Network Dependency Analysis via Deep Learning Flow Patterns
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for identifying dependencies in computer networks are labor-intensive, error-prone, and often outdated, especially in dynamic environments like cloud computing and IoT networks, and can produce false positives or negatives, or impose performance and security concerns.
Innovation Solution
A network analysis tool that uses deep learning to identify recurrent temporal sequence-based patterns in network flow information, pre-processing data to produce input vectors and applying neural networks to model high-level abstractions and reveal dependencies between network assets, allowing for near real-time updates.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If monitoring software is deployed at network nodes to discover dependencies, then dependency identification accuracy is improved, but system performance deteriorates and security risks increase
Solution Approach 1:
The patent extracts the dependency analysis function from the network nodes themselves and relocates it to an external analysis system that processes exported network flow information. This extraction eliminates the performance impact and security risks of deploying monitoring software at network nodes while maintaining dependency identification accuracy through external pattern recognition algorithms
Solution Approach 2:
The patent introduces network flow information as an intermediary medium between network assets and the dependency analysis system. Instead of directly monitoring network nodes, the system analyzes exported flow data that serves as a mediator, enabling indirect but accurate dependency discovery without intrusive software deployment
2Loss of information
If knowledge elicitation exercises are conducted to identify dependencies, then comprehensive dependency information is obtained, but time consumption and labor intensity increase
Solution Approach 1:
The patent enables the network system to automatically discover and document its own dependencies through analysis of its operational flow data. Instead of requiring human personnel to manually elicit dependency knowledge, the system self-analyzes its network flow information to automatically identify dependencies, dramatically reducing time and labor while maintaining information completeness
Solution Approach 2:
The patent replaces the mechanical process of human knowledge elicitation with automated computational analysis of network flow data. The manual survey process is substituted by algorithmic pattern recognition in flow information, eliminating labor-intensive activities while preserving comprehensive dependency discovery
3Device complexity
If traditional network traffic analysis is used to discover dependencies, then deployment complexity is reduced, but result accuracy deteriorates due to false positives and negatives
Solution Approach 1:
The patent transforms the analysis approach by changing parameters such as analyzing bidirectional flow patterns, temporal sequences, and higher-order combinations of network events rather than simple unidirectional traffic. These parameter changes enable accurate dependency identification without false positives while maintaining low deployment complexity through non-intrusive flow data analysis
Data Source
AI summary
A network analysis tool receives network flow information and uses deep learning—machine learning that models high-level abstractions in the network flow information—to identify dependencies between network assets. Based on the identified dependencies, the network analysis tool can discover functional relationships between network assets. For example, a network analysis tool receives network flow information, identifies dependencies between multiple network assets based on evaluation of the network flow information, and outputs results of the identification of the dependencies. When evaluating the network flow information, the network analysis tool can pre-process the network flow information to produce input vectors, use deep learning to extract patterns in the input vectors, and then determine dependencies based on the extracted patterns. The network analysis tool can repeat this process so as to update an assessment of the dependencies between network assets on a near real-time basis.