human agent.

### Claim 31

A system for automated quality management of agents of a contact center, comprising:
a processor; and
a memory coupled to the processor, the memory storing instructions that, when executed by the processor, cause the processor to:
identify a trigger for invoking evaluation of a particular human agent of the contact center;
select a topic for interacting with the human agent, wherein the selected topic is based on the identified trigger;
identify a dialog tree associated with the selected topic;
invoke an automated response module for engaging in an automated communication session with the human agent based on the identified dialog tree, wherein the automated response module is configured to emulate a human customer during the automated communication session;
evaluate the automated communication session with the human agent based on a defined criteria;
determine whether the criteria has been satisfied; and
invoke an action in response to the determination.

### Claim 32 (depends on 31)

The system of claim 31, wherein the instructions further cause the processor to:
receive an agent input from the human agent during the automated communication session;
identify a current node of the dialog tree based on the agent input;
select an automated phrase associated with the identified current node; and
output the selected automated phrase as a response to the agent input.

### Claim 33 (depends on 32)

The system of claim 32, wherein the instructions that cause the processor to evaluate the automated communication session further include instructions that cause the processor to:
identify a target agent input;
semantically compare the agent input to the target agent input;
determine whether the agent input is semantically equivalent to the target agent input; and
calculate a performance score for the human agent based on the semantic equivalence of the agent input to the target agent input.

### Claim 34 (depends on 33)

The system of claim 33, wherein the instructions further cause the processor to determine that the criteria has been satisfied in response to the performance score exceeding a threshold score.

### Claim 35 (depends on 32)

The system of claim 32, wherein the automated phrase is selected from a plurality of phrases provided by human customers during interactions with the agents of the contact center, the plurality of phrases being in response to inputs by the agents of the contact center that correspond to the agent input from the human agent.

### Claim 36 (depends on 35)

The system of claim 35, wherein the instructions that cause the processor to select the automated phrase further include instructions that cause the processor to:
identify a number of occurrences of each of the plurality of phrases; and
select one of the plurality of the phrases based on the identified number of occurrences.

### Claim 37 (depends on 31)

The system of claim 31, wherein the trigger is a particular contact center optimization criterion.

### Claim 38 (depends on 31)

The system of claim 31, wherein the trigger is a particular level of performance of the human agent in handling interactions associated with the topic.

### Claim 39 (depends on 31)

The system of claim 31, wherein the instructions that cause the processor to invoke the action include instructions that cause the processor to invoke a coaching session for the human agent.

### Claim 40 (depends on 31)

The system of claim 31, wherein the instructions that cause the processor to invoke the action include instructions that cause the processor to trigger a reward or promotion for the human agent.
