Anomaly Detection via Predicted Data Differential Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Complex IT systems face challenges in detecting advanced alert situations and anomalies post-system upgrades, making it difficult to determine the source and cause of issues, and often result in false alerts due to baseline changes.
Innovation Solution
A computer system comprising a data preprocessing system and a data analysis system that generates predicted data based on system data, calculates differential data to identify anomalies, and uses decision tree analysis to trace back the source of alerts, while tolerating variance to avoid false alerts.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional alert detection systems monitor system messages for abnormal behavior, then anomalies can be detected, but false alerts increase due to baseline changes after system upgrades
Solution Approach 1:
The system performs preliminary actions by generating predicted data before actual anomalies occur. It uses decision tree analysis to predict expected system behavior patterns in advance, allowing the system to distinguish between expected variations and actual anomalies, thereby reducing false alerts while maintaining detection accuracy
Solution Approach 2:
The system implements feedback mechanisms by continuously comparing actual system data against predicted data and using decision tree analysis to learn from historical patterns. This feedback loop allows the system to adapt to baseline changes after upgrades and maintain accurate anomaly detection without generating false alerts
2Difficulty of detecting and measuring
If the system analyzes system data to detect anomalies, then issue identification improves, but the complexity of the detection system increases
Solution Approach 1:
The system segments the complex detection process into distinct functional components: a data preprocessing system that generates predicted data, a decision tree analysis system that evaluates patterns, and an anomaly detection system that identifies issues. This segmentation reduces overall complexity by making each component more manageable and easier to implement
Solution Approach 2:
The decision tree analysis acts as an intermediary between raw system data and anomaly detection. It processes and interprets complex data patterns, translating them into actionable insights about expected versus actual system behavior, thereby simplifying the overall detection process while maintaining high accuracy
3Measurement precision
If the system generates predicted data and compares it with actual data, then anomaly detection improves, but data processing time increases
Solution Approach 1:
The system applies partial action by generating predicted data only for critical system parameters and using decision tree analysis to evaluate only the most significant patterns. This selective approach maintains high detection precision for important anomalies while reducing overall data processing time by avoiding unnecessary analysis of less critical data
Data Source
AI summary
A computer system to detect data alerts includes a data preprocessing system and a data analysis system. The data preprocessing system obtains system data of the computer system, generates predicted data based on the system data, and generates differential data indicating a difference between the system data and the predicted data. The data analysis is in signal communication with the data preprocessing system and determines that the differential data is one of expected event or an anomaly event in response to adding at least one new value from the differential data to the predicted data.