Purpose

The possibility function-based grey clustering model has evolved into a complete approach for dealing with uncertainty evaluation problems. Existing models still have problems with the choice dilemma of the maximum criteria and instances when the possibility function may not accurately capture the data's randomness. This study aims to propose a multi-stage skewed grey cloud clustering model that blends grey and randomness to overcome these problems.

Design/methodology/approach

First, the skewed grey cloud possibility (SGCP) function is defined, and its digital characteristics demonstrate that a normal cloud is a particular instance of a skewed cloud. Second, the border of the decision paradox of the maximum criterion is established. Third, using the skewed grey cloud kernel weight (SGCKW) transformation as a tool, the multi-stage skewed grey cloud clustering coefficient (SGCCC) vector is calculated and research items are clustered according to this multi-stage SGCCC vector with overall features. Finally, the multi-stage skewed grey cloud clustering model's solution steps are then provided.

Findings

The results of applying the model to the assessment of college students' capacity for innovation and entrepreneurship revealed that, in comparison to the traditional grey clustering model and the two-stage grey cloud clustering evaluation model, the proposed model's clustering results have higher identification and stability, which partially resolves the decision paradox of the maximum criterion.

Originality/value

Compared with current models, the proposed model in this study can dynamically depict the clustering process through multi-stage clustering, ensuring the stability and integrity of the clustering results and advancing grey system theory.

中文翻译：

---

多阶段倾斜灰云聚类模型及其应用

目的

基于可能性函数的灰色聚类模型已经发展成为处理不确定性评估问题的完整方法。现有模型仍然存在最大标准和实例的选择困境问题，当可能性函数可能无法准确捕获数据的随机性时。本研究旨在提出一种混合灰色和随机性的多阶段倾斜灰云聚类模型来克服这些问题。

设计/方法论/途径

首先，定义了倾斜灰色云可能性（SGCP）函数，其数字特征表明正常云是倾斜云的特定实例。其次，建立了最大准则决策悖论的边界。第三，以偏斜灰云核权（SGCKW）变换为工具，计算多阶段偏斜灰云聚类系数（SGCCC）向量，并根据该具有整体特征的多阶段SGCCC向量对研究项目进行聚类。最后给出了多阶段倾斜灰云聚类模型的求解步骤。

发现

将模型应用于大学生创新创业能力评估结果表明，与传统灰色聚类模型和两阶段灰云聚类评估模型相比，该模型的聚类结果具有更高的辨识度和稳定性。 ，部分解决了最大准则的决策悖论。

原创性/价值

与现有模型相比，本研究提出的模型可以通过多阶段聚类动态描述聚类过程，保证聚类结果的稳定性和完整性，推进灰色系统理论。