Automated Root-Cause Detection for 5G Data Processing Errors
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Identifying the root causes of defects in complex data processing systems, such as 5G wireless networks, is challenging, especially under unusual operating conditions, making it difficult to prevent future defects.
Innovation Solution
An automated process using a design studio, system monitor, distributed data platform, and defect analysis system with AI capabilities to track, store, and analyze defect data, identifying patterns and predicting additional defects based on commonalities.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If extensive testing is performed in large-scale data processing systems, then defect detection capability is improved, but the complexity of isolating root causes increases
Solution Approach 1:
The patent segments the complex defect isolation problem into manageable components by analyzing individual code changes, file modifications, and commit patterns separately. The system breaks down root cause analysis into discrete analytical units that can be processed independently and then synthesized to identify the underlying cause of defects.
Solution Approach 2:
The system performs preliminary analysis of code changes, file modifications, and commit patterns before defects occur in production. By establishing baseline metrics and analyzing historical data in advance, the system prepares defect detection models that can quickly identify root causes when defects are detected, reducing the complexity of real-time isolation.
2Measurement precision
If manual analysis of defect data is performed to identify patterns, then measurement precision is improved, but productivity decreases
Solution Approach 1:
The patent replaces manual mechanical analysis with automated computational systems. Machine learning models and algorithms automatically analyze code changes, file modifications, and commit patterns, substituting human analysts with automated systems that can process data at much higher speeds while maintaining or improving pattern detection accuracy through consistent application of analytical criteria.
Solution Approach 2:
The system creates copies of defect data, code changes, and metadata for automated analysis. By duplicating and processing multiple instances of defect-related information through analytical models, the system can identify patterns across numerous cases without requiring manual examination of each individual defect, thereby improving both precision and productivity.
3Measurement precision
If comprehensive defect data is collected and stored, then analysis accuracy is improved, but data storage requirements increase
Solution Approach 1:
The system extracts only the most relevant features and metrics from comprehensive defect data for storage and analysis. By identifying and extracting key attributes such as code change patterns, file modification types, commit frequency metrics, and other critical indicators, the system maintains high analysis accuracy while storing only the essential data elements needed for effective pattern recognition.
Solution Approach 2:
The system performs preliminary processing and filtering of defect data before storage, pre-processing the data to retain only the most analytically valuable information. This preliminary action reduces the volume of data that needs to be stored while preserving the accuracy needed for subsequent pattern analysis and root cause identification.
Data Source
AI summary
An automated process identifies root causes of defects in a 5G wireless or other data processing system. A design studio or similar tool can be used to track information about one or more particular defects. Information collected could include, for example, results of simulated or actual data processing, technical conditions identified by a system monitor, defect insertion information, defect escape information, and the like. Defect data can be analyzed by an artificial intelligence or other logic to identify root cause attributes that gave rise to the defects. These attributes, in turn, can be used to locate new defects that would have otherwise remained undetected.