Root Cause Identification System for Anomalous Event Records
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Identifying the root cause of anomalous events in systems, such as medical scanners, is challenging due to the large volume and complexity of event records, which are difficult to understand and annotate manually, leading to time-consuming and inefficient troubleshooting.
Innovation Solution
A method and system that retrieve event records from a database, determine a risk category and priority based on baseline normal functioning data, and use these to identify the root cause of anomalous events, incorporating natural language processing and risk matrices for effective prioritization and analysis.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual annotation of event records is performed to distinguish normal and anomalous events, then accuracy in identifying root cause is improved, but time consumption and labor effort increase significantly
Solution Approach 1:
The system performs self-diagnosis by automatically analyzing event records using machine learning models to identify anomalous events and determine root causes, eliminating the need for manual annotation and significantly reducing time consumption while maintaining high accuracy
Solution Approach 2:
The patent replaces manual mechanical analysis with automated computational systems including event record retrieval, risk category determination, and machine learning-based root cause identification, substituting human effort with algorithmic processing
2Measurement precision
If all event records are analyzed in detail to identify root cause, then completeness of analysis is improved, but processing time and computational resources increase
Solution Approach 1:
The system segments event records into different risk categories (first risk category, second risk category, etc.) based on their importance and anomaly level, allowing prioritized processing where high-risk events receive detailed analysis while lower-risk events are processed more efficiently
Solution Approach 2:
Different levels of analysis depth are applied to different event records based on their risk category and priority, with computational resources concentrated on the most critical events rather than uniform processing of all records
3Reliability
If event records with technical keywords are processed without translation, then data integrity is maintained, but user understandability decreases
Solution Approach 1:
The system introduces a natural language generation component that acts as an intermediary, translating technical event record data into user-friendly explanations while preserving the underlying technical accuracy, allowing users to understand anomalies without losing data integrity
Data Source
AI summary
A root cause associated with an anomalous event in a device is determined. A method includes retrieving one or more event records associated with the device from a database. The method further includes determining a risk category associated with the one or more event records based on information present in the one or more event records. The risk category indicates a risk associated with a functioning of the device. Additionally, the method includes determining a priority associated with each of the one or more event records based on a baseline associated with the one or more event records. The baseline is defined based on a set of events that occur during a normal functioning of the device. The method includes determining the root cause associated with the anomalous event in the device based on the risk category and the priority associated with the event records.