Multi-attribute group decision-making is an important research field in decision science, and its theories and methods have been widely applied to engineering, economics and management. However, as the information embedded volume and complexity of decision-making expand, the diversity and heterogeneity of decision-making groups present significant challenges to the decision-making process. In order to effectively address these challenges, this paper defines the concept of spherical Z-number, which is a fuzzy number that takes into account a wide range of evaluation and its reliability. Additionally, a group decision-making model in a spherical Z-number environment is proposed. First, an objective phased tracking method is used to determine expert weights, maintain the consistency in decision-making group evaluations. The gained and lost dominance score method is combined with prospect theory to integrate expert psychological behavior when facing risks. The proposed method considers both group utility and individual regret, and balances the gains and losses of various options in the decision-making process. Finally, in response to the 3R principle, the model is employed to address the shared e-bike recycling supplier selection problem and to assess the viability of the decision-making outcomes. The results demonstrate that the model is robust in the context of varying parameter configurations. Moreover, the correlation coefficients between its ranking outcomes and those of alternative methodologies are all above 0.77, and its average superiority degree is 1.121, which is considerably higher than that of other methods. Consequently, the model's effectiveness and superiority are substantiated.

多属性群决策是决策科学的一个重要研究领域，其理论和方法已广泛应用于工程、经济和管理学领域。然而，随着决策信息嵌入量和复杂性的不断扩大，决策群体的多样性和异质性给决策过程带来了重大挑战。为了有效应对这些挑战，本文定义了球形Z数的概念，它是一种考虑到大范围评价及其可靠性的模糊数。此外，还提出了球形 Z 数环境中的群体决策模型。首先，采用客观的阶段性跟踪方法确定专家权重，保持决策群体评价的一致性。得失优势评分法与前景理论相结合，整合专家面临风险时的心理行为。该方法同时考虑群体效用和个人遗憾，并平衡决策过程中各种选项的得失。最后，响应3R原则，利用该模型解决共享电动自行车回收供应商选择问题，并评估决策结果的可行性。结果表明，该模型在不同参数配置的情况下具有鲁棒性。而且，其排名结果与替代方法的相关系数均在0.77以上，平均优越度为1.121，明显高于其他方法。因此，该模型的有效性和优越性得到证实。