ABBYY has been awarded 22 new patents covering technologies used in document processing, citing growing interest in specialized approaches to processing business data as the adoption of generative AI grows.
With this addition, ABBYY’s portfolio now has more than 400 patents and patent applications worldwide. The company develops software for document process automation and related analytics, and has offices in Singapore and Australia alongside its headquarters in Austin, Texas.
Newly issued patents include language detection, user interface design, image identification, information extraction, and document decoding. ABBYY said the research behind it was done over five years and the patent was issued in the past two years.
document focus
Several patents relate to the extraction and structuring of information from document images, a common requirement in fields dealing with large volumes of forms, correspondence, invoices, billing documents, and identification materials.
ABBYY highlighted patents such as “Extraction of multiple documents from a single image” and “Detection of fields within document images.” These methods belong to the broader field of combining optical character recognition with classification and data capture.
ABBYY also pointed to patents that cover associations between data points in documents, such as “Identifying key-value associations in documents using neural networks.” The other, “continuous learning for document processing and analysis,” involves systems that adapt to changes in document formats and inputs.
Batch also includes user interface work. ABBYY cites a “display panel or portion thereof with a graphical user interface” and focuses on how document automation tools display information for review and exception handling.
image decoding
Two of the patents focus on processing images and barcodes under less controlled conditions: “Decoding two-dimensional barcodes under adverse conditions” and “Assessing image quality for optical character recognition using machine learning.” These issues often occur when organizations capture documents on mobile devices or ingest scans with varying resolutions, lighting, and alignment.
Document AI suppliers are increasingly positioning image quality assessment and robust barcode decoding as part of front-end capture. Poor input quality can increase manual review and increase the risk of extracting incorrect data.
GenAI Risk
ABBYY framed the new patent in the context of enterprise use of generative AI, where companies weigh potential productivity gains against accuracy concerns, auditability, and regulatory expectations. The company describes its efforts as “purpose-built AI” for documents and business processes, and positions the approach as a way to deliver accurate output in line with compliance standards.
Document workflows remain a major source of operational and compliance risk for many organizations. Errors in extracted fields can impact downstream systems in finance, procurement, customer onboarding, and billing. Regulated industries in particular face pressure to demonstrate how automated decision-making and data collection steps are generated.
ABBYY said its customer base includes more than 10,000 companies and has 35 years of experience in document and process automation software.
Software-related patent grants are often closely scrutinized. ABBYY stated at the beginning of the announcement, without citing sources, that the acceptance rate for technology patents is approximately 55%.
ABBYY CEO Ulf Persson linked the patent award to the company’s product direction.
“ABBYY’s latest patent is a testament to our ability to drive next-level innovation. By combining cutting-edge AI with intelligent document processing and a deep understanding of business needs, we are shaping the future of intelligent automation and delivering solutions that help businesses grow in an ever-evolving environment,” said Ulf Persson, CEO of ABBYY.
ABBYY will be showcasing its products at ABBYY Ascend events in Nashville and Brussels this spring.
