KDD (Knowledge Discovery in Databases) process has become a new and important research area. Within the framework of KDD process and the GLS (Global Learning Scheme) system recently proposed by us, this paper concentrates on the issue of KDD process planning. In our method, the KDD process is modeled as an organized society of intelligent agents (called KDD agents), and planning is a meta-agent. We propose a formalism to describe KDD agents, in the style of OOER (Object Oriented Entity Relationship data model). Based on this representation of KDD agents as operators, we apply AI planning techniques to organize dynamically the KDD process so that the GLS system increases both autonomy and versatility.