ML-Based Data Backup Strategy for Enterprise Applications

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current data backup systems lack automation and efficiency in managing increasing data volumes and complexities, requiring more advanced methods to determine data protection and recovery options for enterprise applications.

Innovation Solution

The use of machine learning models to identify static and runtime metadata for computing applications, determining application criticality and generating data backup options based on these analyses, enabling automated and optimized data protection and recovery processes.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Extent of automation

If traditional manual data backup management methods are used, then human control and decision-making are maintained, but automation and efficiency are insufficient to manage increasing data volumes and complexities

Engineering Contradiction:

Improveautomation of data backup managementVSAvoidefficiency in managing data volumes

Core Design Contradiction:

Extent of automationVSProductivity

Solution Approach 1:

The system enables self-service through machine learning models that automatically analyze application metadata, determine criticality levels, and generate backup recommendations without human intervention. The ML models autonomously process runtime and static metadata to classify applications and create protection strategies, allowing the system to serve itself in managing backup operations.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

Manual mechanical processes of data backup management are replaced with intelligent machine learning systems. The patent substitutes human decision-making mechanisms with ML models that process metadata, evaluate application criticality, and generate backup recommendations, transforming manual operations into automated intelligent processes.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Reliability

If more data is stored for longer periods to meet competition and growth requirements, then data availability and company dependence on data increase, but data protection complexity and resource requirements increase

Engineering Contradiction:

Improvedata availabilityVSAvoiddata protection complexity

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The system applies local quality by differentiating backup strategies based on individual application criticality levels. Instead of uniform backup approaches, the ML models analyze specific application metadata and runtime characteristics to assign appropriate protection levels, creating tailored backup recommendations for each application based on its unique requirements and importance to the organization.

Inventive Principle:

Principle #3Local quality

Solution Approach 2:

The system changes parameters dynamically by adjusting backup strategies based on application criticality assessments. The ML models evaluate multiple parameters including runtime metadata, static metadata, and business importance to determine appropriate protection levels, retention periods, and resource allocation, transforming fixed backup policies into adaptive parameter-based strategies.

Inventive Principle:

Principle #35Parameter changes

Data Source

PatentUS11567835B2Data protection and recovery

Publication Date: 2023.01.31 KYNDRYL INC

AI summary

Generating a data protection and recovery data backup option by identifying static and runtime metadata for a computing application, determining application criticality of the computing application according to the static metadata using a first machine learning model, determining a data backup option for the computing application according to application criticality and the runtime metadata, using a second machine learning model.