CARROT II: Collaborative Agent-based Routing and Retrieval of Text
September 20, 2001
We describe CARROT II (C2), an agent-based architecture for distributed information retrieval and document collection management. In C2, agents pro vide search services over local document collections or information sources. A C2 system can consist of an arbitrary number of agents, distributed across a variety of platforms and locations and integrating widely varying information sources. C2 agents advertise content-derived metadata that describes their local document store; this metadata is sent to other C2 agents, which agree to act as brokers for that collection - every agent in the system has the ability to serve as such a broker. A user query is sent to any C2 agent, which can decide to answer the query itself from its local collection or to send the query on to other agents whose metadata indicate that they would be able to answer the query or send the query on further. Search results from multiple agents are merged and returned to the user. C2 can be used to implement a wide variety of distributed information services, such as common single-stage web metasearch or Harvest-style brokering, as well as more sophisticated collection selection and ranking algorithms. C2 differs from similar systems in that metadata takes the form of an unstructured feature vector and that any agent in the system can act as a broker, so there is no centralized control. Furthermore, the agent architecture uses a sophisticated agent communication language for information ex change, opening the door to sophisticated coordination algorithms among C2 agents. Search abilities are further enhanced with the integration of tools and ideas from the Semantic Web effort.
Downloads: 46 downloads