Abstract ：The rapid evolution of digital-intelligence courses in higher education has created a pressing need for sophisticated quality evaluation frameworks. This study constructs a comprehensive framework that integrates critical dimensions—including course design, teaching resources, faculty competence, and learning outcomes—to address this gap. Moving beyond traditional surveys and academic assessments, we leverage advanced data mining and artificial intelligence techniques. This mixed-method approach enhances the objectivity, depth, and analytical rigor of evaluations. Our findings demonstrate that intelligent analytical tools significantly improve the reliability of assessment outcomes and facilitate actionable insights for continuous course improvement. By bridging conventional evaluation models with the demands of modern digital education, this research offers a novel, technology-driven contribution to the field, emphasizing the application of evaluation results for meaningful pedagogical and curricular refinement.
Keywords: Digital-intelligence courses; quality evaluation system; course quality evaluation; university course evaluation
1. Introduction
In the 1990s, higher education institutions and social organizations began integrating computer-related information technology into teaching, exploring its potential for instructional enhancement[1]. Due to the relatively underdeveloped IT infrastructure in China at that time, such initiatives were largely confined to demonstration projects and pilot schools. It was not until the early 21st century that the strategic importance of information technology in education gained broader recognition, leading governments to introduce policy documents aimed at advancing educational informatization[2].
Driven by these policies, a variety of digital educational resources—such as online courses, learning platforms, and management systems—began to emerge. However, the “Education Informatization 2.0 Action Plan” highlighted ongoing challenges, including the need to strengthen teacher training and improve the quality of IT-supported teaching environments[3]. The plan explicitly emphasized that, alongside developing digital course resources, equal attention must be paid to curriculum quality, teaching implementation, and maintenance—ensuring the sustainable development of digital education with Chinese characteristics.
Clearly, expanding the forms of digital courses is not enough; ensuring their educational quality is essential. With the deepening integration of artificial intelligence and digital education, data-intelligent courses have become a key focus in higher education management. Their impact extends beyond the education sector into social, economic, and cultural domains, making the evaluation of such courses a research priority[4].
Traditional course quality evaluation in universities has relied on methods such as reviews by teaching supervision groups, peer assessments, and student evaluations via academic systems. In practice, however, these approaches often focus disproportionately on teaching performance, with limited attention to evaluating student learning outcomes and educational effectiveness[5]. As artificial intelligence becomes increasingly embedded in higher education management, it offers new possibilities for more scientific evaluation and accurate monitoring of educational quality[6]. Therefore, analyzing and improving the quality evaluation system for data-intelligent courses is crucial—not only for safeguarding course quality but also for fostering innovation in higher education and cultivating talent that meets societal needs.
2. Methods
This study adopts a systematic literature review approach to analyze the characteristics and evaluation frameworks of data-intelligent courses. Compared to traditional digital classrooms, data-intelligent courses exhibit greater completeness, systematicity, and practicality, aligning more closely with disciplinary norms while offering enhanced depth and flexibility[7]. Supported by artificial intelligence technologies, these courses adapt to students’ learning styles and needs, enabling personalized learning pathways.
2.1 Keyword Definition and Classification Framework
The concept of “data intelligence” in education traces back to Herbert A. Simon’s work “The Sciences of the Artificial” in the 1950s, which laid the foundation for complexity analysis and adaptive systems[8]. In this study, “data-intelligent courses” refer to educational offerings that leverage AI and data analytics to optimize learning processes and outcomes.
Based on platform functionality, data-intelligent courses are categorized into ten types (Table 1), while their manifestations are classified into six forms (Table 2). This dual classification captures both the technological infrastructure and pedagogical applications of data intelligence in higher education.
