Subjects: Library Science，Information Science >> Library Science submitted time 2023-08-26 Cooperative journals: 《图书情报工作》
Abstract： [Purpose/significance] This study aims to analyze and propose the knowledge discovery strategy and build a knowledge discovery model of virtual health community text data. [Method/process] Firstly it summarized features of virtual health community text data, in view of the difficult of data mining to formulate the corresponding knowledge discovery strategy, and guided by DIKW system, to build knowledge discovery model of virtual health community text data based on knowledge discovery strategy. Through the application of computer code, natural language processing, syntactic analysis, and methods of inference rules, it realized the sublimation process of data value from free text data to the wisdom of adverse drug reactions. [Result/conclusion] Empirical research is carried out to verify the effectiveness and operability of the proposed knowledge discovery strategy and knowledge discovery model, so that it can provide reference for the subsequent theory and empirical research on knowledge discovery of virtual health community text data.
Subjects: Library Science，Information Science >> Library Science submitted time 2023-07-26 Cooperative journals: 《图书情报工作》
Abstract： [Purpose/significance]Based on the current big data environment and the demand for knowledge services in the field of medical intelligence, this paper explores the training objectives and the construction of knowledge ecosystem of medical intelligence talents.[Method/process] First of all, from the perspective of medical intelligence personnel providing medical services, it explores its multi-angle analysis of user needs, multi-level matching of needs and resources, and the ability to provide knowledge services through multiple channels. Then, according to the composition and operation mechanism of the knowledge ecosystem, from three perspectives which include knowledge resources, knowledge service activities and knowledge innovation activities, it constructs a knowledge ecosystem, which includes professional curriculum system, teaching practice platform and knowledge ecosystem of educational incentives for the training of medical intelligence personnel. Finally, taking the reform of the curriculum system of the medical informatics major of Jilin University, the setting of the teaching practice platform and the training program of knowledge innovation activities as an example, this study analyzes the role of the knowledge ecosystem in the training process of medical intelligence talents.[Result/conclusion] The research constructs the goal and the knowledge ecosystem of cultivating medical intelligence talents driven by innovation ability, promoting the application of information science research theories and methods in medical intelligence.
Subjects: Library Science，Information Science >> Library Science submitted time 2023-07-26 Cooperative journals: 《图书情报工作》
Abstract： [Purpose/significance] This paper designs a digital library user profile model, in order to explore the hidden value behind user data, comprehensively understand the needs of users, and provide new kinetic energy for the digital library to achieve precise services. [Method/process] This paper analyzes the connotation and characteristics of the user profile of the digital library, analyzes the data source and collection process of the user's profile, and regards its driven main route as digitization, labeling, association and visualization. From the natural dimension, interest dimension and social dimension, the article constructs a multi-dimensional user profile model. [Result/conclusion] The paper describes the construction process of the user profile model and designs a model framework for user profile. Simultaneously this article applies the user profile to the precise recommendation, personalized retrieval, accurate publicity and reference decision-making to promote the digital library's knowledge service upgrade.
Subjects: Library Science，Information Science >> Library Science submitted time 2023-07-26 Cooperative journals: 《图书情报工作》
Abstract： [Purpose/significance] This paper proposes a recommendation algorithm based on user interest metrics and content analysis for the current issues of low personalization and poor recommendation in knowledge discovery services. [Method/process] Through characteristic word distribution, LDA topic distribution and citation association, this paper constructs the academic resource model. Through the measurement of user behavior (browsing time, downloading, forwarding, collecting, etc.), the user's interest in browsing academic resources can be calculated, and the user interest model is constructed. Matching the user interest model with the academic resource model and calculating its similarity, the user's interest value for each academic resource can be obtained. Finally, the TOP-N academic resources with the highest interest value can be recommended to the user. [Result/conclusion] The paper tests the effectiveness of the algorithm and the accuracy of the recommendation through experiments. From the experimental results, we can show that the recommendation algorithm can predict the user's interest better and the recommendation effect is significant, simultaneously providing ideas for precise recommendation of discovery services.
