Neural Network Model Transfer Suitability Identification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing technologies face challenges in efficiently transferring personalized neural network models between devices with different hardware specifications, and there is a need for a method to identify transition suitability and efficiently transfer neural network models during device changes.
Innovation Solution
An electronic device equipped with a communicator, memory, and processor that can identify transition suitability of neural network models by comparing hardware specifications and model information between devices, and facilitate the transfer of suitable neural network models through device-to-device communication.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If neural network models are transferred between devices with different hardware specifications, then device personalization and service continuity are improved, but hardware compatibility and system reliability deteriorate
Solution Approach 1:
The patent performs hardware suitability identification before transferring neural network models. The processor compares hardware specifications of the source and target devices in advance, and only transfers models that are suitable for the target device's hardware capabilities, preventing compatibility issues before they occur.
Solution Approach 2:
The patent changes the parameter of model selection based on hardware specifications. By adjusting which neural network models are transferred according to the target device's processing power, memory, and other hardware parameters, the system ensures that transferred models are compatible with the destination device while maintaining personalization benefits.
2Reliability
If hardware suitability identification is performed before model transfer, then transfer reliability is improved, but processing time and system complexity increase
Solution Approach 1:
The patent segments the suitability identification process into distinct modules: hardware information acquisition, model information acquisition, and suitability determination. This modular approach organizes the complexity into manageable parts while ensuring reliable transfer decisions.
Solution Approach 2:
The system performs self-identification of hardware suitability automatically without requiring external intervention. The processor autonomously compares hardware specifications and determines model compatibility, reducing the need for complex external verification systems.
Data Source
AI summary
An electronic device and a controlling method of an electronic device are provided. The electronic device includes identifying whether each of one or more neural network models included in a first external device is suitable for hardware of the electronic device and whether each of the one or more neural network models identified as suitable for the hardware of the electronic device is suitable to replace the neural network models included in the electronic device, based on first device information on a hardware specifications of the electronic device, second device information on a hardware specification of the first external device, first model information on the one or more neural network models included in the first external device, and second model information on the one or more neural network models included in the electronic device.