Cloud Service Error Signal Anomaly Detection

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Manual installation and configuration of dispersed computing resources in cloud computing environments are not cost-effective, and existing solutions lack efficient anomaly detection in error signals for cloud-based services.

Innovation Solution

An analysis application uses a machine learning algorithm to identify and filter periodic patterns from error signals, detect anomalies, and update itself with new data to improve pattern recognition and anomaly detection in cloud-based services.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If manual installation and configuration support is provided to cloud computing assets, then installation and configuration support is available, but it is not cost effective

Engineering Contradiction:

Improveinstallation and configuration supportVSAvoidcost effectiveness

Core Design Contradiction:

Ease of operationVSProductivity

Solution Approach 1:

The system enables self-service through automated anomaly detection and classification. Error signals are automatically processed by machine learning models that identify patterns and classify anomalies without human intervention, allowing the cloud computing system to self-diagnose and self-monitor, eliminating the need for costly manual technical support while maintaining operational effectiveness

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

Manual mechanical processes of technical support are replaced with automated electronic systems. The patent implements automated error signal processing, pattern recognition algorithms, and machine learning-based anomaly classification that substitute human technicians with computational systems, achieving both cost reduction and maintained support quality

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Reliability

If existing solutions are used for anomaly detection, then some detection capability is provided, but efficient anomaly detection in error signals is lacking

Engineering Contradiction:

Improveanomaly detection capabilityVSAvoiddetection efficiency

Core Design Contradiction:

ReliabilityVSProductivity

Solution Approach 1:

The system transforms error signal parameters by converting raw error data into classified anomaly categories. Machine learning models process error signals and transform them into meaningful anomaly classifications, changing the parameter representation from raw error counts to structured anomaly types that enable more efficient and reliable detection

Inventive Principle:

Principle #35Parameter changes

Solution Approach 2:

Machine learning models serve as intermediaries between raw error signals and anomaly detection outcomes. The patent introduces pattern recognition algorithms that mediate between incoming error data and final anomaly classifications, enabling efficient processing by translating complex error patterns into interpretable anomaly categories that improve both reliability and detection speed

Inventive Principle:

Principle #24Intermediary (Mediator)

Data Source

PatentUS9378079B2Detection of anomalies in error signals of cloud based service

Publication Date: 2016.06.28 MICROSOFT TECHNOLOGY LICENSING LLC

AI summary

Anomalies detection in error signals of a cloud based service is provided. An application such as an analysis application identifies a machine learning algorithm that matches error signals of components of a cloud based service. A periodic pattern from the error signals is removed with the machine learning algorithm to filter the periodic pattern from an error count in the error signals. The error signals are processed with the machine learning algorithm to detect one or more anomalies with the components. The machine learning algorithm is updated while processing new data to detect new patterns.