Wireless Device Type Prediction for Diagnostics
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing technologies face challenges in accurately diagnosing and optimizing the performance of wireless computing devices, as they have diverse purposes, capabilities, and characteristics, leading to sub-optimal performance and less accurate detection.
Innovation Solution
A method and apparatus that predict the type of a wireless computing device by receiving an indication of its model and characteristics from a wireless access point, using a type detector module to classify the device, and applying optimization and diagnostics policies based on the predicted type.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If device-specific information is collected from wireless access points without user intervention, then automation is improved, but measurement precision and reliability deteriorate due to sub-optimal performance in diverse device types
Solution Approach 1:
The system segments wireless devices into different device types (mobile devices, fixed devices, portable devices) based on detected characteristics. This segmentation allows the system to apply device-specific optimization policies tailored to each category, improving detection accuracy while maintaining automation. The segmentation is performed by analyzing characteristics such as mobility patterns, communication protocols, and operational behavior without requiring user intervention.
Solution Approach 2:
The system changes operational parameters and optimization policies based on the detected device type. Different parameters are applied to different device categories - for example, mobility thresholds, transmission power levels, and quality of service parameters are adjusted according to whether the device is classified as mobile, fixed, or portable. This dynamic parameter adjustment maintains high measurement precision across diverse device types while preserving automated operation.
2Device complexity
If a single optimization policy is applied to all wireless devices, then device complexity is reduced, but productivity deteriorates due to sub-optimal performance across different device types
Solution Approach 1:
The optimization policy is made dynamic rather than static. The system continuously monitors device characteristics and automatically adjusts optimization parameters in real-time based on the detected device type. This dynamic approach allows a single policy framework to adapt to different device categories, maintaining low overall complexity while achieving high productivity through automated parameter adjustment.
Solution Approach 2:
Different optimization parameters and quality settings are applied locally to different device types. The system identifies the specific device category and applies tailored optimization parameters to that local group while maintaining a unified policy architecture. This local quality approach improves productivity for each device type without requiring completely separate policies for each category.
3Ease of operation
If device type classification is performed without user intervention, then ease of operation is improved, but loss of information increases due to difficulty in obtaining accurate device-specific information
Solution Approach 1:
The wireless access point performs self-service by automatically collecting and analyzing device characteristics without requiring user or administrator intervention. The system autonomously detects device type by monitoring communication patterns, mobility behavior, and operational parameters. This self-service mechanism maintains ease of operation while preserving information accuracy through systematic automated data collection and analysis.
Solution Approach 2:
The system implements feedback loops where the access point continuously monitors device behavior and adjusts its classification and optimization parameters accordingly. This feedback mechanism ensures that device type identification remains accurate over time, compensating for any initial information loss by continuously refining the classification based on observed device characteristics and performance patterns.
Data Source
AI summary
A software application executing on a server and communicating with an agent in a wireless access point predicts a type of a computing device wirelessly connected via a radio frequency link to the wireless access point. The application receives an indication of a model of the computing device from the wireless access point, and further receives one or more characteristics of the computing device from the wireless access point. The application then predicts the type of the computing device associated with the one or more of the indication of the model, and characteristics, of the computing device.