In IBM Watson Knowledge Studio, you train an Artificial Intelligence (AI) on specialist terms of your company or specialist area ("domain knowledge"). In this way, you lay the foundation for the automated text processing of extensive, specialized documents.
Entities and relations are first used to define a corpus that describes the terms and their interrelationships.
The defined corpus is then trained on existing documents: using a combination of dictionaries (containing fixed terms) and a graphical interface (in which subject matter experts mark the terms and relationships they know), the system is taught the domain knowledge. The activity can be divided among a team of subject matter experts until the AI is finally trained based on the specifications.
Definition of the use case
Our procedure is determined by the approach of first identifying the concrete use cases and challenges – technical and functional – with different workshops. Afterwards, the procedure and the selection of solution components are defined.
Identifying the effort
In the spirit of an agile project approach, it has proven useful to first create an "MVP" (Minimum Viable Product), which can be used to determine not only the technical feasibility, but also the technical effort required.
Know-how and expertise
We support our customers through broad know-how, intensive partnership with manufacturers and project experience.
Recognizing addresses, names, even credit card numbers, etc., is a basic function of modern AI systems à la Watson. But only the combination with technical terms enables the AI to analyze extensive, technical documents correctly, relevantly and thus valuable for the company. For example, article numbers in a common scheme, order quantities and prices that appear in ever similar constellations on an invoice. Or in other specialist areas where, for example, court decisions are analyzed according to "judgment", "plaintiff", "reasoning".
In this way, an AI model is created with which new, unknown – but similar – documents can later be read by the AI and automatically analyzed according to their content. Within the Watson cosmos, this model is integrated into the other modules "Watson Discovery" or "Watson Natural Language Processing" in order to always analyze the document inventory in the company during operations. This includes uncovering potential for recourse, processing invoices / orders automatically or processing damage reports.
We would be happy to advise you in a non-binding conversation and show you the potential and possible applications of IBM Watson Knowledge Studio for your company. Simply leave your contact details and we will get back to you as soon as possible.
