基于神经网络的投标报价系统
摘要
本文针对建筑行业投标报价过程中的种种难题，利用神经网络等人工智能技术开发了一套投标报价决策支持系统。全文主要的研究内容和研究成果概括如下：
针对建筑行业投标报价过程中难以确定“投标形势”的难题，首次将层次贡献分析法应用于投标报价过程中的变量选择问题，一方面避免了在建模过程中如何正确设定函数形式的困难，另一方面也扩充了回归建模研究中的函数类型，使变量选择研究更具有一般性，仿真结果表明：使用层次贡献分析法删减变量后的投标报价模型更加符合实际的报价需要。
众所周知，神经网络模型的输出质量在很大程度上依赖于作为训练样本的数据的质量。在实际的投标报价过程中，参与竞标的承包商每次所面临的“投标形势”都不可能与过去完全相同。因此对于报价系统来说，系统的泛化能力显得尤为重要。为了进一步改进系统的泛化能力，使其满足报价的实际需要，本文利用神经网络的概率描述，通过研究K-L信息距离和神经网络泛化能力的关系，构造了一个新的神经网络学习误差函数，并将此法与其它各种算法的泛化结果进行比较。仿真结果表明：将K-L信息距离引入神经网络学习误差函数后得到的改进BP算法具有更好的泛化能力，可以进一步提高报价系统的泛化性能。
在合理建模的基础上，利用面向对象的编程技术，以Visual C++6.0为开发平台，从应用的角度出发，开发出基于ACCESS数据库的投标报价系统，通过人机交互将整个报价系统应用到实际例子中。
Aiming at various difficulties in the bidding procedure of construction industry, the paper develops a decision-support system based on the artificial intelligence techniques such as neural networks. The following is the main content of the study:
First, as known to all, the "bidding situation" that includes the factors must be considered during the bidding procedure in construction industry is always hard to make clear. The paper uses the method of layer contribution analysis to solve the variable selection problem in the bidding procedure for the first time. On the one hand, the difficulty of setting the right function during the modeling procedure is avoided, and on the other hand, the types of function in regressive modeling are extended, which makes the study of variable selection is more general. The simulation proves that not only the calculation is simplified, but also the reduced model is more coincident to the requirement of the bidding process.
Second, the outputs' quality of the NN system is greatly depended on the data sent to the network as the training samples. In the real bidding procedure, the bidding situations the contractor faces are always quite different. So the generalization ability of the system is more important. In order to improve the generalization ability and to make the system more accordant to the practical requirement, the paper introduces the K-L information distance to the error function of the traditional BP algorithm. The simulation proves that the generalization ability of the system trained with the modified algorithm is much better than that of other algorithms.
Based on the reasonable model, a bidding demo system is developed in the environment of Visual C++ 6.0. By the interface between the users and the computer, the demo system put the bidding system into the practical use.
针对建筑行业投标报价过程中难以确定“投标形势”的难题，首次将层次贡献分析法应用于投标报价过程中的变量选择问题，一方面避免了在建模过程中如何正确设定函数形式的困难，另一方面也扩充了回归建模研究中的函数类型，使变量选择研究更具有一般性，仿真结果表明：使用层次贡献分析法删减变量后的投标报价模型更加符合实际的报价需要。
众所周知，神经网络模型的输出质量在很大程度上依赖于作为训练样本的数据的质量。在实际的投标报价过程中，参与竞标的承包商每次所面临的“投标形势”都不可能与过去完全相同。因此对于报价系统来说，系统的泛化能力显得尤为重要。为了进一步改进系统的泛化能力，使其满足报价的实际需要，本文利用神经网络的概率描述，通过研究K-L信息距离和神经网络泛化能力的关系，构造了一个新的神经网络学习误差函数，并将此法与其它各种算法的泛化结果进行比较。仿真结果表明：将K-L信息距离引入神经网络学习误差函数后得到的改进BP算法具有更好的泛化能力，可以进一步提高报价系统的泛化性能。
在合理建模的基础上，利用面向对象的编程技术，以Visual C++6.0为开发平台，从应用的角度出发，开发出基于ACCESS数据库的投标报价系统，通过人机交互将整个报价系统应用到实际例子中。
Aiming at various difficulties in the bidding procedure of construction industry, the paper develops a decision-support system based on the artificial intelligence techniques such as neural networks. The following is the main content of the study:
First, as known to all, the "bidding situation" that includes the factors must be considered during the bidding procedure in construction industry is always hard to make clear. The paper uses the method of layer contribution analysis to solve the variable selection problem in the bidding procedure for the first time. On the one hand, the difficulty of setting the right function during the modeling procedure is avoided, and on the other hand, the types of function in regressive modeling are extended, which makes the study of variable selection is more general. The simulation proves that not only the calculation is simplified, but also the reduced model is more coincident to the requirement of the bidding process.