Table 1. Classification of data-intelligent course platforms
| Name | Content |
| LMS | Platforms supporting course management, recording, tracking, reporting, and delivery |
| VR and AR | Immersive technologies creating simulated environments for enhanced learning experiences |
| Gamification/Metaverse | Game elements and design techniques in non-gaming environments to engage learners |
| Mobile Learning | Learning through mobile devices, enabling anytime, anywhere access to educational content |
| AI in Education | AI technologies for personalized learning, adaptive feedback, and automated educational management |
| Video-based Learning | Educational content delivery through videos including lectures and tutorials |
| Adaptive Learning | Data-driven algorithms tailoring learning experiences to individual needs and preferences |
| Collaborative Tools | Platforms facilitating collaboration and communication between learners and teachers |
| Learning Analytics | Collection, analysis, and interpretation of learning activity data to optimize processes |
| OAT/VSP | Platforms for creating and managing quizzes, tests, and assessments |
2.2 Literature Search Strategy
Following keyword definition, a comprehensive literature search was conducted across Chinese academic databases (CNKI, Wanfang, and Baidu Scholar) using both Chinese and English keywords. The search strategy combined terms related to data-intelligent courses and course evaluation. Results were exported and screened for relevance to both data-driven course implementation and evaluation methodologies[9].
Table 2. Forms of data-intelligent courses in higher education
| Name | Content |
| Chatbot | Computer programs simulating conversation with users to provide information and assistance |
| Expert systems | AI systems mimicking human expert decision-making in specific domains |
| Intelligent tutor or agents | AI systems offering personalized learning guidance and feedback |
| Machine learning | Algorithms that learn from experience to analyze data, identify patterns, and make predictions |
| PLS/E | Customized teaching based on individual needs, preferences, and learning styles |
| Visualizations | Graphical representations of data and information to facilitate understanding |
3 Literature Review
Keyword analysis reveals that research on quality evaluation of data-driven courses in higher education evolves through four distinct phases: theoretical exploration and framework construction, evaluation methodology development, empirical validation, and interdisciplinary integration.
3.1 Theoretical Foundations and Framework Development
Globally, quality assurance mechanisms exhibit national characteristics: the United States emphasizes self-assessment and peer review, the United Kingdom employs institutional audit models, France utilizes government-led evaluation systems, while Japan focuses on institutional self-improvement through self-study[8]. Representative theoretical frameworks can be classified into three primary models: goal-oriented evaluation, learning-level assessment, and comprehensive quality evaluation.
3.1.1 Goal-Oriented Evaluation Model
American educator Tyler pioneered the goal-based educational evaluation system in the “Eight-Year Study,” establishing the foundational framework for teaching objectives, content, methodology, and assessment[9]. This model emphasizes predetermined behavioral objectives as the cornerstone of course evaluation, featuring purpose-driven, planned evaluation activities (Table 3).
Table 3. Initial-stage goal evaluation framework
| Component | Content |
| Objectives | Define educational objectives and expected learning outcomes |
| Content | Establish course content and teaching methodologies |
| Evaluation | Implement formative and summative assessment methods |
| Improvement | Enhance course design based on assessment data analysis |
During mid-term development, digital literacy courses entered rapid expansion. Learning platforms began identifying alignment between practical work and educational objectives through behavioral evidence analysis (Table 4). Recent advancements incorporate neural network-based approaches, with transformer architectures (e.g., BERT, GPT-series) achieving remarkable success in educational assessment (Table 5).
Table 4. Developmental-stage goal evaluation framework
| Component | Content |
| Objectives | Emphasize personalized training considering individual learning characteristics |
| Content | Incorporate qualitative resources including external materials and practical assignments |
| Evaluation | Implement diversified assessment tools and data analysis software |
| Improvement | Establish feedback mechanisms for teaching strategy adjustment |
Table 5. Mature-stage intelligent goal evaluation framework
| Component | Content |
| Objectives | Develop personalized objectives based on learning analytics |
| Content | Integrate AI technologies (GPT-3.5/4) for content delivery |
| Evaluation | Employ big data analytics to identify learning patterns |
| Improvement | Utilize predictive analytics for personalized interventions |
3.1.2 Learning-Level Evaluation Model
Originating from Bloom’s cognitive taxonomy (1956), this model categorizes learning into hierarchical levels from basic knowledge acquisition to advanced cognitive skills[10]. The revised Chinese framework enhances this model by incorporating metacognitive dimensions and elevating “creation” as the highest cognitive level (Table 6). The integration of critical thinking skills further enriches this framework through information generation and behavioral guidance dimensions (Table 7).
