AI Message Prioritization for Aviation Unstructured Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Air traffic control systems face challenges in quickly reviewing and comprehending unstructured messages, such as NOTAMs, which can burden pilots with extensive information, leading to increased head-down time and reduced situational awareness.
Innovation Solution
Implementing a system that uses natural language processing and artificial intelligence to analyze textual content, identify relevant information, assign priority levels, and provide graphical indicia, thereby reducing the manual burden on pilots by prioritizing and recommending actions based on discrepancies between message values and current flight plan values.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If pilots review all unstructured messages manually, then complete information comprehension is achieved, but head-down time increases and situational awareness deteriorates
Solution Approach 1:
The system segments the large volume of unstructured messages into smaller, organized groups based on relevance criteria. Messages are divided into relevant and irrelevant categories, allowing pilots to focus only on segmented portions that require attention, thereby reducing review time while maintaining complete information comprehension.
Solution Approach 2:
The system extracts relevant information from unstructured messages using natural language processing and artificial intelligence. By taking out only the essential information and presenting it in a structured format, the system enables pilots to comprehend complete information without manually reviewing entire message texts, thus reducing head-down time.
2Loss of information
If all messages are presented to pilots, then complete information availability is achieved, but cognitive burden increases
Solution Approach 1:
The system applies local quality by providing different levels of information processing to different messages based on their relevance. High-priority messages receive detailed analysis and structured presentation, while low-priority messages are summarized or filtered. This differentiated approach maintains complete information availability while reducing overall cognitive burden through selective detail provision.
Solution Approach 2:
The system introduces an intermediary layer of AI-based message analysis between the raw unstructured messages and the pilot. This intermediary automatically processes, prioritizes, and structures messages, serving as a cognitive assistant that reduces the pilot's mental workload while ensuring all relevant information remains available for review.
3Reliability
If manual message review is performed, then thorough understanding is achieved, but operational efficiency decreases
Solution Approach 1:
The system performs preliminary action by automatically analyzing, prioritizing, and structuring messages before they are presented to the pilot. This pre-processing ensures that when pilots review messages, they are already organized by relevance and importance, maintaining thorough understanding while significantly improving operational efficiency by eliminating manual sorting and prioritization tasks.
Solution Approach 2:
The system replaces the mechanical process of manual message review with an automated AI-based analysis system. Natural language processing algorithms substitute for human cognitive processing in the initial message evaluation phase, maintaining accurate comprehension through systematic analysis while improving operational efficiency by performing message processing faster and without fatigue.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Methods and systems are provided for assisting operation of a vehicle by intelligently prioritizing messages relevant to a route for the vehicle. One method involves analyzing textual content of the message to automatically identify values for a plurality of fields of information specified by the message and obtaining current values for one or more of those fields from one or more data sources associated with the vehicle. In response to identifying a difference between a specified value and the corresponding current value for a field of information, the method automatically assigns a priority level to the message based at least in part on the difference and provides graphical indicia of the priority level assigned to the message and the specified value for the field.