Cloud Neural Network for Autonomous Measurement Triggering
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing measurement devices face inaccuracies and inefficiencies due to untrained trigger systems, which hinder precise and efficient signal triggering in measurement applications.
Innovation Solution
A method and cloud server for training a neural network to autonomously determine and provide trigger types and parameters, utilizing feedback to continuously improve the neural network, thereby enhancing measurement accuracy and efficiency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a traditional untrained trigger system is used in measurement devices, then the device complexity is reduced and ease of operation is improved, but measurement precision and reliability deteriorate due to inaccuracies in signal triggering
Solution Approach 1:
The patent implements a feedback mechanism where trigger feedback information is collected from measurement devices and sent to the cloud server to train and improve the neural network. This closed-loop feedback system continuously enhances measurement precision by learning from actual triggering outcomes and adjusting trigger type and parameter selections accordingly.
Solution Approach 2:
The neural network performs preliminary analysis of input signals to autonomously determine optimal trigger types and parameters before actual measurement triggering occurs. This preliminary action enables accurate triggering decisions to be made in advance, improving measurement precision without requiring complex real-time trigger system adjustments.
2Productivity
If a neural network is trained locally in each measurement device, then measurement efficiency can be improved through autonomous determination, but device complexity and processing requirements increase significantly
Solution Approach 1:
The patent merges the neural network training and processing functions into a centralized cloud server, combining computational resources from multiple measurement devices. This allows measurement efficiency to be improved through autonomous trigger determination while avoiding the complexity burden on individual devices, as the heavy neural network processing is performed centrally in the cloud.
Solution Approach 2:
The cloud server acts as an intermediary between measurement devices and the neural network processing system. It receives input signals from devices, performs autonomous trigger type and parameter determination through the neural network, and returns trigger settings to the devices. This intermediary approach enables efficient autonomous operation without requiring complex local processing capabilities in each measurement device.
3Reliability
If trigger feedback information is collected and used to continuously train the neural network, then measurement precision and reliability improve over time, but loss of time occurs during data collection and processing
Solution Approach 1:
The patent implements periodic action by collecting trigger feedback information continuously from measurement devices and training the neural network at optimized intervals. This periodic training approach maintains high trigger system reliability by regularly updating the model with new data, while avoiding excessive processing time by scheduling training operations efficiently rather than continuously.
Data Source
AI summary
A method for training a neural network for triggering an input signal in a measurement device is provided. The method comprises the steps of providing a trigger type and/or trigger parameter from a cloud server hosting the neural network via a network to the measurement device, triggering the input signal based on the trigger type and/or trigger parameter received in the measurement device, and collecting trigger feedback information from the measurement device at the neural network to train the neural network.