Enterprise Europe Network

Solution for data extraction and digitalization of any document

Country of origin:
External Id: 
Last update
Expiration date


Partner keyword: 
Archivistics/Documentation/Technical Documentation
Data Processing / Data Interchange, Middleware
Databases, Database Management, Data Mining
Banks/financial institutions software
Insurance related
Other finance, insurance and real estate


A Spanish company, specialized in data capture process digitalization, has developed a proprietary solution that extracts and digitalizes any relevant data from any document. It allows businesses to switch from any manual data extraction process to an automatized one that provides remarkably higher efficiency. The company is looking for license agreements.



Document Processing is a critical capability for the world´s best performing companies. Every business today must deal with massive volumes of data, most of which is unstructured and locked in documents.

Solutions so far, like manual data entry and latest RPA (Robotic Process Automation) systems are totally insufficient when trying to scale to millions of documents and process natural language style written documents, respectively.

In this challenging context, the Spanish company has developed a syntactic-semantic engine based on a hybrid approach that combines statistical with symbolic processing.

The solution provides digitalization for any data process that is carried out by manual data entry. It classifies and extracts any data from any document according to the taxonomy needed for each project.

Main solution features are the following:

-Deployment modalities: On premise or on cloud
-Integrability: It can be integrated with various repositories, document management systems, BPM (Business Project Management) solutions, RPAs (Robotic Process Automation), etc.
-It can work with any OCR (Optical Character Recognition) system.
-It supports natively all main European Languages: English, Spanish, German, French, Italian, Portuguese, among others.
-It is based on NLP (Natural Language Processing) technology and AI (Artificial Intelligence) and supervised learning is applied in order to achieve high success rates from the beginning.
-The data extraction success ratio exceeds 95%. and the document classification exceeds 98%.

The solution is specially useful for those sectors that manage huge amounts of manual data classification and extraction such as banking, insurance, real estate, etc.

The company has already successfully deployed its solution in many of the main Spanish business players, mainly in the sectors mentioned above, and now is ready to start its international development through ICT integrators under license agreements.

Advantages & innovations

Cooperation plus value: 
Main solution advantage, compared with similar solutions in the market is its ability to extract data from non-standardized document such as, for example, a public deed. On the other hand, other solutions in the market only can extract data from standardized documents such as, for example, the energy bill.

Stage of development

Cooperation stage dev stage: 
Already on the market

Partner sought

Cooperation area: 
In order to start its international business development, the company is looking for international ICT integrators willing to cooperate under license agreement. The partner sought will preferably have a good network of contacts within sectors such as banking, insurance or real estate and its role is to commercialized in within a defined area.