[Purpose/Significance] This research analyzes the current state of digitizing ancient books in China and abroad, constructs a path for digitization, identifies shortcomings in domestic research, proposes future directions, and provides a reference for the convenient development and inheritance of traditional culture. [Method/Process] This research analyzed the main contents of the existing digitization research of ancient books in China and abroad.Combined with the Five Primitives Theory and the Digital Humanistic Technology System, this paper explored the path mode of ancient book digitization, and looked for the deficiencies and development directions of the current ancient book digitization research according to the domestic research status. [Results/Conclusion] This paper takes out the construction path of ancient book digitization in four stages: transformation, reconstruction, application and control, and plan the main research content of these four parts.Based on the literature analysis results and digitization path of ancient books, propose the future development direction of digitalization of ancient books in China.

[Purpose/Significance] Based on the digital humanistic perspective, taking the ancient Tibetan medical book"four medical codes"as an example, explore the relationship between diseases, etiology, drug use laws and new prescription mining paths in Tibetan medicine, and put forward the process and methods of knowledge discovery in ancient Tibetan medical books, which is conducive to the development and utilization of ancient Tibetan medical books and helps to interpret and disseminate the medical resources of ethnic minorities from specific practice. [Method/Process] This study used Python, Gephi and relative software to analyze the disease relationship, etiology relationship, medication rule mining and new prescription prediction and analysis of Tibetan medicine according to the research process of document identification and proofreading, data segmentation and extraction, data analysis and processing, data visualization and result interpretation. [Results/Conclusion] The relevant analysis process and results are helpful to complete the knowledge discovery of ancient Tibetan medical books, determine the feasible methods of content mining of ancient Tibetan medical books, and provide new ideas for the content mining and knowledge discovery of ancient Tibetan medical books.

[Purpose/Significance] In view of the lack of organization and utilization of the knowledge of ancient books of Tibetan medicine, a Named Entity Identification model for ancient books of Tibetan medicine was proposed to provide the basis and support for the in-depth mining of knowledge of ancient books of Tibetan medicine. [Method/Process] Based on the data set of the ancient Tibetan medical books"The Four Medical Tantras", on the basis of manual annotation and text pre-processing, ALBERT-BERT-BILSTM-CRF, BERT-BILSTM-CRF, BILSTM-CRF and BERT were used to carry out named entity recognition experiments, and the experimental results were compared and analyzed. [Results/Conclusion] The F1-score of ALBERT-BERT-BILSTM-CRF model entity recognition reached 96.28%, which is about 7 percentage points higher than other methods.

[Purpose/Significance] In order to fulfill the research demand of professionals in Tibetan medicine, this paper explores the path to realize knowledge organization and knowledge service of Tibetan medicine ancient books, and designs knowledge service functions for the Tibetan medicine ancient books service platform. [Method/Process] On the basis of designing the knowledge ontology model and knowledge graph of Tibetan medicine ancient books, this paper tried to apply three service ways of knowledge retrieval, knowledge reasoning and knowledge push in the field of knowledge service of Tibetan medicine ancient books to enhance the quality of the knowledge service and the fine-grained of knowledge organization, and provide more efficient and high-quality knowledge service for the professionals. [Results/Conclusion] The research shows that the application of intelligent algorithms such as humanities computing in the knowledge processing of Tibetan medical ancient books can provide users with accurate and efficient knowledge services, and fully explore and utilize the vitality and value of Tibetan medicine ancient books.

[Purpose/Significance] Establish a scientific service quality evaluation system for the digital platform on Traditional Chinese Medicine(TCM)ancient literatures, providing reference for the platform to improve service quality and enhance user satisfaction in the future. [Method/Process] Beginning with the service characteristics of the digital platform on TCM ancient literatures and the classical theoretical model for service quality evaluation, the SERVQUAL model was firstly established for reference in the evaluation of the service quality of the digital platform on TCM ancient literatures through literature review, then the service quality evaluation index of the digital platform on TCM ancient literatures was determined by factor analysis, and the weights of indicators at all dimensions in the evaluation system were determined by using the principal component analysis. [Result/Conclusion] The service quality evaluation system of the digital platform on TCM ancient literatures, which includes 6 dimensions and 22 secondary indicators.According to the proposed evaluation index, three platforms are selected for service quality evaluation.Finally, the service quality improvement strategy of the digital platform on TCM ancient literatures is proposed.

