评标是建设工程招投标中的关键环节，能否对投标人进行一个全面、客观且正确的评价是招标成功的关键。随着互联网的飞速发展，针对人工评标的主观性、随意性和倾向性可能给建设工程招投标工作带来的评标结果偏差。本文在建立合理的评标指标体系的基础上，以BP神经网络算法的网络均方误差进行适应度函数设计，然后利用MATLAB编程建立了一种基于GA-BP神经网络的计算机自动评标模型，并采用建设工程项目实例对模型的评价效果进行了检验。该模型除了具有BP神经网络的并行处理、鲁棒性、自适应和自学习的优势外，与基于传统的BP神经网络建立的模型相比，其预测性能、预测精度和泛化能力都得到了有效改进，大大提高了评标的客观性和工作效率，也适用于建设工程项目其他类型评标中的非线性问题的求解。本文设计和实现了智能评标决策系统并将数据挖掘和云计算的相关技术引入该系统中，大大提高了评标的客观性和工作效率。
Bid evaluation is a key link in the bidding of construction projects. Whether a bidder can be com-prehensively, objectively and correctly evaluated is the key to successful bidding. With the rapid development of the Internet, the subjectivity, arbitrariness, and inclination of manual bid evalua-tion may cause deviations in the bid evaluation results of construction projects. Based on the es-tablishment of a reasonable bid evaluation index system, this paper uses the network mean square error of the BP neural network algorithm to design the fitness function, and then uses MATLAB programming to establish a computer automatic bid evaluation model based on the GA-BP neural network. The evaluation effect of the model was tested by using a construction project example. In addition to the advantages of parallel processing, robustness, self-adaptation and self-learning of the BP neural network, compared with the model based on the traditional BP neural network, the model has obtained prediction performance, prediction accuracy and generalization ability. Effec-tive improvement greatly improves the objectivity and work efficiency of bid evaluation, and is also applicable to the solution of non-linear problems in other types of bid evaluation of construc-tion projects. This paper designs and implements an intelligent bidding decision-making system and introduces data mining and cloud computing related technologies into the system, which greatly improves the objectivity and efficiency of bid evaluation.
Wan, D.S., Hu, Y.T. and Ren, X. (2009) BP Neural Network with Error Feedback Input Research and Application. Proceedings of 2009 Second International Conference on Intelligent Computation Technology and Automation, 1, 63-66. https://doi.org/10.1109/ICICTA.2009.24
[17]
Shi, H.W. (2009) Application of Unascertained Method and Neural Networks to Quality Assessment of Construction Project. Proceedings of 2009 Second International Conference on Intelligent Computation Technology and Automation, 1, 52-55. https://doi.org/10.1109/ICICTA.2009.21
Chaovalitwongse, W.A., Wang, W., Williams, T.P., et al. (2012) Data Mining Framework to Optimize the Bid Selection Policy for Competitively Bid Highway Construction Projects. Journal of Construction Engineering & Management, 138, 277-286. https://doi.org/10.1061/(ASCE)CO.1943-7862.0000386
