and flexible
in handling

semantha® can be used directly with already existing user interfaces of course you can also extend existing systems in your IT landscape with semantic functions. For this purpose semantha® offers a comprehensive REST-API.

The platform

Our platform semantha® provides flexible web services that you can use out-of-the-box for semantic processing of text documents and data extractions. Depending on the application, these services can be combined as desired. In many cases, one of our applications is already sufficient - for example, for a hotspot analysis or a direct comparison of documents. Furthermore, we make all analyses available via a standardized REST interface. With it, semantha® can be optimally used for your application and integrated into your process and IT landscape.

The semantha® Analyzer can search your entire documents for relevant topics (hotspots) and highlight all applicable areas in no time. The hotspots are specified by the user in any desired formulation. If you like, you can export the results as Excel or PDF file.
The semantha® Compare user interface is used for the display and user-guided revision of a semantic comparison. Missing contents/paragraphs can be displayed directly or differences in the paragraphs can be displayed visually. To make recurring comparisons more efficient, intermediate results can be saved.
semantha® Requirements supports the evaluation of new specifications. Based on historical specifications semantha® takes over the classification of requirements, the identification of risks and the cross-reference to external standards and other applicable documents. Through this input, the requirements process gains in efficiency and quality.


Interface (REST API)

All semantic services of semantha are accessible via a JSON-based REST API and can thus be integrated into any other services. Developer documentation is included in each server component. An API key is required to use the API.

File formats

With semantha any file formats containing written text can be processed. These can be text documents (.docx, .txt, .xml, .json), tables (.xlsx) or PDF documents (.pdf). It is also possible to read in more specific formats, such as the XML-based ReqIF format. Other XML formats can be read in configuratively using xslt. Furthermore, it is possible to import the container format Zip and to import all documents in it en bloc.

Extraction / Further processing

Results can be displayed and analyzed directly in the application. Alternatively, they can be exported as commented PDF files or Excel tables. If you want to further process the results you are looking for in another software, they can also be extracted directly.

Der Document Annotator (Dokument-Typen)

The majority of documents processed with semantha are PDF files today. However, in PDF documents, in comparison to other formats such as Word documents (.docx), no document structure can be read out, such as headings, paragraphs, etc. In order to better understand the structure and layout of a PDF file, we have developed the Document Annotator.

The Document Annotator can be used to visually combine documents of the same type, such as package inserts, quotation letters, etc. into one document type. The annotator is taught using sample documents. Here, methods of artificial intelligence (AI) from the field of machine learning (ML) are used to create a document-type model. This model is then applied to new unknown documents of this type to better recognize the document structure. This then helps in the future processing of such documents with semantha, so that they can be processed semantically in an optimal way. 

Additionally, you can also set a document type to ignore certain pages of a document (for example: always ignore the cover page.) or to read only a certain area on the pages (only the upper half of the document or only the right column of a document, e.g. for bilingual documents etc.).


Data protection concept

Our IT security concept provides for a strict separation of our customers' data areas - more precisely even within customers if they host different domains with us. Access is only possible with an API key that grants access to a fixed set of domains. The data transmission is encrypted - without exception!


Not least because our customers process sensitive and in some cases personal data with semantha, we attach great importance to IT security and data protection. We conclude appropriate agreements with our customers and work in compliance with GPDR. We will be happy to answer any questions - you can reach our data protection officer at


EU Hosting

Unsere Software wird ausschließlich auf Servern in der Europäische Union gehostet. Die Rechenzentren unserer Service Provider sind nach ISO 27001 zertifiziert und garantieren ein hohes Maß an Sicherheit und eine sehr hohe Verfügbarkeit.


An extract from our customers

  • Gothaer Versicherungen

    Die Gothaer Gruppe ist eine deutsche Versicherungsgesellschaft mit rund 4,1 Millionen Mitgliedern. Kerngeschäfte sind alle Versicherungsdienstleistungen. Zu den Kunden der Gothaer Allgemeinen Versicherungs AG zählen Privatkunden sowie kleine und mittlere Unternehmen.
  • HELLA GmbH & Co. KGaA

    Die HELLA GmbH & Co. KGaA ist ein börsennotierter, international operierender deutscher Automobilzulieferer mit Hauptsitz in Lippstadt, Nordrhein-Westfalen. Die Kerngeschäfte des Konzerns gliedern sich in drei Segmente: Automotive, Aftermarket und Special Applications.
  • experimenta gGmbH

    Unter dem Motto „Wissen schafft Erleben“ vermittelt die experimenta seit 2009 Kindern, Jugendlichen, Schulklassen und Familien auf einzigartige Weise naturwissenschaftliche und technische Themenfelder.

Im Vergleich zu anderen KIs, ist die CO2-Bilanz von semantha® um ein vielfaches besser.

Das FORBES Magazin beschreibt uns mit den Worten "Hirn mit künstlicher Intelligenz".