US 11,113,048 B1Granted

Utilizing artificial intelligence and machine learning models to reverse engineer an application from application artifacts

AssigneeAccenture Global Solutions Limited

InventorsRajendra Prasad Tanniru, Balaji Venkateswaran, Alok Jain, Koushik M Vijayaraghavan, Aditi Kulkarni, Rajesh Nagarajan, Niyaz Shaffi Hameed Musthafa, Srinivasan Kootalai Sundaram, Roopalaxmi Manjunath, Jayashri Sridevi

Life of this patent

Estimating the term…

patentgrep

Loading patent…

Abstract

A device may receive input data identifying user stories, test case documents, event logs, and application logs associated with an application, and may perform natural language processing on the user stories and the test case documents, identified in the input data, to generate a first state diagram associated with the application. The device may process the event logs identified in the input data, with a heuristic miner model, to generate a second state diagram associated with the application, and may process the application logs identified in the input data, with a clustering model, to generate a volumetric analysis associated with the application. The device may perform post processing of the first state diagram, the second state diagram, and the volumetric analysis, to remove duplicate data and unmeaningful data and to generate modified outputs, and may perform actions based on the modified outputs.

Claims20

Dependent claims

A method, comprising:

receiving, by a device, input data identifying user stories, test case documents, event logs, and application logs associated with an application;
processing, by the device, the input data, with a machine learning model, to determine application change data and application overview data associated with the application;
performing, by the device using a natural language tool kit, natural language processing on the user stories and the test case documents, identified in the input data, to generate a first state diagram associated with the application;
processing, by the device, the event logs identified in the input data, with a heuristic miner model, to generate a second state diagram associated with the application;
processing, by the device, the application logs identified in the input data, with a clustering model, to generate a volumetric analysis associated with the application;
performing, by the device and using the natural language tool kit, post processing of the first state diagram, the second state diagram, the volumetric analysis, the application change data, and the application overview data, to remove duplicate data and unmeaningful data and to generate modified outputs,
wherein the modified outputs include one or more of:
a modified first state diagram,
a modified second state diagram,
a modified volumetric analysis,
modified application change data, or
modified application overview data;
and
performing, by the device, one or more actions based on the modified outputs,
wherein the one or more actions includes modifying the application.

12 more elements

A device, comprising:

one or more memories;
and
one or more processors, coupled to the one or more memories, configured to:
receive input data identifying user stories, test case documents, event logs, and application logs associated with an application;
perform, using a natural language tool kit, natural language processing on the user stories and the test case documents, identified in the input data, to generate a first state diagram associated with the application;
process the event logs identified in the input data, with a heuristic miner model, to generate a second state diagram associated with the application;
process the application logs identified in the input data, with a clustering model, to generate a volumetric analysis associated with the application;
perform post processing, using the natural language tool kit, of the first state diagram, the second state diagram, and the volumetric analysis, to remove duplicate data and unmeaningful data and to generate modified outputs,
wherein the modified outputs include one or more of:
a modified first state diagram,
a modified second state diagram, or
a modified volumetric analysis;
and
perform one or more actions based on the modified outputs,
wherein the one or more actions includes modifying the application.

12 more elements

A non-transitory computer-readable medium storing instructions, the instructions comprising:

one or more instructions that, when executed by one or more processors, cause the one or more processors to:
receive input data identifying user stories, test case documents, event logs, and application logs associated with an application;
process the input data, with a machine learning model, to determine application change data and application overview data associated with the application;
perform, using a natural language tool kit, natural language processing on the user stories and the test case documents, identified in the input data, to generate a first state diagram associated with the application;
process the event logs identified in the input data, with a heuristic miner model, to generate a second state diagram associated with the application;
process the application logs identified in the input data, with a clustering model, to generate a volumetric analysis associated with the application;
perform post processing using the natural language tool kit of the first state diagram, the second state diagram, the volumetric analysis, the application change data, and the application overview data, to remove duplicate data and unmeaningful data and to generate modified outputs,
wherein the modified outputs include one or more of:
a modified first state diagram,
a modified second state diagram,
a modified volumetric analysis,
modified application change data, or
modified application overview data;
provide, for display, one or more of the modified first state diagram, the modified second state diagram, the modified volumetric analysis, the modified application change data, or the modified application overview data;
and
modify the application based on the modified outputs.

13 more elements

Dependencies are inferred from the claim text.