The invention discloses a quantitative evaluation system for a teaching state of normal school students, and belongs to the technical field of educational training. The system comprises a cloud server, a virtual classroom, a man-machine interaction device, a language detection module, a blackboard-writing detection module and a teaching posture detection module, wherein the man-machine interaction device, the language detection module, the blackboard-writing detection module and the teaching posture detection module are installed in the virtual classroom. The cloud server comprises a data acquisition module, a data processing module and a data comparison module, and the man-machine interaction equipment is connected with the data comparison module through a network, so that an objective evaluation system can be constructed by utilizing big data processing, and an intelligent teacher and a real classroom are virtualized by combining artificial intelligence and a modern sensing technology; the immersive autonomous training method is adopted by trainees, while the problems of high training time and space cost, insufficient teacher guiding resources, lack of objective evaluation and the like are effectively solved, grading up-to-standard training can be achieved, the purpose of accurate individual training is achieved, the training efficiency is effectively improved, and then the quality of normal school student training is improved.