Press Release

Doculayer 2.0 supports companies with automating document processing at record speed

New features include advanced table extraction, autoML-based document classification and enhanced anonymisation and pseudonymisation functionality

The Hague, 2 September 2021 -, a solution for the intelligent processing and analysis of document flows based on AI and machine learning, introduces Doculayer 2.0, a significant update to its AI platform. The new version of the platform includes advanced table extraction, autoML-based document classification and extended anonymisation and pseudonymisation functionality. With the new update, supports organisations to get unprecedented value from their documents at record speed.

Richard Smit, CTO and co-founder of "Organisations are increasingly using 'automation' as part of their digital transformation strategy. Their goal is to become less dependent on manual work, to reduce costs and to distinguish themselves from the competition. Fast ROI is also becoming increasingly important. This requires solutions for intelligent document processing that can be implemented quickly and deliver results in no time. This is exactly what we want to achieve with Doculayer 2.0."

Doculayer 2.0 contains a large number of innovations. The most significant improvements can be divided into optimized document digitisation (intelligent OCR), document classification, data extraction and integration.

Document digitisation (intelligent OCR) 
Doculayer 2.0's built-in Optical Character Recognition (OCR) engine has improved pre-processing functionality. As a result, documents are optimally prepared for processing by the OCR-engine. This provides up to 99 percent accuracy when digitising documents. Doculayer 2.0 also enables direct reading of data from the Machine Readable Zone (MRZ) of identity documents such as passports. This allows the accuracy of the extracted data to be verified immediately, increasing the reliability even further.

Document classification
In Doculayer 2.0, it is a lot easier to manage the classification models generated by machine learning. The dashboard now allows you to go back to previously saved classification models. This makes it easier to select the most efficient model. The optimal algorithms and parameter settings are now automatically selected via autoML. This makes document classification in Doculayer 2.0 easier to configure and maintain.  

Data extraction
Tables are often difficult to understand for automated document processing software. Extracted data often lack context, making documents containing tables unreadable. As a result documents with a lot of tabular data, such as financial reports, invoices and contracts, often have to be processed manually. With the new table extraction functionality, these documents can also be processed automatically resulting in time savings of over sixty per cent. 

The new 'Named Entity Recognition (NER)' functionality detects personal data such as names, addresses and social security numbers and makes it possible to anonymise or pseudonymise them immediately making it easier for companies to comply with privacy legislation.

Picture: detection of data in a text. Doculayer 2.0 offers the option of anonymising these data or replacing them with other data (pseudonymisation).

Besides integration with existing environments, Doculayer 2.0 now also integrates with Office 365. Attachments in an Office 365 environment can be automatically processed in Doculayer 2.0.

Doculayer 2.0 is immediately available for Doculayer customers, both on-premise and in the cloud. Please contact Doculayer for more information about all the new features in Doculayer 2.0.

About is a solution for intelligent processing and analysis of document flows, based on AI and machine learning technology. can automatically analyze, improve, enrich and make findable large amounts of data. integrates seamlessly with business applications and processes in the existing IT landscape and can process unstructured information in existing IT systems. The company responds to the explosive growth of information and the actions required to process data correctly, in accordance with privacy legislation (GDPR). For more information, visit

Like this? Share it with everyone: