IoT Device and Network Reliance Control With Compact Feature Vectors
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In modern computing environments, there is a challenge in quantifying and managing reliance on IoT devices and network connections due to resource constraints and security concerns, necessitating efficient metadata collection and processing to support informed decision-making.
Innovation Solution
A computer-implemented method for generating and encoding device and connection feature vectors, using instrumentation and inferencing to derive quantified reliance data, minimizing resource consumption and ensuring security by isolating metadata from user data.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If metadata collection and processing is performed to support reliance assessment, then informed decision-making capability is improved, but resource consumption (processing power, memory, network bandwidth) increases
Solution Approach 1:
The patent segments metadata processing into two distinct locations: lightweight collection at the device level (generating feature vectors from local data) and heavy processing at the cloud level (computational inferencing to generate reliance indicators). This segmentation allows devices to contribute minimal resources while still enabling comprehensive reliance assessment through cloud-based analysis of aggregated metadata from multiple devices.
2Reliability
If comprehensive monitoring of device state and network connections is implemented, then system reliability is improved, but device complexity and implementation difficulty increase
Solution Approach 1:
The patent introduces an intermediary cloud-based computational inferencing system that acts as a mediator between simple device monitoring and complex reliance assessment. Devices use straightforward instrumentation to collect local metadata and transmit it to the cloud, where complex inferencing algorithms process the data to generate reliance indicators. This intermediary approach enables comprehensive monitoring without requiring complex local processing at each device.
3Loss of information
If metadata is transmitted and processed over the network, then reliance quantification capability is improved, but network bandwidth consumption and transmission time increase
Solution Approach 1:
The patent extracts only the essential features needed for reliance assessment from device data, encoding them as compact feature vectors that capture the most relevant state information. This extraction approach transmits minimal necessary data over the network rather than complete raw datasets, enabling efficient metadata transmission while preserving the information needed for accurate reliance quantification through subsequent cloud-based inferencing.
Data Source
AI summary
A technology provides quantified reliance data for at least one of an electronic computing device node and a connection in network, the technology comprising instrumenting at least one of the device and the connection to generate datasets comprising at least one of a device feature vector and a connection feature vector, each feature vector being encoded in a form suitable for transmission over a connection in the network; performing computational inferencing over the datasets to generate quantified reliance data comprising at least one of a trust indicator, a diagnostic indicator and a performance indicator associated with at least one of the device and the connection; and supplying the quantified reliance data in a form usable for selecting an action to be performed, the action being performed by or performed to at least one of the at least one electronic computing device node and the at least one connection.