Technical Research On Geo-spatial Big Data Knowledge Discovery And Information Extraction

Data is the carrier of information technology.The development of geological information cannot be separated from the support of big data.Geological big data is the practice and application of big data methods,technologies,and ideas in the geological field in the context of cloud computing,Internet of things and other technological innovations.How can we effectively use,store,visualize,and mine potential geological data has become a major issue in the geological world.Most of the current geological information processing platforms are integrate geo-spatial information on a small scale.Research on integrated integration of two-and three-dimensional data based on largescale nation-wide and geological information is lacking,and it is difficult to meet the need for rapid discovery of spatial data in geological data environments.Information extraction and sharing services need new information technologies to meet the application needs in the geological data environment.Based on the GIS platform,this paper proposes the integration and visualization framework of geospatial big-data information under the local area network(LAN).It aims at the discovery of data knowledge and information extraction,proposes the discovery,storage,visualization and management of multi-source heterogeneous geospatial data based on C# and ArcEngine.The main work of this article includes the following aspects:(1)By summarizing and sorting out geological data,a multi-source heterogeneous geologic data model is proposed.An orderly intelligent storage of geological data based on the combination of MySQL and MongoDB database is used,which can improve the safety and flexibility of geospatial data access;(2)Based on the situation of China's geological management and application,it explores the mining and integration of national geospatial data in large-scale servers and establishes a knowledge discovery system for geological data.This system includes data discovery,data cleaning and data classification and can discover and extract valid data from massive geospatial data rapidly.(3)The concept of national thematic data set framework was proposed.Using C# and ArcEngine key technologies,the overall architecture of the geospatial big data knowledge discovery and information extraction platform was designed,and accomplished the national geological information classification visualization,spatial location mapping,dynamics search,attribute query,feature management,spatial analysis,statistical analysis and other functions based on knowledge discovery.The knowledge discovery and information extraction system of geological data based on LAN in this paper can effectively solve a series of needs of geological spatial data from format conversion,storage organization,retrieval,analysis and sharing,it will effectively improve the level of geological informatization,and meet the application needs of geological big data services better.