Abstract: In recent years, there have been several safety incidents involving textbook and teaching materials, which has led people to pay more attention to research in the field of textbook content security. With the increase in textbook publishing volume, it is impossible to handle the huge workload of textbook review solely through manual review. Therefore, this paper proposes a textbook content intelligent review technology, including three review parts:image aesthetics review, image content security review, and text content security review. Image aesthetics review uses image aesthetics theory to establish a evaluation model; image content security review is based on image object detection method; text content security review uses natural language processing and language model. The experimental results show that the performance of the methods proposed in this paper is good in all aspects, and has certain ability to review textbook content security. In the final part of this paper, the existing shortcomings of the research and the direction of improvement are pointed out.