Vehicle Communication Channel Selection With Live AI Rule Updates
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing vehicle communication systems face challenges in dynamically selecting optimal access subnetworks due to varying communication requirements and network conditions, necessitating manual software updates and administrative configurations that disrupt operations.
Innovation Solution
A rules-based decision system utilizing artificial intelligence and machine learning to update parametric rules in real-time, allowing flexible selection of access subnetworks without software upgrades, using a centralized tool to manage and enhance communication policies.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If manual software updates and administrative configurations are used to update parametric rules, then communication management can be updated, but operational disruptions occur and updates cannot be performed in real-time
Solution Approach 1:
The system transitions from static, manually-updated parametric rules to dynamic rules that are automatically updated in real-time through machine learning. The rules are continuously adapted based on real-time inputs from vehicle state, network conditions, and communication requirements, eliminating the need for operational disruptions during updates.
Solution Approach 2:
The communication management system performs self-updating through automated machine learning processes. The system autonomously analyzes real-time data, generates updated parametric rules, and implements changes without requiring external administrative intervention or causing operational interruptions, enabling continuous productivity improvement.
2Reliability
If fixed software versions with programmed logic are used, then system stability is maintained, but the system cannot adapt to changing communication requirements and network conditions
Solution Approach 1:
The system maintains stability by preserving the core software architecture while enabling continuous adaptation through dynamic parameter changes. Machine learning algorithms generate updated parametric rules that adjust communication decisions based on changing conditions, allowing the system to evolve without requiring software version changes or compromising stability.
Solution Approach 2:
The system combines static structural stability with dynamic operational adaptability. The core software framework remains stable and reliable, while the parametric rules layer dynamically adapts to changing communication requirements and network conditions through automated machine learning updates.
3Productivity
If real-time machine learning is used to update parametric rules, then operational continuity is maintained and adaptability improves, but system complexity increases
Solution Approach 1:
The system segments functionality by separating the stable core software from the dynamic parametric rules layer. This architectural segmentation allows machine learning operations to occur in a dedicated rule-generation component without complicating the core communication management software, maintaining operational continuity while managing complexity through modular design.
Data Source
AI summary
Systems and methods for communication management using rules-based decision systems and artificial intelligence are provided herein. In certain embodiments, a system includes a memory unit that stores a knowledge base, wherein the knowledge base stores parametric rules associated with the selection of a communication channel in one or more communications channels, status, performance and usage metrics for communications through the one or more communication channels, vehicle state information, and pre-configured policy on use of communication channels. Also, the system includes a processing unit configured to acquire data related to vehicle state and communication through the one or more communication channels. Additionally, the processing unit is configured to update the knowledge base with updated parametric rules without stopping execution of software, wherein the updated parametric rules are created using machine learning performed on the acquired data and the information associated with the performance goals.