Automatic knowledge recontextualization
The concept of generating a kSig or kThread to retrieve relevant results and organize them around the discovery context while fabricating a number of other semantic operator and viewing knowledge objects can be referred to as contextualization. Meanwhile, the process of using the retrieved and ordered context within the Knowledge Sweetspot of results to regenerate subsequent queries on a recursive basis and contextualizing those results can be referred to as recontextualization.

Recontextualization is a key semantic operator required to facilitate knowledge hunting where the information takes on the property of reflexivity (self-awareness), paving the way for a self-generating knowledge inferencing engine, fed by the very knowledge it hunts. Here causal reasoning that reflects induction through forward chaining, rendered as outcome trees in a Baysean or Management Decision Tree metaphor, and deduction through backward chaining on the very same outcome tree can be leveraged for capturing behavioral rules that approximate best practices and collaborative patterns against planned knowledge curriculums.

In such an architecture, outcome trees can be automatically rendered on the fly, captured, and monitored by abstract policies like rules that have a relevancy above 60% where relevancy is a goodness of fit pattern-based semantic similarity, monitored through intelligent self-aware data.

To be continued...
In the next article in this series we will address the concept of leveraging how you think, using multiple semantic perspectives so that you can gain a faster and deeper understanding and utility of the knowledge tapped within large document collections that can be brought to focus on your problem and your personal learning styles automatically.