US 12,073,297 B2
System performance optimization
Kamal Bablani, Winnersh (GB); Jayanthi Mohanram, Bangalore (IN); Deepika Bhaskar, Bangalore (IN); Abhishek Sharma, Delhi (IN); Baljit Malhotra, Gurgaon (IN); Ankit Khurana, Delhi (IN); Priyanka Niranjan, Jhansi (IN); Supriya Sahoo, Rourkela (IN); and Ragavendran Ramesh, Harur (IN)
Assigned to ACCENTURE GLOBAL SOLUTIONS LIMITED, Dublin (IE)
Filed by ACCENTURE GLOBAL SOLUTIONS LIMITED, Dublin (IE)
Filed on Dec. 29, 2020, as Appl. No. 17/136,925.
Prior Publication US 2022/0207414 A1, Jun. 30, 2022
Int. Cl. G06N 20/00 (2019.01); G06F 8/77 (2018.01); G06F 18/21 (2023.01); G06F 18/214 (2023.01)
CPC G06N 20/00 (2019.01) [G06F 8/77 (2013.01); G06F 18/214 (2023.01); G06F 18/217 (2023.01)] 18 Claims
OG exemplary drawing
 
1. A system comprising:
a processor;
a data extractor coupled to the processor, the data extractor to:
scan multiple predefined levels of a software solution to extract corresponding metadata information from each of the multiple predefined levels, the multiple predefined levels comprising an inventory level, a code level, an application level, an automation level, and a data archiving level;
a data lake coupled to the processor, the data lake to:
store the extracted corresponding metadata information, the metadata information pertaining to one or more of standard parameters associated with performance of the software solution;
a data analyzer coupled to the processor, the data analyzer to:
determine a standard score based on a plurality of attributes of the extracted corresponding metadata information, the plurality of attributes pertaining to weight, severity and violation count of each of the one or more of standard parameters;
optimize the determined standard score based on training data received from a learning model, the training data pertaining to pre-determined rule violations and the determined standard score; and
generate an insight information comprising information related to determined rule violations and one or more of evaluation steps involved in determining the determined standard score, wherein the data analyzer comprises a predictive engine, and the predictive engine is to:
optimize and train the determined standard score and the one or more of standard parameters based on the training data received from the learning model, wherein the learning model is an Artificial Intelligent (AI)-based reinforcement learning (RL) model, wherein the AI-based RL model is to generate AI-driven predictions and interactive user interface dashboards, and wherein the AI-driven predictions comprise AI-driven predictive recommendations on software solutions benchmark improvements, and the interactive user interface dashboards comprise an interactive user interface allowing users to simulate an appropriate software solution benchmark by changing rules, violations and corrections suggested by the AI-driven predictive recommendations.