111 Research on the Theoretical Framework of Intelligence System Leading Science and Technology Development Li Pin, Yang Jianlin, Yang Guoli DOI: 10.3772/j.issn.1000-0135.2019.02.001 This article argues that competitive, confrontational, and uncertain environmental issues have caused science and technology development to need a new intelligence service, and that the direction of science and technology development also shows signs of transition from being problem-oriented to goal-and vision-oriented, with leading function becoming the core function of intelligence work. “Leading function” is defined in this article; a theoretical framework for an intelligence system that leads science and technology development is constructed; and basic elements and their relationships are analyzed. Furthermore, the application of predictive and foreseeable intelligence analysis methods and the importance of “presumption” in the intelligence analysis process are emphasized. Finally, basic strategies for intelligence system implementation is explored, based on important national strategies. 2019 Vol. 38 (2): 111-120 [Abstract] ( 185 ) HTML (151 KB)  PDF (872 KB)  ( 1000 )

121 Research on the Scientific Research Level of the Excellence 9 League in the Field of Opportunity Discovery of Cooperation in the Humanities and Social Sciences Lin Yuan, Li Luying, Xu Kan, Liu Shengbo DOI: 10.3772/j.issn.1000-0135.2019.02.002 The development of a high level of humanities and social sciences points toward the direction of breakthroughs in the construction of first-rate universities and world-renowned high-level universities in the field of science and engineering. By statistically analyzing the basis for cooperation in scientific research in universities of science and engineering, high-efficiency potential cooperation opportunities are discovered. Our country??s “Excellent 9” league is taken as an example, based on the three cooperative basic indicators of joint cooperation institutions, discipline distribution, and keywords, to analyze the motivation of cooperation and explore potential cooperation directions for universities. At the same time, a similarity measure based on the information vector of a university is proposed, and the difference of information between colleges is compared and analyzed; thus, potential cooperation is suggested. The combination of quantitative analysis and vector representation reveals the potential cooperation direction of five pairs of universities and provides a feasible information representation model for mining potential cooperation opportunities in colleges and universities, which can be used to guide the development of scientific research. 2019 Vol. 38 (2): 121-131 [Abstract] ( 184 ) HTML (164 KB)  PDF (1114 KB)  ( 722 )

132 Information Service Quality of Online Health Platform Based on User Participation Qian Minghui, Xu Zhixuan, Wang Shan DOI: 10.3772/j.issn.1000-0135.2019.02.003 Based on the SERQUAL and E-SERQUAL evaluation models, this study investigates the uneven distribution of the information service quality of online health platforms in China, constructing an evaluation index system for the information service quality of China's online health platforms from the six dimensions of information service efficiency, ease of use of the information service, protection of private information, comprehensiveness of the information service, contact, and responsiveness; then, the research builds a model between information service quality and user participation and further explores the relationship between information service quality and user participation through an empirical study, which provides a reference for the standardization of information service quality and promotion of user participation in China's online health platform. 2019 Vol. 38 (2): 132-142 [Abstract] ( 266 ) HTML (158 KB)  PDF (729 KB)  ( 1734 )

143 Research on the Multi-granularity Integrated Knowledge Service in Digital Libraries Wang Zhongyi, Huang Rong, Zheng Xin, Huang Jing DOI: 10.3772/j.issn.1000-0135.2019.02.004 This paper is a study of the multi-granularity integrated knowledge service mode of digital libraries based on linked data. Its aim is to deepen the knowledge service units of digital libraries, turning them from document units into knowledge units; establish links between the knowledge units, according to the logical relationship between them; and then provide a multi-granularity integrated knowledge service based on related theories services. It includes the steps of multi-granularity association data creation, indexing, and retrieval, so as to realize a one-stop multi-granularity integrated knowledge service of “what you retrieve is what you want” in digital libraries, and thus improve the usability of digital libraries and reduce users?? cognitive burden and use cost. 2019 Vol. 38 (2): 143-158 [Abstract] ( 293 ) HTML (190 KB)  PDF (7569 KB)  ( 425 )

