# US 10,313,521 B2 · 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 10,313,521 B2
- Document ID: US10313521B2
- Status: Granted
- Kind: B2
- Application number: 15/677,927
- Filed: 2017-08-15
- Published: 2019-02-21
- Granted: 2019-06-04
- Earliest claimed: 2017-08-15
- Applicants: Genesyc Telecommunications Laboratories, Inc
- Inventors: Yochai Konig; David Konig
- Web page: https://patentgrep.com/patent/US10313521B2

## 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 1

A method for automated quality management of agents of a contact center, the method comprising:
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 input from the human agent;
identifying, by the processor, a current node of the dialog tree associated with the 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.

### Claim 2 (depends on 1)

The method of claim 1, further comprising:
identifying, by the processor, a target agent input associated with the identified current node;
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;
calculating, by the processor, a performance score for the human agent based on the determining; and
outputting, by the processor, feedback based on the determined performance score.

### Claim 3 (depends on 2)

The method of claim 2, wherein the feedback comprises a report summarizing the human agent's proficiencies and/or areas of improvement.

### Claim 4 (depends on 2)

The method of claim 2, further comprising:
invoking, by the processor, a coaching session for the human agent based on the feedback.

### Claim 5 (depends on 1)

The method of claim 1, wherein the automated phrase is selected from a plurality of phrases provided by human customers for a current dialog state during interactions with agents of the contact center, the interactions relating to the selected topic.

### Claim 6 (depends on 5)

The method of claim 5, wherein the selecting of the automated phrase further comprises:
identifying, by the processor, frequency of each of the plurality of phrases for the current dialog state; and
selecting, by the processor, one of the plurality of the phrases based on the identified frequency.

### Claim 7 (depends on 1)

The method of claim 1, wherein the topic is selected based on a criterion to be optimized by the contact center.

### Claim 8 (depends on 1)

The method of claim 1, wherein the topic is selected based on performance of the human agent during interactions with human customers relating to the topic.

### Claim 9 (depends on 1)

The method of claim 1, wherein the topic is selected based on performance of the human agent during previous automated communication sessions.

### Claim 10 (depends on 1)

The method of claim 1, wherein the automated communication session is a text based chat session.

### Claim 11

A system for automated quality management of agents of a contact center, comprising:
a processor; and
a memory coupled to the processor and storing instructions that, when executed by the processor, cause the processor to:
select a topic for interacting with a human agent of the contact center;
identify a dialog tree associated with the selected topic; and
engage 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 an input from the human agent;
identifying a current node of the dialog tree associated with the agent input;
selecting an automated phrase to be output in response to identifying the current node; and
outputing the automated phrase.

### Claim 12 (depends on 11)

The system of claim 11, wherein the instructions further cause the processor to:
identify a target agent input associated with the identified current node;
semantically compare the agent input to the target agent input;
determine whether the agent input is semantically equivalent to the target agent input;
calculate a performance score for the human agent based on the determining; and
output feedback based on the determined performance score.

### Claim 13 (depends on 12)

The system of claim 12, wherein the feedback comprises a report summarizing the human agent's proficiencies and/or areas of improvement.

### Claim 14 (depends on 12)

The system of claim 12, wherein the instructions further cause the processor to:
invoke a coaching session for the human agent based on the feedback.

### Claim 15 (depends on 11)

The system of claim 11, wherein the automated phrase is selected from a plurality of phrases provided by human customers for a current dialog state during interactions with agents of the contact center, the interactions relating to the selected topic.

### Claim 16 (depends on 15)

The system of claim 15, wherein the selecting of the automated phrase further comprises:
identifying frequency of each of the plurality of phrases for the current dialog state; and
selecting one of the plurality of the phrases based on the identified frequency.

### Claim 17 (depends on 11)

The system of claim 11, wherein the topic is selected based on a criterion to be optimized by the contact center.

### Claim 18 (depends on 11)

The system of claim 11, wherein the topic is selected based on performance of the human agent during interactions with human customers relating to the topic.

### Claim 19 (depends on 11)

The system of claim 11, wherein the topic is selected based on performance of the human agent during previous automated communication sessions.

### Claim 20 (depends on 11)

The system of claim 11, wherein the automated communication session is a text based chat session.