IoT Device Type Assignment via Communication Feature Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current IoT device tracking methods are inefficient and prone to human error, leading to inaccurate identification and updating of device types, which compromises network security and timely software/firmware updates.
Innovation Solution
A processor-based system that analyzes communication characteristics to automatically assign device types to IoT devices by comparing extracted features with predefined thresholds and utilizing a knowledge graph to identify device types when thresholds are not met, reducing the need for additional information and minimizing resource usage.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If manual identification methods are used to track IoT devices, then device tracking can be performed, but human error leads to inaccurate identification and updating of device types
Solution Approach 1:
The system automatically performs device type identification by analyzing communication characteristics and comparing them against a knowledge graph, eliminating the need for manual identification and reducing human error. The processor autonomously extracts features, queries the knowledge graph, and assigns device types without human intervention.
Solution Approach 2:
The patent replaces manual mechanical identification processes with an automated electronic system that analyzes communication characteristics (data packets, protocols, ports) and uses a knowledge graph to determine device types, substituting human operators with an automated processing system.
2Measurement precision
If comprehensive device information is collected to ensure accurate device type identification, then identification accuracy improves, but resource usage and processing time increase
Solution Approach 1:
The system uses partial action by selectively analyzing only the most relevant communication characteristics (source/destination ports, protocols, data patterns) rather than collecting all possible device information. The knowledge graph enables accurate identification using a subset of key features, reducing processing overhead while maintaining precision.
Solution Approach 2:
The knowledge graph is pre-populated with device type information and communication characteristic patterns before runtime. This preliminary preparation allows the system to quickly match observed communications against known patterns without performing exhaustive analysis, reducing real-time processing resources while maintaining accurate identification.
Data Source
AI summary
According to examples, a processor may receive data pertaining to a communication sent over a network by a device, extract a set of characteristics associated with the communication from the received data, and determine whether the extracted set of characteristics meets a predefined similarity threshold with respect to a previously identified set of characteristics, in which the previously identified set of characteristics is assigned with a certain device type. The processor may also, based on a determination that the extracted set of characteristics meets the predefined similarity threshold with respect to the previously identified set of characteristics, assign the device with the certain device type.