159 The Novelty Evaluation of Articles on WeChat Subscription Based on Recursive Neural Tensor Network Wang Ping, Hou Jingrui, Wu Renli DOI: 10.3772/j.issn.1000-0135.2019.02.005 The problem of content homogeneity in We-Media platforms is becoming increasingly serious, making it difficult for users to obtain high-quality information. Therefore, it is particularly important to evaluate the novelty of We-Media articles. Taking the articles of WeChat Subscription as an example, this paper proposes a novelty evaluation method for articles on We-Media platforms, using an unsupervised sentence level Doc2Vec language model to construct the text vector, and establishes a novelty evaluation model to quantify articles’ novelty based on the recursive neural tensor network. This paper automatically collected 4,628 articles from WeChat Subscription to conduct an empirical research. First, a number of different tensor slices were selected to conduct contrastive experiments, and the optimal parameters were obtained by combining the feature of novelty distribution and training time. Subsequently, the linear regression relationship between novelty and similarity was discovered and then verified by calculating the similarity of the documents. The experimental results demonstrate the feasibility and effectiveness of this approach. This paper expands and enriches the research on document novelty evaluation from the perspective of deep learning. It also supports the novel topic detection and frontier knowledge discovery of We-Media platforms. 2019 Vol. 38 (2): 159-169 [Abstract] ( 232 ) HTML (195 KB)  PDF (3058 KB)  ( 757 )

170 A User Influence Strength Model in E-commerce Social Networks Based on Closeness and Users?? Credit Ju Chunhua, Zhao Kaidi, Bao Fuguang DOI: 10.3772/j.issn.1000-0135.2019.02.006 Opinion leaders play a major role in promoting information dissemination in social networks. Opinion leaders can often influence the masses and guide the trend of network public opinion. Looking for opinion leaders in the network can timely and can accurately grasp network dynamics. In this paper, we propose a calculation model of user influence intensity that integrates closeness centrality and tightness of credit, and looks for opinion leaders in e-commerce social networks. First, the model obtains the relationship adjacency matrix according to the friend relationship between users. Then the compactness centrality of each user is calculated with an adjacency matrix. The social credit rank algorithm is proposed for calculating user influence. The algorithm chooses the density centrality proportion of the user in the network as the probability that the user is randomly selected. The ratio of the user??s credibility to that of the friend's contribution is revised. In this paper, the user data of Alipay is used as an experimental object. The experimental results show that the method is more accurate than the general opinion leader identification method. 2019 Vol. 38 (2): 170-177 [Abstract] ( 234 ) HTML (123 KB)  PDF (1248 KB)  ( 746 )

178 Dynamic Identification of Key Nodes in Information PropagationNetworks During Emergencies Chen Sijing, Li Gang, Mao Jin, Ba Zhichao DOI: 10.3772/j.issn.1000-0135.2019.02.007 In order to effectively identify the key nodes in information propagation networks during emergencies and their dynamic characteristics during different stages of an emergency, this paper proposes a method that introduces crisis lifecycle theory and considers characteristics of user behaviors and global network attributes in the information propagation of social networks, as well as the decay law of spreading influence. Hurricane Harvey was chosen as a study case to conduct the experiment. Spearman??s correlation analysis and the SIR model were used to verify the effectiveness of this method. The results show that the TPR method is somewhat better than PageRank in terms of spreading speed and spreading scope. With the evolution of different stages of information propagation, the verification rate of key nodes increases. Therefore, the information advantage decreases at first, then increases after the chronic period, while the response advantage shows an opposite trend. There are no significant differences in the aspect of structural advantage. The results shed light on the management of public opinion: administrators should a) focus on the key nodes in the prodromal period that are non-verified and outstanding in terms of originality and information advantage; b) pay more attention to information provided by key nodes that are common netizens in the breakout period; c) strengthen the coordination among different types of key nodes in the chronic period; and d) keep an eye on small-scale clusters during the recovery period. 2019 Vol. 38 (2): 178-190 [Abstract] ( 328 ) HTML (189 KB)  PDF (1709 KB)  ( 1182 )

