Device Clustering via IP Log Feature Vectors
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional clustering methods lack accuracy in grouping external devices based on their relationships, leading to inappropriate service provision and user inconvenience.
Innovation Solution
An electronic apparatus and method that utilize log data to identify external devices connected to the same IP, generate feature vectors, and apply neural network models to define groups and sub-groups, ensuring accurate clustering and targeted service delivery.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional clustering methods using simple rules (e.g., same IP address) are used to group external devices, then the device complexity and processing requirements are low, but the clustering accuracy and service appropriateness deteriorate
Solution Approach 1:
The patent transforms the clustering approach by changing from simple rule-based parameters (IP address matching) to multiple analytical parameters including connection frequency, data volume, timing patterns, and device type compatibility. This parameter transformation enables more accurate clustering while maintaining manageable system complexity through structured processing of these parameters.
Solution Approach 2:
The patent adds multiple new dimensions to the clustering process beyond basic IP address matching. These dimensions include temporal patterns (connection timing), quantitative metrics (data volume, connection frequency), and device characteristics (type compatibility). By operating in this multi-dimensional space, the system achieves superior clustering accuracy without proportionally increasing complexity.
2Reliability
If simple IP-based clustering is used to group external devices, then the ease of operation and implementation are high, but the service quality and user satisfaction deteriorate
Solution Approach 1:
The patent implements preliminary analysis of external device connection patterns before providing services. By pre-processing connection data to extract patterns in timing, volume, and frequency, the system establishes accurate device groupings in advance. This preliminary action ensures high service quality when services are delivered, while the complexity is managed through automated pattern recognition rather than manual configuration.
Solution Approach 2:
The system performs self-service by automatically analyzing connection patterns and determining device groupings without requiring manual intervention. The external devices themselves provide the data needed for clustering through their connection behavior, and the system autonomously processes this data to create accurate clusters, thereby maintaining ease of operation while improving service quality.
Data Source
AI summary
An electronic apparatus is provided. The electronic apparatus includes a communication interface, a memory storing log data with respect to external devices connected to the electronic apparatus, and a processor configured to identify a plurality of external devices having a history of being connected to the same internet protocol (IP) based on the log data, acquire, based on the log data, a first feature vector with respect to a relationship between the plurality of external devices and a second feature vector with respect to each of the plurality of external devices, acquire a graph of the relationship between the plurality of external devices based on the first feature vector and the second feature vector, and define at least one group configured by the plurality of external devices based on the graph.