Table 6. Revised learning-level evaluation model
| Level | Description |
| Knowledge | Remember, identify and recall information |
| Comprehension | Understand and explain learned material |
| Application | Apply knowledge to practical situations |
| Analysis | Analyze components and relationships |
| Synthesis | Integrate knowledge to create new concepts |
| Evaluation | Assess information value and effectiveness |
Table 7. Learning hierarchy evaluation framework
| Dimension | Level | Content |
| Information Generation | Knowledge Memory | Accuracy in remembering and understanding |
| Application | Practical application of learned knowledge | |
| Analysis/Synthesis | Comprehensive understanding through integration | |
| Creation/Evaluation | Creative utilization and critical judgment | |
| Problem-solving | Independent thinking and solution strategies | |
| Behavioral Guidance | Corresponding levels | Observable behavioral manifestations |
3.1.3 Comprehensive Quality Evaluation Model
Professor Wang Zhaocheng’s 1980s comprehensive teaching quality evaluation model pioneered multidimensional assessment in Chinese higher education[11]. Subsequent developments include three-dimensional frameworks evaluating teaching processes, outcomes, and environments. Modern iterations integrate various evaluation models (Taylor, CIPP, CSE) combining formative and summative approaches (Table 8).
Table 8. Comprehensive evaluation framework
| Component | Evaluation Focus |
| Context | Objective rationality, environmental factors, stakeholder needs |
| Input | Resource adequacy, design feasibility, operational practicality |
| Process | Implementation effectiveness, management efficiency, participant engagement |
| Product | Outcome quality, objective achievement, societal impact |
3.2 Research on Curriculum Quality Evaluation Methods
The integration of information technology in teaching practice has catalyzed significant advancements in curriculum quality evaluation methodologies. Representative developments include the Stake Representation Model by Robert E. Stake and Australia’s educational standards framework, which provide structured guidance for evaluators in assessing curriculum quality[12]. Existing evaluation methods can be systematically categorized into three dimensions: management methods, practical methods, and measurement techniques.
3.2.1 Curriculum Quality Evaluation Management Methods
Current research indicates that university course quality evaluation predominantly relies on specialized administrative bodies under academic affairs offices, which establish standardized evaluation procedures. Institutions frequently categorize courses into theoretical and practical components, with laboratory management departments often overseeing practical course evaluations[12]. Modern evaluation frameworks emphasize diversity in purpose, design, and implementation judgment, while accounting for teaching environments and course design specifics. From a stakeholder perspective, management evaluation methods comprise eight distinct approaches (Table 9).
Table 9. Course quality management evaluation methods
| Method | Evaluation Content |
| Student Evaluation | Teaching materials, instructor quality, content relevance, instructional design, satisfaction |
| Teacher Self-assessment | Teaching resources, course performance, learning attitudes, motivation, satisfaction |
| Peer Evaluation | Content design, methodology selection, teaching effectiveness, student satisfaction |
| Platform Evaluation | Resource completeness, student engagement, resource utilization, comprehensive satisfaction |
| Leadership Assessment | Teaching competence, equipment utilization, resource deployment |
| Expert Review | Learning outcomes, teaching process, resources, environment, management |
| Industry Certification | Facility conditions, learning atmosphere, spatial comfort |
| Professional Accreditation | Curriculum rationality, assessment fairness, feedback mechanisms |
Contemporary evaluation systems increasingly integrate outcome assessment with value-added metrics, incorporating distinctive evaluation dimensions. Beyond traditional institutional evaluations, many universities now employ corporate certifications and international accreditation systems to enhance methodological rigor and implementation effectiveness.
3.2.2 Curriculum Quality Evaluation Practical Methods
Practical evaluation methods emphasize direct operational implementation through teaching-related activities, providing more immediate and specific assessment data compared to traditional questionnaires and examinations[13]. These methods align more closely with actual teaching processes, facilitating authentic evaluation outcomes.
Practical implementation follows a systematic process: defining evaluation objectives, selecting appropriate methods, designing evaluation protocols, implementing activities, collecting data, analyzing results, and proposing improvements. Common practical approaches include student evaluations, expert reviews, teaching observations, and specialized questionnaires (Table 10).
