The main focus of the BII-Instiute research is the field of semantic and semiotic text analytics solutions. The question was, if there is a way to FINGERPRINT a full message, for example a whole unstructured text paragraph, with ist semantic content, but context related! That means the inherent semantic message of the text is set in relation of the context, which leads to a semiotic system. (SEMIOTIC)

Basics of semantic fingerprint

The words in each text are not accidentally placed the way they are, they are placed according to the generative grammar, rules of the used language. The theory of generative grammar, especially of naturally evolved languages, that considers grammar to be a system of rules that generate exactly those combinations of words which form grammatical sentences in a given language. Modern talking means; all words build a cloud wherefrom a human will recognize a message and meaning, if a human understands the concept of grammar in that language.

The right positioning of words in a text corpus builds a virtually weighted structure from where message and meaning, the intrinsic semantic, is understood.

BrainDocs™A.I. agents detect and understand concepts & ideas! They generalize concepts into knowledge.

Context related semantic (Semiotic)

Context-oriented semantics, better known as SEMIOTICS, is a general theory of signs and symbolism, as elements of communicative behavior, which is divided into the branches of pragmatics, semantics, and syntactics. Pragmatics stands for time and place / circumstance where the communication takes place, semantics for the content (meaning) of the message and syntax for the used characters for word formation in the mean.

Same syntax does not have to mean the same semantics!

A message with identical syntax has a different semantic meaning depending on when (time) and where (location) and under what circumstance (situation), this message was created.

The inclusion of pragmatics in the semantic and syntactic analysis of texts allows the content meaning of a text to be determined more precisely and qualitatively, this content can now also be generalized.

All words with focus on the BEARING WORDS are analyzed for their semantic relations, and context they are used, weighted and transferred into a word cloud structure wherefrom a virtually fingerprint graph forms up. This fingerprint graph is stored as logarithmic hash-code.

Semantic concept (generalizations; higher-level thinking)

Concepts occur as abstractions or generalizations from experience; from the result of a transformation of existing ideas; or from innate properties.
Concepts are defined as components of human cognition in the cognitive science disciplines of linguistics, psychology and philosophy. Concepts are used as formal tools or models in mathematics, computer science, databases and artificial intelligence where they are sometimes called classes, schema or categories.

Sometimes concepts are known by other names in everyday language such as "kinds", "types" or "sorts", as in "Chamomile is a kind of tee", or "A SUV is a kind of a car".

Generalizations and higher-level thinking are the key for humans for superior and complex decision making. Innovation, creativity, science, research and development, the questioning about the next and unknown, all finds its motivation in the fact that our brain always thinks in higher-level. Like a flywheel, the brain tries to connect, understand and explore all data and information we receive and store. Understand concepts means generalizing the gathered knowledge and trying to apply it in other occasions or situations for solution solving in any kind of life circumstances. 

Advantage of semantic fingerprints

The concept of the semantic fingerprint is reducing the challenge of handling semantic concepts and messages to get communication between machines and men, making machines simpler and faster.

With the generative semantic hash-code, containing neutralized message concepts, the barriers between languages can be overcome very simply.

By adding on further codes the hash-code not only contains the complex message, it also contains the action commands if the matching with other codes have a certain result. So, the hash-code turns into a “function” or a smart machine.

Copyright © by BII-Institute 2013-2017,