Machine learningLearning analytics
知识追踪
知识追踪（Knowledge Tracing, KT）是一种学生建模技术，它在每个时间点估计学习者掌握目标知识组件的概率。经典的贝叶斯知识追踪（Bayesian Knowledge Tracing, BKT）模型由 Corbett 和 Anderson 于 1994 年提出，将技能习得视为一个两态隐马尔可夫模型（Hidden Markov Model, HMM），由四个可解释的参数驱动：先验知识、学习率、遗漏（slip）和猜测（guess）。后来的深度变体（DKT, DKVMN, AKT）用循环神经网络（recurrent）和 Transformer 架构取代了 HMM。
阅读完整方法
仅限会员
登录使用免费账户登录即可阅读本节。
Method map
The neighbourhood of related methods — select a node to explore.
来源
- Corbett, A. T., & Anderson, J. R. (1994). Knowledge tracing: Modeling the acquisition of procedural knowledge. User Modeling and User-Adapted Interaction, 4(4), 253–278. DOI: 10.1007/BF01099821 ↗
如何引用本页
ScholarGate. (2026, June 2). Knowledge Tracing (Bayesian / Deep). ScholarGate. https://scholargate.app/zh/education-analytics/knowledge-tracing
Which method?
Set this method beside its closest kin and read them side by side — the library lays the books on the table; the choice is yours.
Compare side by side →