Table 10. Course quality practical evaluation methods
| Method | Implementation Approach |
| Student Evaluation | Collect feedback via questionnaires or online systems regarding content, methods, and instructor performance |
| Expert Review | Engage educational specialists to assess course design and teaching effectiveness |
| Teaching Observation | Conduct classroom observations to evaluate teaching competence and student engagement |
| Course Questionnaire | Administer targeted surveys gathering student opinions on various course aspects |
| Achievement Analysis | Analyze grade distributions and pass rates to assess course difficulty and effectiveness |
| Graduate Tracking | Survey alumni regarding workplace performance and course impact on career development |
Unlike management-focused approaches, practical methods prioritize teaching process data for quantitative quality assessment. Data visualization assists institutions and instructors in comprehending course quality, while objective metrics support evidence-based teaching reforms.
3.2.3 Measurement Methods for Course Quality Evaluation
Advancements in data science and artificial intelligence have prompted universities to develop digitalized teaching assessment systems utilizing intelligent platforms for efficient, objective evaluation[14]. Construction methods typically incorporate both qualitative and quantitative approaches, with qualitative methods gathering stakeholder feedback through observations and interviews, while quantitative methods employ statistical analysis of teaching process data.
System development requires multiple considerations: defining evaluation framework scope, selecting scientific criteria and indicators, establishing impartial evaluation mechanisms, and implementing feedback loops for continuous improvement. Common construction methodologies are detailed in Table 11.
Table 11. Course quality measurement system construction methods
| Method | Application |
| Field Research | Visit enterprises and institutions to integrate practical experience into core knowledge identification |
| Literature Analysis | Synthesize systematic curriculum theories with teaching practice to form course foundations |
| Case Analysis | Optimize evaluation systems using exemplary course cases and teaching content |
| Comparative Study | Enhance systems through cross-institutional curriculum comparisons and practical experience |
| Data Analysis | Improve evaluation systems using analytical results and teaching feedback |
| Longitudinal Tracking | Conduct follow-up surveys with graduated students |
Effectiveness measurement typically employs questionnaires, performance assessments, and teacher evaluations. While some scholars emphasize learning outcome comparisons through academic performance monitoring, others prioritize teacher-led evaluations, arguing that instructors’ direct classroom experience yields more targeted improvement data (Table 12).
Table 12. Course quality evaluation system effectiveness assessment methods
| Method | Implementation |
| Questionnaire Survey | Design comprehensive instruments to collect and analyze satisfaction and learning effectiveness data |
| Structured Interviews | Conduct face-to-face interviews to gather detailed feedback and suggestions |
| Work Assessment | Evaluate student submissions including assignments, reports, and projects with rating systems |
| Examination Analysis | Design specialized tests to assess knowledge acquisition and skill development |
3.3 Empirical Research on Course Quality Evaluation
Empirical research on course quality evaluation employs systematic observation, recording, and analysis of teaching practices to identify and resolve pedagogical issues, thereby enhancing educational outcomes[15]. To ensure timeliness and rigor, researchers are increasingly utilizing real-time data to validate the effectiveness and reliability of evaluation methods. Current empirical studies in higher education primarily focus on four key areas: criteria setting, process implementation, result calculation, and application of findings.
3.3.1 Criteria Setting
In criteria formulation, approaches vary among institutions: some employ unified standards set by academic affairs offices, while others permit disciplinary adaptation according to course-specific needs[16]. Despite these differences, common evaluation dimensions include teaching content, methodology, effectiveness, and teacher competence. More progressive frameworks additionally incorporate students’ learning experiences, resource allocation efficiency, and teaching management effectiveness.
Implementation requires robust course resources and comprehensive teaching practices. Data typically derive from institutional teaching quality evaluation systems and course management platforms, providing multidimensional inputs ranging from student feedback to teaching documentation. The Analytic Hierarchy Process (AHP) with nine-point scaling is frequently employed to determine indicator weights, producing a balanced and applicable evaluation framework[17].
Institutional positioning fundamentally influences criteria setting. Research-oriented universities emphasize academic capability and innovative thinking, whereas application-oriented institutions prioritize practical skills and employment outcomes, resulting in distinctly different evaluation foci.
3.3.2 Evaluation Process Implementation
Evaluation processes incorporate diverse methodologies including classroom observations by supervisors, quality course applications, and multi-source assessments involving students, peers, and administrators[18]. However, subjective biases frequently compromise result accuracy.
