Machine Learning Configuration Analysis for Automated Storage Issue Resolution

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional storage management techniques are unable to effectively analyze and understand user actions in resolving storage capacity issues, relying on error-prone and resource-intensive ad hoc methods.

Innovation Solution

The use of machine learning techniques to automatically generate conditional instructions by processing configuration data, identifying relevant changes, and grouping them using hashing algorithms to connect issue and resolution phases, thereby generating automated resolution actions.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If conventional storage management techniques use ad hoc methods based on human observation to resolve storage capacity issues, then the system can address storage capacity problems, but the process becomes error-prone and resource-intensive

Engineering Contradiction:

Improveaccuracy of issue resolutionVSAvoidcomplexity of resolution process

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The system automatically analyzes configuration data, identifies relevant changes, and generates resolution instructions without human intervention. The machine learning model processes historical configuration data to autonomously determine resolution steps, eliminating the need for human operators to manually analyze and resolve storage capacity issues.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The patent replaces manual human observation and ad hoc resolution methods with an automated machine learning-based system. The mechanical process of human analysis is substituted with computational algorithms that process configuration data, identify patterns, and generate resolution instructions automatically.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Productivity

If conventional storage management techniques rely on manual analysis of configuration data, then the system can identify resolution steps, but the process becomes resource-intensive and time-consuming

Engineering Contradiction:

Improvespeed of issue resolutionVSAvoidtime for analysis and resolution

Core Design Contradiction:

ProductivityVSLoss of time

Solution Approach 1:

The system pre-processes and stores historical configuration data in a structured format, preparing it for rapid analysis. By organizing configuration data ahead of time with clear temporal markers (pre-issue and post-issue states), the system enables quick retrieval and comparison when issues occur, reducing resolution time.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system creates copies of configuration data at different time points (before and after issue resolution) and compares these copies to identify relevant changes. This copying approach allows rapid analysis without modifying the original data, enabling fast resolution while preserving data integrity.

Inventive Principle:

Principle #26Copying

3Measurement precision

If the system includes all configuration changes in the dataset, then the data is comprehensive, but irrelevant changes increase noise and reduce analysis accuracy

Engineering Contradiction:

Improveprecision of relevant change identificationVSAvoidvolume of configuration data

Core Design Contradiction:

Measurement precisionVSQuantity of substance

Solution Approach 1:

The machine learning model extracts and identifies only the relevant configuration changes from the complete dataset by comparing pre-issue and post-issue configuration states. The system filters out irrelevant changes and focuses analysis on the specific modifications that resolved the storage capacity issue, improving precision by eliminating noise.

Inventive Principle:

Principle #2Taking out (Extraction)

Solution Approach 2:

The configuration data is segmented into distinct time-based segments (before issue onset and after issue resolution). By dividing the comprehensive dataset into these temporal segments, the system can precisely identify changes that occurred during the resolution period, separating relevant from irrelevant modifications.

Inventive Principle:

Principle #1Segmentation

Data Source

PatentUS20220207388A1Automatically generating conditional instructions for resolving predicted system issues using machine learning techniques

Publication Date: 2022.06.30 DELL PROD LP

AI summary

Methods, apparatus, and processor-readable storage media for automatically generating conditional instructions for resolving predicted system issues using machine learning techniques are provided herein. An example computer-implemented method includes obtaining a dataset comprising configuration data for a system; identifying portions the configuration data associated with configuration changes unrelated to the resolution of the at least one system issue by processing the dataset using machine learning-based feature selection techniques; creating an updated dataset by filtering the identified portions from the dataset; grouping the configuration data within the updated dataset into two or more groups using hashing algorithms and similarity metrics; generating a hash model based on the groups of the configuration data; generating, using the hash models, a set of conditional instructions for resolving one or more predicted system issues; and performing at least one automated action based on the set of conditional instructions.