Machine Learning Device for Network Failure Resolution
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
General users without specialized knowledge face challenges in selecting appropriate network devices to address performance limitations or specification-related network failures due to the complexity of understanding communication state information between network devices and terminals.
Innovation Solution
A machine learning device that obtains information from communication relay devices, performs calculations using neural networks to classify communication data, and selects candidate devices based on determined characteristics, providing users with information to select suitable replacement devices.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If general users attempt to select appropriate network devices to address performance limitations or specification-related network failures, then they can resolve network issues, but they face challenges due to the complexity of understanding communication state information between network devices and terminals
Solution Approach 1:
The patent introduces an information processing device that acts as an intermediary between network devices and general users. This device automatically acquires communication state information from network devices, performs neural network calculations to determine device characteristics, and presents simplified selection criteria to users. The intermediary translates complex technical data into user-friendly recommendations, enabling general users to resolve network failures without needing specialized knowledge.
Solution Approach 2:
The system enables self-service by automatically performing the complex analysis that would otherwise require specialized knowledge. The information processing device autonomously acquires communication state information, executes neural network calculations to determine device characteristics, and generates replacement device recommendations without human intervention in the analysis process. This allows general users to independently resolve network failures by following the system's guidance.
2Measurement precision
If network administrators manually analyze communication state information to determine appropriate replacement devices, then they can make informed decisions, but it requires specialized knowledge and increases the time needed to resolve failures
Solution Approach 1:
The patent replaces the manual mechanical process of analyzing communication state information with an automated neural network system. The information processing device uses machine learning models to automatically process communication state data, determine device characteristics, and recommend replacement devices. This substitution of automated intelligent processing for manual analysis maintains high accuracy in device selection while dramatically reducing the time required to resolve network failures.
Solution Approach 2:
The system performs preliminary actions by pre-calculating device characteristics and preparing replacement device recommendations before actual network failures occur. The information processing device continuously monitors network devices, performs neural network calculations to determine characteristics, and maintains ready-to-use replacement recommendations. When a failure occurs, the system can immediately present pre-analyzed options to users, eliminating the time needed for on-the-spot analysis.
3Measurement precision
If the system stores detailed communication state information for analysis, then it can provide accurate device recommendations, but it increases the computational burden and cost of recalculating neural network weights with new devices
Solution Approach 1:
The patent extracts and stores only the essential device characteristics determined by neural network calculations, rather than retaining all raw communication state information. The information processing device processes communication state data through neural networks to extract key characteristics such as device performance metrics and compatibility parameters. By storing only these extracted essential features rather than complete raw data, the system maintains recommendation accuracy while significantly reducing the computational burden and storage requirements for future calculations.
Data Source
AI summary
A machine learning device includes at least one processor; and at least one memory device configured to store a program, the program executed by the at least one processor to cause the at least one processor to obtain at least one first information from a communication relay device, the first information changing due to communication of the communication relay device; and to correlate the obtained at least first information with at least one characteristic of a replaceable candidate device to perform machine learning.