International Journal of Networking and Virtual Organisations (18 papers in press)

Regular Issues

• Social Network Analysis Method of Teaching Constraints and Development Approach of Online Courses  
  by Siyue Wang, Weisheng Wang 
  Abstract: In order to overcome the low student participation rate, homework completion rate and course satisfaction existing in the traditional analysis method of online course teaching constraints and development paths, a social network analysis method of teaching constraints and development approach of online courses is proposed. Calculate the network density of social network and the centrality between points, identify the key time points or events that affect the teaching effect of online courses, thus determine the constraints of online course teaching, including technology, resources, educational environment and student factors, and analyse the development path of online course teaching from the aspects of technological innovation and application, updating teaching concepts, optimizing course design and management, and strengthening resource integration and sharing. The experimental results show that the average student participation rate is 97.17%, the average homework completion rate is 96.79%, and the course satisfaction is always above 96.6.
  Keywords: Social network analysis; Online courses; Constraints; Development approach; Network density; Centrality between points.
  DOI: 10.1504/IJNVO.2024.10067045
   
  
• Study on Comprehensive Management of Online Learning Resources for Digital Education and Teaching Reform  
  by Yali Zhang 
  Abstract: In order to improve the efficiency of utilising online learning resources and the quality of students learning, this paper proposes a comprehensive management method for online learning resources aimed at digital education and teaching reform. Firstly, this paper provides a detailed explanation of the definition, classification, and application of online learning resources in education. Furthermore, this paper conducts an in-depth analysis of the resource merging and classification problems and recommendation issues in current online learning resource management, and points out the challenges of these problems. On this basis, this paper adopts an adaptive sliding window mutual information method to extract the features of network learning resources, thereby achieving resource merging and classification management. The experimental results show that under the background of digital education and teaching reform, the method proposed in this paper can not only effectively classify and manage online learning resources.
  Keywords: Digital education and teaching reform; Online learning resources; Comprehensive management; LDA User Interest Model.
  DOI: 10.1504/IJNVO.2024.10067046
   
  
• Resource Allocation of Distributed Wireless Network Based on Mobile Edge Computing  
  by Xiaobo Zhang, Ketong Liu, Yan Zhang 
  Abstract: To solve the problems of high packet loss rate, low configuration balance and long time in traditional resource allocation methods, a resource allocation method of distributed wireless network based on mobile edge computing is proposed. The mobile edge computing is used to select the distributed wireless network service nodes, so as to determine the constraints such as task unloading, resource allocation, task execution delay, transmission rate, etc., build the distributed wireless network resource allocation objective function, and use the genetic-annealing algorithm to solve the objective function. The optimal solution is the optimal distributed wireless network resource allocation scheme. The experimental results show that the average packet loss rate of this method is 3.06%, the resource allocation balance of distributed wireless network varies from 0.96 to 0.96, and the average allocation time is reduced by 2.12s and 1.19 respectively compared with the two experimental comparison methods.
  Keywords: Mobile edge computing; Distributed; Wireless network; Resource allocation; Constraints; Objective function; genetic-annealing algorithm.
  DOI: 10.1504/IJNVO.2024.10067311
   
  
• Evaluation of Interactive Teaching Effectiveness under Social Network Analysis  
  by BinBin Yan 
  Abstract: In order to effectively improve the accuracy and comprehensiveness of evaluation results, a method for evaluating the effectiveness of online interactive teaching under social network analysis is proposed. Firstly, collect online interactive teaching data, use Pearson correlation coefficient to calculate the correlation coefficient between the data, and screen out indicators that are significantly related to teaching effectiveness. Secondly, use information entropy to calculate the weight of evaluation indicators. Finally, construct a social network model, measure the node intimacy function, and identify important nodes in the social network to optimise the social network model and more accurately evaluate teaching effectiveness. The experimental results show that the highest accuracy value of the method proposed in this paper is 95%, the highest precision value is 72%, and the highest recall value is 92%, all of which are better than existing methods, fully demonstrating the effectiveness of its teaching effectiveness evaluation.
  Keywords: Social network; Interactive teaching; Effect evaluation; Pearson correlation coefficient.
  DOI: 10.1504/IJNVO.2024.10067312
   
