中文摘要：

一个多代理人系统(妈) 是一条有希望的途径造复杂系统。这篇论文介绍内部企业的信用等级妈(IECRMAS ) 的研究。提起 ratingaccuracy，我们不仅考虑 rating-target 的信息，而且集中于计算程序的特征信息并且基于这个组的反偏爱大小建议合理等级组形成算法。我们也建议合理等级个人，它由计算程序和助理等级代理人组成。一个清醒的组形成协议被设计协调自治代理人执行评价工作。

英文摘要：

A Multi-Agent System （ MAS ） is a promising approach to build complex system. This paper introduces the research of the Inner-Enterprise Credit Rating MAS （ IECRMAS）. To raise the rating accuracy, we not only consider the rating-target＇s information, but also focus on the evaluators＇ feature information and propose the rational rating-group formation algorithm based on an anti-bias measurement of the group. We also propose the rational rating individual, which consists of the evaluator and the assistant rating agent. A rational group formation protocol is designed to coordinate autonomous agents to perform the rating job.