Human cognition has a ``large-scale first'' cognitive mechanism, therefore possesses adaptive multi-granularity description capabilities. This results in computational characteristics such as efficiency, robustness, and interpretability. Although most existing artificial intelligence learning methods have certain multi-granularity features, they do not fully align with the ``large-scale first'' cognitive mechanism. Multi-granularity granular-ball computing is an important model method developed in recent years. This method can use granular-balls of different sizes to adaptively represent and cover the sample space, and perform learning based on granular-balls. Since the number of coarse-grained "granular-ball" is smaller than the number of sample points, granular-ball computing is more efficient; the coarse-grained characteristics of granular-balls are less likely to be affected by fine-grained sample points, making them more robust; the multi-granularity structure of granular-balls can produce topological structures and coarse-grained descriptions, providing natural interpretability. Granular-ball computing has now been effectively extended to various fields of artificial intelligence, developing theoretical methods such as granular-ball classifiers, granular-ball clustering methods, granular-ball neural networks, granular-ball rough sets, and granular-ball evolutionary computation, significantly improving the efficiency, noise robustness, and interpretability of existing methods. It has good innovation, practicality, and development potential. This article provides a systematic introduction to these methods and analyzes the main problems currently faced by granular-ball computing, discussing both the primary applicable scenarios for granular-ball computing and offering references and suggestions for future researchers to improve this theory.

翻译：人类认知具有“先大后小”的认知机制，因此具备自适应多粒度描述能力，从而表现出高效、鲁棒和可解释的计算特性。尽管现有人工智能学习方法大多具备一定多粒度特征，但尚未完全契合“先大后小”的认知机制。多粒度颗粒球计算是近年来发展的重要模型方法，该方法可利用不同大小的颗粒球自适应地表示和覆盖样本空间，并基于颗粒球进行学习。由于粗粒度“颗粒球”数量少于样本点数，颗粒球计算更为高效；颗粒球的粗粒度特性使其不易受细粒度样本点影响，因而更具鲁棒性；颗粒球的多粒度结构可生成拓扑结构和粗粒度描述，提供天然的可解释性。目前，颗粒球计算已有效扩展到人工智能的多个领域，发展了颗粒球分类器、颗粒球聚类方法、颗粒球神经网络、颗粒球粗糙集和颗粒球进化计算等理论方法，显著提升了现有方法的效率、噪声鲁棒性和可解释性，具有良好的创新性、实用性和发展潜力。本文系统介绍了这些方法，分析了当前颗粒球计算面临的主要问题，探讨了颗粒球计算的主要适用场景，并为未来研究者改进该理论提供了参考与建议。