Reportbrain Platon

Machine Learning & Text-Analytics to drive knowledge for smart business

Named after the Greek philosopher “Plato” (Greek: Πλάτων), Reportbrain Platon is the world’s first cognitive computing platform that simulates human thought processes in scale by comprehending text in multiple languages to interlinking small pieces of seemingly unlinked information found throughout the internet to augment knowledge.

Reportbrain Platon incorporates proprietary technologies including

Entity Extraction
Entity extraction adds semantic knowledge to content, enabling quicker understanding of the subject of the text. Entity extraction identifies people, companies, organizations, cities, geographic features and other typed entities from HTML, text or web-based content, such as the news articles.

Data Interlinking
It connects and exposes further semantic meaning to data. Linked data extend the knowledge in text documents, by setting semantic links between data from different sources. Therefore, this enables any content to be brought effectively into the semantic web.

Topic & Concept Identification
Topic Detection identifies topics and concepts, in a manner similar to the way humans classify information. It uses high-level text analysis, to make sophisticated abstractions and help understand how concepts relate. Additionally, it identifies concepts that aren’t necessarily directly referenced in the text.

Relation Extraction
Relation extraction is used to identify and amplify signals, key events and other important activities. Relation extraction currently performs the identification of the strongest relations between Persons and Organizations. It parses each sentence into subject, action and object form and then matches semantic information, such as entity extraction, keyword extraction, sentiment analysis and location identification.

Taxonomy Classification
Taxonomy Classification categorizes text, HTML or web-based content, into a hierarchical taxonomy, using complex statistics and natural language processing technology. Content is classified into a few levels deep, allowing to use more accurate and lucrative segmentation and better decision-making. Taxonomy classification can help filter and group content before performing further analysis, to track the high-level topics of documents first.

Sentiment Analyzer
Sentiment Analyzer examines the attitude, opinion or feeling toward a person, organization, product or location. Sentiment analyzer identifies the positive or negative sentiment within any document or webpage, computing document-level sentiment, sentiment for a user-specified target, entity-level sentiment, quotation-level sentiment, directional-sentiment and keyword-level sentiment. The algorithm identifies positive or negative connotations, as well as the person, place or entity to which it refers.