Remote examination anti-cheating system based on machine learning and use method

The invention discloses a remote examination anti-cheating system based on machine learning and a use method, and relates to the technical field of computer technology and machine learning. The remote examination anti-cheating system comprises a camera shooting terminal module, an algorithm module, a data storage module and a B-end operation platform. Wherein the algorithm module analyzes video data frame by frame in real time through a multi-layer neural network model, analyzes actual behaviors of examinees in an examination process, and judges whether potential cheating behaviors occur or not; compared with a traditional remote examination anti-cheating system, the system can effectively monitor the core action area of the examinee in the examination process and recognize the cheating mode which is more likely to be made by the examinee in the examination process, and meanwhile the system is easy and convenient to operate for the examinee, low in cost and better in practicability. 本发明公开了基于机器学习的远程考试防作弊系统与使用方