International Journal of Continuing Engineering Education and Life-Long Learning (9 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
   
  

• Open Access

  Generative neural network for AI engineering education courses based on knowledge evolution ( Free Full-text Access )

  by Kangzhe Wang 
  Abstract: To address the issues of lagging course system update and insufficient personalised adaptation in artificial intelligence engineering education, a knowledge evolution course generation network is proposed. This network achieves dynamic course generation by integrating temporal knowledge graphs and conditional generative adversarial networks, and introduces a closed-loop optimisation mechanism based on pedagogical perception. This framework models the temporal evolution pattern of knowledge from publicly available educational knowledge graphs and incorporates course objectives and prerequisite relationships as constraints to enhance the logic and teachability of the generated content. Experiments show that this method increases course diversity by 6.2%, improves knowledge coverage completeness by 5.8%, enhances the coherence of learning paths by 4.7%, and increases alignment with educational goals by 5.1%. All these improvements have passed statistical significance tests. This research provides a practical and feasible new approach for generating adaptive and explainable artificial intelligence engineering education courses.
  Keywords: temporal knowledge graph; conditional generative adversarial network; curriculum generation; knowledge evolution.
  DOI: 10.1504/IJCEELL.2026.10080106
   
  

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
   
  

• Open Access

  English machine translation based on parallel corpus mining and transfer learning ( Free Full-text Access )

  by Lipin Fang 
  Abstract: With the rapid development of neural machine translation, encoder—decoder models have become mainstream but still suffer from insufficient semantic alignment, limited long-distance dependency modelling, and inconsistent technical term translation. They often struggle with complex sentence structures and contextual understanding, affecting translation fluency and accuracy. This paper proposes an English machine translation model based on parallel corpus mining and transfer learning to enhance semantic representation and cross-lingual alignment. Experiments on a self-constructed Chinese— English parallel corpus show an error rate of 6.21, a semantic similarity of 98.22, and a technical term translation accuracy of 98.25%. The model achieves a translation latency of 63.52 s and an inference speed of 61.53 ms, demonstrating strong contextual consistency in long-text translation tasks. These results indicate that the proposed model effectively mitigates semantic deviation and improves contextual utilisation, offering a robust and efficient solution for cross-lingual natural language processing.
  Keywords: English translation; machine translation; parallel corpus mining; transfer learning; pretrained language model.
  DOI: 10.1504/IJCEELL.2026.10080200
   
  

• Open Access

  English essay topic analysis using conceptual prior knowledge and Bi-GRU ( Free Full-text Access )

  by Bing Huang 
  Abstract: This paper addresses key challenges in English essay topic analysis, including cross-domain text variability, multi-topic integration, fine-grained topic discrimination, and limited adaptability to new topics. To overcome these issues, we propose a hybrid method integrating conceptual prior knowledge with an improved bidirectional GRU, enhanced by a knowledge-memory attention mechanism for dynamic knowledge selection and redundant information filtering. A CNN—LSTM module is further incorporated to strengthen semantic representation, while model-agnostic meta-learning and Bayesian optimisation with random forest construct the final adaptive framework. Experiments on student essay assessment and reading comprehension datasets show strong performance, achieving at least 93.28% local argument matching, 97.26% multi-label topic matching, 95.26% meta-test accuracy, 98.12% error attribution accuracy, and 98.41% topic hierarchy accuracy. The method also demonstrates superior efficiency, supporting accurate and practical English essay topic analysis for teaching feedback and automated multi-topic scoring.
  Keywords: conceptual prior knowledge; CPK; Bi-GRU; knowledge memory attention; English essay; topic analysis.
  DOI: 10.1504/IJCEELL.2026.10080201
   
  

• Open Access

  Construction of an English academic writing teaching algorithm integrating LLM and move segmentation ( Free Full-text Access )

  by Yifang Ding, Xiaolong Ren 
  Abstract: English dominates global scientific research, but existing writing tools often fail to address disciplinary logic and conventions. Therefore, this study proposes an algorithm for assisting English academic writing teaching by integrating sentence-level segmentation with large language models. The research first uses a text feature extraction algorithm to extract local features of the text, achieving precise segmentation of academic text sentences. Then, through a thinking chain-constrained large language model, it generates writing templates, semantic error correction, and logical solutions for different disciplines. Finally, a multi-dimensional evaluation module is constructed using LightGBM to precisely fit the nonlinear relationship between text features and evaluation indicators, completing the objective quantification of text quality. Experiments achieved 0.9613 correlation with human scoring, with accuracy reaching 95.67% for empirical papers and 96.41% for reviews. The system attained 95.24% F1-score in STEM and 94.58% in humanities, while maintaining memory usage below 413.6 MB and response time under 6.27s. This approach effectively addresses logical evaluation and feedback limitations in existing methods, offering comprehensive writing support for non-native researchers.
  Keywords: move segmentation; large language model; LLM; academic writing; teaching assistance; CNN-BiLSTM; LightGBM.
  DOI: 10.1504/IJCEELL.2026.10080251