  
• Online Financial Product Marketing Information Push Method based on Social Relationship Network Analysis  
  by Zihan Gao 
  Abstract: The research on online financial product marketing information push is of great significance for improving the efficiency of financial institutions, optimizing product design, and promoting financial technology innovation and digital transformation. In order to solve the problems existing in current methods, an online financial product marketing information push method based on social relationship network analysis is proposed. This method uses social network to analyse and calculate the influence of user relationship, and combines with two-way GRU neural network to extract user interest. Push online financial product marketing information based on user interests and multi-Markov chain. Experimental results show that the proposed method performs well in accuracy, push time and user retention rate. Therefore, this method has the characteristics of high precision and high efficiency.
  Keywords: Social relationship network analysis; Online financial product; Marketing information push; Two-way GRU neural network; Multi-Markov chain.
  DOI: 10.1504/IJNVO.2024.10067417
   
  
• Personalized Learning Resource Online Recommendation Method based on Multi-Dimensional Feature Extraction  
  by Yi Liu, Fu Peng 
  Abstract: To enhance the efficiency of resource suggestion, the article introduces an online approach for recommending customized educational materials through the extraction of multi-faceted characteristics. Initially, leveraging the descriptors and density metrics of user activity data, a clustering technique is employed to group users with analogous inclinations and behaviors; Subsequently, the user's chronological attributes, predilection traits, and educational material specifics are culled, and these are organized into feature matrices to facilitate thorough feature analysis; Conclusively, the culled attributes of customized educational materials are fed into the SOM neural network, and via a scoring system for resources and a process of calculating similarities, predictive values for suggestions are computed and ranked to compile a tailored suggestion list. The empirical findings indicate that this technique adeptly and swiftly furnishes resource options that align with user requirements as the volume of resources and users swells, with the suggestion success rate consistently surpassing 90%.
  Keywords: Personalized learning resources; Resource recommendation; User clustering; Time characteristics; Preferential features; Feature extraction; SOM network; K-means algorithm.
  DOI: 10.1504/IJNVO.2024.10067428
   
  
• An Optimisation Strategies for Organisational Structure of Human Resource Management based on Social Networks  
  by XiaoYan Shi, Ao Jiang 
  Abstract: In order to solve the problems of high employee turnover rate, low task completion rate, and long decision-making time in traditional human resource management organisational structure optimization methods, an optimisation strategies for organizational structure of human resource management based on social networks was studied. Establish a human resources management organisational network, identify key individuals, teams, and potential problem areas within the organisation through intermediary centrality, weighted centrality, and clustering coefficients, identify existing problems in the human resources management organizational structure, and propose optimisation strategies for the human resources management organisational structure from multiple aspects such as optimising management structure, innovating management concepts, optimising talent allocation, and strengthening internal communication. The test results show that the employee turnover rate in the 10th month under the application of the proposed method is 8.36%, the task completion rate is 92.76%, and the minimum enterprise decision-making time is 4.5 minutes.
  Keywords: Social networks; Human resource management; Organizational structure; Optimization strategies; Intermediary centrality; Weighted centrality; Cluster coefficients.
  DOI: 10.1504/IJNVO.2024.10067429
   
