The KIM Platform provides a novel Knowledge and Information Management (KIM) infrastructure and services for automatic semantic annotation, indexing, and retrieval of unstructured and semi-structured content. The most direct applications of KIM are:

• Generation of meta-data for the Semantic Web, which allows hyper-linking and advanced visualization and navigation;
• Knowledge Management, enhancing the efficiency of the existing indexing, retrieval, classification and filtering applications.

• A platform similar in purpose and usage to the RDBMS and KM systems;
• A 3rd party extension bundled with larger KM products (the OEM model);
• A web service, provided remotely with minimal installation and maintenance overheads.

As a base line, KIM analyzes texts and recognizes references to entities (like persons, organizations, locations, dates). Then it tries to match the reference with a known entity, having a unique URI and description. Alternatively, a new URI and description are automatically generated. Finally, the reference in the document gets annotated with the URI of the entity. We call this process (as well as the result) semantic annotation. This sort of meta-data can be used for indexing, retrieval, visualization and automatic hyper-linking of documents.

In order to allow the easy bootstrapping of applications, KIM is equipped with an upper-level ontology (PROTON) of about 250 classes and 100 properties. Further, a knowledge base (KIM KB), pre-populated with about 200 000 entity descriptions, is bundled with KIM. Its role is to provide as background knowledge (resembling a human's common culture) a quasi-exhaustive coverage of the entities of general importance - those, which are considered well-known and because of this, typically, not introduced in the documents. For this reason, their descriptions are hard to be automatically extracted.

From a technical point of view, the architecture allows KIM-based applications to perform automatic semantic annotation, content retrieval, based on semantic restrictions, as well as querying and modifying the underlying ontologies and knowledge bases.