<?xml version="1.0" encoding="utf-8"?>
<?xml-stylesheet href="client.xsl" type="text/xsl"?>
<article article-type="other">
<front>
<journal-meta>
<journal-id/>
<issn/>
<banner>
<!--<href>banner.jpg</href>-->
<size width="100%"/>
</banner>
</journal-meta>
<article-meta>
<title-group>
<article-title>Filters for Semantic Service Composition in Service-oriented Multiagent Systems</article-title>
</title-group>

<author><a href="mailto:alberto.fernandez@urjc.es"><name>Alberto Fern&#225;ndez</name></a></author>
<aff>Universidad Rey Juan Carlos, Tulip&#225;n s/n, 28933, M&#243;stoles (Madrid) - Spain, +34 91 488 7084</aff>

<author><a href="mailto:sascha.ossowski@urjc.es"><name>Sascha Ossowski</name></a></author>
<aff>Universidad Rey Juan Carlos, Tulip&#225;n s/n, 28933, M&#243;stoles (Madrid) - Spain, +34 91 664 7485</aff>

</article-meta></front>
<body>
<abstract>
<title>ABSTRACT</title>
<p>In Service-Oriented MAS middle-agents provide different kinds of matchmaking functionalities. If no adequate services are available for a specific request, a planning functionality can be used to build up <italic>composite</italic> services. In order to take advantage of recent advances in the field of AI planning for this purpose, we propose exploiting organisational information of Service-Oriented MAS to heuristically filter out those services that are probably irrelevant to the planning process. We present a novel framework for service-class based filtering and show how it can be instantiated to a particular MAS domain based on organisational information.
</p>
</abstract>
<fpdf>
<href>pdflogo.jpg</href>
<hpdf>AAMAS07_0423_13f8042c6c91617956501ee1f03c192e</hpdf>
</fpdf>
</body>
</article>

