[Purpose/Significance] To give full play to the leading role of intelligence personnel, provide theoretical guidance for the management optimization, analysis and refinement of electronic medical record data from the perspective of"data potential energy", expand the application scenarios of information science, increase the means of hospital knowledge service, and improve the efficiency of knowledge service. [Method/Process] Based on the concept of"data potential energy"and related theories of information science, the potential energy accumulation and release model of electronic medical records was constructed, and the potential energy accumulation dimension and release process of electronic medical records data were analyzed.The potential energy model was verified by case study and machine learning algorithm. [Result/Conclusion] Taking the information science perspective as the starting point and the end result, this paper uses the concept of"data potential energy"to elaborate the mode of organization, integration, analysis and application of electronic medical record data, and uses real-world case data and electronic medical record data to verify the validity and rationality of the theory.

[Purpose/Significance] Integration of Yangtze River Delta is part of the national strategy in China.It is of great value to study regional innovation ecosystem in the Yangtze River Delta from the perspective of knowledge collaboration. [Method/Process] Based on the analysis of relevant papers, this paper analyzed the regional innovation ecosystem in the Yangtze River Delta.Besides, it analyzed the process and mechanism. [Result/Conclusion] Above all, it is believed that the regional innovation ecosystem in the Yangtze River Delta has great foundation for knowledge collaboration, which enables to promote innovation by creating mechanism of knowledge collaboration.

[Purpose/Significance] The Internet technology in the 21st century has provided an open communication platform for academic research, and scientific research information resources have grown exponentially.It is difficult for scholars to quickly obtain the required information, resulting in a low utilization rate of academic resources.Accurate and personalized recommendation of academic resources has become an effective way to improve the efficiency of academic information transfer and its value appreciation. [Method/Process] In this paper, the heterogeneous information network was weighted by using the publication time factor and the semantic similarity of the literature, and based on this weighted network, Node2vec was used to generate graph node sequences with biased random walks, and then the skip-gram language model was used for sequence learning, and finally the similarity of node vectors was calculated to achieve academic information recommendation. [Result/Conclusion] The model is verified by the data set in CNKI.The empirical results show that the papers and scholars recommended by the model are in line with the research direction of the target scholars on the one hand, and the time dimension on the other hand.It is also more accurate, which can effectively meet the information needs of scholars and promote academic communication.

[Purpose/Significance] Massive digital resources of Dunhuang mural images, which possess high research and artistic value, are stored in the LAMs.The inefficient utilization of them needs to be solved urgently by optimizing resource acquisition services. [Method/Process] A mobile visual search model was contructed for Dunhuang murals to provide users with accurate, fast, and rich resource acquisition services.This model comprised four parts: repository construction, image feature extraction, image feature compression, and semantic feature fusion and re-ranking.Deep learning were used to extract image features of Dunhuang murals, hash algorithms were used in the output layer to perform feature hash coding, and similar images were matched through Hamming distance calculation; top-1 similar image features and semantic features extracted by SimHash algorithm were combined to reduce the semantic gap.At the same time, the image dataset and the text dataset of Dunhuang murals were constructed, then the optimal algorithm combination was selected through experiments, and the effectiveness and superiority of the model were verified. [Results/Conclusion] Compared with existing models, the search performance of the mobile visual search model of Dunhuang murals proposed in this paper, the mAP of which is 69.93%, is significantly improved, and the similar image search that integrates the semantic features of images helps users to gain a better understanding of the connotation of Dunhuang murals.

[Purpose/Significance] In order to solve the problems of insufficient semantic description and weak semantic coherence of the learned topic in the comment text.This paper combines sentence embedding model of sentence Bert with LDA model to improve the semantics of the topic of comment text. [Method/Process] The sentence Bert model was used to obtain the vector features of the comment text at the sentence level.At the same time, the LDA model was used to obtain the probability topic vector of the comment text.Then the automatic encoder was used to connect the two groups of vectors, and the K-means algorithm was used to cluster the potential spatial vectors to obtain the contextual topic information from the cluster. [Result/Conclusion] Through the experiment of comment text, this method can better obtain the subject words with semantic information.Through comparison, the topic consistency index obtained by this method is better than the current comment text topic recognition methods.

