Actionable companion · Assessment & reasoning

Learning with agency: Construction and Application of a Human-Computer Collaborative Multimodal Practice Teaching Model for Preschool Education

AI-assisted editorial implementation guide, separate from the original research. Proposed actions are not claims or recommendations attributed to the source authors. No independent peer review of this guide is asserted.

Read original paper Search paper agent CC BY 4.0

Evidence and context

Title and abstract screening; stage labels describe reported settings, not verified numerical ages. Design labels require full-text appraisal. Reported stage(s): Early childhood · preschool. Verify the participant population and task before transferring the findings.

Original authors’ abstract, reproduced under the linked source license:

This paper adopts the multimodal approach of human-computer collaboration to conduct an in-depth study and analysis of the practical teaching model of preschool education, and applies the designed model to the actual teaching process. The application of multimodal theory to preschool teaching is chosen to theoretically help expand the research scope of multimodal theory and enrich the research of preschool teaching, and practically help break through the previous single-modal teaching model, further enrich the theoretical guidance of preschool teaching, and improve the quality of preschool classroom teaching. Then, from the perspective of human-machine synergy, this paper analyzes the advantages of artificial intelligence technology and teachers in the English classroom, puts forward the new roles of teachers and learners in the human-computer cooperation teaching environment, and discusses the significance and value of applying the four main modules of human-computer cooperation teaching, human-computer gesture mapping and human-computer cooperation manipulator control in the preschool classroom. According to the physical structure of hand joints, the human hand joint angles are obtained through the inverse kinematic solution, and the human hand joint angles correspond to the dexterous manipulator one by one so that the dexterous manipulator can be controlled to imitate the human hand to complete flexible gesture movements and realize the vision-based collaborative human-machine control of the dexterous manipulator. Combined with Gagne's nine teaching events, a model of the English teaching process based on human-computer collaboration was constructed. Based on this model, the “EasyDotWise English Teaching System” was designed to combine the basic lesson types of preschool classroom teaching and the secondary objectives of the English curriculum standards, including “reading text–reading aloud evaluation,” “playing speech–sound recognition,” and “presenting text–selection.” We designed and implemented three types of teaching activities: “reading text–reading aloud assessment,” “playing phonetic sounds–sound identification,” and “presenting text–comprehension selection.”

What kind of evidence is this?

Supporting AI learning science · Design requires full-text appraisal

Stage: Early childhood · preschool. Screening labels describe reported context and study-design language. They are not a risk-of-bias rating or proof of effectiveness for an age band.

Study methods · source passage

The learning paradigm based entirely on data will be difficult to get rid of the shackles of the law of large numbers and other statistical laws, and will not be able to achieve an efficient learning ability like that of human beings. In the future machine learning ecology, different learning tasks and learned models will not be isolated from each other. Knowledge migration between learning tasks and model reuse across tasks will become common, thus making learning models become learning components corresponding to software. This requires models that are not black boxes obtained from closed processes of learning, but open models with interpretability and transferability. The use of a series of intelligent technology products in the English classroom has enriched the content and mode of English classroom teaching, and to a certain extent has improved the teaching efficiency of the English classroom, but the use of technology also limits the development of teachers themselves [6]. How to balance the role of intelligent technology and teachers in the classroom and realize the “human-computer collaboration” teaching mode are important issues facing the technology-enhanced classroom teaching at present. To address the above problems, this study designs and develops an intelligent teaching assistant for English from the perspective of “human-computer collaboration” to solve the problems of speech input and language environment creation in English teaching. The assistant has the main functions of text-to-speech, automatic speech evaluation, listening materials production, etc. The intelligent teaching assistant assists English teachers to carry out classroom teaching, thus solving many problems in English teaching such as nonstandard speech input, promoting the modernization and intelligence of English teaching, and realizing the integration of artificial intelligence technology and English subject teaching [7].

Limitations and uncertainty · source passage

Multimodality exists in every interactive activity in the classroom. Teachers use sound, pictures, animation, and other channels, and various teaching methods to attract students' interest in learning in the classroom, thereby enhancing students' participation in multimodal teaching. By leveraging the wisdom of intelligent technology in concert with human teachers, it can help human teachers implement evaluation activities more objectively and rationally. At present, intelligent speech assessment technology has far surpassed human ability in terms of objectivity, quantification, and concurrent multiple evaluations, and intelligent speech assessment in English has been widely used in English-speaking examinations. Introducing intelligent speech assessment technology in English teaching and creating a collaborative human-computer evaluation method will be an important way to solve the problems of insufficient objectivity of evaluation and limitations in the scope of the evaluation.

Design the system before the pilot

Use this study to inform a learning mechanism or implementation question. It is not direct evidence that autonomous agents improve learning. Keep the proposed agent behavior separate from what the source actually tested.

Use common rubrics, blind scoring where feasible and a fresh unaided reasoning task. Document permissible assistance and avoid treating AI-detector scores as proof of misconduct.

A 90-day district pilot

Days 1–15 · Appraise. Have the curriculum lead and a teacher read the methods and limitations. Record the study design, sample, comparator, outcomes and evidence gaps. Define a local question that the study can help inform.
Days 16–30 · Design. Use a brief adult-mediated story, turn-taking or language activity. An educator controls every interaction; the agent never becomes an unsupervised companion. Preserve hands-on play and human conversation. Name an accountable owner and set the baseline, success threshold and budget before implementation.
Days 31–60 · Test. Start with a small voluntary cohort, preserve an accessible non-AI route and require teacher review. Use synthetic or de-identified examples; approve data handling and tool terms through district processes.
Days 61–90 · Decide. Measure independent naming, explanation or turn-taking in a human-led activity after the tool is removed. Record frustration, overstimulation and the amount of adult help. Compare with baseline, document uncertainty and stop or revise if learning worsens, access is unequal or critical errors persist.

The board decision brief

Report the learning problem, evidence quality, participating population, total cost including review time, measured benefit, errors, access differences and remaining uncertainties. Make a dated recommendation to stop, revise or expand. A positive perception survey alone does not establish learning improvement.

Attribution and reuse

Meimei Tuo; Baoxin Long. Construction and Application of a Human-Computer Collaborative Multimodal Practice Teaching Model for Preschool Education. Computational Intelligence and Neuroscience (2022-06-24). https://doi.org/10.1155/2022/2973954

Companion prepared 2026-10-30. Original authorship and DOI are preserved. The abstract is an attributed source extract; the implementation plan is new AI-assisted editorial material, offered under the same CC BY 4.0 license. This guide has not undergone independent peer review.