Loading article...
Loading article...
Stream/Area:
-
Subject:
-
Paper ID:
IJSREM69119
Volume:
10 |
11 |
Nov 2026
Pages:
1-5
Publication Frequency:
Monthly (12 issues per year)
License:International Journal of Scientific Research in Engineering and Management follows the Creative Commons Attribution 4.0 (CC BY 4.0) License, allowing free use and distribution with proper attribution.

department of computer engineering
svpm college of engineering

department of computer engineering
svpm college of engineering

department of computer engineering
svpm college of engineering

department of computer engineering
svpm college of engineering

department of computer engineering
svpm college of engineering
Organizations receive invoices as structured electronic messages, digitally generated PDFs, scans, and sometimes photographs. Manual handling across these formats can delay payment, introduce keying errors, and make policy checks difficult to scale. Recent document AI combines optical character recognition (OCR), layout analysis, language models, and workflow rules to extract invoice fields and line items. Yet reliable automation requires more than reading text: it must reconcile totals, match purchase orders and receipts, route exceptions, preserve evidence, and post approved records to financial systems. This paper surveys AI-powered invoice automation across document intake, field and table extraction, validation, exception handling, and enterprise integration. It compares rule-based, machine-learning, multimodal-transformer, and structured e-invoice approaches, then presents a modular framework with human review and audit controls. We outline evaluation measures for extraction, workflow quality, and operational risk, and identify open challenges in generalization, privacy, fraud detection, and compliance. This paper proposes a framework and evaluation plan; it reports no original system performance results. .
KEYWORDS
AI-powered invoice automation combines OCR, layout-aware extraction, multimodal document models, structured e-invoicing, and workflow rules. The main challenge is not simply reading a document; it is converting evidence into a valid, matched, approved, and traceable financial record. This survey organized the field around input formats, extraction approaches, validation, and enterprise workflow, and proposed a modular framework that preserves human review and accounting controls. Reliable deployment depends on representative evaluation, line-item accuracy, supplier-aware testing, secure integration, and clear separation between model suggestions and authorized business decisions.
1. Saout, T., Lardeux, F., Saubion, F.: An Overview of Data Extraction From Invoices. IEEE Access 12, 19872–19886 (2024). https://doi.org/10.1109/ACCESS.2024.3360528 2. Ha, H.T., Horák, A.: Information Extraction from Scanned Invoice Images Using Text Analysis and Layout Features. Signal Process. Image Commun. 102, 116601 (2022). https://doi.org/10.1016/j.image.2021.116601 3. Palm, R.B., Winther, O., Laws, F.: CloudScan: A Configuration-Free Invoice Analysis System Using Recurrent Neural Networks. In: Proc. 14th IAPR Int. Conf. on Document Analysis and Recognition (ICDAR), pp. 406–413. IEEE (2017). https://doi.org/10.1109/ICDAR.2017.74 4. Xu, Y., et al.: LayoutLM: Pre-training of Text and Layout for Document Image Understanding. In: Proc. ACM SIGKDD, pp. 1192–1200. ACM (2020) 5. Huang, Y., et al.: LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking. In: Proc. ACM Multimedia. ACM (2022) 6. Kim, G., et al.: OCR-free Document Understanding Transformer. In: Proc. ECCV (2022) 7. Jaume, G., Ekenel, H.K., Thiran, J.-P.: FUNSD: A Dataset for Form Understanding in Noisy Scanned Documents. In: Proc. ICDAR Workshops (2019) 8. Park, S., et al.: CORD: A Consolidated Receipt Dataset for Post-OCR Parsing. In: Proc. Document Intelligence Workshop, NeurIPS (2019) 9. Hamri, M., Devanne, M., Weber, J., Hassenforder, M.: Document Information Extraction: An Analysis of Invoice Anatomy. Appl. Comput. Intell. Soft Comput. (2024), Art. 7599415 10. OASIS: Universal Business Language Version 2.4. OASIS Standard (2024)
Publication Date
11/17/2026
Peer Review Type
Double-Blind Peer Review
Review Rounds: 2
Documents
Article Views
0
Total views since publication
PDF Downloads
0
Total downloads since publication
Geographic Reach
5
Digital Preservation: This article is permanently archived on Zenodo and complies with all data preservation standards across major indexing platforms.
Plagiarism Screening
This manuscript has been checked for plagiarism using TurnitinPlagiarismChecker software.
Conflict of Interest
The authors declare no conflict of interest related to this research work.
Funding Information
No funding information available for this research.
Related research in the same subject area
Loading similar articles...