Aug 2026· International Conference on Digital Transformation: Informatics, Economics, and Education· Vol 14303, pp. 143030K - 143030K-13· 0 citations· 13 references
Engineering
Abstract
In this work, presented is a technical description of a software module for automating customer order processing in an industrial company. Analyzed is the finding that manual processing of unstructured orders takes twenty to forty minutes per document and leads to errors when matching against a catalog of four thousand items. Investigated is the microservice architecture based on FastAPI, comprising a RAG service, telemetry collector, and an embedded widget for the Bitrix24 CRM system. Revealed is that hybrid search combining semantic vector representations and a lexical inverted index provides high accuracy in matching customer descriptions against catalog nomenclature. Studied is the application of a three-level text extraction strategy for documents in PDF, Excel, CSV, and ZIP formats with Tesseract OCR fallback. Determined is that text chunking with overlap and a multi-level LLM API invocation strategy enable reliable extraction of product items from orders of arbitrary volume. Established is that fine-tuning the E5-base model on a domain-specific corpus using triplet loss with hard negatives improves semantic search quality. Formed is an iterative accuracy improvement mechanism through a closed-loop telemetry collection and manager feedback system. Proposed is a two-stage nomenclature matching scheme with gate optimization and caching to accelerate processing of typical queries. Developed is integration with Bitrix24 and 1C systems automating the complete cycle from file upload to order creation in the accounting system. Substantiated is the advantage of the proposed approach over manual processing and classical full-text search in both speed and result quality. Presented is a description of validation results on real customer data confirming a three-to-four-fold reduction in order processing time.
The design realization and evaluation of an Automated Summarization Tool (AST) is presented which is a document intelligence platform based on google gemini 2.5 flash that outperforms the strongest fine-tuned transformer baselines (PEGASUS, BART) by ~14 points and is clearly ahead of BERTSUM-ext (a strong transformer baseline), Pointer-Generator Network, TextRank.
K. Kumar, A. Amandeep, Dharmender Kumar et al.· International Journal of Inn...· 0 citations
An end-to-end assignment verification system that uses computer vision (CV) and natural language processing (NLP) to handle various complex types of modern academic documents. The solution uses multi-scale convolutional neural networks to capture writing and layout features. Using transformer-based structures for semantic parsing and segmentation. At its core is an adaptive cross-modal fusion mechanism, used to synchronize and merge visual and textual features to enhance the ability to recognize anomalous structures, fraudulent handwriting, and semantic mismatches. To train and test the system, we used a large, meticulously annotated dataset containing over 15,000 assignment papers, including handwritten, typed, and mixed-type papers. Many experiments compared the proposed framework with rule-based, vision-based, and language-based frameworks. The algorithm combinations performed excellently in document region detection, semantic mapping, and overall correctness. Cross-modal solutions can be used for real-time education. Further analysis showed the proportion of all subsystems and confirmed the necessity of reliably obtaining results from a wide range of heterogeneous and noisy data. There are limitations when dealing with charts that have different writing styles or do not follow standard drawing conventions, which may make understanding and grouping more difficult. Has it been proven that there is a reliable computational method to verify automatically high-fidelity tasks?
Yufei Ye, Wenyao Cao, Zerong Huang et al.· International Conference on...· 0 citations
ATEM is a term extraction tool for web and mobile environments that incorporates a hybrid method for identifying relevant terms in English-language scientific literature on IoT and contributes to the development of lexicographic resources; language translation; and the creation of shared databases.
A. M. Rios, C. M. M. Otálvaro, J. Andrade et al.· international journal of eng...· 0 citations
Experiments on three real-world datasets demonstrate that AnnoIndex consistently outperforms state-of-the-art baselines, achieving the highest average F1 score while maintaining robust performance on complex multi-hop join and progressive reasoning queries.
Traditional document management systems suffer from inefficiencies in organization, retrieval, and data extraction, often relying on manual entry and rigid field structures that fail to accommodate diverse document types. This project proposes an AI Smart Document Management System with Dynamic Field Extraction that leverages Deep Learning and modern web technologies to address these limitations. The system supports a broad range of document categories including invoices, contracts, medical records, and academic transcripts enabling intelligent, automated extraction of key fields without requiring predefined templates. Optical Character Recognition (OCR) powered by
Tesseract processes uploaded documents, while a Large Language Model (LLM) running through the Groq API performs context-aware, dynamic field extraction and document summarization. All documents are indexed and stored in MongoDB, with vector embeddings enabling semantic search across the repository. Users can perform natural language queries to retrieve relevant documents efficiently, bypassing traditional keyword-based search limitations. The backend is developed using FastAPI for scalable and asynchronous API handling, while the frontend is built with React.js for a modern, responsive user experience. Authentication and session management are secured using JWT tokens. The system further incorporates AI-assisted summarization and an intelligent assistant for document-level querying. By combining OCR, LLM-driven extraction, and semantic retrieval, this solution significantly reduces manual processing overhead and modernizes organizational document workflows.
Keywords:
Smart Document Management, Dynamic Field Extraction, Optical Character Recognition, Large Language Models, Semantic Search, Vector Embeddings
Kata Raju Reddy, Korada Ramya· International Journal of Sci...· 0 citations
The developed application is an example of the effective use of Artificial Intelligence in processing documents in regional languages and lays the groundwork for creating automated systems for document management.
Apoorva S., Usha B. S., S. Darshan· International Journal of Inn...· 0 citations