Bank of America Corporation

Srinath Chakinam

Kalyan Chakravarthy Pallapolu

Bharathi Tadepalli

Praveen Kumar Bolla

Ambica Poola

Trishul Vuppalanchi

Artificial Intelligence/Machine Learning-based performance monitoring of database applications to identify performance issues/bottlenecks that may lead to application failure. In response to identifying the performance issues, AI/ML-based analysis of the database is performed to determine the root cause of the performance issues and resolutions for addressing/overcoming the probable causes. As a result, a comprehensive system that capable of monitoring and determining database related performance issues within database application and capable of determining and implementing the resolution to such performance issues. In addition, an auto-correction feature for errors that may occur during the monitoring of the database applications and related analysis.

System for resolving heterogenous database-level application failures

Apparatus and methods for an intelligent audit engine are provided. Product development artifacts may be associated with artifact tags and stored in an artifact repository. The audit engine may retrieve an artifact for audit. The audit engine may identify a set of development guidelines in a rule repository based on their artifact tags. The audit engine may determine whether the development guidelines have been satisfied based on stored product testing data. A failed development guideline may initiate a workflow that includes notification of a project stakeholder regarding the failure. The notification may include remediation measures to be taken by the stakeholder. The validation process may iterate until all guidelines have passed validation. A machine-learning algorithm may prioritize a development guideline for future audits to increase efficiency. The machine learning algorithm may educate stakeholders to reduce audit failures.

Growing community of inventors

Hyderabad Telangana, India

Srinath Chakinam