Skip to content

ECNUClaw

Product or Programme · All products and programmes
Evidence · 2 claims (2 for) · 1 study (1 design), q1 · 0 of 1 report an effect size · 2 claims rest on one study

Description

An open-source Python framework developed by Yizhou Zhou et al. for building learner-profiled intelligent study companions for K–12 subject learning and emotional and metacognitive support.

Components

  • Five-dimension learner profile maintained across subject switches from dialogue signals: ECNUClaw constructs and maintains a learner profile across five dimensions—cognitive, behavioral, emotional, metacognitive, and contextual—stored as per-dimension JSON fields in a SQLite table. Signals are extracted at every turn via keyword dictionaries and turn counting: Bloom's taxonomy level from question patterns, weak knowledge points from error markers, mood and self-efficacy from sentiment keywords, and reflection and strategy preference from metacognitive markers. All subject companions share a single memory store, so the profile persists across subject switches. (Yizhou Zhou et al. (2026))
  • Education Brain model: A bio-inspired three-layer architecture for educational AI systems that separates multimodal data capture, pedagogical decision generation, and intervention output.

Claims

-

Key Sources

  • Yizhou Zhou, Jiayin Li, and Zhi Zhang. (2026). ECNUClaw: A Learner-Profiled Intelligent Study Companion Framework for K-12 Personalized Education. arXiv preprint. https://arxiv.org/abs/2605.08040
Page metadata
Field Value
type product
id ecnuclaw
aliases education-brain-model
title ECNUClaw
description An open-source Python framework developed by Yizhou Zhou et al.
status review
product_kind software
generated by process:settle-candidates on 2026-10-10
trust unverified — no one has confirmed this page's content

Frontmatter is the page's machine-readable record — see the Schema & Guide.