[Purpose/Significance] On the basis of technical similarity, a multi-layer heterogeneous network link prediction algorithm is introduced, and a method for predicting the patent cooperation relationship between industry university research enterprises and scholars is proposed. [Method/Process] Firstly, the feature vector system of enterprises and scholars was constructed, and the node features were constructed.Secondly, a two-layer network of scholar cooperation network and enterprise scholar cooperation network was built, R-GCN algorithm for model training was used, and the technical similarity between enterprise scholars was calculated.Finally, the technical similarity was fitted with the results of R-GCN model by logistic regression, and the final cooperative prediction results were obtained. [Result/Conclusion] Through the empirical analysis of the patent data set in the field of biomedicine, the accuracy, recall, AUC, MSE, F2 score and MRR of the technical similarity+multi-layer heterogeneous network link prediction algorithm were 67.74%、78.02%、90.95%、4.41%、34.00%、52.05%, respectively, among which the MRR was 8.67 times、1.78 times、2.58 times、1.65 times higher than that of R-GCN, Jaccard, cosine and Euclidean respectively. [Limitations] Adding new nodes in R-GCN model requires global training and calculation.It is suitable for small networks and static networks. [Conclusion] This scheme proposes a scheme to directly recommend patent cooperation scholars for enterprises, which integrates patent content and patent cooperation network, and has a good prediction effect.

[Purpose/Significance] As a crucial aspect of promoting the development of libraries, the evaluation of smart library is very important to further strengthen the development of its theoretical research and practice. [Method/Process] The maturity evaluation model and the triangular fuzzy function evaluation method were introduced into the evaluation process of smart library, so as to the fuzzy evaluation method of the construction maturity of smart library was determined, and an empirical analysis of typical college libraries was carried out. [Result/Conclusion] Some achievements have been made in the construction of smart libraries in China, but there are still many shortcomings.It is suggested that in the process of smart library construction in the future, relevant construction subjects should clarify their ideas, and promote the realization of the construction and development goals of smart libraries by constructing a collaborative development mechanism of stakeholders, formulating a gradual path of realizing smart, establishing a comprehensive security system, and selecting differentiated construction modes.

[Purpose/Significance] Strengthening the innovation capability of the IC industry and building a stable network of cooperative innovation relationships is an important economic development strategy to promote China's IC field to break through the technological bottleneck as soon as possible and stand out in the international competition. [Method/Process] Based on the patent data in the IC field, the inter-enterprise evolutionary network, industry-academia-research evolutionary network, and relationship characteristic evolutionary network was constructed, and the network evolutionary development law in the IC field was explored from the perspective of overall evolutionary trend and network characteristic changes. [Result/Conclusion] The gap between the head enterprises and other small and medium-sized enterprises is large, and the long-tail effect is more obvious.Universities and research institutions are pioneers in the field and can help enterprises reduce the influence of distance and deepen the trust mechanism.Inter-enterprise network centrality and cohesion have fluctuated in recent years, with a slight decrease in the growth rate of network size and a gradual bias of cooperation towards the trend of technological diversity, geographical proximity, and upstream and downstream development of the industry chain.

[Purpose/Significance] As social network has a more and more advantage in the process of obtaining information and sharing convenience for people's daily life, it is of great significance to study the information dissemination mechanism of social networks and mine high influential nodes in the network for controlling the dissemination of network information and deepening the ecological governance of network information. [Method/Process] Based on the influence of interaction mode between network nodes on the scale of social network information dissemination, a network information dissemination model, which was studied by making full use of the positive interaction between user nodes, was proposed, and the role of positive interaction mode in network information dissemination was discussed.A random walk algorithm, which maximized the active interaction between nodes, was introduced to identify high impact nodes in social networks by considering that the active interaction between nodes can affect the activity of their neighbors. [Result/Conclusion] The research results show that the interaction between network nodes plays a strong role in activating the group influence effect of their neighbors and promoting the scale of network information dissemination.In addition, the new algorithm based on the positive interaction factors between network nodes is more effective than the weighted PageRank algorithm and the weighted LeaderRank algorithm in identifying high influence nodes.

[Purpose/Significance] It is a new direction to study the opinion evolution of micro-individuals from psychology to govern public opinion, which extends the theoretical research on people-oriented public opinion management.Based on cognitive dissonance, this paper constructs an opinion evolution model to study the group viewpoint trend. [Method/Process] First, the paper summarized the dynamic mechanism of network topology by analyzing the mitigation measures of individuals to cognitive dissonance.Then, according to the network structure, the intimacy degree of everyone was defined, and the acceptance of other individuals' opinions was measured by the intimacy degree, so a new opinion evolution rule was constructed.Finally, the paper set different psychological environments by adjusting the parameters and made the opinion simulation under different circumstances. [Result/Conclusion] The experimental results show that the aggregation of group opinion is more significant in the cognitive dissonance environment; The larger the social threshold of individuals in the cognitive dissonance environment is, the stronger the tolerance to contradictory opinions, which is conducive to the achieve social consensus; For different numbers of stubborn individuals in the group, if the supervision departments want to achieve different public opinion guidance effects, they should take differentiated governance measures.

