High-quality talent cultivating Internet of Things (IoT) Engineering is the basis for the rapid development of IoT technology. To train high-quality application-oriented IoT technical talents, guided by educational psychology, this article conducts in-depth research; analyzes the characteristics of IoT Engineering; makes professional talent cultivating programs and cyclical adjustment plans; builds a high-quality teaching system based on the professional knowledge system of the IoT; explores the “spiritual level” and “psychological level” characteristics of teachers and students in teaching; highly integrates “Industry-University-Research-Competition” from the perspective of students, teachers, and colleges; infiltrates positive psychological cues appropriately; formulates the construction method of the “student teaching assistant” auxiliary system to enhance the efforts to promote learning by learning; and finally innovates the talent cultivating system for the IoT Engineering. The implementation results show that the students trained by this system have a solid foundation of knowledge related to IoT Engineering and strong engineering practice application, adaptability, and innovation ability.

Text recognition in natural scenes has been a very challenging task in recent years, and rich text semantic information is of great significance for the understanding of a scene. However, text images in natural scenes often contain a lot of noise data, which leads to error detection. The problems of high error detection rate and low recognition accuracy have brought great challenges to the task of text recognition. To solve this problem, we propose a text recognition algorithm based on natural scenes. First, the task of text detection and recognition is completed in an end-to-end way in a framework, which can reduce the cumulative error prediction and calculation caused by cascading, and has higher real-time and faster speed. In addition, we integrate a multi-scale attention mechanism to obtain attention features of different scale feature maps. Finally, we use the efficient deep learning network (EE-ACNN), which combines a convolutional neural network (CNN) with an end-to-end algorithm and multi-scale attention to enrich the text features to be detected, expands its receptive field, produces good robustness to the effective natural text information, and improves the recognition performance. Through experiments on text data sets of natural scenes, the accuracy of this method reached 93.87%, which is nearly 0.96–1.02% higher than that of traditional methods, and which proves the feasibility of this method.