  
• High Quality Construction of Innovation and Entrepreneurship Education System from the Perspective of Three Comprehensive Education  
  by Xiao-Ying Fang, MingXing Lu 
  Abstract: In order to overcome the problems of low quality index, innovative thinking path coefficient, and high error value in traditional methods, a high quality construction method of innovation and entrepreneurship education system from the perspective of three comprehensive education is proposed. Firstly, analyse the participants and influencing factors in the construction of the innovation and entrepreneurship education system from the perspective of comprehensive education. Secondly, establish a preliminary innovation and entrepreneurship education system. Finally, after evaluating the quality of the innovation and entrepreneurship education system, we will optimise and adjust the preliminary construction system to achieve high-quality construction of the innovation and entrepreneurship education system. The experimental results show that the quality index of the innovation and entrepreneurship education system constructed in this article is high, the path coefficient of innovative thinking is high, and the average evaluation error value is low.
  Keywords: Three comprehensive education; Innovation and entrepreneurship; Education system; High quality; Evaluating.
  DOI: 10.1504/IJNVO.2024.10067430
   
  
• The Construction of Innovation and Entrepreneurship Education Ecosystem in Universities Based on Social Network Analysis  
  by Yang Zhang, Jing Liu, Yunmin Xie 
  Abstract: In order to solve the problems of resource utilisation rate, achievement conversion rate, and low student satisfaction in traditional methods, a construction method of innovation and entrepreneurship education ecosystem in universities based on social network analysis is proposed. Analyse the concept of the innovation and entrepreneurship education ecosystem in universities, determine the relationship between the constituent elements, and use social network analysis methods to identify the bottlenecks and shortcomings of the innovation and entrepreneurship education ecosystem in universities. Starting from establishing innovative educational models, strengthening interdisciplinary integration, establishing innovation and entrepreneurship practice platforms, and strengthening industry and enterprise cooperation, will complete the construction of the innovation and entrepreneurship education ecosystem in universities. The test results of the example application show that the average resource utilization rate of the proposed method is 83.27%, the average achievement conversion rate is 86.55%, and student satisfaction varies between 91.2 and 93.6%
  Keywords: Social network analysis; Universities; Innovation and entrepreneurship education; Ecosystem; Constituent elements; Educational models.
  DOI: 10.1504/IJNVO.2024.10067431
   
  
• Research on Financial Systemic Risk in the Digital Era and its Dual Pillar Regulatory Framework  
  by Anan Zheng 
  Abstract: To address the issues of elevated inaccuracy levels, prolonged verification durations, and diminished efficacy in risk management associated with conventional approaches, a financial systemic risk in the digital era and its dual pillar regulatory framework construction method are proposed. Analyse the impact of systemic financial risks on financial stability, combined with financial system risk measurement indicators such as CoVaR and Sharply value are used to identify financial system risks in the digital era. Based on the identification results of financial systemic risks in the digital era, a dual pillar regulation framework is constructed to achieve financial systemic risk regulation in the digital era from the perspectives of monetary policy and macro prudential policy. After experimental testing, it was found that the average risk misreporting rate of this method is 3.02%, the recognition time range is 0.21s~0.63s, and the average success rate of risk control is 96.17%
  Keywords: Digital era; Financial systemic risk; Dual pillar regulatory framework; Risk measurement indicators; Identify financial system risks; Monetary policy; macro prudential policy.
  DOI: 10.1504/IJNVO.2024.10067432
   
  
• Study on Digital Financial Fraud Risk Identification based on Heterogeneous Graph Convolutional Attention Network  
  by Yang Jin 
  Abstract: To enhance the accuracy of digital financial fraud risk identification and reduce the identification time, this paper introduces a digital financial fraud risk identification method utilising a heterogeneous graph convolutional attention network. Initially, financial business data is gathered and processed for data imbalance using generative adversarial networks. Subsequently, extreme learning machines are employed to extract spatially correlated features among various transactions. Following this, a robust graph convolutional attention network is constructed, a risk identification function is designed, and ultimately, the fraud data is fed into the graph convolutional neural network for training. The output data is categorised by transaction type to ascertain the presence of digital financial fraud risk. The results indicate that our method achieves a recognition accuracy exceeding 96%, with time consumption not surpassing 8.5 s, demonstrating that our method exhibits excellent recognition performance.
  Keywords: Heterogeneous Graph Convolutional Attention Network; LSTM training; Digital finance; Fraud risk; Extreme learning machine.
  DOI: 10.1504/IJNVO.2024.10067433
   