Second, the outputs' quality of the NN system is greatly depended on the data sent to the network as the training samples. In the real bidding procedure, the bidding situations the contractor faces are always quite different. So the generalization ability of the system is more important. In order to improve the generalization ability and to make the system more accordant to the practical requirement, the paper introduces the K-L information distance to the error function of the traditional BP algorithm. The simulation proves that the generalization ability of the system trained with the modified algorithm is much better than that of other algorithms.
Based on the reasonable model, a bidding demo system is developed in the environment of Visual C++ 6.0. By the interface between the users and the computer, the demo system put the bidding system into the practical use.
引文
[1]蔡淑琴，石双元，梁静，张金隆．建设工程投标报价辅助决策系统．计算机工程与应用，1998，4：79-81
[2]王长涛．浅论工程投标报价的策略．福建建设科技，1998，2：42-43
[3]阎长俊，王绍华．工程投标信息评价的熵方法．系统工程，2001，19(5)：82-85
[4]肖维品，陈松吟，符宁强．工程项目投标报价决策模型及其风险评估方法．石家庄铁道学院学报，2000，13(4)：13-16
[5]肖维品．工程项目投标效应分析方法．系统工程，1987，5(6)：63-67
[6]王雪青，万彩芸．我国建筑企业国际工程投标报价存在的问题及对策．港工技术，2000，4：31-33
[7]Hegazy, T and Moselhi,O. Analogy-based solution to markup estimation problem. Journal of computing in civil engineering,ASCE, 1994,8(1):72-87
[8]Moselhi,O., Hegazy, T. and Lorterapong,P. Toward the development of an optimum problem-solving strategy. Proc. 7th Int. Congress AI Engrg., Waterloo, Canada, 1992:939-953
[9]Friedman, L. A competitive bidding strategy. Operation research, 1956,4:104-112
[10]Gates,M. Bidding strategies and probabilities. Journal of the construction division,ASCE, 1967,93 (1):75-10
[11]Carr, R.I. Optimum markup by direct solution. Journal of construction engineering and managment,ASCE, 1987,113(1):367-373
[12]Ahmad,I. and Minkarah,I. An additive utility model for selecting optimum bid price. Proc.,18th Annual Pittsburg Conf. On Modeling and Simulation, 1987,18(1), 367-373
[13]Seydel,J. and Olson,D. Bids considering multiple criteria. Journal of construction engineering and managment,ASCE, 1990,116(4):609-623
[14]Ahmad,I. and Minkarah,I. Questionnaire survey on bidding in construction. Journal of management in engineering,ASCE, 1988,4(3):229-243
[15]Tavakoli,A. and Utomo,J. Bid markup assistant: an expert system. Cost engineering, 1989,31(6):28-33
[16]李启明，袁永松．国际工程投标报价计算机辅助系统．东南大学学报，1994，24(3)：127，129
[17]赵平，谢行皓．工程项目投标报价系统的设计与实现．西安建筑科技大学学报，1999，31(3)：266-303
[18]张建明，康杰，李文华，倪天智，王萍．《土建工程投标报价专家系统》程序设计与实现．河北省科学院学报，1995：60-64
[19]Moselhi,O., Hegazy, T. and Fazio,P. Markup estimation using AI methodology. AI and Civ Engrg., Proc., 2nd Int. Conf. On the Application of Al Techniques to Civ. And Struct. Engrg., B. H. V. Topping, ed., Civil-Comp Press, Oxford, England, 1991:257-266
[20] Griffs,F.H. Bidding strategy: winning over key competitors. Journal of construction engineering and managment,ASCE,1992,118(1) , 151-165
[21] 司昕．预测方法中的神经网络模型．预测，1998，2：32-35
