The soaring development of Web technologies and mobile devices has blurred time-space boundaries of people’s daily activities. Such development together with the life-long learning requirement give birth to a new learning style, micro learning. Micro learning aims to effectively utilize learners’ fragmented time to carry out personalized learning activities through online education resources. The whole workflow of a micro learning system can be separated into three processing stages: micro learning material generation, learning materials annotation and personalized learning materials delivery. Our micro learning framework is firstly introduced in this paper from a higher perspective. Then we will review representative segmentation and annotation strategies in the e-learning domain. As the core part of the micro learning service, we further investigate several the state-of-the-art recommendation strategies, such as soft computing, transfer learning, reinforcement learning, and context-aware techniques. From a research contribution perspective, this paper serves as a basis to depict and understand the challenges in the data sources and data mining for the research of micro learning.

中文翻译：

---

从理想到现实：细分，注释和推荐，智能微学习的重要轨迹

Web技术和移动设备的飞速发展已经模糊了人们日常活动的时空界限。这种发展以及终身学习的需求催生了一种新的学习方式，即微学习。微学习旨在通过在线教育资源有效利用学习者分散的时间来开展个性化学习活动。微型学习系统的整个工作流程可以分为三个处理阶段：微型学习材料生成，学习材料注释和个性化学习材料交付。本文首先从更高的角度介绍了我们的微观学习框架。然后，我们将回顾电子学习领域中的代表性细分和注释策略。作为微学习服务的核心部分，我们进一步研究了几种最新的推荐策略，例如软计算，转移学习，强化学习和上下文感知技术。从研究贡献的角度来看，本文是描述和理解微学习研究中数据源和数据挖掘挑战的基础。