Processor Scheduling AI Model File Initialization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing electronic devices face challenges in efficiently initializing model files for AI applications, leading to suboptimal execution speed and resource management, particularly when multiple applications with different initialization requirements are installed.
Innovation Solution
An electronic device with a processor that identifies target model files based on neural networks and determines optimal initialization times among preset options, allowing for efficient resource allocation and initialization of model files based on usage patterns and application requirements.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Speed
If model files are initialized immediately when applications are installed, then execution speed of AI functions is improved, but device resource consumption and startup time are increased
Solution Approach 1:
The system performs preliminary identification and categorization of model files during application installation, but delays the actual initialization action until a later optimal time. The processor identifies target model files and determines their initialization priorities, then schedules initialization for when device resources are available and usage is predicted, rather than immediately
Solution Approach 2:
The initialization timing is made dynamic rather than static. The system continuously monitors device resource status, application usage patterns, and predicts future usage needs to determine the optimal initialization moment. This allows the system to adapt initialization timing based on real-time conditions, balancing execution speed requirements against resource availability
2Productivity
If all model files are initialized at once, then AI application performance is improved, but device memory and processing resources are overwhelmed
Solution Approach 1:
The system divides model files into separate groups based on their initialization priorities and usage patterns. Instead of initializing all model files simultaneously, the processor segments them into high-priority, medium-priority, and low-priority groups, then initializes them in stages according to device resource availability and predicted usage needs, preventing resource overload
Solution Approach 2:
Different initialization strategies are applied to different model files based on their specific characteristics and usage patterns. High-priority model files associated with frequently used AI functions are initialized earlier and with higher resource allocation, while lower-priority files are deferred. This localized quality approach optimizes resource distribution across different model files rather than applying a uniform initialization strategy
Data Source
AI summary
An electronic device includes a memory configured to store one or more applications, and at least one processor configured to control the electronic device. The processor may identify a target model file based on a neural network and associated with a target application among the one or more applications, determine a target initialization time of the target model file among a plurality of preset initialization times, and initialize the target model file at the target initialization time. In addition, various example embodiments may be implemented.