Work smart not harder by using intelligent document management system in aviation
summary
Createq implements an intelligent document management pipeline that processes 300,000 documents per transition, targets the 6–8 week aircraft handover window and aims to cut the up-to-$5.5M planned cash out. The system uses page-level classification plus NER (spaCy NER tested, BERT and “LSDM” evaluated), applies post‑processing reliability estimation, and links parent/child records; Random Forest with feature engineering surprisingly matches or outperforms BERT and reduces manual input and errors while automating missing‑document queries.
AI-written summary · about
chapters (9)
- 0:00Introduction and company overview
- 2:00Aviation documentation challenges
- 5:51Defining the problem and goals
- 8:15Key requirements for document management
- 11:28Machine learning solution approach
- 15:16Classification and NER techniques
- 19:17Document structuring and automation
- 20:32Results and benefits summary
- 21:02Q&A session
related talks
32mUsing AI to power a circular economy for aerospace
31mIntelligent Documents Management System
43mImplementing AI Document Processing at Scale: Syngenta
30mIntelligent document processing for the insurance industry
30mIntelligent document processing: Extract data & insights from documents
47mRevamping the Document Automation Workflow with Generative AI
20mDocument Management and AI: The Perfect Pair
29mBetter Understand Your Documents with AI