ML Model Correlating IT Changes to Machine Data Phenomena
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current IT systems face challenges in promptly identifying and addressing issues caused by IT changes due to the vast amount of machine-generated data, leading to delayed problem resolution and increased complexity in correlating symptoms with underlying causes, often resulting in misclassification and longer time-to-resolve issues.
Innovation Solution
Implementing a machine learning model that correlates detected phenomena in machine-generated data with IT changes by analyzing specifications from IT service management systems and log data, enabling automatic identification of impact and severity, and facilitating proactive issue detection before they propagate.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual verification processes are used to detect IT change issues, then human operators can investigate problems, but the process is time-consuming and delays issue resolution
Solution Approach 1:
The patent replaces manual verification processes with automated machine learning models that analyze machine-generated data to detect and correlate IT change issues. The system automatically compares pre-change and post-change data to identify anomalies, eliminating the need for human operators to manually investigate each issue while maintaining high detection accuracy.
Solution Approach 2:
The system enables self-service by automatically monitoring and detecting issues without requiring human intervention. The machine learning model continuously analyzes system data, correlates changes with detected phenomena, and generates alerts autonomously, allowing the system to serve itself in detecting and reporting problems.
2Loss of information
If users manually report IT issues through tickets or portals, then issue information is captured, but the process delays detection until users are available to report
Solution Approach 1:
The system performs preliminary detection by continuously monitoring machine-generated data and correlating it with IT changes using machine learning models. Issues are detected and correlated with specific changes before users can report them, enabling proactive identification of problems that would otherwise wait for user reporting.
Solution Approach 2:
The patent replaces the manual user reporting mechanism with an automated system that uses machine learning to detect and correlate issues with IT changes. The system automatically analyzes system data, identifies anomalies, and links them to specific changes without requiring user action, eliminating the delay inherent in manual reporting processes.
3Measurement precision
If extensive machine-generated data is collected for IT monitoring, then comprehensive issue detection is possible, but the complexity of correlating symptoms with causes increases
Solution Approach 1:
The patent replaces complex manual data correlation processes with machine learning models that automatically analyze machine-generated data. The models learn patterns and relationships from the data, enabling accurate correlation of symptoms with underlying causes without requiring human operators to manually navigate the complexity of extensive monitoring data.
Solution Approach 2:
The machine learning model acts as an intermediary between the extensive machine-generated data and the issue detection process. It processes and interprets the complex data, extracting meaningful correlations between IT changes and detected phenomena, thereby simplifying the overall system architecture while maintaining high detection accuracy.
4Adaptability or versatility
If frequent IT changes are implemented to improve system functionality, then system capabilities are enhanced, but the difficulty of post-change verification increases
Solution Approach 1:
The system performs preliminary correlation by automatically comparing pre-change and post-change data using machine learning models. This preliminary analysis establishes a baseline and automatically identifies deviations caused by changes, simplifying the verification process for frequent IT changes by providing automated, data-driven insights into change impacts.
Solution Approach 2:
The patent replaces manual post-change verification with automated machine learning-based correlation. The system automatically analyzes machine-generated data to detect and correlate issues with specific IT changes, eliminating the need for manual verification processes and reducing the complexity associated with frequent changes.
Data Source
AI summary
A specification of an information technology change is received via an information technology service management system. The specification of the information technology change is analyzed to determine features of the information technology change. Machine-generated data is analyzed to identify a phenomena detected in the machine-generated data. To a machine learning model, the features of the information technology change and features of the detected phenomena in the machine-generated data are provided to determine a correlation between the information technology change and the detected phenomena in the machine-generated data.