Data processing for role assessment and course recommendation

Patent metadata

Field	Value
Publication number	US-10885477-B2
Application number	US-201816042719-A
Country	US
Kind code	B2
Filing date	Jul 23, 2018
Priority date	Jul 23, 2018
Publication date	Jan 5, 2021
Grant date	Jan 5, 2021

Abstract

A device receives a command to identify an automation evaluation for a role, determines tasks of the role based on data relating to the role, and determines activities for the tasks based on the data relating to the role. The device determines one or more automation scores, which correspond to a suitability for automation of the activities, based on a set of characteristics of the activities and based on the data relating to the role. The automation scores are determined using a machine learning model to parse natural language descriptions of the activities and score parsed portions of the natural language descriptions. The device generates, for the role, an aggregate automation score based on the automation scores, determines the automation evaluation for the role based on the aggregate automation score and characteristics of an entity associated with the role, and performs an action relating to the automation evaluation.

First claim

What is claimed is:

1. A device, comprising:
one or more memories; and
one or more processors, communicatively coupled to the one or more memories, to:
receive a command to identify an automation evaluation for a role;
provide a user interface element to receive a natural language description of the role;
parse, using a machine learning model, the natural language description to determine one or more tasks of the role;
parse, using the machine learning model, the natural language description to determine one or more activities for the one or more tasks of the role;
train a model of activity automatability using an artificial neural network processing technique to perform pattern recognition with regard to patterns of whether the one or more activities, described using different semantic descriptions, are automatable and whether the one or more tasks of the role will be automated;
determine, using the model of activity automatability, one or more automation scores for the one or more activities, which correspond to a suitability for automation of the one or more activities, based on entity characteristic data of an entity associated with the role, data relating to the role, and organization data,
wherein the entity characteristic data includes one or more of:
information associated with one or more skills of the entity,
information associated with a level of experience of the entity,
information associated with a set of entity evaluations, or
information associated with a set of entity preferences;

generate, for the role, an aggregate automation score based on the one or more automation scores for the one or more activities;
set a first threshold, associated with the entity, for determining that the role is likely to be automated based on the aggregate automation score,
wherein the first threshold is associated with whether the entity repeats a client facing activity with a threshold frequency;

set a second threshold, associated with another entity, for determining that the role is likely to be automated based on the aggregate automation score,
wherein the second threshold is associated with whether the other entity repeats a client facing activity that does not meet the threshold frequency;

determine the automation evaluation for the role based on the aggregate automation score, the first threshold, and the entity characteristic data,
wherein the entity is prioritized for enrollment in a training course based on the aggregate automation score, and
wherein the other entity is not prioritized for enrollment in the training course based on another aggregate automation score of the other entity,
wherein the other aggregate automation score is less than the aggregate automation score;

search, based on the automation evaluation indicating a likelihood of the role being automated, an internet for the training course associated with a recommended skill,
wherein the training course is determined based on the entity characteristic data and data associated with one or more similar entities;

receive, from the internet and based on searching the internet, the training course,
the training course being a video-based course or an audio-based course,

perform an allocation of resources of a content delivery network (CDN) to distribute the training course to one or more user devices;
generate, based on receiving the training course, a user interface for providing the training course; and
provide, via the user interface and utilizing the resources of the CDN, the training course to the one or more user devices.

2. The device of claim 1 , wherein the one or more processors are further to:
determine, based on the automation evaluation and a skills model, the one or more skills of the entity,
the one or more skills including the recommended skill;

determine one or more courses relating to the one or more skills,
the one or more courses including the training course; and

provide information identifying the one or more skills and the one or more courses.

3. The device of claim 1 , wherein the one or more processors are further to:
perform, based on the automation evaluation, at least one of:
an automated training enrollment action,
an automated training scheduling action,
an automated role reassignment action,
an automated job application action,
an automated job posting action, or
an automated job searching and reporting action.

4. The device of claim 1 , wherein the one or more processors are further to:
generate a prediction of a timeline for automation of the role based on the aggregate automation score; and
provide information identifying the timeline for automation of the role.

5. The device of claim 1 , wherein the one or more processors are further to:
provide the user interface; and
receive, based on detecting one or more interactions with the user interface, information identifying the entity characteristic data.

6. The device of claim 1 , wherein the one or more processors are further to:
generate a set of user interface elements to enable a communication channel for the entity and a manager entity for the entity.

7. The device of claim 1 , wherein the one or more processors are further to:
selectively assign the role to the entity or for automation based on the automation evaluation.

8. The device of claim 1 , wherein the one or more processors are further to:
automatically assign the one or more tasks of the role for automated completion based on the automation evaluation.

9. The device of claim 1 , wherein the entity characteristic data further includes one or more of:
information associated with one or more timesheets associated with the entity, or
information associated with computer usage associated with the entity.

10. A method, comprising:
providing, by a device, a user interface element to receive a natural language description of a role;
parsing, by the device and using a machine learning model, the natural language description to determine a set of tasks of the role;
parsing, by the device and using the machine learning model, the natural language description to determine a set of activities for the set of tasks;
training, by the device, a model of activity automatability using an artificial neural network processing technique to perform pattern recognition with regard to patterns of whether the set of activities, described using different semantic descriptions, are automatable and whether the set of tasks will be automated;
determining, by the device and using the model of activity automatability, a set of automation scores for the set of activities,
an automation score, of the set of automation scores, representing an automation potential predicted for a task of the set of tasks, and
the set of automation scores being determined based on entity characteristic data of an entity associated with the role, data relating to the role, and organization data,
wherein the entity characteristic data includes one or more of:
information associated with one or more skills of the entity,
information associated with a level of experience of the entity,
information associated with a set of entity evaluations, or
information associated with a set of entity preferences;

determining, by the device, an aggregate automation score for the role based on the set of automation scores,
wherein the role is defined by the set of tasks, and
wherein each task, of the set of tasks, includes at least one activity of the set of activities;

setting, by the device, a first threshold, associated with the entity, for determining that the role is likely to be automated based on the aggregate automation score,
wherein the first thres

Assignees

• Accenture Global Solutions Ltd

Inventors

• Ghosh Bhaskar
• Nr Srikanth
• Prasad Rajendra T
• Mallapur Shankaranand
• Damle Sarvesh Madhusudan
• Bhadre Prashant
• Rajaram Anandakrishnan
• SEKHAR Mohan

Classifications

• G06N3/09

  Supervised learning · CPC title

• G06N3/0499

  Feedforward networks · CPC title

• G06N20/10

  using kernel methods, e.g. support vector machines [SVM] · CPC title

• G06N3/08

  Learning methods · CPC title

• G06N20/00

  Machine learning · CPC title