Synthesizing Database Entries for Aircraft Hardware Identification

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Aircraft hardware component suppliers and maintenance entities face inefficiencies in deriving consensus values due to excessive bandwidth usage and data entry errors in existing processes, leading to inaccuracies and prolonged resolution times.

Innovation Solution

A machine-learned model is trained to determine consensus values for aircraft hardware components, avoiding the need for large historical data lakes, enabling re-training with new data and generating a searchable database that provides confidence outputs for variance identification.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If existing processes are used to derive consensus values through back-and-forth network communications, then multiple entities can exchange data, but bandwidth is wasted and resolution time increases

Engineering Contradiction:

Improveconsensus value accuracyVSAvoidbandwidth consumption

Core Design Contradiction:

ReliabilityVSLoss of energy

Solution Approach 1:

A centralized server acts as an intermediary that receives data from multiple entities, processes it through machine learning models to determine consensus values, and distributes results back to entities. This eliminates redundant back-and-forth communications between entities while maintaining consensus accuracy through the server's coordinated processing.

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The system creates a synthesized copy of data from multiple source databases, combining historical and new data into a unified training set. This copied and synthesized data is then processed by machine learning models to generate consensus values, avoiding the need for continuous real-time communication while preserving data integrity.

Inventive Principle:

Principle #26Copying

2Reliability

If existing processes are used to derive consensus values through multiple communications, then data can be exchanged among entities, but resolution time increases

Engineering Contradiction:

Improveconsensus value accuracyVSAvoidresolution time

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The system performs preliminary actions by pre-processing and synthesizing data from multiple sources into a unified training set before consensus is needed. Machine learning models are trained in advance on this synthesized data, so when consensus values are required, they can be generated quickly without time-consuming communication loops.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent replaces the mechanical communication system (back-and-forth network exchanges between entities) with an automated information processing system using machine learning models. The server autonomously processes data and generates consensus values without requiring iterative communications, dramatically reducing resolution time.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

3Adaptability or versatility

If data is entered manually in existing processes, then entities can contribute their values, but data entry errors occur reducing accuracy

Engineering Contradiction:

Improvedata collection capabilityVSAvoidvalue accuracy

Core Design Contradiction:

Adaptability or versatilityVSMeasurement precision

Solution Approach 1:

Entities automatically submit their data to the server without manual entry. The system uses self-service mechanisms where data is electronically transmitted and processed automatically, eliminating human intervention in data entry and thus preventing data entry errors while maintaining the ability to collect diverse data from multiple sources.

Inventive Principle:

Principle #25Self-service

4Measurement precision

If large data lakes of historical training data are maintained, then model training can be comprehensive, but processing power and storage requirements increase

Engineering Contradiction:

Improvemodel accuracyVSAvoidprocessing power requirement

Core Design Contradiction:

Measurement precisionVSPower

Solution Approach 1:

The system extracts only the essential features and synthesized patterns from historical data rather than storing and processing entire raw datasets. By synthesizing data from multiple sources into condensed training sets and using machine learning models to identify key patterns, the system achieves high model accuracy without requiring massive computational resources to process complete historical data lakes.

Inventive Principle:

Principle #2Taking out (Extraction)

Data Source

PatentUS11593681B2Synthesizing disparate database entries for hardware component identification

Publication Date: 2023.02.28 CAMP SYST INT INC

AI summary

A device retrieves historical data and new data each a respective hardware component identifier and a respective associated value. The device creates a synthesized set of data by having subsets for anomalous data, data that is associated with an attenuation signal, and other data. The device discards the anomalous data and weights the data associated with an attenuation signal. The device generates a searchable database, the searchable database including each hardware component named by an entry of the synthesized set of data, along with an associated value determined based on the weighted value of the entry. The device receives user input of a search query, and outputs search results based on a comparison of the user input of the search query to entries of the searchable database.