AI-Assisted Airline Safety Comment Recommendation and Finding Mapping
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The manual process of writing airline operational safety comments and mapping findings is time-consuming and prone to human errors such as spelling mistakes and non-standardized categorization, which affects the efficiency and accuracy of airline operational safety evaluations.
Innovation Solution
An AI system utilizing two generative pre-trained transformer (GPT) algorithms to automate the recommendation of comments and mapping of findings by learning from historical aviation safety data, providing suggested comments and findings based on user input, thereby reducing human error and saving time.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If manual process is used for writing comments and mapping findings, then human can exercise judgment and flexibility, but time consumption increases and errors occur
Solution Approach 1:
The system enables self-service by automatically generating comments and mapping findings based on evaluation data. The AI model processes evaluation inputs and produces standardized comments and finding mappings without requiring manual intervention, thus reducing time loss while maintaining reliability through consistent application of safety criteria.
Solution Approach 2:
The patent replaces the manual mechanical process of writing comments and mapping findings with an automated AI-based system. The large language model processes evaluation data and generates standardized outputs, substituting human manual work with an automated intelligent system that reduces time consumption and eliminates human errors.
2Reliability
If manual process is used for comment writing and finding mapping, then flexibility in handling unique cases is maintained, but standardization and consistency deteriorate
Solution Approach 1:
The AI system performs multiple functions including comment generation, finding mapping, and categorization standardization through a single integrated process. The large language model handles various evaluation scenarios universally, applying consistent safety criteria across different cases while maintaining the ability to handle unique situations through its trained understanding of aviation safety standards.
3Productivity
If AI automation is implemented for comment recommendation and finding mapping, then time efficiency and accuracy improve, but system complexity increases
Solution Approach 1:
The system uses an intermediary approach by integrating the AI model with the existing evaluation workflow. The large language model acts as an intermediary component that receives evaluation inputs and provides standardized outputs, bridging the gap between manual evaluation processes and automated decision-making while managing system complexity through modular integration.
Data Source
AI summary
Airline evaluation, comment recommendation, and finding prediction mapping are provided. Responsive to a first user partial entry in an evaluation category entry field, a first large language model (LLM) provides prompts of suggested categories. Selection of one of the prompts or user entry of an alternative category is received. Responsive to a partial entry of a task description, the first LLM provides prompts of suggested task descriptions. Selection of one of the prompts or user input of an alternative task description is received. Responsive to a partial entry of a comment, the first LLM provides prompts comprising subsets of words of suggested comments. Selection of one the prompts or input of an alternate comment is then received. A second LLM provides predicted findings based on the evaluation category, task description, and comment. Selection of one of the predicted findings or user input of an alternative finding is then received.