With the advancement of artificial intelligence technology, a vast amount of data is transmitted during the model training process, significantly increasing the risk of data leakage. In an era where data privacy is highly valued, protecting data from leakage has become an urgent issue. Federated Learning (FL) has thus been proposed and applied across various fields. This paper presents the applications of FL in five key areas: healthcare, urban transportation, computer vision, Industrial Internet of Things (IIoT), and 5G networks. This paper discusses the feasibility of implementing FL for privacy protection in the aforementioned five real-world application scenarios and analyzes its accuracy and effiency. Additionally, it compares the FL framework with traditional frameworks, exploring the improvements FL has made in terms of privacy protection and performance, as well as the existing shortcomings of the FL framework. Further discussions are provided on potential future improvements. Moreover, this paper offers an outlook on current research trends and the developmental prospects in this research field.