Airport Information Updates Using ML Change Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Airport publications are voluminous and require manual, time-consuming comparison to identify changes, making it difficult for users to detect updates such as runway status changes.
Innovation Solution
A system utilizing machine-learning models for natural language processing and image recognition to automatically identify and update airport information, reducing the need for manual parsing by generating and verifying changes using metadata and scheduling information.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual comparison of airport publications is used, then users can identify changes between versions, but the process is laborious and time-consuming
Solution Approach 1:
The patent replaces the manual mechanical process of line-by-line comparison with an automated system using machine-learning models. The system processes airport publication data, identifies changes between versions, and generates updated datasets automatically, eliminating the need for manual parsing and comparison while maintaining high accuracy in change detection.
2Loss of information
If detailed airport publication data is provided, then comprehensive airport information is available, but the voluminous data makes it difficult for users to identify relevant changes
Solution Approach 1:
The system extracts only the relevant change information from the voluminous airport publication data. By using machine-learning models to identify and extract specific changes between publication versions, the system presents users with condensed, actionable information rather than requiring them to navigate through complete detailed datasets.
Solution Approach 2:
The patent segments the voluminous airport publication data into manageable components, processing different elements (runways, terminals, gates) separately through machine-learning models. This segmentation allows the system to identify changes in specific airport features independently, making it easier for users to locate and understand relevant updates without being overwhelmed by the complete dataset.
3Productivity
If automated machine-learning models are used, then change identification is faster and more efficient, but the system complexity increases
Solution Approach 1:
The patent implements a universal machine-learning framework that handles multiple types of airport data and change detection tasks through a single integrated system. The models are designed to process various airport publication formats and identify different types of changes (runway status, terminal updates, gate assignments) using the same core architecture, reducing overall system complexity despite the multifunctional capabilities.
Data Source
AI summary
A method includes receiving a data source that includes information associated with one or more airports. The method also includes determining, using a first machine-learning model, a particular classification of the data source and scheduling information associated with the data source. The method further includes allocating, using a second machine-learning model, particular information in the data source to a particular airport. The particular airport is associated with a particular database, and the particular information is scheduled to be descriptive of a feature of the particular airport. The method also includes generating, using a third machine-learning model, an updated dataset based on the particular information. The current dataset is indicative of the feature of the particular airport. The method further includes updating the current dataset in the particular database with the updated dataset based on the scheduling information in response to a user verification.