Concept Trees: Indexing and Memory from Semi-Structured Data

This paper describes a method for creating structure from heterogeneous sources, as part of a concept base, or other information database. ‘Concept trees’ can grow from the heterogeneous sources when correct and consistent sequences of concepts are presented. The method maintains the key requirement of generality, allowing it to be used as part of a generic framework. The nature of the method also means that some level of optimisation or normalisation of the concept base will occur. The method also provides memory and indexing structures, to allow for more complex concepts to be stored and accurately retrieved, possibly as part of a more cognitive model.