Research On The Construction And Application Of Knowledge Graphs In The Field Of Poverty Alleviation

With the popularity of smart devices and the rapid development of the Internet,data on the network is exploding,and there is a large amount of discrete information and complex relationships behind the data.In order to make efficient use of network data,domestic and foreign enterprises and research institutions have built knowledge graph in specific fields to serve the future smart life work scene.Knowledge graph can break the limitations of traditional data storage media,and form a unified network structure for relatively isolated and discrete multi-source heterogeneous data,providing underlying data and technical support for applications such as intelligent question and answer,intelligent search and recommendation.The Chinese government has been working hard to solve the problem of poverty.However,because the poverty alleviation data storage of local governments is relatively independent and the structure is not the same,it is difficult to achieve data sharing and sharing.Therefore,it is difficult for the country to formulate accurate and effective poverty alleviation strategies to solve the poverty problem.The emergence of knowledge graph technology provides a new solution to this problem.At present,the domestic research work on the knowledge graph of poverty alleviation is very scarce.Therefore,this thesis has carried out the construction and application research of knowledge map in poverty alleviation field for government poverty alleviation data,and elaborated on the specific operations of knowledge extraction,data fusion and system construction and application.This has greatly helped to make full use of the data in the field of poverty alleviation.This thesis studies the construction method of the knowledge graph of poverty alleviation and the realization of the application system.It hopes to apply the knowledge graph technology to the poverty alleviation field,so as to realize the efficient use of open government data and serve the needs of precision poverty alleviation.Firstly,the data analysis and collation of the government poverty alleviation data set is carried out.After analysis,the main classes,objects and their attributes are extracted,and the ontology of the poverty alleviation domain is constructed as the upper data specification of the knowledge graph.Then,according to the constructed ontology data source integration tool Karma,the original data is semantically mapped between the concept and the data,and then integrated into a unified RDF triplet data.For the unstructured text data in the dataset,the entity recognition and relation extraction techniques in natural language processing are mainly used,and the deep neural network algorithm is used to solve the extraction of the triad data of the character relationship in the unstructured text.After the extracted triplet information is fused and parsed,according to the characteristics of the triple data in the knowledge graph,the Neo4 j graph database based on the graph structure is used as the data storage scheme.Finally,based on the constructed knowledge graph design,the poverty alleviation knowledge graph application system was developed,and the functions of data retrieval and intelligent question answering were realized.Based on the government's poverty alleviation data,this thesis solves the problem of isolated and unstructured data sources by constructing knowledge graph.At the same time,the integrated data is stored in the Neo4 j graph data to overcome the shortcomings of the traditional database for insufficient depth query capability.The knowledge graph designed based on this method greatly saves the time of integrating multi-source heterogeneous data and knowledge graph construction,and improves the speed at which users can obtain accurate information,which is of great significance for meeting the government's demand for precision poverty alleviation.