# US 2019/0244152 A1 · Method of using machine learning to predict problematic actions within an organization

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

- Number: US 2019/0244152 A1
- Document ID: US20190244152A1
- Status: Published application
- Kind: A1
- Application number: 16/265,893
- Filed: 2019-02-01
- Published: 2019-08-08
- Earliest claimed: 2018-02-02
- Assignees: Findo, Inc.
- Applicants: Findo, Inc.
- Inventors: David Yan; Victor Kuznetsov; Aleksandr Mertvetsov; Marina Chilingaryan; Eric Pelletier
- Web page: https://patentgrep.com/patent/US20190244152A1

## CPC

- G06Q 10/06398: {Performance of employee with respect to a job function}
- G06N 20/00: Machine learning
- 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
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

A method to predict problematic actions in an organization, executed by a processing device, includes accessing stored employee-related data, such as at least one of emails, surveys, minutes, or records of conversations, identifying a subset of the employee-related data that is associated with an employee, and predicting, based on the subset of the employee-related data associated with the employee, at least one of a likelihood that the employee is engaged in an adverse relation with other employees or a likelihood that the employee is to resign from the organization within a period of time.

## Claims

### Claim 1

A method comprising:
accessing employee-related data stored in one or more data stores, the employee-related data comprising at least one of emails, surveys, minutes, or records of conversations;
identifying, by a processing device, a subset of the employee-related data that is associated with an employee; and
predicting, by the processing device, based on the subset of the employee-related data associated with the employee, at least one of a likelihood that the employee is engaged in an adverse relation with other employees or a likelihood that the employee is to resign within a period of time.

### Claim 2 (depends on 1)

The method of claim 1, wherein the adverse relation with other employees relates to at least one of an instance of personal conflict, an instance of sexual harassment, or an instance of discrimination.

### Claim 3 (depends on 1)

The method of claim 1, wherein predicting, based on the subset of the employee-related data associated with the employee, at least one of a likelihood that the employee is engaged in an adverse relation with other employees or a likelihood that the employee is to resign within a period of time further comprises:
applying a machine-learning model to the subset of the employee-related data associated with the employee.

### Claim 4 (depends on 3)

The method of claim 3, further comprising training the machine-learning model, wherein the training comprises:
generating, by a training set generator, a historical data input;
generating, by the training set generator, an adverse relation label; and
generating, by the training set generator, an association between the historical data input and the adverse relation label.

### Claim 5 (depends on 3)

The method of claim 3, further comprising training the machine-learning model, wherein the training comprises:
generating, by a training set generator, a historical data input;
identifying, by the training set generator, an occurrence of resignation; and
forming, by the training set generator, an association between the historical data input and the occurrence of resignation.

### Claim 6 (depends on 1)

The method of claim 1, further comprising:
generating, based on the subset of the employee-related data associated with the employee, a plurality of metrics associated with a job satisfaction of the employee;
creating a dashboard displaying the plurality of metrics associated with the job satisfaction of the employee; and
providing the dashboard to a supervisor of the employee.

### Claim 7 (depends on 1)

The method of claim 1, further comprising:
associating a first numerical value with the likelihood that the employee is engaged in an adverse relation with other employees;
associating a second numerical value with the likelihood that the employee is to resign within the period of time; and
notifying a supervisor of the employee in response to determining that the first numerical value or the second numerical value exceeds a predetermined threshold value.

### Claim 8

A system comprising:
a memory; and
a processing device, operatively coupled to the memory, the processing device to
access employee-related data stored in one or more data stores, the employee-related data comprising at least one of emails, surveys, minutes, or records of conversations;
identify, by a processing device, a subset of the employee-related data that is associated with an employee; and
predict, by the processing device, based on the subset of the employee-related data associated with the employee, at least one of a likelihood that the employee is engaged in an adverse relation with other employees or a likelihood that the employee is to resign within a period of time.