While international institutions employ balanced evaluation portfolios, domestic approaches remain comparatively conservative. Student evaluations often carry administrative constraints—such as mandatory completion for course registration—and peer assessment receives insufficient emphasis. Prior to analysis, data cleansing eliminates invalid responses, followed by course categorization according to undergraduate talent development plans. Structural equation modeling then validates comprehensive course operation mechanisms.
Teaching quality emerges as a pivotal yet contentious factor. Although teaching ability, attitude, and effectiveness represent crucial indicators, subjective weighting methods often generate significant disputes in faculty assessment.
3.3.3 Calculation of Evaluation Results
Result calculation methodologies directly determine evaluation scientificity. Comprehensive frameworks like Taylor, CIPP, and goal-achievement models require hierarchical indicator systems with carefully calibrated weights and measurement validity[19]. Tool selection must accommodate course characteristics, teacher proficiency, and student needs, while data interpretation demands integrated quantitative-qualitative approaches.
Student needs and feedback constitute essential references, yet systematic integration into evaluation systems remains challenging. Overreliance on quantitative metrics—whether through statistical calculations or evaluator-weighted scoring—often produces reductive outcomes that neglect nuanced qualitative dimensions.
3.3.4 Application of Evaluation Results
Result application completes the evaluation cycle, determining its incentivizing and guiding functions. Domestically, results primarily inform personnel decisions including rewards, promotions, and appointments[20]. Internationally, greater emphasis lies in pedagogical improvement—the U.S., for instance, emphasizes real-time tool refinement to stimulate teaching innovation.
Empirical findings reveal student dissatisfaction across multiple dimensions: classroom discipline, participation mechanisms, teacher-student interaction, and learning outcome achievement. These patterns highlight needs for improved disciplinary maintenance, enhanced teaching experiences, and strengthened student support systems.
As educational technology advances, evaluation systems must continuously evolve through enriched teaching resources and digital tools to maintain relevance in rapidly changing educational environments[21].
3.4 Interdisciplinary Application Research
The application of data-intelligent course evaluation systems is increasingly extending beyond information technology disciplines, reflecting a broader shift from traditional manual management toward digital and intelligent governance in higher education[22]. Interdisciplinary research, grounded in systems theory, information science, and management science, integrates theories and methods from multiple fields to address complex educational challenges.
3.4.1 Application Scope
Studies indicate that data-intelligent course evaluation systems, underpinned by data science and AI technologies, provide scientifically objective criteria applicable across various disciplines[23]. These systems not only accurately reflect course quality but also support continuous improvement through evidence-based feedback. Several universities have developed interdisciplinary evaluation frameworks that characterize teaching effectiveness, resource quality, and academic climate, employing intelligent recommendation algorithms for precise interventions in decision-making[24].
Such systems have also facilitated the evaluation of interdisciplinary research teams. However, challenges remain in team goal-setting, institutional mechanisms, and talent development. Furthermore, the adoption of AI in traditional disciplines is often hindered by cautious attitudes among teachers and students, highlighting the need for targeted training in AI and data literacy to foster institutional readiness for digital-intelligent transformation[25].
3.4.2 Application Scenarios
The transition from experience-based management to data-driven intelligent management in higher education has been accelerated by interdisciplinary approaches. Integrating knowledge from education, psychology, and computer science has enriched the evaluation scenarios for data-intelligent courses, enabling more robust and adaptable assessment systems[26].
These systems support personalized learning and data-informed teaching optimization through machine learning and analytics. They also provide an analytical framework for identifying biases in course evaluation, thereby enhancing the scientific rigor and accuracy of teaching development. For example, cross-disciplinary course assessments help pinpoint disciplinary strengths and weaknesses, informing targeted improvements[27].
3.4.3 Optimization through Interdisciplinary Integration
Interdisciplinary approaches not only expand the application scope of evaluation systems but also optimize their design and functionality:
Systems Science offers a holistic perspective, emphasizing interconnections among disciplines and promoting integrated, systematic analysis[28].
Information Science provides the methodological foundation for processing and analyzing educational data, extracting meaningful insights to support evaluation.
Management Science contributes decision-analysis and resource-allocation tools, improving the organization and coordination of interdisciplinary evaluation efforts.
