Machine Learning Network Analysis Automation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing network analysis techniques rely heavily on manual input, leading to inefficiencies, inaccuracies, and excessive time and effort in resolving network events, due to the complexity and repetitive nature of manual procedures.
Innovation Solution
A computer-implemented method using machine learning models to analyze network attributes, where a first model generates an output about network events, and if the confidence level is below a threshold, a second model is engaged to refine the analysis, reducing the need for manual intervention and improving accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If manual analysis procedures are used for network events, then users can perform analysis, but the process becomes time-consuming and inefficient
Solution Approach 1:
The patent replaces manual mechanical analysis procedures with an automated machine learning system. The machine learning model automatically processes network attributes, identifies events, and generates resolutions without requiring manual intervention, thereby eliminating the time loss associated with manual analysis while maintaining analytical capability.
Solution Approach 2:
The system performs self-service by automatically analyzing network events and generating resolutions without human intervention. The machine learning model independently processes network attributes, identifies patterns, and produces actionable insights, allowing the system to serve itself rather than requiring continuous manual operation.
2Ease of operation
If manual procedures are used for network analysis, then analysis can be performed, but the procedures become complicated and require extensive input
Solution Approach 1:
The patent replaces complex manual procedures with an automated machine learning system that handles complexity internally. The machine learning model processes multiple network attributes and identifies complex patterns automatically, presenting simplified results to users without exposing them to the underlying complexity of the analysis procedures.
Solution Approach 2:
The machine learning model acts as an intermediary between the complex network data and the user. It processes complex network attributes through its internal algorithms and presents simplified, actionable results, shielding users from the complexity of the underlying analysis while maintaining ease of operation.
3Reliability
If manual analysis is performed repeatedly, then network events can be investigated, but user effort and time increase excessively
Solution Approach 1:
The patent replaces repeated manual analysis with a single machine learning model inference that automatically processes network events. The machine learning model maintains high reliability by learning from training data and consistently applying learned patterns, eliminating the need for repeated manual procedures while maintaining analytical accuracy.
Solution Approach 2:
The machine learning model performs preliminary analysis by pre-processing network attributes and identifying patterns before final resolution is needed. This preliminary action prepares the analysis in advance, reducing the need for repeated manual procedures and minimizing time spent on iterative investigations.
Data Source
AI summary
There is provided a computer-implemented method for analysing one or more network attributes of a network. One or more first network attributes of the network are analysed using a first machine learning model to generate a first output comprising information about an event in the network. If an estimated confidence level for the first output is less than a confidence level threshold, the one or more first network attributes are analysed using a second machine learning model to generate a second output. The second output is indicative of one or more second network attributes of the network to analyse using the first machine learning model.