Please wait a minute...
浙江大学学报(工学版)
J4  2009, Vol. 43 Issue (6): 1053-1059    DOI: 10.3785/j.issn.1008-973X.2009.
计算机技术、自动化技术     
Agent网络法——一种多元商务智能技术融合方法
 陈明亮
（浙江大学 管理学院,浙江 杭州 310058 ）
Agent-network:a fusion method for heterogeneous business intelligence technologies
 CHEN Meng-Liang
(College of Management, Zhejiang University,Hangzhou 310058,China)
 全文: PDF(926 KB)   HTML
摘要：

为了融合粗糙集、模糊逻辑、决策树、群决策、蚁群算法、数据挖掘、遗传算法、人工神经网络等异质商务智能（BI）技术,基于复杂网络和多Agent,提出了一种称为Agent网络法的融合方法,该方法包括3大机制：自治主体,网络集聚的智能资源集成机制;“竞争上岗,择优合作”的智能资源利用机制;“绩效评估,优胜劣汰”的智能资源优化机制.基于该方法构建的BI系统是一个以众多Agent为节点的复杂网络,其中的每个Agent都是一个独立的智能单元,代表BI技术中的一个计算模型或算法.3大机制实现了多元BI技术两个层次的融合：新的Agent不断加入,被实践证明低价值的旧Agent不断剔出,网络中始终聚合着所有高价值的Agent,从而在系统结构层面上实现优秀BI技术的全面融合；借助谈判、招标、拍卖等竞争性合作机制,每次响应任务时,选出的是网络中最能胜任当前任务的Agent组合,从而在系统应用层面上实现 BI技术的动态融合.
Abstract:

In order to fuse heterogeneous business intelligence (BI) technologies such as rough set, fuzzy logics, decision tree, group decision, swarm algorithm, data mining, genetic algorithm, artificial neural networks, a complex network and multi-Agent based  method called as Agent-network was put forward. The method includes three basic mechanisms: intelligence resource (IR) aggregating mechanism based on autonomous Agent and complex network, IR using mechanism based on “competing for post” and “selecting the best for cooperation”, IR optimizing mechanism based on performance evaluation and “survival of the fittest”. A BI software system based on the method is a complex network composed of many Agents as nodes. Each Agent is a unit of BI resource which represents a computing model or an algorithm. By means of the three mechanisms of Agent-network, a BI system can realize two levels of BI technology fusion. One is called as fusion on system structure: new Agents are added into the network continuously and less value existing Agents are deleted from it, all valued Agents (on behalf of all excellent BI technologies) are aggregated in the system. Another is called as fusion on system application: by using some marketing mechanism such as negotiation, bidding and auction, the system always can find an optimal Agent portfolio to respond to a specific service request of user．
出版日期: 2009-06-01
:  C931.6  
基金资助:

国家自然科学基金资助项目（70671092、70372020）.
作者简介: 陈明亮（1963-），男，江苏常州人，副教授.从事管理信息系统复杂性、客户关系管理和智能技术融合等方向的研究.
服务　　
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章　　

引用本文:

陈明亮. Agent网络法——一种多元商务智能技术融合方法[J]. J4, 2009, 43(6): 1053-1059.

CHEN Meng-Liang. Agent-network:a fusion method for heterogeneous business intelligence technologies. J4, 2009, 43(6): 1053-1059.

链接本文:

http://www.zjujournals.com/eng/CN/10.3785/j.issn.1008-973X.2009.    或    http://www.zjujournals.com/eng/CN/Y2009/V43/I6/1053


[1] CHANG H J,HUNG L P, HO C L. An anticipation model of potential customers purchasing behavior based on clustering analysis and association rules analysis［J］. Expert Systems with Applications ,2007,32：753764．

[2] WANG H F, HONG W K. Managing customer profitability in a competitive market by continuous data mining［J］. Industrial Marketing Management,2006,35:715723．

[3] 陈伯成,叶伟雄. 用Hopfield神经网络求解一类Markov链的客户关系管理模型［J］.清华大学学报：自然科学版,2005,45（12）:16961699.
CHEN Bo-cheng,YE Wei-xiong. Markov chain customer relationship management model based on the Hopfield neural network［J］. Journal of Tsinghua University : Science and Technology,2005, 45（12）：16961699.

