Research On The Construction And Application Of The Cultural Knowledge Graph Of Ethnic Minorities Costumes

Ethnic minority costume is the crystallization of culture and wisdom in the development of ethnic minority history.With the rapid development of information technology in recent years,the application of digital technology has greatly promoted the inheritance and protection of ethnic minority clothing culture.However,because of the large number of ethnic minority clothing culture network resources,large quantity and scattered sources,the traditional retrieval efficiency of catalog retrieval is low,so that users can not obtain more accurate and structured information;meanwhile,the professional and deep information in the field of ethnic minority clothing is still based on academic monographs and journals,and most of the network media resources content it is superficial and lack of systematicness.Therefore,this paper aims to explore the new ideas and methods of digital technology application of ethnic minorities' culture by using the advantages of knowledge graph in the construction of knowledge system and knowledge expression,and to carry out the construction and application of the knowledge graph of ethnic minority costume culture.The specific work of this paper is as follows:(1)The construction of ethnic minority costume culture ontology.There is no mature ontology construction method in the field of minority costume culture.Based on the analysis of the existing ontology construction methods and the information characteristics of minority costume culture,this paper proposes an ontology construction method suitable for the field of minority costume culture by combining seven step method and IDEF-5,and selects OWL as the ontology description language to complete the construction of minority costume culture.(2)The construction of the cultural knowledge graph of ethnic minority costumes.Aiming at the situation that the original data contains a large amount of unstructured data,this paper uses the Bi-LSTM+CRF model to extract entities from the data.The Bi-LSTM is combined with the double-layer attention mechanism for relation extraction,which effectively solves the influence of irrelevant words on the result of relation extraction.Finally,the extracted knowledge is saved in the Neo4 j to complete the construction of the ethnic costume cultural knowledge graph.(3)Research on semantic retrieval model based on the knowledge graph of ethnic minority costume culture.In order to solve the problem that traditional information retrieval lacks semantic information and leads to inaccurate retrieval results,this paper proposes a semantic retrieval model based on knowledge graph by using word segmentation,semantic extension,knowledge reasoning and other technologies,which can meet the retrieval needs of users by adding semantics in the retrieval process.Finally,the experimental results show that the model can return accurate retrieval results to users.(4)Design and development of the retrieval platform based on the knowledge graph of ethnic minority costume culture.Based on Python + Django + My Sql +Neo4j,this paper develops a knowledge graph retrieval platform,which mainly includes knowledge management module and application display module.It realizes the management of minority clothing culture knowledge,provides users with concise knowledge structure relationship and information display with pictures and texts,and also has the recommendation function of related knowledge and concepts,which has a good user experience.