Download presentation
Presentation is loading. Please wait.
Published byCatherine Fields Modified over 9 years ago
1
Non-holistic Agents A project idea Patrick De Causmaecker
2
23-11-00Semantic Web Technologies Workshop, Luxembourg, Patrick.DeCausmaecker@kahosl.be 2 Who we are Research group within Kaho St-Lieven in Ghent, Belgium Research group within Kaho St-Lieven in Ghent, Belgium Four years of technology transfer research in agents technolgy Four years of technology transfer research in agents technolgy Sponsored by the Flemish government Sponsored by the Flemish government
3
23-11-00Semantic Web Technologies Workshop, Luxembourg, Patrick.DeCausmaecker@kahosl.be 3 Agents Agents are specialised in one problem domain Agents are specialised in one problem domain They are not designed to understand the whole business model of an application they are visiting They are not designed to understand the whole business model of an application they are visiting They have a thorough understanding of their own field, and bear a model of this field (ontology) They have a thorough understanding of their own field, and bear a model of this field (ontology)
4
23-11-00Semantic Web Technologies Workshop, Luxembourg, Patrick.DeCausmaecker@kahosl.be 4 Holistic systems The applications they are visiting may be holistic or not The applications they are visiting may be holistic or not In general, they have to communicate with a set of applications, more or less integrated, which do solve the actual automation problem of the business In general, they have to communicate with a set of applications, more or less integrated, which do solve the actual automation problem of the business In this sense they visit a system bearing a model of the business In this sense they visit a system bearing a model of the business
5
23-11-00Semantic Web Technologies Workshop, Luxembourg, Patrick.DeCausmaecker@kahosl.be 5 Agents on foreign territory Agents are designed to serve Agents are designed to serve They must apply their specialised knowledge to boost the performance of their client systems They must apply their specialised knowledge to boost the performance of their client systems The model of their specialisation will in general not fit into the application set of the client The model of their specialisation will in general not fit into the application set of the client They have to be able to find the crucial hooks in the client application They have to be able to find the crucial hooks in the client application
6
23-11-00Semantic Web Technologies Workshop, Luxembourg, Patrick.DeCausmaecker@kahosl.be 6 Goal of the proposal For this they need a mapping methodology For this they need a mapping methodology One side of the mapping is the system of the client One side of the mapping is the system of the client The other side is the domain model the agent is carrying The other side is the domain model the agent is carrying This model may be a (thin) ontology enabling the agent to communicate with other agents from the same domain This model may be a (thin) ontology enabling the agent to communicate with other agents from the same domain
7
23-11-00Semantic Web Technologies Workshop, Luxembourg, Patrick.DeCausmaecker@kahosl.be 7 Goal continued The client system will look as a chaotic set of data to the agent The client system will look as a chaotic set of data to the agent The mapping will require other knowledge and expertise about the business domain than the agent knows about The mapping will require other knowledge and expertise about the business domain than the agent knows about The agent may have to build on previous experiences and will be a learning machine The agent may have to build on previous experiences and will be a learning machine It will perform an analysis of the system in which it arrives It will perform an analysis of the system in which it arrives
8
23-11-00Semantic Web Technologies Workshop, Luxembourg, Patrick.DeCausmaecker@kahosl.be 8 Technological Domains Intelligent agents, mobile or not Intelligent agents, mobile or not Rule based systems Rule based systems Machine learning Machine learning Ontology building Ontology building –See related proposal “An ontology for planning applications” by Peter Demeester Data mining Data mining
Similar presentations
© 2024 SlidePlayer.com. Inc.
All rights reserved.