IoT Subsystem Discovery Using Activity Correlation and Link Salience
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Automated industrial and commercial environments face challenges due to the extreme heterogeneity of IoT devices, requiring manual reverse engineering to identify subsystems, which is time-consuming and error-prone, especially when connected to IP-based networks through the Internet of Things (IoT).
Innovation Solution
The implementation of a platform that automatically identifies subsystems in automated environments using activity correlations and link salience, involving data source discovery, activity detection, correlation determination, and salience analysis, with components like data storage systems, correlation algorithms, and machine learning models to determine relationships between IoT devices.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual reverse engineering is used to identify subsystems in heterogeneous IoT environments, then subsystem identification can be achieved, but the process becomes extremely time-consuming and error-prone
Solution Approach 1:
The patent replaces manual reverse engineering (mechanical human intervention) with an automated system that uses machine learning models and algorithms to discover and identify subsystems. The system automatically analyzes device relationships, communication patterns, and data flows to identify subsystem boundaries without human intervention, thereby eliminating time loss while maintaining or improving identification accuracy.
Solution Approach 2:
The system enables automated environments to self-identify their own subsystem structures through self-service mechanisms. By continuously monitoring device interactions and applying correlation algorithms, the system automatically discovers and updates subsystem configurations without requiring external manual analysis, thus resolving the time-consuming nature of traditional methods.
2Adaptability or versatility
If humans are involved in provisioning and maintaining automated systems with tens of thousands of heterogeneous devices, then system configuration can be achieved, but operational complexity increases significantly
Solution Approach 1:
The patent introduces an intermediary automated discovery system that mediates between the complex heterogeneous IoT environment and human operators. This intermediary system abstracts the complexity by automatically analyzing device relationships, protocols, and communication patterns, then presenting simplified subsystem information to users, thereby reducing operational complexity while maintaining configuration capability.
Solution Approach 2:
The system provides universal functionality by handling multiple device types, protocols, and communication patterns through a single automated discovery platform. Rather than requiring separate configuration processes for different device categories, the universal system automatically adapts to various device heterogeneities, reducing operational complexity while preserving adaptability.
3Loss of information
If traditional network monitoring is used in IP-based IoT environments, then device connectivity can be detected, but relationships between devices remain masked by network complexity
Solution Approach 1:
The patent applies dimensionality change by moving from traditional flat network monitoring to a multi-dimensional analysis approach. The system analyzes device relationships across multiple dimensions including communication patterns, data flows, temporal correlations, and protocol interactions. This multi-dimensional perspective cuts through network complexity to reveal underlying device relationships that are invisible in traditional monitoring views.
Solution Approach 2:
The system performs preliminary analysis of device relationships by continuously monitoring and pre-processing communication patterns before queries are made. By pre-computing relationship metrics and storing them in optimized data structures, the system makes relationship information readily available without requiring complex real-time analysis, thus reducing information loss while managing network complexity.
Data Source
AI summary
Described are platforms, systems, and methods to combine counts of activity correlations over time with a link salience method to identify collections of digital devices in an automated environment to identify sub-systems comprised of portions of the overall environment. The platforms, systems, and methods detect activity in a plurality of data sources associated with an automation environment; determine correlation in the detected activity between two or more of the data sources; store records of determined correlation in the detected activity over time in a data storage system; apply a link salience algorithm to the stored records of determined correlation in the detected activity to determine a salience property; and identify one or more subsystems in the automation environment based on the salience property.