Subjects: Library Science，Information Science >> Library Science submitted time 2023-07-26 Cooperative journals: 《图书情报工作》
Abstract： [Purpose/significance] In the context of big data, the user's knowledge needs are changed from decentralization to correlation, and multi-feature coupling is used to assist the knowledge discovery service to discover multiple correlations between resources, thereby optimizing knowledge discovery services. [Method/process] The concept of multi-feature coupling was defined by analyzing the internal and external attribute characteristics of the literature. This paper analyzed the relationship between multi-feature coupling and digital library knowledge service according to the function of multi-feature coupling. Then, by combining the existing knowledge discovery system, the multi-feature coupling structure was constructed. And the method of improving the supply side of the knowledge discovery service was proposed based on data layer-coupling layer-service layer. [Result/conclusion] The data layer guarantees the quality of the data, the data source changes from single to mixed; the coupling layer enhances the effect of coupling analysis, the unit of analysis changes from coarse-grained to fine-grained, the semantic association between fine-grained units attracts much attention; the service layer attaches importance to the user's interactive experience and develops multi-dimensional visualization function.
Subjects: Library Science，Information Science >> Library Science submitted time 2023-07-26 Cooperative journals: 《图书情报工作》
Abstract： [Purpose/significance] Under the data-driven environment, exploring the data-driven mechanism and optimization scheme of knowledge discover platform of digital library is conducive to provide theoretical support for supply-side reform from the perspective of methodology. [Method/process] By means of the system dynamics method, the data-driven dynamic formation mechanism of digital library knowledge discovery is presented through simulation. From the perspective of performance optimization, the granular computing method is used to provide a feasible solution for its drive optimization. [Result/conclusion] The data driving factors that influence the knowledge discovery of digital library mainly include data dimension, semantic association dimension, visualization dimension and value dimension. From the perspective of the formation of dimensions and the role of performance, the data drive of digital library knowledge discovery is a dynamic system of spiral development, the key point of performance optimization lies in the exploitation degree of knowledge value of data. The knowledge granularity as the starting point to achieve its optimization can better improve the data-driven effect of digital library knowledge discovery, according to the experimental studies.
Subjects: Library Science，Information Science >> Information Science submitted time 2023-04-01 Cooperative journals: 《图书情报工作》
Abstract： [Purpose/significance] Combining sociological perspective and information science means, the social attributes and external manifestations of public opinion events on microblog are correspondingly integrated, which provides a new perspective for explaining the social problems behind public opinion events.[Method/process] Combing the current research situation related to public opinion, and constructing the social attributes and externalization performance model of public opinion on microblog. Focusing on public opinion and explaining the internal logic between the 3 social attributes of crowd, content and sentiment and the 3 external manifestations of opinion leader, event and emotion. Then taking a vaccine incident as an example for empirical research and visual display.[Result/conclusion] The results of empirical research verify the validity and operability of the social attributes and externalization performance model of microblog public opinion. From the perspective of sociology, using the advantages of quantitative and visual research methods in the field of information science, we can fully understand the externalization of different social attributes of public opinion events and dig deeply into the essential problems behind public opinion events.
Subjects: Library Science，Information Science >> Information Science submitted time 2017-10-11 Cooperative journals: 《数据分析与知识发现》
Abstract： 【Objective】Disease risk factors were discovered from heterogeneous electronic medical record data to provide reference for data mining and knowledge discovery. 【Method】Clinical electronic medical record data with various structures were selected, and three data mining algorithms, decision tree, logistic regression and neural network, were used to establish disease risk factor prediction models, and the three prediction models were compared and analyzed statistically. . [Results] The precision and recall of the decision tree prediction model are higher than those of logistic regression and neural network, and the overall performance of the decision tree is the best, but there is little difference between the three. [Limitations] The attributes of electronic medical records are not optimized. 【Conclusion】Decision tree is superior to logistic regression and neural network in the discovery of risk factors and prediction of disease. In the research, a knowledge discovery framework of heterogeneous data sources based on data mining algorithm is established, which provides certain reference and reference for the future domain knowledge discovery and knowledge base construction and the selection of data mining algorithms.
Hits
Hits
Downloads
Comment