International Journal of Continuing Engineering Education and Life-Long Learning (5 papers in press)

Special Issue on: OA AI and Digital Technology driven Innovation in Continuing Engineering Education and Lifelong Learning

• Open Access

  AI-powered precision training pathways for engineering ethics and professional competence in Industry 4.0 ( Free Full-text Access )

  by Shuqin Cai, Yu Lei 
  Abstract: Driven by Industry 4.0, the implementation of precision delivery pathways for engineer ideological education urgently requires deep integration with cutting-edge artificial intelligence technologies. This study proposes an AI-driven framework for “data-informed, adaptive delivery, and iterative optimization” in ideological education. The model employs natural language processing to analyze multi-source educational content, constructs knowledge graphs and dynamic learner profiles to support personalized recommendation, and optimizes teaching strategies through deep reinforcement learning. Experiments on public datasets demonstrate that this approach significantly outperforms traditional online instruction and baseline recommendation models across multiple evaluation metrics, achieving an F1-score of 0.824 on learning outcome prediction and improving interaction depth by 31.5%, with statistical significance (p < 0.01). The results validate the proposed precision delivery pathways in enhancing the targeting accuracy and pedagogical effectiveness of ideological education for Industry 4.0 engineers through AI-powered adaptive learning.
  Keywords: engineering skill training; continuing engineering education; virtual practice teaching; digital twin; ethical risk control.
  DOI: 10.1504/IJCEELL.2026.10078547
   
  

• Open Access

  Generative content synthesis with controllable output for engineering continuing education incorporating copyright rules ( Free Full-text Access )

  by Guohui Yang, Yu Chai 
  Abstract: As the demand for efficient content updates in continuing education continues to grow, generative AI shows potential in providing large-scale personalized materials. However, its unregulated application poses a risk of up to 15% infringement, which hinders its compliant use. This paper proposes a controllable synthesis framework that embeds copyright rules into the generation process. By converting legal provisions into constraints that the model can execute, it controls the content's compliance from the source. Experiments based on public datasets show that compared to conventional generation methods, this framework reduces the infringement risk from 15% to below 3%, while improving the content's educational applicability (normalised discounted cumulative gain metric) by 18%. This approach provides a feasible path to break through the compliance bottleneck of generative AI in professional education.
  Keywords: engineering continuing education; generative content; copyright rules; controllable synthesis.
  DOI: 10.1504/IJCEELL.2026.10079063
   
  

• Open Access

  Personalised generation of physical literacy curricula for engineering talent cultivation ( Free Full-text Access )

  by Lin Wei 
  Abstract: Engineering students frequently receive uniform physical education programs that disregard individual differences, leading to low engagement and underdeveloped physical literacy. Existing approaches lack systematic integration of exercise science and educational theory, often produce unsafe or pedagogically unsound recommendations. To overcome this limitation, this paper proposes a knowledge-enhanced conditional variational autoencoder that embeds the frequency, intensity, time, type principle as differentiable constraints and introduces a cognitive load regulariser grounded in cognitive load theory. Experiments demonstrate that our method outperforms six state-of-the-art baselines, achieving an expert acceptability score of 4.32 out of 5, a personalization fit of 0.81, a diversity of 0.39, a frequency, intensity, time, type violation rate of only 2.3 percent, and a cognitive load score of 0.09. A case study confirms its practical utility. This work provides a scalable, theory-driven solution for personalised physical education generation in engineering talent cultivation.
  Keywords: personalised physical education; generative models; cognitive load theory; engineering education.
  DOI: 10.1504/IJCEELL.2026.10079090
   
  

• Open Access

  Precision-targeted provision of ideological education in construction engineering vocational education courses in the big data era ( Free Full-text Access )

  by Xiangjun Xia 
  Abstract: To address the common issues of ‘massive watering’ in course ideological education and the ‘two-layered’ nature of professional teaching in construction engineering vocational education, this study proposes a precise supply solution driven by big data. By constructing a domain knowledge graph integrating professional knowledge points and ideological education elements, and analysing students’ learning behaviours and project data to form personalised profiles, this paper designs an intelligent matching algorithm. Experiments show that compared with the traditional unified push mode, this model improves the accuracy of matching ideological education cases with teaching scenarios from 65% to 89%, and student satisfaction with the relevance of ideological content rises from 70% to 92%. Therefore, leveraging multisource educational big data to achieve precise supply can effectively address the challenge of insufficient targeting in ideological education, providing a quantifiable technical path for deepening the ‘three-all education’ reform.
  Keywords: digital twin; virtual practice teaching; continuing education credit bank; cross-regional resource sharing; ethical risk control.
  DOI: 10.1504/IJCEELL.2026.10079269
   
  

Special Issue on: OA Intelligent Learning Ecosystems AI, Metaverse and Emerging Technologies for Continuing Engineering Education Part Two

• Open Access

  Intelligent English composition scoring method based on transfer paragraph segmentation and Pearson detection ( Free Full-text Access )

  by Haibei Chen 
  Abstract: With the growing demand for intelligent education, automated English composition scoring has gained significant research attention. Addressing limitations in cross-prompt generalisation and feature extraction, this study proposes a transfer learning-based method incorporating paragraph segmentation and Pearson detection. The approach combines BERT encoding, convolutional and bidirectional LSTM networks, augmented with attention mechanisms and cross-topic feature sharing. In performance evaluation, the proposed model achieved a weighted kappa coefficient of 0.866 and a Pearson correlation coefficient of 0.79 on the test set, significantly better than the comparison model in terms of consistency and correlation. It also showed lower prediction bias in error metrics, demonstrating higher fitting accuracy and rating stability. In three typical application scenarios, the model consistently outperformed the baseline method in terms of off topic detection accuracy and F1 score, and could more effectively capture semantic and structural features. In addition, in terms of resource consumption, the model parameter count was only 16.7M, the inference time was 28.9 ms, and the maximum processor utilisation rate was only 73.6%, demonstrating good deployment adaptability. The experimental results show that this method has good accuracy and generalisation ability in multi-scenario automatic scoring tasks, and has potential value for deployment and application in educational scenarios.
  Keywords: English composition scoring; transfer paragraph segmentation; semantic modelling; off topic detection; feature sharing.
  DOI: 10.1504/IJCEELL.2026.10079803