MindCite’s innovative Citer® Platform is used by many government and private organizations to tackle this challenge. Citer® can automatically gather information from many sources: Internet, Intranet, e-mail, Office Documents, databases and more, analyze them by attributing meta-data to each information-item, and then store this information in a searchable repository.
Users can use Citer® as a single-point-of access to information from disparate sources, based on their organizational privileges. They can keep-track in near-real-time on new information that appears on the web to rapidly locate opportunities (new enders, new ventures) or new threats (competitors, changes in legislation).
Users are presented with feature-rich, easy-to-use tool that puts relevant information at their fingertips, just when they need it.
MindCite employs a ground-breaking approach to information gathering, analysis and retrieval. The foundation component of the framework is called the Ontology. The Ontology is a formal definition of a body of knowledge. It is a way to allow humans and computers communicate bits of knowledge with each other.
The ontology retains information about entities (People, Organizations, Locations etc.) and the associations between them. The Ontology is an embodiment of the organizational knowledge that can be viewed, queried and visually navigated by knowledge workers.
The ontology is also used in each one of the platform subsystems, to better focus the information accessed around the organization and user domain of knowledge.
The Citer Platform is an all-Java software package deployable on a myriad of infrastructure contexts, operating-systems and databases. The Citer platform is comprised of the following main technological modules and capabilities:
Ontology-Focused Internet Crawler: A high-performance internet crawler which chooses the link-traversal order using the semantics encapsulated in the Ontology.
Metadata Extraction Module: Based on Natural-Language-Processing (NLP) technologies, this module can extract keywords and key phrases from documents and attribute an ontology-inclined content-summary to documents (abstract), among other types of fields that can be extracted. This analysis capability is available for almost 20 languages.
Search-Engine Module: the platform includes a powerful multilingual search-engine.
Classification and Categorization tools: The platform includes several tools for manually, semi-automatically and automatically classify and categorize information in order to streamline retrieval.
Ontology Tools: Ontology-Server is an enterprise-class Ontology-Store which can retain information on large amounts of entities and the associations between them, it can be accessed simultaneously by many users and it also provides ontological-insight to the Crawler and Metadata-Extraction modules. Ontology-Editor is an Ontology manipulation tool which also includes powerful visualization capabilities for Social-Network-Analysis (SNA).
Profiler: The Profiler is a component which is capable of matching a single-document against a large (Over 50,000) set of queries instantly. It can be used for rapid real.
