The Game Study Of Bidding Quotation Based On BP Neural Network

In recent years,China's economy has developed rapidly,and the construction industry will be the pillar industry of China's national economy in the future.However,with the continuous development and improvement of China's bidding management system and the increasing number of construction enterprises,China's construction market competition is increasingly fierce.In order to make the construction enterprise bigger and stronger,it must adopt scientific and reasonable bidding strategy.Therefore,improving the winning rate has become the goal pursued by many construction companies.In order to improve the success rate,our predecessors have taken a lot of methods of tender offer forecasting conducted in-depth research,the game theory and artificial intelligence is the study of this problem the mainstream thought method,but these methods are still some deficiencies,such as:for the bidding enterprise risk attitude is harsh hypothesis,the data dependence is strong,and so on.It is because of these shortcomings that the prediction effect of the established bidding decision analysis model is not ideal,leading to a big gap between the prediction result and the real problem.Therefore,this paper introduces the risk attitude factor of bidding enterprises into the decision-making model in the form of function,and USES BP neural network to optimize the parameter setting interval,making the decision-making model more suitable for the actual situation.The main results of this study are as follows:(1)Using the idea of combination optimization,the bidding game model based on BP neural network is constructed.First,through the analysis and selection of the influencing factors of bidding price limit,the factor matrix is established,the model structure is designed,the collected data is trained and simulated to obtain the BP network bidding price limit prediction model;then,according to the current comprehensive evaluation method in the construction bidding market,the bidding price decision model is established by using the idea of incomplete information static game.(2)The risk attitude factor is introduced into the game analysis model in the form of function.In the actual construction project bidding activities,each construction enterprise bidding decision-maker will have different risk attitudes when making decisions,which will affect whether the enterprise wins the bid and the profit of the project.Therefore,when constructing the bidding game model,the paper introduces the risk attitude factors of each bidding party into the game model in the form of function to make it more close to practice(3)From the point of view of a virtual bidder,a simulation bidding is carried out for an engineering example.The results show that BP network technology is used to optimize the bidding interval,which greatly improves the prediction accuracy of the original game model.At the same time,it is found that the established model has a very good role in promoting the development of bidding theory,and has great practical significance in improving the bid winning rate of bidding enterprises.