[4] HSIEH N C. An integrated data mining and behavioral scoring model for analyzing bank customers［J］. Expert Systems with Applications, 2004, 27: 623633．

[5] LIU H H,ONG C S. Variable selection in clustering for marketing segmentation using genetic algorithms［J］. Expert Systems with Applications,2008,34（1）：502510．

[6] KIM E, KIM W, LEE Y. Combination of multiple classifiers for the customers purchase behavior prediction［J］. Decision Support Systems, 2002, 34 : 167175．

[7] 项后军,周昌乐.人工智能的前沿——智能体（Agent）理论及其哲理［J］.自然辩证法研究,2001,17（10）：2933.
 XIANG Hou-jun,ZHOU Chang-le. The frontier of AI: the development of Agent theory and its philosophy［J］. Studies in Dialectics of Nature,2001,17（10）：2933．

[8] 汪小帆,李翔,陈关荣. 复杂网络理论及其应用［M］. 北京：清华大学出版社, 2006.

[9] 石存一,张伟. 基于Agent的计算［M］. 北京：清华大学出版社,2007.

[10] 江瑞,罗予频,胡东成,等. 基于多Agent协同构建分布式并行遗传算法［J］. 清华大学学报: 自然科学版,2002,42（9）:12091213.
JIANG Rui, LUO Yu-pin,HU Dong-cheng, et al. Distributed parallel genetic algorithms based on multi-Agent cooperation［J］. Journal of Tsinghua University : Science and Technology,2002, 42（9）：12091213．

[11] 李志华,陈德钊,胡上序. 基于M-Agent 的遗传算法及其在二甲苯异构化装置优化中的应用［J］.化工学报,2003,54（5）：653658.
LI Zhi-hua , CHEN De-zhao, HU Shang-xu. Application of genetic algorithms based on intelligent multi-Agent for optimization of equipment of isomerization of xylene［J］.Journal of Chemical Industry and Engineering, 2003,54（5）：653658．

[12] 钟伟才,刘静,焦李成.多智能体遗传算法用于线性系统逼［J］.自动化学报,2004,30（6）：933938.
ZHONG Wei-cai,LIU Jing,JIAO Li-cheng. Optimal approximation of linear systems by multi-Agent genetic algorithm［J］.ACTA Automatica Sinica, 2004,30（6）：933938．

[13] 杨博,王亚东,苏小红,等.基于Agent 和数据切片的分布式神经网络协同学习研究［J］.计算机研究与发展,2006,43 (12) : 20962103.
YANG Bo , WANG YA-dong , SU Xiao-hong, et al. Neural networks distributed cooperative learning strategy based on Agent and chips［J］.Journal of Computer Research and Development ,2006,43 (12) : 20962103．

[14] 杜荣华,姚刚,吴泉源. 蚁群算法在移动Agent 迁移中的应用研究［J］.计算机研究与发展,2007,44 (2) : 282287.
DU Rong-hua, YAO Gang , WU Quan-yuan. Application of an ant colony algorithm in migration of mobile Agent［J］. Journal of Computer Research and Development ,2007,44 (2) : 282287．

[15] JOSENILDO C S, CHRIS G, RUCHITA B, et al. Distributed data mining and Agents［J］. Engineering Applications of Artificial Intelligence, 2005, 18: 791807．

[16] LUO J,WANG M G,HU J， et al. Distributed data mining on Agent grid: issues, platform and development toolkit［J］.Future Generation Computer Systems, 2007,23 :6168．

[17] 金涬,石存一.拍卖方法引入多Agent系统［J］.计算机科学,2003,30（8）：104107.
JIN Xing, SHI Cun-yi.The auction and its application in multi-Agent systems［J］.Computer Science, 2003,30（8）：104107．

[18] 王海,李一军,侯新培. 基于Agent的电子商务自动谈判系统研究［J］. 系统工程理论与实践,2005(11):1419.
WANG Hai,LI Yi-jun,HOU Xin-pei. E-commerce oriented ANS based on Agent［J］.Theory and Practice of System Engineering, 2005(11):1419．

[19] 朱付保,关佶红,牛晓太.一种基于Agent推理的自动谈判方法研究［J］.复旦学报:自然科学版,2004,43(5):845846.
ZHU Fu-bao, GUAN Ji-hong, NIU Xiao-tai.An automatic negotiation method based on Agent reasoning［J］. Journal of Fudan University: Natural Science, 2004, 43(5):845846．

[20] MALAMATI L, IOANNA R, LAMBROS P.An intelligent Agent negotiation strategy in the electronic marketplace environment［J］. European Journal of Operational Research, 2008,187: 13271345．

[21] 胡晶晶,曹元大,胡军. 基于英式拍卖协商协议的多智能体任务分配［J］. 计算机集成制造系统,2006,12(5):795799.
HU Jing-jing,CAO Da-yuan,HU Jun. Task assignment of multi-Agent based on english auction protocol［J］. Computer Integrated Manufacturing Systems, 2006,12(5):795799．
No related articles found!