MUMBAI, India, Oct. 26 -- Intellectual Property India has published a patent application (202641122802 A) filed by Pamula Udayaraju; Suseelkousic Gogineni; Vijayasai Madamanchi; Venkata Makineni; Boddu L V Siva Rama Krishna; M. Sitharam; Gaddala Punnam Chander; and V. Dilip Kumar on October 14, 2026, for An Ai-Driven Self-Healing Data Engineering System For Autonomous Detection, Explanation, And Restoration Of Data Trust.
Inventors include Pamula Udayaraju; Suseelkousic Gogineni; Vijayasai Madamanchi; Venkata Makineni; Boddu L V Siva Rama Krishna; M. Sitharam; Gaddala Punnam Chander; and V. Dilip Kumar.
The application for the patent was published on October 23, 2026, under issue no. 43/2026.
Abstract: The rapid growth of data-driven applications has increased the need for reliable, accurate, and trustworthy data. However, modern data engineering pipelines frequently suffer from data quality issues such as missing values, duplicates, schema changes, inconsistencies, anomalies, and pipeline failures. Detecting and resolving these problems manually is time-consuming and may lead to incorrect decisions. This paper proposes an AI-Driven Self-Healing Data Engineering System that autonomously detects, explains, and restores data trust across data pipelines. The proposed system integrates Artificial Intelligence (AI), Machine Learning (ML), anomaly detection, data quality monitoring, root-cause analysis, and automated data remediation to continuously monitor data and pipeline behavior. When an issue is detected, the system identifies the affected data, analyzes the probable root cause, explains the detected problem in an understandable manner, and automatically selects an appropriate recovery strategy. Self-healing mechanisms can perform actions such as correcting data inconsistencies, handling missing or duplicate records, adapting to schema changes, restoring failed pipeline components, and validating the repaired data. A continuous feedback mechanism enables the system to learn from previous incidents and improve future detection and recovery decisions. The proposed approach aims to reduce manual intervention, improve data reliability, minimize pipeline downtime, and establish continuous data trust in modern data engineering environments. This system can be applied to cloud-based analytics platforms, enterprise data warehouses, real-time data pipelines, and AI/ML data infrastructures.
Disclaimer: Curated by HT Syndication.