Artificial Intelligence enables advanced modeling and analytical capabilities, facilitating complex tasks such as behavioral pattern recognition and adaptive feedback[29].
In summary, interdisciplinary research enhances the scientific depth, applicability, and effectiveness of data-intelligent course evaluation systems, fostering continuous innovation in both course design and educational governance.
4 Results
A review of current research on the quality evaluation of data-intelligent courses reveals that scholars have progressed from examining evaluation content, methods, and tools to developing comprehensive evaluation systems. This includes theoretical, methodological, and application-oriented research, with increasing emphasis on interdisciplinary approaches to course assessment[30].
4.1 Human-Centered Evaluation Framework
The human-centered evaluation framework for data-intelligent courses is typically administered by academic authorities and employs multiple assessment methods, including class observations, student ratings, and teacher-submitted course quality applications. Many institutions utilize Likert scales to design quantitative teaching evaluation forms, with expert ratings used to calculate indicator weights—often through entropy weighting or the Analytic Hierarchy Process (AHP)[31].
In terms of indicator significance, primary dimensions such as teaching quality, learning outcomes, and teacher-student interaction are highly valued. Secondary indicators including teaching attitude, skill enhancement, instructional methods, and student support also receive considerable emphasis. However, the strong reliance on quantitative metrics often overlooks qualitative aspects, and the use of evaluation results for performance-based rewards may lead teachers to prioritize their own interests over student needs[32].
4.2 Student-Centered Outcome Assessment
Student-centered outcome assessment often over-relies on singular evaluation methods, such as high-stakes final exams, which fail to comprehensively capture the course knowledge system or align with students’ personalized development. In engineering courses, for instance, traditional exams are inadequate for covering the full range of learning objectives, limiting the scientific validity of assessment data[33].
To address these limitations, some institutions have adopted learning platforms to collect and analyze educational data for continuous monitoring of teaching processes. By integrating feedback from intelligent platforms and student evaluations, course design is iteratively refined. However, an overemphasis on platform metrics and exam performance may lead to neglect of individual student learning trajectories[34].
In response, many universities have introduced diversified evaluation mechanisms, including subject competitions, competency certifications, and micro-credentials, involving multiple stakeholders—students, teachers, and course experts—for more comprehensive assessment. Recent advances in information retrieval, natural language processing, and machine learning also enable automated analysis of student outputs, supporting more efficient evaluation[35]. Nevertheless, most existing models still lack support for student self-assessment and fail to evaluate unintended learning outcomes, remaining largely result-oriented rather than process-informed.
5 Discussion
5.1 Optimizing the Content Framework of the Digital-Intelligence Course Quality Evaluation System
The current evaluation framework for digital-intelligence courses emphasizes student-centered metrics, focusing on practicality, applicability, and continuous improvement. However, despite the diversification of evaluation mechanisms, these elements often lack systematic integration. This leads to fragmented insights and limits the system’s capacity to identify underlying patterns or developmental trends. For instance, students often approach evaluations with insufficient engagement, resulting in superficial feedback. Similarly, peer evaluators may conduct irregular class observations or let personal biases affect scoring, further undermining the accuracy and fairness of outcomes. Moreover, the administrative burden of comprehensive evaluation makes it difficult to achieve full coverage and consistency.
To address these issues, interdisciplinary research should be encouraged to develop more scientific and dynamic evaluation models. It is also essential to incorporate analyses of students’ learning behaviors and performance data to more accurately assess competency development. Such efforts will help enhance course quality and foster the cultivation of innovative and skilled graduates.
5.2 Enhancing Measurement Tools in the Digital-Intelligence Course Evaluation System
The measurement tools used in digital-intelligence course evaluation require further refinement. In developing these systems, it is valuable to draw on well-established international theories and practices in teaching quality monitoring, while adapting them to fit China’s educational context. A key challenge lies in the inconsistency and incompleteness of course data—such as missing class size or semester details—which complicates accurate analysis and introduces subjectivity during course reclassification.
To improve this, digital learning platforms should align with teacher training objectives, refine course structures, and adjust weighting mechanisms. Leveraging data technologies—enabled by richer datasets and more relevant metrics—can support more accurate and insightful evaluations of teaching quality.
