To address challenges in the teaching skill evaluation of preservice teachers, such as traditional models being unable to meet digital demands, and intelligent evaluation suffering from ambiguous indicators and insufficient interpretability, this study constructs a comprehensive panorama of teaching skill evaluation covering the entire process of pre-class, in-class, and post-class. Centered on in-class teaching skills, the panorama adopts a three-level hierarchical design, establishing a specific, observable, and interpretable underlying framework. It balances interdisciplinary commonalities with the characteristics of information technology, while highlighting emerging skills such as curriculum-based ideological and political education and AI application. As a standardized data framework for the intelligent evaluation of preservice teachers’ teaching skills, the panorama integrates with interpretability methods to support the reverse tracing of evaluation results from atomic-level skills to segment effects, ensuring the fairness and credibility of the evaluation. This framework provides theoretical support and practical pathways for empowering evaluation with intelligent technologies and realizing result interpretability, and holds significant importance for improving the quality of teacher training.

Sujuan Yang, Qiuyu Chen, Sijing Pu. Research on the Construction and Application of the Panorama of Teaching Skill Evaluation for Preservice Teachers. Frontiers in Educational Research (2026), Vol. 9, Issue 4: 84-91. https://doi.org/10.25236/FER.2026.090413.

[1] Hu Xiaoyong, Li Wanyi. Artificial intelligence empowers high-quality cultivation of pre-service teachers [J]. The Educator, 2022(33): 42-43.

[2] Sun Shuo, Hu Xiaoyong, Mu Su, et al. Research on the intelligent training model and application of teaching basic skills for pre-service teachers [J]. Research on Educational Technology, 2024, 45(06): 113-120.

[3] Wang Yiyan, Zheng Yonghe. Explainable learner modeling: Value significance and application prospects [J]. Modern Distance Education Research, 2023, 35(05): 96-103.

[4] Peng Bo, Wang Weiqing, Zhang Jinliang, et al. How educational evaluation reform is possible under the vision of artificial intelligence [J]. Contemporary Education Forum, 2021(06): 1-15.

[5] Yu Qingkui, Deng Tao. Construction and challenges of the final integrated assessment for pre-service teachers in New Zealand [J]. Higher Education Development and Evaluation, 2023, 39(05): 78-87+122.

[6] Sun Zhong, Lu Kaiyue, Shi Zhiping, et al. TESTII framework: Development trends of AI-supported classroom teaching analysis [J]. Research on Educational Technology, 2021, 42(02): 33-39+77.

[7] Zhu Ke, Liu Yuying, Shang Yunxiang, et al. Artificial intelligence-enabled value-added evaluation in teacher education: Value significance, internal mechanisms, and implementation pathways [J]. Digital Education, 2023, 9(05): 15-21.

[8] Christoph Molnar. Interpretable Machine Learning: A Guide for Making Black Box Models Explainable [M]. Translated by Zhu Mingchao. Beijing: Publishing House of Electronics Industry, 2021.2.

[9] Liu Tong, Gu Xiaoqing. Towards explainability: Opening the “black box” of artificial intelligence in education [J]. China Educational Technology, 2022(05): 82-90.