Research On Semantic Mapping Of Basic Geographic Information And Hydrological GIS Information Based On Improved BP Neural Network

With the rise of China's new science and technology,China's urban form is also constantly reform and transformation,digital city to the wisdom of the city successfully upgraded.Based on the digital city,relying on the "Internet +" platform,the explosive information into our lives.Smart City will bring a big change in data integration,sharing and interoperability.It will be related to the data of various industries,including industry applications,industry special data,administrative approval data,and Internet of things,video,positioning and so on.The data into the geographical space above the integration will be hot nowadays.Data show the form of large data,for the growing amount of data,the data is "big" but does not reflect its due value.Different areas in the development of their respective information are gradually formed their own system,the relatively independent data system.There are many repetitive phenomena in these data,such as the same content,due to differences in the field led to differences in the concept of data.How to realize data interoperability between different domains and different systems,and realize the reuse of data.Semantic mapping is an urgent problem to be solved at present.With the ontology semantic and semantic similarity research gradually deep,to solve this problem has brought new ideas.Based on the semantic mapping of basic geographic information and GIS ontology,this paper proposes a semantic similarity calculation and mapping model for geographic entities,and uses the improved BP neural network to study the similarity of subjective evaluation(2)Through the selection operator in the genetic operation,the crossover operator,the crossover operator,the crossover operator,the crossover operator,the crossover operator,the crossover operator,the crossover operator,the crossover operator,the crossover operator,The mutation operator to optimize the neural network algorithm between the neurons of the connection weights and thresholds,3)to solve the nonlinear relationship between the mapping problem.These improvements further enhance the traditional semantic similarity calculation model,and based on the model to achieve the basic geographic information ontology and water GIS ontology cross-domain semantic mapping test.The experimental results show that the improved algorithm is superior to the traditional BP algorithm,and can be used to realize the mapping,fusion and sharing of cross-domain objects and entities.