KRAFT: An agent architecture for knowledge fusion

Knowledge fusion refers to the process of locating and extracting knowledge from multiple, heterogeneous on-line sources, and transforming it so that the union of the knowledge can be applied in problem-solving, The KRAFT pro ject has defined a generic agent-based architecture to support fusion of kn owledge in the form of constraints expressed against an object data model. KRAFT employs three kinds of agent: facilitators locate appropriate on-line sources of knowledge; wrappers transform heterogeneous knowledge to a homo geneous constraint interchange format; mediators fuse the constraints toget her with associated data to form a dynamically-composed constraint satisfac tion problem, which is then passed to an existing constraint solver engine to compute solutions. The paper presents the KRAFT architecture and the thr ee kinds of agent, and includes a description of a demonstration KRAFT appl ication in the domain of telecommunications service provision.