[22] Li,H. Neural network models for intelligent support of mark-up estimation. Int. J. Engry. Constr. and Arch. Mgmt.,1996,3(l):69-82
[23] Li,H. and Love,P.E.D. Combining rule-based expert systems and artificial neural networks for mark-up estimation. Constr. Mgmt. And Economics, 1998
[24] Li,H. Shen, L.Y. and Love,P.E.D. ANN-based mark-up Estimation system with self-explanatory capacities. Journal of construction engineering and managment,ASCE,1999:185-189
[2]王长涛．浅论工程投标报价的策略．福建建设科技，1998，2：42-43
[3]阎长俊，王绍华．工程投标信息评价的熵方法．系统工程，2001，19(5)：82-85
[4]肖维品，陈松吟，符宁强．工程项目投标报价决策模型及其风险评估方法．石家庄铁道学院学报，2000，13(4)：13-16
[5]肖维品．工程项目投标效应分析方法．系统工程，1987，5(6)：63-67
[6]王雪青，万彩芸．我国建筑企业国际工程投标报价存在的问题及对策．港工技术，2000，4：31-33
[7]Hegazy, T and Moselhi,O. Analogy-based solution to markup estimation problem. Journal of computing in civil engineering,ASCE, 1994,8(1):72-87
[8]Moselhi,O., Hegazy, T. and Lorterapong,P. Toward the development of an optimum problem-solving strategy. Proc. 7th Int. Congress AI Engrg., Waterloo, Canada, 1992:939-953
[9]Friedman, L. A competitive bidding strategy. Operation research, 1956,4:104-112
[10]Gates,M. Bidding strategies and probabilities. Journal of the construction division,ASCE, 1967,93 (1):75-10
[11]Carr, R.I. Optimum markup by direct solution. Journal of construction engineering and managment,ASCE, 1987,113(1):367-373
[12]Ahmad,I. and Minkarah,I. An additive utility model for selecting optimum bid price. Proc.,18th Annual Pittsburg Conf. On Modeling and Simulation, 1987,18(1), 367-373
[13]Seydel,J. and Olson,D. Bids considering multiple criteria. Journal of construction engineering and managment,ASCE, 1990,116(4):609-623
[14]Ahmad,I. and Minkarah,I. Questionnaire survey on bidding in construction. Journal of management in engineering,ASCE, 1988,4(3):229-243
[15]Tavakoli,A. and Utomo,J. Bid markup assistant: an expert system. Cost engineering, 1989,31(6):28-33
[16]李启明，袁永松．国际工程投标报价计算机辅助系统．东南大学学报，1994，24(3)：127，129
[17]赵平，谢行皓．工程项目投标报价系统的设计与实现．西安建筑科技大学学报，1999，31(3)：266-303
[18]张建明，康杰，李文华，倪天智，王萍．《土建工程投标报价专家系统》程序设计与实现．河北省科学院学报，1995：60-64
[19]Moselhi,O., Hegazy, T. and Fazio,P. Markup estimation using AI methodology. AI and Civ Engrg., Proc., 2nd Int. Conf. On the Application of Al Techniques to Civ. And Struct. Engrg., B. H. V. Topping, ed., Civil-Comp Press, Oxford, England, 1991:257-266
[20] Griffs,F.H. Bidding strategy: winning over key competitors. Journal of construction engineering and managment,ASCE,1992,118(1) , 151-165
[21] 司昕．预测方法中的神经网络模型．预测，1998，2：32-35
[22] Li,H. Neural network models for intelligent support of mark-up estimation. Int. J. Engry. Constr. and Arch. Mgmt.,1996,3(l):69-82
[23] Li,H. and Love,P.E.D. Combining rule-based expert systems and artificial neural networks for mark-up estimation. Constr. Mgmt. And Economics, 1998
[24] Li,H. Shen, L.Y. and Love,P.E.D. ANN-based mark-up Estimation system with self-explanatory capacities. Journal of construction engineering and managment,ASCE,1999:185-189