Skip to content

Solutions

Document and Knowledge Intelligence

Understanding documents instead of merely reading them: archives, files, and technical documentation become structured knowledge you can query.

Screenshot of an editing tool: in the centre the scanned page of a course catalogue with highlighted sections, on the right the courses captured from it with title, time, and lecturer
Our review tool: the structure on the left, the scan with detected sections in the centre, the captured entries on the right.

Benefits

  • Knowledge stored in archives becomes findable and comparable
  • The experiential knowledge of individual people becomes accessible to the organisation
  • Answers name their source references and remain verifiable

Functions

  • Capture the document as a whole: detect page types, create a profile
  • Capture individual fields: titles, names, places, years, tables
  • Match names, places, and spellings against reference data
  • Cross-check with alternative contexts; remaining uncertainty becomes visible
  • Expert approval by humans and controlled export

Who it is for

Companies and organisations with document-intensive processes, large archives, or distributed experiential knowledge.

Integration

A single language or vision model does not reliably resolve ambiguities in names, places, and spellings. Only the combination of model, knowledge base, and normalisation delivers a robust result.

A document is not a collection of letters. It is a multimodal object made of text, images, characters, and layout, and much of its information becomes understandable only in the overall context.

Examples from our work

ExampleWhat the system does
Historical music printsDetect page types; capture title, composer, publisher, printer, dedication, and year and match them against the Integrated Authority File (Gemeinsame Normdatei, GND)
Course cataloguesScans from several decades: automatic cropping, layout analysis, text recognition with a vision-language model, human review, export
Concert programmesLarge volumes of highly varied documents: analysis, structuring, database, plausibility check, export
Early modern ordinance in Kurrent scriptTranscription, scribe profile, normalisation of places and persons, uncertainty statements with justification
Household encyclopedia of 1728Transcription and knowledge assistant: questions in natural language, answers with the specific source references

For technical documentation, we describe the same approach using machine tool manufacturing as an example: Document Intelligence for Mechanical Engineering.

Further topics

AI Services

AI Development

We develop the methods that turn your data into reliable results: machine learning, AI pipelines, agents, multimodal analysis, and hybrid models.

AI Services

AI Integration

AI becomes usable where the work is done: as a function in existing software, as an interface, or as a separate application in your system landscape.

AI Services

AI Environments

The environment in which your AI is allowed to work: model access, data connection, access rights, and operations, as the foundation for every further application.

AI Technologies

Document & Knowledge Intelligence

Making large, heterogeneous bodies of information accessible and turning unstructured information into knowledge models that are usable for the business domain.

AI Technologies

Agentic AI

Individual model calls become controllable systems based on a division of labour: specialised agents handle subtasks, use tools, and work together in verified workflows.

AI Technologies

Multimodal AI

Every data source has its strengths and limits. The result becomes reliable when text, images, audio, sensor data, and geodata are interpreted together.

Would you like to make AI usable in your company?

Whether a first AI adoption or a complex development task – we discuss the requirements and suitable next steps with you.

Discuss your AI project