MUMBAI, India, May 1 -- Intellectual Property India has published a patent application (202641051862 A) filed by Abhilash Pakalapati; Madhukar Dongala; Sai Charan Obuladinne; Sathish Kuppan Pandurangan; and Vigneshwarr Venkatesan, Herndon, U.S.A., on April 23, for 'ai-driven autonomous data quality and governance platform for real-time enterprise data pipelines.'
Inventor(s) include Abhilash Pakalapati; Madhukar Dongala; Sai Charan Obuladinne; Sathish Kuppan Pandurangan; and Vigneshwarr Venkatesan.
The application for the patent was published on May 1, under issue no. 18/2026.
According to the abstract released by the Intellectual Property India: "The disclosed invention is an intelligent, autonomous AI (artificial intelligence) platform that provides real-time data quality and governance management for enterprise data pipelines through the use of machine learning model integration, adaptive rule generation techniques, and automated self-healing mechanisms to ensure data validation, monitoring, and correction is continuously achieved across heterogeneous and high-velocity data environments. The platform ingests streaming data from multiple distributed sources, profiles data in real time to understand its characteristics and detects anomalies in the data using both predictive and reactive analysis models. Unlike traditional rule-based systems, this invention generates, modifies and/or updates validation rules for the data dynamically, based upon the patterns associated with the data, thereby improving the accuracy of the data and minimizing false positives. The platform's self-healing capabilities allow it to automatically detect, classify and remediate data anomalies through the use of intelligent remediation strategies such as data imputation, normalization, transformation, and reprocessing. The platform also features a comprehensive governance framework that enforces policy compliance as well as tracking data lineage and supporting auditability across the data lifecycle. The platform's continuous feedback learning loop allows the platform to learn from historical data corrections and user interactions to improve the performance of its underlying machine-learning models over time. As a result, the invention represents a resilient, scalable, and adaptable solution for maintaining high levels of data integrity, reliability, and regulatory compliance in today's distributed enterprise environments."
Disclaimer: Curated by HT Syndication.
