|
|
In recent years we
have seen an explosion in the development and availability of digital
devices of all sorts: personal computers, palm devices, wearable
computers,
digital tags, portable phones, and smart toys. Yet there has been no
corresponding
explosion in the development and availability of the software that
will
give these devices the ability to understand their real-world context.
These
things have no common sense.
The Semantic Agent Platform aims to create an agent framework
that will
allow users to communicate with intelligent communicative
software
agents through the use of natural language (English so far).
User-to-Agent
Natural Language Communication is provided based on UNL standards through the use of
an
enconverter/deconverter based on Thought Treasure Natural
Language Processing
Tool.
Agent-to-agent communication is implemented using technologies
provided
by FIPA-OS (which
implements
FIPA standards).
The Semantic Agent Application Server (SAAS) is able to process
symbolic knowledge through the use of extended
semantic networks that are able to store concepts, relations and
information
about actions. Actions are aggregated to the system through the use
of
software components such as Javabeans.
SAAS Knowledge Base
(SAAS-KB) is stored on a Ozone
OODB, which allows to import different ontology formats. Talk
Agents
default ontology (derived from Thought Treasure) includes about
20.000
concepts and 30.000 relations, which help the easy development of
new
context aware applications.
The resulting paltform will allow developers to create intelligent
agents
by simply adding new knowledge and behaviors (software components) to
the system. The Talk Agent Platform will also bring many benefits to
the
users by allowing them to interact with software agents in a simple
and
intuitive way.
|
|