Research On Resource Aggregation And Knowledge Discovery Service Of Institutional Repository Based On Linked Data

In the context of the open access concept,the institutional repository has achieved considerable development and has attracted the attention of experts and scholars at home and abroad.With the increase of the number of institutional knowledge bases and the ever-increasing content of resources,there is a growing need for resources to be shared among institutions.Admittedly,it should be noted that most of China's current institutional repository resources are still in an isolated island state.They lack scientific and effective organizations for institutional repository's rich of hidden and implicit knowledge resources,and they have not established an effective link between institutional repository and institutional repository,resulting in institutional repository resources to be used and shared.Therefore,how to fully use of the rich academic resources of the organization's knowledge base and how to ample links with the entire information environment,realizing the knowledge relation between the semantic-based institutional knowledge bases in terms of breadth and depth,and in-depth dig into added value of the content of institutional knowledge base resources.Added value is the challenge and opportunity for libraries and other information agencies to enhance their knowledge service capabilities and serve new digital researches.The emergence of linked data and its technical advantages in the semantic association of digital resources provide technical support for the research and practical application of institutional repository resource aggregation and knowledge discovery.The application of linked data technology to the practice of Institutional repository services,exploration of new operational types of institutional repository resource aggregation and knowledge discovery services based on associated data has become the goal and direction of this study.This article attempts to make a breakthrough in the following four aspects:First,build a multi-dimensional association model of institutional repository resources based on associated data and explain the formation mechanism.The multi-dimensional association and linking of institutional repository resources are the clues of knowledge intersection,fusion,discovery and innovation.It is the basis and extension logic of institutional repository resource aggregation and knowledge discovery.It can provide high-quality institutional repository resource aggregation and knowledge discovery based on associated data.Based on the existing research results,this paper proposes a multi-dimensional relational model of institutional repository resources based on linked data,which from the perspective of multi-dimensional associations in the data layer and the multi-dimensional perspectives of the semantic layer,and expounds the intrinsic mechanism and technical route of multi-dimensional relational structures and associated data collaborative ontology.As well as the positive role of ontology has been effected on associated data.It explains the important role that it plays in the semantic analysis of institutional repository resources and the realization of multi-dimensional semantic associations by applying the examples.Second,consolidate and propose the technical strategy and process of institutional repository resource aggregation based on related data,and build an institutional repository resource aggregation system.Institutional repository resource aggregation of linked data is a comprehensive organization of knowledge organization tools such as classification thesaurus and domain ontology.It establishes a mapping relationship between the standardized concept semantic system and the natural language terminology system.It is characterized by knowledge extraction,entity identification,concept semantics and semantic knowledge association description,so as to achieve institutional knowledge base resource aggregation.The institutional repository base resource aggregation strategy based on the associated data refers to the scientific arrangement for realizing the steps of the institutional repository base resource aggregation.Based on theanalysis and condensing of the institutional repository base resource aggregation strategy of the associated data,propose a system framework of institutional repository resource aggregation based on linked data,and describes the key technologies involved in the aggregation of institutional repository resources aggregation,then verify the availability of the proposed theoretical model through experiments.It demonstrates the feasibility of semantic technologies such as associated data and ontology models,and provides support for the application of knowledge discovery services.Third,propose a system framework for knowledge discovery of institutional repository resources based on association aggregationThe association aggregation and release of institutional repository resources provide new methods and ideas for knowledge discovery.The knowledge discovery of Institutional repository resources based on association aggregation is a systematic project.The application goal is to aggregate Institutional repository resources rich into associated data networks,and to dig and discover unknown and novel rules and laws which hidden in data networks.Through model evaluation to find out what is really useful to the user,then visual presentation and utilization.This paper starts from the general process of knowledge discovery,and extends to the knowledge discovery process of institutional repository resources based on association aggregation.On count of association aggregation,we build a knowledge discovery model of institutional repository resources and provides theoretical support for its application research.Finally,according to the research conditions,the development of the institutional knowledge base application prototype system was carried out,and some of the system functions were realized.The value of the knowledge discovery of the organization knowledge base resources based on the associated data was verified.Fourth,put forward the strategy and new kinetic energy of institutional repository service innovation.Data-driven is becoming a kind of value and common sense of institutional repository service innovation.The author believes that the research and practice of data-driven institutional repository service innovation must adhere to the four aspects,that is,to the more complex data network environment,more diverse data analysis methods,more precise user needs and more targeted results.Facing the challenges and opportunities brought by data-driven,institutional repository resource organization and service needs new breakthroughs,new developments,and new values.It is necessary to realize that achieve a service model needs from a single organization to an inter-institutional collaborative service,from domain institutional to user driven,from institutional repository to knowledge discovery service platform.At the same time,we are required to rethink the core competence of the institutional repository and enhance its social contribution,and actively explore and cultivate new kinetic energy for institutional repository service innovation.Achieving data-driven,leveraging data-based research paradigms and implementing precision services on the supply side will be new kinetics for institutional repository service innovation.