Authomatic Negotiation Of E-Commerce Based On MULTI-AGENT

Automatic negotiation and transaction on the internet is becoming more popular with the development of computer technology and e-commerce, and more and more people accept it as a new way of doing business. The negotiation and transaction on the internet can save a lot of human resources and material resources than the traditional negotiation and transaction. Especially automatic negotiation, which does not need a fixed place to negotiate with many participators, can reduce side effect of the traditional negotiation and transaction.We usually decide to accept or reject the offer based on the utility function in the traditional automatic negotiation of e-commerce so that we reject the offers whose utility is lower than a specified value. Here we evaluate the acceptability based on the fuzzy set theory and the membership function. We combine Bayesian learning mechanism with multi-agent to update both negotiators'believes and preserved values. Since different issues have different effect on the negotiators, we state the combined concession in the multi-issue negotiation for the negotiators. We put forward a more practical negotiation model than the traditional negotiation model and state the process of a fuzzy multi-issue negotiation model of e-commerce to implement on computer, and adopt swarm to simulate negotiation model not based on learning and negotiation model based on Bayesian learning.We can see from this simulation that the swarm simulation is effective. We adopt genetic algorithms to get a result acceptable to both buyer and seller. Finally, we compare the fuzzy negotiation model without learning, the fuzzy negotiation model with Bayesian learning, and the fuzzy negotiation model with genetic algorithms, and we state neccessary conditions for three models.