Autoencoder Neural Network for Software Trace Correlation Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Manual analysis of software application trace files is time-consuming and inefficient, especially in heavy load production environments, making it difficult to quickly determine the root cause of abnormal behavior, errors, or defects.
Innovation Solution
An analyzer system using an autoencoder neural network to identify correlations in software application trace data by minimizing reconstruction errors and providing correlation values to aid in root cause analysis, allowing users to direct their analysis more effectively.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of time
If manual inspection of trace files is performed, then analysis accuracy can be maintained, but time consumption increases significantly
Solution Approach 1:
The patent introduces an autoencoder neural network as an intermediary between the trace data and the analyst. The system automatically processes trace files, extracts parameters, builds correlation graphs, and identifies root causes, acting as a mediator that handles the time-consuming manual inspection tasks while preserving analysis accuracy through automated correlation computation.
Solution Approach 2:
The patent replaces the mechanical manual inspection process with an automated computational system. Instead of manually examining trace files and identifying correlations, the system uses neural networks and algorithms to automatically analyze trace data, compute correlations between parameters, and generate root cause analysis results, dramatically reducing time consumption.
2Productivity
If automated analysis systems are introduced to reduce time consumption, then productivity improves, but system complexity increases
Solution Approach 1:
The patent creates a universal analysis system that handles multiple functions: trace file parsing, parameter extraction, correlation computation, graph generation, and root cause identification. The autoencoder neural network serves as a multi-functional component that can analyze different types of trace data and identify various kinds of correlations, reducing the need for multiple specialized tools.
Solution Approach 2:
The patent segments the complex analysis task into distinct components: trace data ingestion, parameter extraction, correlation computation, and result presentation. The system processes trace files in manageable units and builds correlation graphs incrementally, making the overall complex task more tractable and easier to implement.
3Measurement precision
If comprehensive trace data is analyzed to ensure complete root cause identification, then analysis thoroughness improves, but processing time increases
Solution Approach 1:
The patent extracts only the essential parameters and correlations from the comprehensive trace data using the autoencoder neural network. Instead of analyzing every single trace entry in detail, the system identifies and extracts the key parameters that are most relevant to root cause analysis, computing correlations only for these extracted parameters to maintain precision while reducing processing time.
Solution Approach 2:
The patent applies partial action by focusing computational resources on the most critical correlations and parameters identified through the autoencoder. Rather than uniformly processing all possible parameter combinations, the system concentrates analysis on the subset of parameters that have the highest impact on root cause identification, achieving thoroughness in the most important areas.
Data Source
AI summary
An analyzer system inputs parameter values from trace files of a software application into an autoencoder. The analyzer system adjusts weights of the edges between nodes in the autoencoder until reconstruction errors in outputs are minimized. The analyzer system receives a selection of a parameter represented in an autoencoder. In response, the analyzer system identifies hidden layer nodes connected to an output node corresponding to the selected parameter and identifies other output nodes connected to the hidden layer nodes. The analyzer system retrieves weights assigned to edges between the hidden layer nodes and the other output nodes. The analyzer system calculates correlation values between the output node corresponding to the selected parameter and each of the other output nodes and outputs the correlation values. A user can use the correlation values to better direct the root cause analysis.