In recent years, with the rise and popularization of mobile terminals such as mobile phones and tablet computers, people's lives have become more and more dependent on smart mobile terminals such as mobile phones. Payment, entertainment, medical treatment, work, etc. can all be controlled and controlled through mobile terminals and mobile Internet. However, with the development of mobile terminals and mobile Internet, security problems are becoming more and more serious, especially the crime of ransomware based on smart phones is soaring, which makes the cybercrime combat work in the mobile network environment facing challenges. In order to find traces of ransomware from massive mobile phone software and reduce the threat from ransomware, a large number of researchers have begun to study ransomware based on the Android platform, expecting to identify ransomware through early detection methods and take corresponding protective measures. This paper first summarizes the characteristics of ransomware attacks faced by Android, then outlines and analyzes the current new technologies for Android ransomware detection, and then introduces the current ransomware preventive measures, and finally points out that these solutions problems and put forward corresponding suggestions and future research directions. Besides, we choose CICDataset 2017 and exploit ANN, KNN, LR and SVM model to perform the Android Ransomware Detection task. After training the corresponding models, we establish a web server and integrate the trained model as API interface for users to evaluate. Experimental results have shown that our method can recognize with a satisfied accuracy and a maintain as qualified user experience.