External AI Processing Device for Resource-Limited IoT Appliances
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional IoT-based home appliances face challenges in providing advanced artificial intelligence services due to resource limitations, leading to increased manufacturing costs and difficulties in incorporating high-specification components, which are addressed by utilizing an external electronic device to perform AI tasks on their behalf.
Innovation Solution
An electronic device equipped with a memory to store neural network models and profile information, along with processors, identifies suitable processors to perform tasks based on task requests, resource availability, and quality of service requirements, effectively distributing AI tasks across multiple processors to optimize performance and resource utilization.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If IoT-based home appliances incorporate high-specification components to perform AI tasks, then AI service capability is improved, but manufacturing cost increases
Solution Approach 1:
The patent extracts the AI processing function from the IoT home appliance itself and relocates it to an external electronic device with higher processing capabilities. The home appliance retains only the task request generation and result reception functions, while the actual neural network model execution is performed externally, allowing the appliance to provide AI services without incorporating expensive high-specification components.
Solution Approach 2:
The patent introduces an intermediary electronic device that acts as a bridge between the IoT home appliance and the AI processing requirements. This intermediary device receives task requests from the appliance, executes them using its own high-specification processors and neural network models, and returns the results, thereby enabling AI services without requiring the appliance itself to have high specifications.
2Adaptability or versatility
If small home appliances include high-specification components for AI tasks, then AI service capability is improved, but device complexity and cost increase
Solution Approach 1:
The patent extracts the complex AI processing functionality from the small home appliance and places it in an external device. This extraction eliminates the need for the small appliance to contain complex high-specification components, neural network models, and associated hardware, thereby reducing device complexity while maintaining AI service capability through the external processing system.
3Productivity
If multiple processors are used to perform AI tasks, then task processing capability is improved, but resource management complexity increases
Solution Approach 1:
The patent implements a self-service resource management system where the electronic device automatically identifies available processors, selects appropriate neural network models, and assigns tasks based on current resource states without requiring external intervention. The system monitors processor availability, evaluates resource states, and makes autonomous scheduling decisions, thereby managing multiple processors efficiently without increasing operational complexity for users.
Data Source
AI summary
Provided is an electronic device including a communication interface, a memory for storing a plurality of neural network models and a plurality of profile information corresponding to the plurality of neural network models, and a plurality of processors. Each profile information of a plurality of profile information includes information on a neural network model for performing a task corresponding to each task request and resource information of the electronic device that is required for each processor of the plurality of processors to perform the task using the neural network model.