An End-to-End Hybrid Document Intelligence System for Unstructured and Semi-Structured Data

Swapnaja Yadav; Soleha Tamboli; Shaivi Jaiswal; Yash Lulla; Shivam Angral; Preeti Bailke

doi:10.2991/978-94-6239-693-7_103

<Previous Article In Volume

Next Article In Volume>

An End-to-End Hybrid Document Intelligence System for Unstructured and Semi-Structured Data

Authors

Swapnaja Yadav¹^{, *}, Soleha Tamboli¹, Shaivi Jaiswal¹, Yash Lulla¹, Shivam Angral¹, Preeti Bailke²

¹Department of IT, Vishwakarma Institute of Technology, Pune, India

²Assistant Professor, Department of IT, Vishwakarma Institute of Technology, Pune, India

^*Corresponding author. Email: swapnaja.yadav242@vit.edu

Corresponding Author

Swapnaja Yadav

Available Online 16 June 2026.

DOI: 10.2991/978-94-6239-693-7_103 How to use a DOI?
Keywords: Document Intelligence; OCR; EasyOCR; Unstructured Data; LLM; Information Extraction; Receipt Digitization
Abstract: Extracting essential information from unstructured and mixed types of documents is a tremendous challenge in many organizations. Documents like scanned receipts, invoices, and native PDFs often contain noise, uneven layouts, faded text, and formatting differences, which makes it difficult for traditional OCR and rule-based systems to read them accurately. In this work, we present a complete end-to-end Document Intelligence system that cleans and preprocesses documents, uses EasyOCR to extract text, groups tokens into proper lines and columns, and then applies rules to pull out key fields. For digital PDFs and Word files, the system extracts clean text and generates meaningful summaries using an LLM. The system also includes MongoDB for storing results, a FastAPI backend for processing, a user-friendly web interface, and a text-to-speech feature. Testing on real scanned receipts and native documents shows that the system extracts information more accurately, works better on low-quality inputs, and answers user questions reliably. Overall, this hybrid AI pipeline is expandable and useful for automating document understanding across different types of files.
Copyright: © 2026 The Author(s)
Open Access: Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

<Previous Article In Volume

Next Article In Volume>

Volume Title: Proceedings of the International Conference on Intelligent Systems for a Sustainable Future (ISSF 2026)
Series: Atlantis Highlights in Intelligent Systems
Publication Date: 16 June 2026
ISBN: 978-94-6239-693-7
ISSN: 2589-4919
DOI: 10.2991/978-94-6239-693-7_103 How to use a DOI?
Open Access: Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Cite this article

ris enw bib

TY  - CONF
AU  - Swapnaja Yadav
AU  - Soleha Tamboli
AU  - Shaivi Jaiswal
AU  - Yash Lulla
AU  - Shivam Angral
AU  - Preeti Bailke
PY  - 2026
DA  - 2026/06/16
TI  - An End-to-End Hybrid Document Intelligence System for Unstructured and Semi-Structured Data
BT  - Proceedings of the International Conference on Intelligent Systems for a Sustainable Future (ISSF 2026)
PB  - Atlantis Press
SP  - 1069
EP  - 1077
SN  - 2589-4919
UR  - https://doi.org/10.2991/978-94-6239-693-7_103
DO  - 10.2991/978-94-6239-693-7_103
ID  - Yadav2026
ER  -

download .riscopy to clipboard