[Purpose/Significance] This study predicts the diffusion effect of literature based on the knowledge association between target scientific papers and their early citing publications.It helps in the prospective identification of high-impact academic papers from the perspective of value feedback and provides a reference for researchers to establish an early evaluation system for scientific performance. [Method/Process] This study measured the degree of association between target scientific papers and their early citing publications from three perspectives, i.e., topic, journal, and author, and adopted the linear regression and negative binomial regression models to dissect the key factors affecting the diffusion effect(i.e., diffusion speed, breadth, and intensity).Based on the regression result, the study incorporated machine learning algorithms to predict diffusion effect of scientific papers and analyzed the importance ranking of the three types of knowledge association features in the prediction task. [Result/Conclusion] Subject association positively promotes the diffusion speed of scientific literature but shows an inverted U-shaped relationship with the diffusion breadth and intensity.Journal association inhibits the diffusion speed but can positively affect the diffusion intensity and breadth.Author association only has a consistent positive impact on the diffusion intensity.Predicting diffusion speed can be effectively achieved based on topic and journal associations, although accurately predicting diffusion breadth and intensity through knowledge associations proves to be challenging.The random forest model performs best in predicting diffusion speed, with topic association being of higher importance compared to journal association.

[Purpose/Significance] Personal epistemological beliefs are widely considered to be an important factor affecting personal knowledge change and learning process.This research takes the issue of climate change as the research context, interprets the epistemological beliefs and knowledge construction process of individuals in the process of search as learning, and has great significance in expanding and refining the dimension of subject attributes in information search research. [Method/Process] The study used the interpretative phenomenological analysis, interviews and questionnaires to understand participants' general epistemological beliefs, topical epistemological beliefs and retrospective oral; used written reports guided by eye tracking to explore and search from multiple aspects of knowledge quality, knowledge change. [Results/Conclusions] The research finds that the lower the simplicity and certainty of the topic epistemological belief, the more flexible the search strategy, the higher the quality of knowledge, and the greater the breadth of knowledge change; when the belief of epistemic justification is missing, the depth of knowledge change would also be missing.

[Purpose/Significance] This study aims to construct a knowledge representation and semantic enhancement framework for linear cultural heritage resource, which provides guidance for cultural institutions to carry out intelligent data construction of cultural heritage and promotes the innovative development of excellent traditional culture. [Method/Process] Based on the distilled characteristics of"resource communalism, temporal flow, and spatial chaining"in extracting linear cultural heritage, this study analyzed the hierarchical structure of the knowledge system of linear cultural heritage.It constructed a knowledge representation model for linear cultural heritage resources.Basing on representation theory and situational cognition theory, it semantically enriches linear cultural heritage data from the perspectives of structured semantic enhancement and contextual semantic enhancement.It innovatively proposed a dual-dimensional semantic enhancement path of"time and space".Finally, took the Grand Canal linear cultural heritage as an example, conducted a case study on knowledge representation and semantic enhancement of the Grand Canal. [Result/Conclusion] The knowledge representation model and semantic enhancement framework constructed in this study are conducive to multidimensional semantic organization and in-depth mining of linear cultural heritage data, which can enhance the semantic connectivity and extension of linear cultural heritage contents.

[Purpose/Significance] In order to change the evaluation methodology of the academic quality which only measured by journals quality before, this paper attempts to carry out academic quality evaluation of knowledge element granularity from text fragments. [Method/Process] Firstly, knowledge elements in academic literature were extracted based on the description rules of knowledge element; Secondly, it combed the existing evaluation indicators of academic quality and constructed a preliminary quality evaluation system of knowledge element; Thirdly, it improved the quality evaluation system, and score quality of knowledge element according to the experts' opinions; Finally, regression analysis was used to fit each quantitative index and expert score, so as to realize the automatic quality evaluation of knowledge element. [Result/Conclusion] A three-dimensional evaluation model with formal evaluation, content evaluation and utility evaluation has been constructed, which has realized the automatic measurement method of knowledge quality integrating experts' opinions, overcome the shortage of academic quality evaluation relying on academic carriers, and really deepened the element of academic evaluation from knowledge carrier to knowledge content.

