AI Sensing Model for Low-Power Function Triggering
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing electronic devices face challenges in precisely recognizing sensing data, leading to inefficient performance of specific functions, and result in unnecessary power consumption as all hardware components are powered on even when not in use.
Innovation Solution
A trained model creation method using an artificial neural network is employed to precisely understand sensing data and determine when to perform specific functions in electronic devices, reducing power consumption by only activating the system when specific sensing data is received.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If all hardware components are powered on to ensure specific functions can be performed, then the reliability of function execution is improved, but power consumption increases
Solution Approach 1:
The patent applies preliminary action by training an AI recognition model in advance using big data containing sensing data and determination data. The trained model is then stored in the electronic device, enabling it to quickly determine whether to perform specific functions without requiring extensive real-time processing or keeping all components powered on. This pre-computed knowledge base allows the device to reliably execute functions only when necessary, reducing power consumption while maintaining execution reliability.
2Measurement precision
If sensing data is continuously monitored to accurately determine when to perform specific functions, then the precision of function triggering is improved, but power consumption increases
Solution Approach 1:
The patent pre-trains an AI recognition model using big data that includes various sensing data and corresponding determination data. This trained model is then used to quickly and accurately determine whether to perform specific functions based on new sensing data, eliminating the need for continuous complex analysis and reducing power consumption while maintaining high recognition precision.
Solution Approach 2:
The patent replaces traditional mechanical sensing and decision-making systems with an AI recognition model. Instead of using complex hardware circuits and continuous processing to analyze sensing data, the system uses the pre-trained AI model to quickly determine function execution, significantly reducing power consumption while improving or maintaining recognition accuracy.
3Speed
If a previously trained AI recognition model is used to quickly output determination data, then the speed of function decision-making is improved, but the complexity of model training increases
Solution Approach 1:
The patent performs the complex model training operation in advance using big data, storing the trained AI recognition model in the electronic device. This allows the device to quickly output determination data for specific functions without repeating the complex training process. The one-time training complexity is traded for ongoing fast decision-making speed with minimal power consumption.
Data Source
AI summary
A learning model creation method for performing a specific function for an electronic device includes: preparing big data for training an artificial neural network including, in pairs, sensing data received from a random sensing data generation unit for sensing human behaviors and specific function performance determination data for determining whether to perform a specific function of an electronic device with respect to the sensing data; preparing an artificial neural network model, and association parameters between the nodes of the input layer and the nodes of the output layer, and calculates inputs of the sensing data for the nodes of the input layer in order to output the specific function performance determination data from the nodes of the output layer; and repeatedly performing a process of inputting the sensing data included in the prepared big data into the nodes of the input layer.