遗传算法在网上谈判支持系统中的应用研究  

Application of Genetic Algorithms in the Web-based Negotiation Support Systems

作　　者：李玥[1] 冯玉强[1] 王衍华[1] 李一军[1] 

机构地区：[1]哈尔滨工业大学管理学院,黑龙江哈尔滨150001

出　　处：《系统工程理论与实践》2002年第6期87-92,共6页Systems Engineering-Theory & Practice

基　　金：国家自然科学基金 ( 79970 0 84和 70 1 71 0 1 1 )

摘　　要：从 8 0年代后期首次出现谈判支持系统至今 ,国外许多学者从不的角度对其进行了大量的研究 ,而国内在这方面的研究尚处于起步阶段 .网上谈判支持系统不仅要为谈判人提供方便的交流媒介 ,更要为其提供合理的协调解 ,以减少冲突 ,提高谈判的成功率 .目前 ,对于网上谈判支持系统中谈判解支持的研究 ,尚未取得重大突破 ,采用的方法仅仅局限于效用函数法、对策分析法以及国内近期研究出的基于兴趣点的选择方案搜索算法等等 .但是 ,这些方法在实际应用中很难方便、及时地为谈判人提供有效的建议解或方案支持 ,无法满足网上谈判的实际需求 .本文针对遗传算法的全局收敛性快速寻优、可并行性寻优以及模拟自然进化过程解决最优问题等特点 ,尝试着将遗传算法用于网上谈判支持系统中 ,为谈判人提供对于双方而言满意的协调解 ,对此 ,文中进行了一系列的理论分析及实践检验 ,证明了这种方法的可行性及特殊的优越性 .Since later 1980′s,lots of foreign researchers have been researching and developing different kinds of Negotiation Support Systems (NSS)from various perspectives. Nevertheless, dommestic studies on it are just on the step of beginning. NSS should not only provide the negotiators with convenient communication mediator,but also offer rational negotiation solutions in order to decrease conflicts and increase the chance of an agreement. By now, the study on solution supporting is still going on, the methods include Utility Function, Game Theory and Interested-Based Alternative Seeking (IBAS).But all of them cannot conveniently,timely and effectively help negotiators make decisions in the real-time bargaining.Since Genetic Algorithms have the advantages of converging global search space fast, intrinsic parallelism and resolving the optimal problems with simulating natural evolution processes, in this paper we attmpt to apply GA to provide solution supporting in the Web-based NSS in order to offer optimal or near-optimal solutions for negotiators. We verify the feasibility and special superiority of this method through theory analysis and experiments.

关 键 词：遗传算法 网上谈判支持系统 电子商务 INTERNET 

分 类 号：F713.36[经济管理—产业经济] O242.23[理学—计算数学]