Functional presence engine

A Functional Presence Engine, or FPE, is a probabilistic parsing mechanism that uses at least four components to respond to input patterns. It comprises a lexing system, a probabilistic fitness function, a knowledge base, and a set of functions that the knowledge base can trigger.

The lexing system accepts and parses inputs and or query patterns. The fitness mechanism determines close approximations and viable responses to the input patterns from a given knowledge base and then selects one or more functions that produce appropriate responses. A Functional Presence Engines can subsequently respond to queries that are not discreetly available in their knowledge base but have a high likelihood of being mathematically near the correct answer. In essence, it is a stimulus-response engine that allows for a higher variability of inputs to elicit response patterns with a high likelihood of correctness, even from incomplete training.

Such systems allow chatbots and virtual assistants to respond correctly to new inputs outside their training sets, The US Army's Sgt Star being one example. The system is widely used for intelligent customer service systems and for digital assistants. FPEs have also been deployed as black-box solutions and embedded in security appliances.

The first Functional Presence Engine was deployed in 2001 by SpectreAI, LLC. The technology and a number of embodiments were subsequently patented by Robert Hust (its original inventor) and Mark Zartler (SpectreAI's lead developer).

The development of the FPE also resulted in an obscure markup language that the company referred to as FPML (Functional Presence Markup Language), which was based largely on AIML (Artificial Intelligence Markup Language).

The FPE and similar derivative mechanisms have become a common deployment method for conversational AI and intelligent decision support systems.

The original FPE and FPML are proprietary technologies deployed and owned by Verint Systems.