DESIGN OF A SOURCE-AWARE STRUCTURED DATA MODEL FOR MULTIMODAL EXTRACTION OF MEDICINAL PRODUCT INFORMATION
DOI:
https://doi.org/10.36074/grail-of-science.15.05.2026.120Summary
Multimodal large language models (LLMs) open up opportunities for the automated extraction of textual information from photographic images of objects of various nature. These may include photographs of documents, pages of books and journals, packaging of food products and pharmaceuticals, paper receipts, and others. Recently, ready-made solutions that employ LLMs for automated information extraction from photographs for subsequent data entry have already appeared, for example, Billka AI [1,2], Receipt Scanner: Smart Track [4], and others.
Downloads
Downloads
License
Copyright (c) 2026 Olena Yakovleva, Yevheniia Datsok
References
Billka AI application for bill splitting and expense tracking, simplified by intelligence. (2026, May). SYTOSS | Software Development Company. https://www.sytoss.com/billka-ai
Billka AI intelligent receipt scanning & expense tracking. (2026, May). Billka AI. https://billka.sytoss.com/
Bourhis, P., Reutter, J. L., & Vrgoč, D. (2020). JSON: Data model and query languages. Information Systems, 89, 101478. https://doi.org/10.1016/j.is.2019.101478 DOI: https://doi.org/10.1016/j.is.2019.101478
NeogenxAI. (2026, May). Receipt scanner : Smart track - apps on google play. Android Apps on Google Play. https://play.google.com/store/apps/details?id=com.neogexai.receiptscanner.
Downloads
How to Cite
Issue
Section
Categories
Funding data
-
HORIZON EUROPE Framework Programme
Grant numbers 101136775
