The school-enterprise cooperation practice teaching system has increasingly become the core of the field of education research on the basis of the Internet and mobile communications. Based on the big data IoT theory and relying on the industrial collaborative innovation platform, this study designs and implements a general service platform for school-enterprise cooperation practice teaching for IoT applications. The platform is divided into two parts: the IoT data transmission part and the Web practice teaching service section. On the Internet of Things big data transmission platform, after the big data processing provided by the intelligent industry collaborative innovation end is completed, it disguises as a web practical teaching service platform built by the Internet of things framework based on B/S architecture. It solves the problem of data transmission on the order of millions. During the simulation process, the platform realizes flexible deployment and automatic integration of online upgrades. The code management script module based on scripts such as SQL, Python, and shell can complete the online platform. The automatic upgrade finally achieves the goals of the platform being easy to maintain, simple to deploy, and flexible in business logic. The experimental results show that starting from the actual situation of a digital intelligent collaborative innovation platform in a university, the practical teaching system designed and implemented adopts the object-oriented development method, and has a three-tier architecture of the collaborative innovation platform. In addition, the functional modularization and standardization reach 88.7% and 79.4%, respectively, effectively improving the performance of the practical teaching system.

Multilabel learning (MLL), as a hot topic in the field of machine learning, has attracted wide attention from many scholars due to its ability to express output space polysemy. In recent years, a large number of achievements about MLL have emerged. Among these achievements, there are several typical issues worthy of attention. Firstly, the correlation among labels plays a key role in improving MLL model training process. Many MLL algorithms try to fully and effectively use the correlation among labels to improve the performance. Secondly, existing MLL evaluation metrics, which is different from those in binary classification, often reflects the generalization performance of MLL classifiers in some aspects. How to choose metrics in algorithms to improve their generalization performance and fairness is another issue that should be concerned. Thirdly, in many practical MLL applications, there are many unlabeled instances due to their labeling cost in training datasets. How to use the wealth information contained in the correlation among unlabeled instances may contribute to reducing of the labeling cost in MLL and improving performance. Fourthly, labels assigned to instances may not be equally descriptive in many applications. How to describe the importance of each label in output space to an instance has become one of research points that many scholars have paid attention to in recent years. This paper reviews the MLL-related research results of correlation among labels, evaluation metric, multilabel semisupervised learning, and label distribution learning (LDL) from a theoretical and algorithmic perspective. Finally, the related research work on MLL is summarized and discussed.