Automated process analysis and automation implementation

Patent metadata

Field	Value
Publication number	US-10831448-B2
Application number	US-201916376693-A
Country	US
Kind code	B2
Filing date	Apr 5, 2019
Priority date	Aug 30, 2018
Publication date	Nov 10, 2020
Grant date	Nov 10, 2020

Abstract

A device may obtain process data relating to a set of processes. The device may process the process data to generate a process analysis model. The device may classify, using the process analysis model, a particular process into a particular class of a set of classes of the process analysis model. The device may automatically assess the particular process based on the particular class, wherein a set of assessment parameters for assessing the particular process is selected based on the particular class, and wherein an assessment score is assigned to the particular process based on values for the set of assessment parameters. The device may determine, based on the assessment score and the particular class, an automation recommendation for the particular process. The device may automatically complete the particular process using a particular tool based on determining the automation recommendation.

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:
obtain process data relating to a set of processes;
process the process data to generate a process analysis model;
classify, using the process analysis model, a particular process into a particular class of a set of classes of the process analysis model;
provide, to a user device and based on classifying the particular process, a process assessment user interface,
the process assessment user interface including a set of automatically generated questionnaire questions for the particular process and one or more of:
a scope of the particular process,
a set of areas of the particular process, or
automatically determined responses for the particular process;

receive a set of responses from a user regarding a questionnaire question of the set of automatically generated questionnaire questions;
automatically assess the particular process based on the particular class,
wherein a set of assessment parameters for assessing the particular process is selected based on the particular class, and
wherein an assessment score is assigned to the particular process based on values for the set of assessment parameters,
wherein the values for the set of assessment parameters are determined based on the set of responses;

generate, based on the process analysis model and the values for the set of assessment parameters, an automation maturity score representing a level of task automation weighted based on the set of responses,
wherein the assessment score is based on the automation maturity score;

determine, based on the assessment score and the particular class, an automation recommendation for the particular process,
wherein the automation recommendation requires a particular tool, of a set of tools, for completing the particular process, and
wherein the automation recommendation is displayed via the process assessment user interface;

generate a set of tool scores for the set of tools,
wherein each tool score, of the set of tool scores, represents a suitability of each tool for completing the particular process;

select the particular tool for completing the particular process based on the set of tool scores in comparison to the automation recommendation; and
automatically complete the particular process using the particular tool based on determining the automation recommendation.

2. The device of claim 1 , wherein the one or more processors, when determining the automation recommendation, are to:
process, using a natural language processing technique, a set of tool descriptions of the set of tools; and
select the particular tool for completing the particular process based on processing the set of tool descriptions, a process description for the particular process, and a class description for the particular class.

3. The device of claim 1 , wherein the one or more processors, when determining the automation recommendation, are to:
select the particular tool for completing the particular process based on a deep neural network model of process automation.

4. The device of claim 1 , wherein the one or more processors, when determining the automation recommendation, are to:
select the particular tool for completing the particular process based on a collaborative filtering technique applied to the set of tools.

5. The device of claim 1 , wherein the one or more processors, when determining the automation recommendation, are to:
select the particular tool for completing the particular process based on a content-based filtering technique applied to the set of tools.

6. The device of claim 1 , wherein the one or more processors are further to:
use the set of responses to determine whether a particular project is complying with the particular process.

7. A method, comprising:
obtaining, by a device, process data relating to a set of processes;
processing, by the device, the process data to generate a process analysis model;
providing, by the device, to a user device, and based on classifying a particular process using the process analysis model, a process assessment user interface,
the process assessment user interface including a set of automatically generated questionnaire questions for the particular process and one or more of:
a scope of the particular process,
a set of areas of the particular process, or
automatically determined responses for the particular process;

receiving, by the device, a set of responses from a user regarding a questionnaire question of the set of automatically generated questionnaire questions;
determining, by the device and based on the process analysis model, an automation recommendation for the particular process,
wherein a set of assessment parameters for assessing the particular process is selected based on a particular class of the particular process determined based on the process analysis model,
wherein an assessment score is assigned to the particular process based on values for the set of assessment parameters,
wherein the values for the set of assessment parameters are determined based on the set of responses,
wherein the automation recommendation requires a particular tool, of a set of tools, for completing the particular process selected based on the assessment score, and
wherein the automation recommendation is displayed via the process assessment user interface; and

generating, by the device and based on the process analysis model and the values for the set of assessment parameters, an automation maturity score representing a level of task automation weighted based on the set of responses,
wherein the assessment score is based on the automation maturity score;

generating, by the device, a set of tool scores for the set of tools,
wherein each tool score, of the set of tool scores, represents a suitability of each tool for completing the particular process;

selecting, by the device, the particular tool for completing the particular process based on the set of tool scores in comparison to the automation recommendation; and
automatically completing, by the device, the particular process using the particular tool based on determining the automation recommendation.

8. The method of claim 7 , where processing the process data comprises:
parsing a set of questionnaire response documents associated with the set of responses to determine the process analysis model.

9. The method of claim 7 , where processing the process data comprises:
applying a set of weights to the set of assessment parameters based on the process analysis model.

10. The method of claim 7 , where processing the process data comprises:
determining the set of assessment parameters based on a set of sub-process areas determined for the particular process based on the process analysis model.

11. The method of claim 7 , where determining the automation recommendation comprises:
determining that the particular tool can be applied to one or more tasks of the particular process based on the process analysis model without changes to the particular tool.

12. The method of claim 7 , where determining the automation recommendation comprises:
determining that the particular tool can be applied to one or more tasks of the particular process based on the process analysis model with less than a threshold level of changes to the particular tool; and
altering the particular tool to adapt the particular tool to the one or more tasks of the particular process.

13. The method of claim 7 , where determining the automation recommendation comprises:
determ

Assignees

• Accenture Global Solutions Ltd

Inventors

• Prasad Rajendra T
• Ghosh Bhaskar
• SEKHAR Mohan
• Athreyee Priya
• Jana Koustuv
• Vijayaraghavan KOUSHIK
• Swain Amaresh
• Senapati Pradeep
• Girish Kamakshi
• Narasimhan Lakshmi
• Roy Somen
• Nagarajan Rajesh
• Jeyachandran Senthil
• Dharmar Arulmozhi

Classifications

• G06N7/01

  Probabilistic graphical models, e.g. probabilistic networks · CPC title

• G06F40/40

  Processing or translation of natural language (natural language analysis G06F40/20; semantic analysis G06F40/30) · CPC title

• G06N5/02

  Knowledge representation; Symbolic representation · CPC title

• G06N20/10

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

• G06N20/00

  Machine learning · CPC title