Pythagorean模糊集理论是软计算的一个重要分支，也是人工智能的一个新兴研究领域，在大规模决策和医疗诊断中具有广阔的应用前景。为描述和解决大数据环境下的非确定和多因素问题，提出复Pythagorean模糊集和Pythagorean模糊集对分析2种新的扩展模型，探讨其运算和相关性质，重点分析和挖掘模型间的潜在共性，拟提出统一Pythagorean模糊集模型。在此基础上，进一步研究Pythagorean模糊集间的信息测度理论和正则化特征选择技术，建立疾病的Pythagorean模糊集模型参照库，设计相似度计算仿真系统，以实现对疾病有价值的辅助诊断；同时，基于新整合算子的Pythagorean模糊决策算法，可望解决大规模决策中的反直觉现象。本项目的研究有望为大规模决策和医学诊断提供一种新的解决方案，而且对推动人工智能的发展具有重要的理论意义。

Pythagorean fuzzy set theory is an important branch of soft computing and an emerging research field of artificial intelligence. It has broad application prospects in large scale decision making and medical diagnosis. In order to describe and solve the non-deterministic and multi-factor problems in the big data environment, this project proposes two new extension models of complex Pythagorean fuzzy set and Pythagorean fuzzy set pair analysis, discusses their operation and related properties, focuses on analyzing and mining the potential commonalities between models, and proposes a unified Pythagorean fuzzy set model. On this basis, the information measure theory and regularization feature selection technology between Pythagorean fuzzy set models are further studied, the reference library of Pythagorean fuzzy set model of diseases is established, and the similarity computing simulation system is designed to realize valuable auxiliary diagnosis of diseases. At the same time, the Pythagorean fuzzy decision-making algorithm based on the new aggregation operator is expected to solve the counterintuitive phenomenon in large scale decision making. The research of this project is expected to provide a new solution for large scale decision making and medical diagnosis, and has important theoretical significance for promoting the development of artificial intelligence.