Research On The Selection Of Car-free Carrier Partners Based On AHP-BP Neural Network

At present,90% of the market share of China's highway transport industry is occupied by various small and medium-sized logistics transport enterprises and individual transport,while the release of cargo information has been in a closed state,which leads to the phenomenon of multiple no-load waste in China's highway logistics transport industry.In order to solve one of the problems,the Ministry of Transport of China has put forward the concept of "Car-free Carrier".As a car-free carrier enterprise,the most important thing is to link up the supply chain upstream and downstream cooperative companies,which shows that the choice of partners in the car-free carrier enterprise is particularly important.How to choose the right partner and how to evaluate the partner enterprises comprehensively are the practical problems faced by many enterprises.Therefore,it is an important prerequisite for enterprises to make correct decisions to put forward the index system of enterprise partners and make effective evaluation of partner enterprises,which has important practical value for the survival and development of enterprises.Firstly,this paper combs the important literature related to the research of enterprise partners,classifies the literature according to the research contents,and deeply studies the theoretical basis and importance of partner selection.Then,through the discussion and analysis of the concept,connotation and characteristics of the cooperative relationship of the vehicle-free carrier,combined with the previous research theory and the proposed evaluation system of the partner selection of the vehicle-free carrier,and combined with the guidance of off-campus tutors,the evaluation index system model of this paper is established.Relying on the relevant research results at home and abroad,this paper designs the AHP method to determine the relative importance of each level of factors and their weight values,and to analyze the essence of solving the problem by discharging the primary and secondary order of measurement values from high to low,and get the expert values.Then through the mature BP neural network in the artificial neural network,BP neural network has the ability of non-linear mapping.It is a one-way multi-layer feedforward network.It consists of input layer,hidden layer and output layer.The adjacent layer of each neuron forms a complete connection relationship,while there is noconnection between each neuron in the same layer.Finally,we use the MATLAB software to create the neural network,take the evaluation index as the sample,train the neural network,and use the trained network to carry on the empirical analysis.In the past,the former authors mostly used one or two simple methods to choose partners for vehicular carriers,but some errors would inevitably arise.In this paper,the combination of these two methods in the selection of partners for the carrier without vehicles has not been studied before.In summary,this paper discusses the theoretical basis and importance of partner selection.On this basis,the analytic hierarchy process is used to accurately and quantitatively evaluate the company's partners and help the company select excellent partners according to the ranking results.At the same time,it can provide reference and suggestions for general enterprises to choose dynamic partners,consolidate and strengthen their own strong core competitiveness,and occupy a dominant position in the industrial value chain.