We use Transfer Learning with ULMFiT especially for our information extraction solutions. The main advantage is the small amount of data required to train the Deep Learning Model. Transfer Learning is one of the most important techniques used in the field of Deep Learning applications today. It is about the transfer of learned knowledge from a general to a specialized AI model.

Filing a document. With this project we show that it is possible to learn documents of different origin and type from a filing system in a secretary's office (default to filing) and to apply it to new documents.

Coupling between SAP and BIM system. We create the accuracy in the DIN booking key in the construction information system that it needs, starting from a general contractor invoice.

In order to provide development in construction investment with suitable offers more quickly, an AI-based preliminary decision (analysis platform) is to be used to achieve a significant decision throughput with the same personnel.

The customer wanted to know if types can be identified from the existing construction data material. This can be used to estimate the next step for the evaluation of typical basic assumptions and building types in order to be able to make an investment forecast.