  
• Dynamic Mining of Multimedia Marketing Information for Products under the Background of Data Driven  
  by Yingjun Liu, Kuineng Chen 
  Abstract: In this paper, a new dynamic mining method of multimedia marketing information for products under the background of data driven is proposed. Using web crawler technology to crawl multimedia marketing information data of products, and extracting data features through sliding clustering. By using fuzzy clustering algorithm to perform fuzzy clustering on data features, a clustering dataset item set is constructed and merged into an item set to assign weights. Combined with association rules, dynamic mining of multimedia marketing information for products is achieved. Experimental results have shown that the mining coverage rate of this method is 91%~97%, and the product conversion rate is 19.1% when the data volume is 8000. The mining coverage rate and product conversion rate are both at a high level, and the mining effect is good.
  Keywords: Data driven; Multimedia marketing information; Dynamic mining; Fuzzy clustering; Association rules.
  DOI: 10.1504/IJNVO.2024.10067434
   
  
• Construction of Teaching Service Quality Evaluation Index System under the Digital Background  
  by Xin Liu, Lei Wang 
  Abstract: In order to solve the problems of low system integrity, poor closeness and reliability of evaluation indicators in traditional methods, a construction method of teaching service quality evaluation index system under the digital background is proposed. Complete the selection of evaluation indicator data through the ripple effect model. By calculating the Mins distance to measure the similarity of evaluation index data and removing data with high similarity, principal component analysis (PCA) is used to normalise and reduce the dimensionality of the data. Using extreme learning machine algorithm to classify and process evaluation indicators, and achieving research on the construction of teaching service quality evaluation indicator system. The case analysis results show that when the number of indicators is 1000, the completeness of the indicator system of the proposed method is 98%, the closeness is closer to 1, and the maximum reliability is 97%, which has the characteristics of high feasibility.
  Keywords: Digital; Teaching service quality; Evaluation indicators; Min's distance; PCA; Information gain.
  DOI: 10.1504/IJNVO.2025.10068084
   
  
• Evolution and Coordination Optimisation of Regional Innovation and Entrepreneurship Space Layout under the Background of Social Networks  
  by Jing Liao 
  Abstract: To address the problems of poor adaptability of layout evolution parameters, poor convergence of constraint conditions, and high deviation in coordination optimisation in traditional methods, a evolution and coordination optimization method of regional innovation and entrepreneurship space layout under the background of social networks has been designed. Determine the impact mechanism and layout constraints of the evolution of regional innovation and entrepreneurship spatial layout, and combine social networks to complete the analysis of the evolution of regional innovation and entrepreneurship spatial layout. Construct a spatial topology diagram for coordinating and optimising the layout of regional innovation and entrepreneurship spaces, determine the fitness of regional spatial layout parameters, and combine the coordination optimisation model to achieve coordinated optimization of new entrepreneurial space layout parameters. The experimental findings indicate that the proposed method has good adaptability of the layout evolution parameters, good convergence of constraint conditions, low deviation in coordinated optimisation.
  Keywords: Social networks; Innovation and entrepreneurship space; Layout evolution; Layout constraints; Impact mechanism; Spatial topology diagram.
  DOI: 10.1504/IJNVO.2025.10068634
   
  
• Innovation of Cross border E-commerce Supply Chain Management Mechanism under Digital Background  
  by Jinling Du 
  Abstract: To address the challenges associated with sluggish inventory circulation, elevated product return percentages, and extended supply chain reaction durations within conventional approaches, an innovation method of cross border e-commerce supply chain management mechanism under digital background is proposed. After analysing the structure of cross-border e-commerce supply chain, based on the reliability and collaboration of the supply chain system, innovative strategies for cross-border e-commerce supply chain management mechanism under the digital background were analysed, including data-driven decision optimisation, digital upgrading of supplier management, intelligent inventory management, digital and intelligent logistics management, technological innovation and digital application, as well as risk management and emergency response. The findings from the trials indicate that the turnover ratio for inventory using the new technique fluctuates between 20.6% and 30.1%. Meanwhile, the typical rate of returns stands at 1.57%, and the supply chains average reaction period is 12.64 days. The practical implementation has yielded positive outcomes.
  Keywords: Digital background; Cross border e-commerce; Supply chain management; Mechanism; Innovation; Reliability; Collaboration.
  DOI: 10.1504/IJNVO.2025.10068638
   
