A learning-enabled infrastructure for electronic contracting agents

With the vigorous development of electronic commerce these years, many expe rts and scholars have devoted themselves to various fields of research and application. Of these fields, electronic contracting is a new research topi c in great demand. In spite of its promise, electronic contracting involves the standardization of ontology and automation of negotiation, which rende rs the implementation of electronic contracting difficult. In view of the n ecessity of electronic contracting, we present a learning-enabled agent-bas ed infrastructure and claim that it will be a solution to the problems enco untered during the process of electronic contracting by a variety of evalua tions. In this infrastructure, the applications of an agent are viewed as a set of application ontologies, each of which is a combination of a context ontology and a object ontology so that the negotiation context and automat ion of negotiation can be flexibly integrated in this infrastructure. The i nfrastructure enables the automation of electronic contracting through a ge neral and automatic communication protocol and provides reusability by the componentization of agents. The infrastructure provides personalized multia ttribute evaluation and proposal generation by a mechanism, which is a comb ination of neural networks and genetic algorithms, in order to enable the a utomatic negotiation ability at agents. (C) 2001 Elsevier Science Ltd. All rights reserved.