Cognitive modeling apparatus for defuzzification of multiple qualitative signals into human-centric threat notifications

Abstract

The present design is directed to a system for defuzzification of multiple qualitative signals into human-centric threat notifications using cognitive computing techniques, including a series of periodic execution components configured to operate over full or partial sets of received data, and a plurality of event reception components configured to operate on each event in a stream relevant to a terrain and selectively provide information to the series of periodic execution components. The system detects and signals anomalies upon detecting behavior inconsistent with normal behavior.

Description

[0001]The present application claims the benefit of U.S. Provisional Patent Application Ser. No. 62 / 397,866, filed Sep. 21, 2016, inventors Michael E. Cormier et al., entitled “Apparatus and Process for Analyzing and Categorizing the Behavior of Actors in an Environment,” and further claims the benefit of U.S. Provisional Patent Application Ser. No. 62 / 467,414, filed Mar. 6, 2017, inventors Michael E. Cormier et al., entitled “Cognitive Modeling Apparatus and Method Including Compute Servers, Statistical Modeling, and Relevancy Engine,” the entirety of both of which are incorporated herein by reference.BACKGROUND OF THE INVENTIONField of the Invention[0002]The present invention relates generally to the field of computing systems, and more specifically to computing systems employing cognitive modeling.Description of the Related Art[0003]Humans typically think about physical behavior using qualitative concepts, such as “risky” or “dangerous,” instead of a precise numerical value, such...

AI Technical Summary

Problems solved by technology

This process, if it exists at all, is both time-consuming and problematic because the numerical values for specific qualitative behavior criteria can vary considerably among different contexts.

While such systems can have benefits, one drawback is the inability to change attributes or criteria dynamically.

A further issue with available designs is the ability to process and operate on large amounts of data, such as data that appears to be relatively infinite.

It can also be difficult to scale the performance of multiple disjoint algorithms across an actor population, particularly when such an actor population is exceedingly large or apparently infinite.

Images