Processor Neural Network Safety Function Monitoring
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing electronic devices face challenges in ensuring that safety functions remain independent from general functions during updates, leading to potential interference and increased costs and time for checking the integrity of safety functions.
Innovation Solution
An electronic apparatus with a processor configured to use a trained neural network model to identify instructions corresponding to safety functions, determining the operation state and switching to a safe state if non-safety functions are detected, and controlling the device to stop operations or provide messages accordingly.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If a new function is added due to device package upgrade, then device functionality is improved, but the safety function may be interfered with and independence cannot be guaranteed
Solution Approach 1:
The processor is divided into a first core dedicated to safety functions and a second core for general functions. This segmentation ensures that safety-critical instructions are isolated in a dedicated core, preventing interference from general function updates while maintaining device adaptability.
Solution Approach 2:
A neural network model is introduced as an intermediary to monitor and identify instructions executed in the first core. The model detects whether executed instructions correspond to safety functions, providing an additional layer of verification that maintains safety independence even when new functions are added.
2Reliability
If separate checking is performed to verify safety function integrity after updates, then safety reliability is improved, but additional cost and time are required
Solution Approach 1:
The neural network model operates continuously in the background to monitor instructions executed in the first core. This continuous monitoring eliminates the need for separate post-update checking procedures, maintaining safety verification without additional time loss while ensuring safety function integrity.
Solution Approach 2:
The system performs self-verification through the neural network model that automatically identifies and monitors safety function instructions. This self-service mechanism eliminates the need for external separate checking processes, reducing both time and cost while maintaining reliability.
3Reliability
If a dedicated core is allocated for safety functions, then safety function independence is improved, but device complexity increases
Solution Approach 1:
The neural network model serves multiple functions: it identifies safety function instructions, monitors core execution, and verifies safety independence. This multi-functionality reduces the need for additional dedicated hardware components, maintaining safety independence without proportionally increasing device complexity.
Data Source
AI summary
An electronic apparatus including a memory; and a processor including at least one core, among a plurality of cores, that is configured to execute an instruction corresponding to at least one safety function. The processor is further configured to, based on at least one instruction being executed in the at least one core while the electronic apparatus operates in a first state, identify whether the at least one instruction corresponds to the safety function based on an output of a trained neural network model; and based on a result of the identification, determine an operation state of the electronic apparatus as one of the first state or a second state.