In summary, while existing research on digital-intelligence course evaluation has laid a valuable foundation, future efforts must focus on creating more integrated, data-informed, and scientifically-grounded evaluation systems. Continuous technological and pedagogical innovation will further advance this field, ultimately supporting higher education quality and reform.
Reference
- Simon H A .（1981）The Sciences of the Artificial, 2nd Edition. general information, 1.
- Simon, & Alexander, H. . (1969). The sciences of the artificial. M.I.T. Press,.
- Li Hua, Gong Yi, Ji Juan, Tan Mingjie, & Fang Jiaming. ( 2013 ).Mooc-oriented learning management system framework design.modern distance education research ( 3 ), 6.
- Wang Tongju. ( 2017 ). Application and Prospect of Virtual and Augmented Reality ( vr / ar ) Technology in Teaching. Digital Education, 3 ( 1 ), 10.
- Liu Geping, Wang Xing, Gao Nan, & Hu Hanlin. ( 2021 ).From Virtual Reality to Meta Universe : A New Direction of Online Education.Modern Distance Education Research, 33 ( 6 ), 11.
- Liu Yujun, Li Shufang. ( 2004 ). Mobile Learning-A Review of Foreign Research.Modern Educational Technology, 14 ( 3 ), 12-16.
- Ren, Wan, & Feng, ( 2019 ).Promoting the Sustainable Development of Artificial Intelligence Education – Artificial Intelligence in UN Education : Sustainability
- Wang Jian, Hao Yinhua, & Lu Jilong. ( 2014 ). Experimental Study on the Effect of Teaching Video Presentation on Autonomous Learning.Electrified Education Research, 35 ( 3 ), 8.
- Jiang Qiang, & Zhao Wei. ( 2011 ). Review of adaptive learning system and its optimization mechanism. Modern distance education ( 6 ), 7.
- Peng Shaodong. ( 2010 ). From face-to-face collaborative learning, computer-supported collaborative learning to blended collaborative learning. Educational Technology Research, 000 ( 008 ), 42-50.
- Kazi Hameedullah, S. Chowdhry B. & Memon Zeesha. (2012). MedChatBot: An UMLS based Chatbot for Medical Students. International Journal of Computer Applications (17), 1-5.
- Vijaya Krishnan, Vishakha Patil & Vrushali Panhale. (2024). Physiotherapists and expert systems: How can I (AI) do it?. Medical education
- Zhang Haibo, & Wang Wei ( 2011 ).Exploration of International Trade Simulation Experiment Teaching Mode Based on Simtrade Foreign Trade Practice Platform.Education and Teaching Forum ( 24 ), 3.
- Tyler, R. W. . (2008). Basic principles of curriculum and instruction. University of Chicago Press,.
- Tyler Luo Kang, & Zhang Yue. ( 2014 ). Basic principles of curriculum and instruction : Basic principles of curriculum and instruction.
- Li Yanbing ( 2001 ).Towards a New Perspective of Curriculum Evaluation.Global Education Outlook, 30 ( 1 ), 2.
- Vaswani, A. , Shazeer, N. , Parmar, N. , Uszkoreit, J. , Jones, L. , & Gomez, A. N. , et al. (2017). Attention is all you need. arXiv.
- Roso, M. , Gsior, J. S. , Aba, J. , Korzeniewski, K. , & Marcel Myńczak. (2023). Evaluation of the performance of gpt-3.5 and gpt-4 on the polish medical final examination. Scientific Reports, 13(1).
- Bloom, B. , & Krathwohl, D. . (1956). Taxonomy of educational objectives: the classification of educational goals, by a Committee of College and University Examiners, Handbook 1: Cognitive Domain.
- Xiao Ziming, & Ji Jianfeng. ( 2001 ). ‘ Sinicization ‘ of educational goal classification theory.Journal of Xianyang Normal University, 16 ( 6 ), 2.
- Ni Xiaopeng. ( 2001 ). Teaching strategies of two stages in the field of cognitive learning. Audio-visual education research.
- Deng Min, Chen Xu, & Fan Jie. ( 2010 ). a new model of moral cognition-moral field model. Shanghai Education Research ( 5 ), 4.
- Maobing( 2010 ). The construction of history teaching objectives in the field of cognition. Contemporary educational science ( 18 ), 3.