### Claim 9 (depends on 8)

The system of claim 8, wherein the adverse relation with other employees relates to at least one of an instance of personal conflict, an instance of sexual harassment, or an instance of discrimination.

### Claim 10 (depends on 8)

The system of claim 8, wherein to predict, based on the subset of the employee-related data associated with the employee, at least one of a likelihood that the employee is engaged in an adverse relation with other employees or a likelihood that the employee is to resign within a period of time further, the processing device is to:
apply a machine-learning model to the subset of the employee-related data associated with the employee.

### Claim 11 (depends on 10)

The system of claim 10, wherein the processing device comprises a training set generator to train the machine-learning model, wherein to train the machine-learning model the training set generator is to:
generate a historical data input;
generate an adverse relation label; and
generate an association between the historical data input and the adverse relation label.

### Claim 12 (depends on 10)

The system of claim 10, wherein the processing device comprises a training set generator to train the machine-learning model, wherein to train the machine-learning model the training set generator is to:
generate a historical data input;
identify an occurrence of resignation; and
form an association between the historical data input and the occurrence of resignation.

### Claim 13 (depends on 8)

The system of claim 8, wherein the processing device is further to:
generate, based on the subset of the employee-related data associated with the employee, a plurality of metrics associated with a job satisfaction of the employee;
create a dashboard displaying the plurality of metrics associated with the job satisfaction of the employee; and
provide the dashboard to a supervisor of the employee.

### Claim 14 (depends on 8)

The system of claim 8, wherein the processing device is further to:
associate a first numerical value with the likelihood that the employee is engaged in an adverse relation with other employees;
associate a second numerical value with the likelihood that the employee is to resign within the period of time; and
notify a supervisor of the employee in response to determining that the first numerical value or the second numerical value exceeds a predetermined threshold value.

### Claim 15

A non-transitory computer-readable storage medium storing instructions which, when executed by a processing device, cause the processing device to:
access employee-related data stored in one or more data stores, the employee-related data comprising at least one of emails, surveys, minutes, or records of conversations;
identify, by a processing device, a subset of the employee-related data that is associated with an employee; and
predict, by the processing device, based on the subset of the employee-related data associated with the employee, at least one of a likelihood that the employee is engaged in an adverse relation with other employees or a likelihood that the employee is to resign within a period of time.

### Claim 16 (depends on 15)

The non-transitory computer-readable storage medium of claim 15, wherein the adverse relation with other employees relates to at least one of an instance of personal conflict, an instance of sexual harassment, or an instance of discrimination.

### Claim 17 (depends on 15)

The non-transitory computer-readable storage medium of claim 15, wherein to predict, based on the subset of the employee-related data associated with the employee, at least one of a likelihood that the employee is engaged in an adverse relation with other employees or a likelihood that the employee is to resign within a period of time further, the instructions further cause the processing device to:
apply a machine-learning model to the subset of the employee-related data associated with the employee.

### Claim 18 (depends on 17)

The non-transitory computer-readable storage medium of claim 17, wherein the instructions further cause the processing device to train the machine-learning model, wherein to train the machine-learning model the instructions are to:
generate a historical data input;
generate an adverse relation label; and
generate an association between the historical data input and the adverse relation label.

### Claim 19 (depends on 17)

The non-transitory computer-readable storage medium of claim 17, wherein the instructions further cause the processing device to train the machine-learning model, wherein to train the machine-learning model the instructions are to:
generate a historical data input;
identify an occurrence of resignation; and
form an association between the historical data input and the occurrence of resignation.

### Claim 20 (depends on 15)

The non-transitory computer-readable storage medium of claim 15, wherein the instructions further cause the processing device to:
associate a first numerical value with the likelihood that the employee is engaged in an adverse relation with other employees;
associate a second numerical value with the likelihood that the employee is to resign within the period of time; and
notify a supervisor of the employee in response to determining that the first numerical value or the second numerical value exceeds a predetermined threshold value.