Anomaly Detection Framework Predicting Auto-Resolution

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional anomaly detection systems generate unnecessary support requests and cases when anomalies automatically resolve, leading to increased support costs and inefficiencies, as they lack the ability to predict self-correction of device issues.

Innovation Solution

The implementation of a machine learning-based intelligent adaptive anomaly detection framework that collects and analyzes operational data to predict the probability of automatic resolution for anomalous events, using client and enterprise device management components to determine if an event has been automatically resolved and notify relevant systems accordingly.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If anomaly detection systems generate support requests for all detected anomalies, then anomaly detection completeness is improved, but support cost increases due to unnecessary requests for automatically resolving anomalies

Engineering Contradiction:

Improveanomaly detection completenessVSAvoidsupport cost

Core Design Contradiction:

ReliabilityVSLoss of energy

Solution Approach 1:

The system performs preliminary analysis of operational data patterns before generating support requests. Machine learning models predict whether an anomaly will automatically resolve, and only requests for non-auto-resolving anomalies are generated, preventing unnecessary support costs while maintaining detection completeness

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

A machine learning-based prediction layer is introduced as an intermediary between anomaly detection and support request generation. This intermediary analyzes operational data patterns and predicts auto-resolution probability, filtering out anomalies that will self-resolve before creating support requests

Inventive Principle:

Principle #24Intermediary (Mediator)

2Productivity

If machine learning models analyze operational data to predict automatic resolution, then unnecessary support requests are reduced, but data processing complexity increases

Engineering Contradiction:

Improvesupport request efficiencyVSAvoiddata processing complexity

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The machine learning models serve multiple functions: they analyze operational data for anomaly detection, predict automatic resolution probability, and inform support request generation decisions. This multi-functionality consolidates what could be separate systems into a unified approach, managing complexity through versatility

Inventive Principle:

Principle #6Universality (Multi-functionality)

Solution Approach 2:

The system transforms operational data into predictive probability parameters that indicate auto-resolution likelihood. By changing the parameter representation from raw operational data to predicted resolution probability, the system simplifies the decision-making process for support request generation

Inventive Principle:

Principle #35Parameter changes

Data Source

PatentUS11544138B2Framework for anomaly detection and resolution prediction

Publication Date: 2023.01.03 DELL PROD LP

AI summary

A method comprises collecting operational data for one or more devices and identifying one or more anomalies associated with the one or more devices based at least in part on the collected operational data. At least a portion of the collected operational data corresponding to the identified one or more anomalies is analyzed, and a probability of automatic resolution for respective ones of the identified one or more anomalies is determined based at least in part on the analysis. The identifying, the analyzing and the determining are performed using one or more machine learning models.