The digital competence of TVET (technical and vocational education and training) teacher is the key to the digital development of TVET. Improving the digital competence of TVET teachers is of great significance to accelerate the digital transformation process of TVET. However, there are still few researches on digital competence of TVET. The aim of this study is to describe the self-cognition of digital competence of Chinese teachers for TVET. For this purpose, based on the development characteristics of China’s TVET, a standard system for digital competence of TVET teachers in China was established, including digital mindset and attitude, digital knowledge and skills, digital education and teaching, digital care and support, and digital collaboration and development. Based on this, an assessment tool was developed to investigate the current situation of competence of 2,514 in-service TVET teachers in China. The results show that the competency system is an effective tool to measure the digital competence of Chinese TVET teachers, and other internal and external factors except gender have different degrees of influence on the digital competence of teachers. According to the results of this study, different suggestions are put forward to train the digital competence of TVET teachers.

The application of non-cognitive factors represented by facial emotion in educational evaluation has attracted much attention in recent years. There are many existing studies on facial emotion assisted education evaluation, but most of them are based on virtual learning environments, which means that the research on facial emotion and learning effect in offline learning environments is sparse. In order to solve this problem, this study designed an emotion observation experiment based on the offline learning environment, obtained the type of learner facial emotion and learning effect of 127 college students, and further explored the relationship between the two. The results show that: 1) We obtained eight types of learner emotion through the combined description method: joy, relaxation, surprise, meekness, contempt, disgust, sadness, anxiety and their respective PAD emotional mean. 2) We obtained the correlation results of the six emotions of joy, relaxation, surprise, meekness, contempt, and anxiety with the learning effect and the predicted value of the learning effect. 3) We then constructed an explanatory model of learner emotion and learning effect based on the offline learning environment.

In the research of Facial Expression Recognition (FER), the inter-class of facial expression data is not evenly distributed, the features extracted by networks are insufficient, and the FER accuracy and speed are relatively low for practical applications. Therefore, a lightweight and efficient method based on class-rebalancing fusion cumulative learning for FER is proposed in our research. A dual-branch network (Regular feature learning and Rebalancing-Cumulative learning Network, RLR-CNet) is proposed, where the RLR-CNet uses the improvement in the lightweight ShuffleNet with two branches (feature learning and class-rebalancing) based on cumulative learning, which improves the efficiency of our model recognition. Then, to enhance the generalizability of our model and pursue better recognition efficiency in real scenes, a random masking method is improved to process datasets. Finally, in order to extract local detailed features and further improve FER efficiency, a shuffle attention module (SA) is embedded in the model. The results demonstrate that the recognition accuracy of our RLR-CNet is 71.14%, 98.04%, and 87.93% on FER2013, CK+, and RAF-DB, respectively. Compared with other FER methods, our method has great recognition accuracy, and the number of parameters is only 1.02 MB, which is 17.74% lower than that in the original ShuffleNet.

The application of non-cognitive factors represented by facial emotion in educational evaluation has attracted much attention in recent years. There are many existing studies on facial emotion assisted education evaluation, but most of them are based on virtual learning environments, which means that the research on facial emotion and learning effect in offline learning environments is sparse. In order to solve this problem, this study designed an emotion observation experiment based on the offline learning environment, obtained the type of learner facial emotion and learning effect of 127 college students, and further explored the relationship between the two. The results show that: 1) We obtained eight types of learner emotion through the combined description method: joy, relaxation, surprise, meekness, contempt, disgust, sadness, anxiety and their respective PAD emotional mean. 2) We obtained the correlation results of the six emotions of joy, relaxation, surprise, meekness, contempt, and anxiety with the learning effect and the predicted value of the learning effect. 3) We then constructed an explanatory model of learner emotion and learning effect based on the offline learning environment.