191 Named Entity Recognition Using Linked Data Liu Xiaojuan, Liu Qun, Yu Mengxia DOI: 10.3772/j.issn.1000-0135.2019.02.008 Named Entity Recognition (NER) is a basic task in the field of Natural Language Processing with generalized applications. Because of plentiful semantic knowledge, Linked Data can improve the performance of NER. This paper realizes a configurable NER System called NERULD （Named Entity Recognition Using Linked Data） that can support Chinese and English texts and is based on Linked Data in order to disambiguate the recognized entities and to extend the results of NER, so that a new idea to improve the performance of NER can be provided. This study was conducted as follows. We first built a cross-domain Chinese named entity dictionary and English named entity dictionary using the DBpedia dataset. We then designed a distributed model based on Hive and Hadoop to organize, store, and extend Linked Data. We developed a graph-based algorithm to recognize and disambiguate named entities, which can make full use of the semantic relationships of Linked Data. We also tested our algorithm using the DBpedia Spotlight NER Corpus, and compared our result with DBpedia Spotlight, NERSO, and Zemanta, and found that the algorithm implemented in this paper has better performance in recall, precision, and F value. 2019 Vol. 38 (2): 191-200 [Abstract] ( 190 ) HTML (91 KB)  PDF (12056 KB)  ( 403 )

201 Identification of the Main Path of Technology Diffusion and Core Enterprises: A Case Study of Patent Citation Network in Mobile Phone Chips Sun Bing, Xu Xiaofei, Su Xiao DOI: 10.3772/j.issn.1000-0135.2019.02.009 Patents are the largest source of information technology in the world. The change of patent reference data can reflect technology diffusion in an objective way. By using mobile phone chip technology as the research object, this paper constructs its patent citation network according to its patent data from 1990-2015 and then carries out an analysis of the overall network and the distribution of node degrees in the network. Consequently, the core patent of its citation network is determined and the main path of the patent technology diffusion of mobile phone chips is identified with respect to the network topology parameters. Furthermore, based on the BCRW algorithm, the differentiation of the core enterprises in the patentee network is completed. 2019 Vol. 38 (2): 201-208 [Abstract] ( 200 ) HTML (132 KB)  PDF (2979 KB)  ( 810 )

209 Explainable Real-Time Book Information Recommendation Model Yu Yisheng, Wei Rui, Liu Xinyan DOI: 10.3772/j.issn.1000-0135.2019.02.010 This study creates a baseline that considers the book and user simultaneously to improve explainability and precision and to maintain good real-time performance. Furthermore, we research it through comparative analysis and offline research, which prove that the bas-ICF algorithm performs better in reasonability and richness of the recommended reason. bas-ICF also performs better in terms of precision and maintains good real-time performance. 2019 Vol. 38 (2): 209-216 [Abstract] ( 212 ) HTML (133 KB)  PDF (999 KB)  ( 853 )

217 Review of Domestic and International Research on Big Data Quality Liu Bing, Pang Lin DOI: 10.3772/j.issn.1000-0135.2019.02.011 As a frontier research field, big data quality research is one of the core contents of big data research; it is also the focus of attention from all walks of life. Based on the literature on big data quality, this paper uses synthesis methods to examine the progress of relevant domestic and international research in terms of its basic implications, quality management, quality evaluation, and application practice. The results show that the study of big data quality is based on big data characteristics, with the basic attributes of big data quality as the core, combined with its application goals and applicable scenarios. It finally forms a complex and multidimensional theoretical system that is different from the conventional data quality theory. At the same time, the results indicate that the study of the essence of big data quality, the combination of technical and human environment, and research on the national and strategic levels based on a macro perspective will be the future research trends and research focus of big data quality research. 2019 Vol. 38 (2): 217-226 [Abstract] ( 153 ) HTML (188 KB)  PDF (693 KB)  ( 1966 )