[Purpose/Significance] In order to explore the knowledge contained in tourism platform travelogue texts and assist travelers in efficiently obtaining information and knowledge that meets their needs, this study aims to provide information support for scientific decision-making in travel planning. [Methods/Process] Firstly, based on Boolean matrix and set logic, the study proposed an improved Apriori algorithm to meet user needs.Then, integrated a named entity recognition to implement travelogue text association knowledge mining and aggregation.Based on association knowledge mining, a personalized recommendation service model was constructed, and empirical research was conducted on Hangzhou-related travelogue texts in Ctrip. [Results/Conclusions] The study finds that the integration of named entity recognition and improved Apriori algorithm can effectively mine the knowledge contained in travelogue texts.The experimental results verifies that the performance and mining results are better than traditional Apriori algorithm.Based on the mining results, personalizes recommendation services can be provided to users, assisting travelers in scientifically and efficiently planning their trips.The research enriches the methodology of travelogue text mining and provides new ideas for optimizing tourism platform service recommendations.

[Purpose/Significance] This article proposes an agricultural named entity recognition method based on the fusion of multiple feature word embedding models in the agricultural field to improve recognition. [Method/Process] The study used multiple feature vectors such as characters, positional semantics, and domain knowledge dictionary features as embedding layers, fully considered the positional and contextual semantic information of characters, and improved the single character vector embedding based on the characteristics of Chinese entities in the agricultural field, obtained more agricultural entity features.Simultaneously, used the bidirectional long and short term memory network(BiLSTM)and multi head attention mechanism to learn the long-distance dependency information of the text, and then used the conditional random field(CRF)to obtain the global optimal annotation sequence. [Result/Conclusion] This article conducts comparative experiments with 9 baseline based methods on the Chinese entity corpus dataset in the agricultural field.The model's Precision is 92.2%, Recall is 92.0%, and F1 value is 92.11%, all of which are better than other baseline models, indicating that the model proposed in this article is more accurate in recognizing Chinese agricultural name entities.

[Purpose/Significance] Users often obtain code-related knowledge in open source software communities, but lack the motivation and intention to contribute their knowledge.This may affect the sustainable development of open source software communities. [Method/Process] Integrating the motivational theory and social capital theory, this research created a model, and used the mixed method of SEM and fsQCA to analyze the data. [Result/Conclusion] The results show that intrinsic motivations(flow experience and self-efficacy), extrinsic motivations(perceived reputation and reciprocity), social interaction ties, identification, and common language positively affect users' intention to contribute knowledge.The fsQCA results indicated that flow experience, perceived reputation, reciprocity and trust are the common core conditions of four configurations.The results show that open source software communities should be concerned with both intrinsic and extrinsic motivations, and develop social capital in order to stimulate users' contribution intention and ensure the continuous and rapid development of communities.

[Purpose/Significance] In order to prevent individuals from falling into the information cocoons, the study focuses on the interactions and correlation paths of the factors influencing the information cocoons of Internet users and proposes some targeted and holistic "cocoon breaking" strategy. [Method/Process] The study determined 16 factors affecting the information cocoons and their direct influence relationships through literature review and expert opinions, and constructed an interpretative structural model to reveal the hierarchical relationships and correlation paths among the factors.The driving forces and dependencies of the factors were further analyzed with the help of the matrix impacts cross-reference multiplication applied to a classification, while the scientific validity of the interpretative structural model verified. [Result/Conclusion] The hierarchical structure model of the influencing factors of network user information cocoons includes 6 levels, which can be divided into 3 layers: direct layer, middle layer and root layer.MICMAC analysis obtains the independent cluster, dependent cluster and autonomous cluster factors that affect the user's information cocoons.The two are unified in the nature of influence, indicating that the constructed interpretative structural model is scientific and reasonable.Based on this, corresponding suggestions are put forward to break through the constraints of the information cocoons effect from 5 aspects: information literacy, opinion leaders, community influence, selective psychology and opinion personalized information needs.

[Purpose/Significance] Studying the influencing factors of user satisfaction on audiobook platform will help platform operators to improve the core issues affecting user satisfaction, improve the service quality of the platform, enhance user satisfaction with the platform, and promote the sound and sustainable development of audiobook platform. [Method/Process] From the perspective of information ecology, the influencing factors of user satisfaction of audiobook platform were divided into dimensions.Based on the existing relevant literature, the influencing factors of user satisfaction were extracted, and the questionnaire was designed with KANO model to judge the importance attributes of each influencing factor. [Result/Conclusion] The influencing factors of user satisfaction of audiobook platform mainly include four dimensions: information, information user, information technology and information environment.Among the 25 influencing factors of user satisfaction, there are 5 attractive factors, 8 expected factors, 1 essential factor, 10 indifference factors and 1 reverse factor.It is suggested that user satisfaction can be improved from the expected attribute factors that have the greatest impact on satisfaction, such as platform design, auditory perception, standardized management and information quality.