The traditional evaluation method of the node importance of railway logistics distribution network has not eliminated redundant data, resulting in errors in the evaluation results. Therefore, the evaluation method of the node importance of railway logistics distribution network based on rough set is proposed. This method uses the rough set theory to eliminate redundant node data, obtain the collection and distribution uncertainty index, establish an importance evaluation index, obtain the node

more »

... mportance evaluation weight, and achieve the higher accuracy of the network node importance evaluation. The experimental results show that compared with the traditional evaluation method, the evaluation results of network node importance based on rough set are closer to the expected results. It can be seen that the performance of this method is superior. Introduction With the continuous development of national economy and the continuous optimization of industrial structure adjustment, China's railway transportation industry has grown rapidly. In order to improve the transportation efficiency and save the transportation cost, the railway logistics collection and distribution requires the importance evaluation of the network nodes, so as to set up the railway transportation scheme. According to this requirement, the traditional evaluation method directly evaluates the node importance of railway logistics with complex road conditions and overlapping lines, and the railway transportation department formulates the collection and distribution scheme according to the evaluation results. However, as the length and complexity of the route become longer, there are some drawbacks in the scheme under the design of the evaluation results. The elimination of redundant data is not complete, resulting in errors in the evaluation results. Therefore, in view of the shortcomings of the traditional methods, this paper puts forward the evaluation method of node importance of railway logistics collection and distribution EAI MOBIMEDIA 2020, August 27-28,