ML-Based Dependency Call Issue Differentiation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In cloud computing environments, distinguishing between issues caused by services and infrastructure dependencies is challenging, leading to burdensome troubleshooting for support personnel.
Innovation Solution
A computer-implemented method using a machine learning model to detect dependency call performance metrics outside a threshold range, identifying the common set of inputs, and determining whether the cause of the issue lies with the service or the dependency by comparing these metrics to expected values.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual investigation is used to determine issue causes, then support personnel can identify problems, but the troubleshooting process becomes burdensome and time-consuming
Solution Approach 1:
The patent replaces manual investigation (mechanical human effort) with an automated machine learning system that uses performance metrics and dependency graphs to automatically identify issue causes, thereby reducing both time loss and maintaining identification accuracy
Solution Approach 2:
The patent introduces a machine learning model as an intermediary between performance metric collection and issue cause identification. This intermediary automatically analyzes the data and determines whether service or infrastructure is at fault, eliminating the need for manual troubleshooting while preserving diagnostic accuracy
2Reliability
If comprehensive monitoring of dependency calls is implemented, then issue detection capability is improved, but system complexity increases
Solution Approach 1:
The patent segments the monitoring system into distinct components: performance metric collection, machine learning analysis, and automated diagnosis. This segmentation improves reliability by ensuring each component has a specific function while managing complexity through modular design
Solution Approach 2:
The machine learning model serves as an intermediary that simplifies the complex task of analyzing dependency call metrics. It automatically processes the data and provides clear diagnostic results, maintaining high issue detection capability while reducing the operational complexity for support personnel
3Productivity
If automated differentiation is implemented using machine learning, then troubleshooting efficiency is improved, but implementation complexity increases
Solution Approach 1:
The patent replaces manual troubleshooting processes with an automated machine learning system that efficiently determines issue causes by analyzing performance metrics and comparing them against learned patterns, thereby improving productivity while managing implementation complexity through automation
Solution Approach 2:
The machine learning model performs self-service by automatically learning from historical data and independently making diagnostic decisions without requiring manual intervention or complex configuration, thus improving troubleshooting efficiency while keeping implementation manageable
Data Source
AI summary
Example aspects include techniques for detecting, for one or more instances of a dependency call from a service to a dependency in the cloud computing platform, the one or more instances of the dependency call having a common set of dependency call inputs, that a value of a dependency call performance metric of the dependency call is outside of a threshold range, providing, to a machine learning (ML) model and based on detecting that the value is outside of the threshold range, the common set of dependency call inputs for the one or more instances of the dependency call, obtaining, from the ML model and based on the common set of dependency call inputs, an expected value for the dependency call performance metric, and determining, based on comparing the value to the expected value, the entity causing the value to be outside of the threshold range.