Computing Device Provisioning with Usage-Based Configuration
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods of provisioning computing devices based on snapshots of other devices consume significant power and may include unnecessary configuration information, leading to inefficient power usage.
Innovation Solution
A manager system collects usage data from multiple devices to determine common and device-specific configurations, intelligently provisioning new devices based on learned user habits and device types using machine learning models to optimize power consumption.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of time
If provisioning is performed using snapshots of other devices, then configuration information can be obtained quickly, but significant power is consumed and unnecessary configuration information is included
Solution Approach 1:
The patent extracts only the necessary configuration information from usage data of existing devices, rather than copying entire device snapshots. The machine learning model identifies and extracts only the relevant configuration parameters needed for the new device type, eliminating unnecessary data transfer and processing while reducing power consumption.
Solution Approach 2:
Instead of copying complete device snapshots which consume significant power, the system creates simplified configuration profiles that capture only essential settings. These lightweight configuration profiles are generated through machine learning analysis of usage patterns, providing sufficient provisioning information with minimal power expenditure.
2Productivity
If provisioning is performed using snapshots of other devices, then configuration information can be obtained quickly, but unnecessary configuration information is included leading to inefficient power usage
Solution Approach 1:
The patent applies local quality by tailoring configuration information specifically to the device type and usage patterns rather than applying generic snapshots. The machine learning model analyzes usage data to determine which configuration parameters are locally relevant to each specific device type, ensuring that only necessary settings are provisioned, thereby improving efficiency and reducing power consumption.
Solution Approach 2:
The system dynamically changes configuration parameters based on analyzed usage patterns from existing devices. Rather than using fixed snapshot templates, the machine learning model adjusts configuration parameters to match actual usage behaviors, ensuring optimal provisioning that avoids unnecessary power-consuming operations while maintaining high productivity.
3Use of energy by moving object
If device configurations are customized for specific usage patterns, then power consumption is optimized, but complexity increases in collecting and analyzing usage data
Solution Approach 1:
The patent implements a universal machine learning model that handles multiple device types and usage patterns through a single system. This multi-functional approach consolidates the complexity of collecting and analyzing usage data across diverse devices into one unified framework, reducing overall system complexity while enabling customized configurations that optimize power consumption for each device type.
Solution Approach 2:
The system performs self-service by automatically collecting, analyzing, and generating configuration information from usage data without requiring manual intervention. The machine learning model autonomously processes usage patterns and generates optimized configurations, reducing the operational complexity of managing device provisioning while achieving power consumption optimization through customized settings.
Data Source
AI summary
An example manager device includes processing circuitry; and a storage device that stores instructions executable by the processing circuitry to: obtain usage data from a plurality of devices, wherein each device of the plurality of devices is associated with one or more device types of a plurality of device types, and wherein each device type of the plurality of device types specifies a usage behavior; store common information based on the usage data; store device type features for a device type based on the usage data corresponding to one or more devices of the plurality of devices associated with the device type; determine a provisioning device type for a first device; determine configuration information for provisioning the first device based on stored device type features associated with the provisioning device type and the common information; and provision the first device based on the configuration information.