# US 2021/0174288 A1 · System and method for predicting performance for a contact center via machine learning

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

- Number: US 2021/0174288 A1
- Document ID: US20210174288A1
- Status: Published application
- Kind: A1
- Application number: 16/706,631
- Filed: 2019-12-06
- Published: 2021-06-10
- Earliest claimed: 2019-12-06
- Assignees: Genesys Telecommunications Laboratories, Inc.
- Applicants: Genesys Telecommunications Laboratories, Inc.
- Inventors: Paul Michael Gvildys; John Russell Christofolakos; Liyuan Qiao; Yizheng Yang; Xiaoyang Guo
- Web page: https://patentgrep.com/patent/US20210174288A1

## CPC

- G06Q 10/06393: {Score-carding, benchmarking or key performance indicator [KPI] analysis}
- G06Q 10/06395: {Quality analysis or management}
- G06Q 10/06398: {Performance of employee with respect to a job function}
- G06Q 10/1053: Employment or hiring
- G10L 15/26: Speech to text systems (G10L15/08 takes precedence)
- G10L 25/48: specially adapted for particular use
- H04M 3/323: {for the arrangements providing the connection (test connection, test call, call simulation)}
- H04M 3/5175: {Call or contact centers supervision arrangements}
- G10L 15/1822: {Parsing for meaning understanding}
- G10L 25/63: for estimating an emotional state
- 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
- G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- H04M: TELEPHONIC COMMUNICATION (circuits for controlling other apparatus via a telephone cable and not involving telephone switching apparatus G08)

## Abstract

A system and method for predicting performance for a contact center via machine learning includes invoking, by a processor, an interaction between a contact center resource and an end user, and recording, by the processor, the interaction. The processor automatically analyzes the recorded interaction for identifying attributes associated with the interaction. The processor provides the identified attributes to a machine learning model which predicts a performance score based on the identified attributes. The performance score is compared against a threshold score, and a recommendation is output by the processor based on the comparing. The end user may be a candidate contact center agent considered for hiring, and the recommendation may be to hire the candidate or advance the candidate to a next step of an interview process.

## Claims

### Claim 1

A method for predicting performance for a contact center via machine learning, the method comprising:
invoking, by a processor, an interaction between a contact center resource and an end user;
recording, by the processor, the interaction;
automatically analyzing, by the processor, the recorded interaction for identifying attributes associated with the interaction;
providing, by the processor, the identified attributes to a machine learning model;
predicting, by the processor, a performance score based on providing the identified attributes to the machine learning model;
comparing the performance score against a threshold score; and
outputting, by the processor, a recommendation based on the comparing.

### Claim 2 (depends on 1)

The method of claim 1, wherein the interaction is a simulated call between the end user and a voice processor of the contact center, wherein the voice processor is configured with a script for conducting the simulated call.

### Claim 3 (depends on 1)

The method of claim 1, wherein the attributes include emotions of the end user during the interaction, adherence of the end user to a script invoked for the interaction, or clarity in speech of the end user during the interaction.

### Claim 4 (depends on 1)

The method of claim 1, wherein the automatically analyzing of the recorded interaction includes assigning a score to each of the identified attributes.

### Claim 5 (depends on 1)

The method of claim 1, wherein the predicted performance score is for predicting performance of the end user in meeting particular metrics for the contact center.

### Claim 6 (depends on 1)

The method of claim 1 further comprising:
monitoring contact center agents of the contact center;
gathering performance scores of the monitored contact center agents;
invoking a second interaction with the contact center agents;
obtaining attribute scores for the contact center agents based on the second interaction;
correlating the attribute scores with the performance scores; and
training the machine learning model based on the correlation.

### Claim 7 (depends on 1)

The method of claim 1 further comprising:
monitoring a criteria of the contact center; and
dynamically adjusting the threshold based on the monitored criteria.

### Claim 8 (depends on 1)

The method of claim 1, wherein the end user is a candidate contact center agent considered for hiring, and the recommendation is hiring the candidate or advancing the candidate to a next step of an interview process.

### Claim 9

A system for predicting performance for a contact center via machine learning, the system comprising:
processor; and
memory, wherein the memory has stored therein instructions that, when executed by the processor, cause the processor to:
invoke an interaction between a contact center resource and an end user;
record the interaction;
automatically analyze the recorded interaction for identifying attributes associated with the interaction;
provide the identified attributes to a machine learning model;
predict a performance score based on providing the identified attributes to the machine learning model;
compare the performance score against a threshold score; and
output a recommendation based on the comparing.

### Claim 10 (depends on 9)

The system of claim 9, wherein the interaction is a simulated call between the end user and a voice processor of the contact center, wherein the voice processor is configured with a script for conducting the simulated call.

### Claim 11 (depends on 9)

The system of claim 9, wherein the attributes include emotions of the end user during the interaction, adherence of the end user to a script invoked for the interaction, or clarity in speech of the end user during the interaction.

### Claim 12 (depends on 9)

The system of claim 9, wherein the instructions that cause the processor to automatically analyze the recorded interaction include instructions that cause the processor to assign a score to each of the identified attributes.

### Claim 13 (depends on 9)

The system of claim 9, wherein the predicted performance score is for predicting performance of the end user in meeting particular metrics for the contact center.

### Claim 14 (depends on 9)

The system of claim 9, wherein the instructions further cause the processor to:
monitor contact center agents of the contact center;
gather performance scores of the monitored contact center agents;
invoke a second interaction with the contact center agents;
obtain attribute scores for the contact center agents based on the second interaction;
correlate the attribute scores with the performance scores; and
train the machine learning model based on the correlation.

### Claim 15 (depends on 9)

The system of claim 9, wherein the instructions further cause the processor to:
monitor a criteria of the contact center; and
dynamically adjust the threshold based on the monitored criteria.

### Claim 16 (depends on 9)

The system of claim 9, wherein the end user is a candidate contact center agent considered for hiring, and the recommendation is hiring the candidate or advancing the candidate to a next step of an interview process.