[Purpose/Significance] In the evaluation of academic journals, different evaluation indexes are often highly correlated.This will lead to data redundancy and information overlap, which will seriously affect the multi-attribute evaluation results of the index system. [Method/Process] On the basis of theoretical analysis, this paper proposed a new index independent information measurement method, and made an empirical study based on the data of CNKI agricultural journals. [Result/Conclusion] The results show that enough attention should be paid to the information overlap caused by the correlation between evaluation indexes.The independent information measurement method based on regression provides a better solution.Independent information index is an inverse index; Independent information index can reflect the"meta information"of the original index, so this method has a certain value of promotion.

[Purpose/Significance] The study was aimed to offer a new way to explore the knowledge map of domain interdisciplinary research based on methods in bibliometrics and text mining. [Method/Process] A domain interdisciplinary knowledge mapping research framework with visualized disciplinary diversity measure index and topic model was proposed.The domain interdisciplinary knowledge mapping was constructed based on Science Overlay Map and LDAvis embedded in the domain ontology.The validity and applicability of the interdisciplinary knowledge mapping research framework was verified by using the nanotechnology domain as an example. [Result/Conclusion] The Science Overlay Map-based domain interdisciplinary science map shows the intersection between the nanotechnology domain and other disciplines from a discipline-wide perspective, while the LDAvis-based interdisciplinary topic interaction map combined with the domain ontology focuses on specific interdisciplinary topics and the interrelationships between the topics.The combination of the two can provide a clearer picture of the intersection of the field of nanotechnology with other disciplines at both the macro and micro levels.The study can make up the limitation that the interdisciplinary topics inferred by LDA cannot be easily interpreted, and provide a new perspective of solution for domain interdisciplinary knowledge mapping research.

[Purpose/Significance] The purpose of this study is to help the academic community deeply understand the development and application of social support theory in IS discipline, and provide reference for the follow-up research. [Method/Process] By searching and systematically combing the relevant literature, this study summarized the current research achievements, limitations and future research directions. [Result/Conclusion] It's found that the researches based on social support theory in IS Discipline mainly focus on three research aspects: "The application of SST in the research of online health information behavior""The application of SST in the research of social commerce consumer behavior"and"The application of PRT in the research of information system/service design and use".There are some limitations such as"the expression forms and subdivision dimensions of social support in different situations have not been thoroughly explored, and a unified framework has not been formed""less attention is paid to the relationship between different types of social support"and so on.Building the connotation framework of social support in different situations, analyzing the relationship between different supports, exploring the reasons for the inconsistency of existing research conclusions, and conducting more detailed, concrete and in-depth research, etc.are important research issues in the future.

[Purpose/Significance] In order to help researchers comprehensively understand the application of self-determination theory in the field of information system, so that the future researches can use this theory to solve the related problems more appropriately. [Method/Process] By summarizing the important research achievements of self-determination theory in the field of information system, this paper revealed their progresses and existing limitations, the future directions were also prospected. [Result/Conclusion] The research on self-determination theory in the field of information system mainly focuses on five aspects: human-computer interaction design, adoption and continued use of virtual communities, willingness of online study, internet addiction and network knowledge contribution.Besides, there are still some problems in the existing researches, include"research subjects have limitations""the pre-variables of the three psychological needs are not explored enough""lacking consideration of individual personality and social factors""the model of influence of basic psychological needs on users' willingness and behavior is uncertain"and"some conclusions diverge", future researches can focus on these aspects.

[Purpose/Significance] To sort out and summarize the relevant research on the elaboration likelihood model in the field of information systems, and provide researchers with ideas and research directions. [Method/Process] After sorting out the origin and development of the elaboration likelihood model, this paper summarized the research questions into three aspects: the application of the elaboration likelihood model in the adoption and use of information technology/systems, the application of the elaboration likelihood model in online information processing and decision-making, and the application of the elaboration likelihood model in the online information security research. [Result/Conclusion] The existing studies have shortcomings such as the unclear roles of information characteristic variables, unclear dual-path mechanism, less attention to qualitative research methods, less attention to the gap between willingness and actual behavior of users, and weak attention to user personality characteristics.However, in the future, research progress can be made in the above aspects.

[Purpose/Significance] The purpose of this study is to help the academic community deeply understand the application and development of communication privacy management theory in information system discipline. [Method/Process] After introducing the origin and evolution of this theory, by searching and coming the relevant literature, this paper summerized the achievements, limitations and future research directions of current research. [Results /Conclusions] It is found that the application of communication privacy management theory in information system discipline mainly focuses on three research aspects: the impact of information technology on organizational management, the factors influencing information system users' willingness to disclose their privacy, and the impact of social media on intimate relationships.In addition, it is found that existing studies remain some limitations such as"inconsistency in the impact of social media use in the work environment on organizational management""insufficient attention to the actual privacy disclosure behavior of users", and"insufficient attention to the middle-aged and elderly IT user groups".Expanding the way to get data, analyzing more objective user behavior data, and exploring the impact of IT on the privacy management of middle-aged and elderly people, etc.are the directions of concern for the future study.