  
• Multi-Level Logistics Supply Chain Transportation Scheduling Method based on Improved Fruit Fly Algorithm  
  by Ping Guo 
  Abstract: This paper proposes a logistics multi-level supply chain transportation scheduling method based on an improved fruit fly algorithm to address the problems of high transportation costs and low transportation efficiency in logistics multi-level supply chain transportation scheduling methods. Firstly, clarify the research scope and objectives by setting objective functions and constraints. Secondly, information exchange, mutation strategy, and probabilistic flight strategy were introduced to improve the fruit fly algorithm. Finally, based on the set algorithm parameters, use the improved Drosophila algorithm to evaluate the fitness of various logistics transportation plans and output the optimal results. After experimental verification, the total transportation time of the logistics transportation plan designed in this article is 854 minutes, with 8 dispatched vehicles and a corresponding fuel cost of 2140.31 yuan. This method can effectively reduce transportation costs, improve logistics transportation efficiency, and has certain practical application value.
  Keywords: Drosophila algorithm; Multi-level logistics supply chain; Information exchange and mutation strategies; Probabilistic Flight Strategy; Transportation scheduling.
  DOI: 10.1504/IJNVO.2025.10068639
   
  
• Network Public Opinion Hotspot Topic Mining Method Based on Improved Support Vector Machine  
  by Yifan Wang 
  Abstract: The research on mining hotspot topic in online public opinion is of great significance for improving social management efficiency and promoting economic development. In order to overcome the problems of low accuracy, low recall, and long response time in traditional methods, a network public opinion hotspot topic mining method based on improved support vector machine (SVM) is proposed. Utilise distributed web crawlers to collect network public opinion data, and extract features of the collected network public opinion data through adaptive domain relationships. Introduce the least squares method to improve the SVM, input the feature extraction results into the improved SVM, and obtain the mining results of network public opinion hotspot topic. The experimental results show that the accuracy of network public opinion hotspot topic mining using this method varies between 96.3% and 98.3%, with an average recall rate of 97.7% and a response time of 5.9 s.
  Keywords: Improve support vector machine; Online public opinion; Hotspot topic mining; Distributed web crawlers; Adaptive domain relationships; Least squares method.
  DOI: 10.1504/IJNVO.2025.10068640
   
  
• Optimisation of Internal Control Strategies in Enterprises under the Background of Digital Empowerment  
  by Suying Nian 
  Abstract: In order to solve the problems of low internal risk identification rate, low accuracy of internal control strategy execution, and long response time in traditional methods, an optimization method of internal control strategies in enterprises under the background of digital empowerment is proposed. Analyzing the impact of digital empowerment on internal control in enterprises, identifying the problems existing in internal control, and proposing an optimization path for internal control strategies from the perspectives of clarifying and integrating strategic objectives and internal control processes, accurately identifying and monitoring key control points in real time, balancing cost-effectiveness and risks, tailoring and continuously optimizing internal control systems, and comprehensively optimizing other key measures for internal control. The test results show that the maximum internal risk identification rate of this method is 97.8%, the maximum accuracy of internal control strategy execution is 97.7%, and the average response time is 37.09 minutes.
  Keywords: Background of digital empowerment; Internal control strategies in enterprises; Optimization of internal control; Problems; Balancing cost-effectiveness and risks; Key measures.
  DOI: 10.1504/IJNVO.2025.10068928