Automated Service Health Scoring via Machine-Learned Deviation Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for monitoring the health of computer-based services rely on manual curation and interpretation of metrics by subject matter experts, which is time-consuming and prone to biases, especially when dealing with numerous metrics from diverse sources.
Innovation Solution
A computer-implemented method that automatically evaluates the health of services by computing deviation values based on machine-learned expected variations and performing classification operations using machine-learned criteria to generate anomaly indicators and overall health scores.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If manual curation and interpretation of metrics by subject matter experts is used, then the health evaluation can be performed with human expertise and context understanding, but the process becomes time-consuming and prone to subjective biases
Solution Approach 1:
The system performs self-service by automatically curating metrics, generating dashboards, and evaluating service health without requiring human subject matter experts. The machine learning model independently selects relevant metrics, determines their relationships, and computes health scores, eliminating the time-consuming manual process while maintaining evaluation reliability through algorithmic objectivity
Solution Approach 2:
The patent replaces the mechanical human expert system with an automated machine learning-based system. Instead of relying on human cognition and manual analysis, the system uses algorithms to curate metrics, build dashboards, and evaluate health, thereby reducing evaluation time while preserving reliability through consistent, bias-free automated decision-making
2Measurement precision
If manual curation and interpretation of metrics by subject matter experts is used, then the evaluation can be performed with domain knowledge, but the process becomes tedious and quite time-consuming when dealing with hundreds of metrics
Solution Approach 1:
The system autonomously performs metric curation and dashboard generation without human intervention. The machine learning model automatically selects relevant metrics from hundreds of available options, determines their relationships, and constructs appropriate dashboards, thereby maintaining measurement precision through expert-level analysis while dramatically improving productivity by eliminating manual tedious work
Solution Approach 2:
The system changes the operational parameters from manual human analysis to automated machine learning processing. This parameter change enables the system to handle hundreds of metrics efficiently by using algorithms to filter, select, and analyze metric data, maintaining accuracy through sophisticated computational methods while achieving high productivity through automation
3Reliability
If subject matter experts curate and interpret metrics, then the evaluation reflects human expertise, but it reflects the innate biases of the SME rather than objective data analysis
Solution Approach 1:
The patent replaces the human expert system with an automated machine learning system that eliminates subjective biases. The machine learning model objectively analyzes metric data without being influenced by personal experiences or preferences, thereby improving evaluation objectivity and reliability while the computational complexity is managed through standardized algorithms and automated processes
4Productivity
If automated machine learning-based health evaluation is implemented, then the evaluation time is reduced and biases are eliminated, but the system complexity increases
Solution Approach 1:
The system achieves high productivity through self-service automation, where the machine learning model independently performs metric curation, dashboard generation, and health evaluation without human intervention. This automation dramatically reduces evaluation time and eliminates biases, while the system complexity is encapsulated within the automated model that handles the computational complexity internally
Data Source
AI summary
In various embodiments, a health evaluation application automatically monitors and evaluates the health of one or more computer-based services. The health evaluation application computes deviation values based on one or more machine-learned expected variations associated with multiple metrics. The metrics are associated with the computer-based service(s). The health evaluation application then performs classification operation(s) based on the deviation values and machine-learned classification criteria to compute anomaly indicators associated with a first service included in the one or more computer-based services. Subsequently, the health evaluation application computes a score that indicates the overall health of the first service based on the anomaly indicators. Advantageously, because the health evaluation application automatically computes the score, the time required to monitor and evaluate the health of the service is reduced compared to the time required to manually monitor and evaluate the health of the service.