During the implementation of China’s Vocational Skill Level Certificate, the Vocational Skill Curriculum Development Organization built an online teaching community of practice (COP) by inviting instructors from several schools to participate. Through this community, instructors constructed a blended teaching system together through multiparty collaboration modes like cooperation, communication, sharing, and mutual assistance. As demonstrated by the research team, when teachers participate in a community of practice, the curriculum development model implemented within that community can strengthen the blended teaching intentions and ability of instructors, thus exerting positive effects on their blended teaching behaviors. Based on an extended Unified Theory of Acceptance and Use of Technology (UTAUT), a theoretical model concerning the influencing factors of online teaching communities of practice on the blended teaching behaviors of instructors was constructed. Through a questionnaire survey and field interviews of 204 instructors, data were analyzed by SPSS and AMOS software and an empirical test of the constructed conceptual model was carried out. The research results demonstrate that performance expectancy influences the blended teaching intentions of instructors only slightly, while effort expectancy and facilitating conditions have significantly positive influences on the blended teaching intentions of instructors. Interactions between the instructors themselves and interactions between instructors and the organization in the online community of practice have significantly positive influences on the blended teaching ability of instructors. The blended teaching intentions and blended teaching ability of instructors both have significantly positive influences on their blended teaching behaviors. In this research conclusion, various methods for online COPs to improve the blended teaching behaviors of instructors were summarized.

The optimized learner evaluation matrix and similarity model are essential methods to deal with the challenges of “data sparsity” and “cold start” in the process of learning resource recommendation on the online learning platform. Accordingly, an improved collaborative filtering algorithm (TRCP) is proposed to improve the accuracy of learning resource recommendation. The TRCP algorithm generates the learner evaluation matrix for recommended projects by classifying learning resources. It comprehensively considers the influence of learners’ online learning behavior, learning time, and popularity of learning resources on learners’ interest and optimizes the sample data in the evaluation matrix. The experimental results on the school online teaching platform verified that this method has achieved obvious and effective results in both the accuracy and satisfaction rate of learning resource recommendation.

Clothing is an important commodity category for e-commerce sites. As the number of consumers and clothing on the e-commerce site continues to grow, the "sparsity" and "cold start" issues of consumer rating data have affected the accuracy of collaborative filtering recommendation algorithms. To solve the above problems, an improved collaborative filtering algorithm is proposed. Based on the classification attributes of clothing, the algorithm weights and combines the clothing category preference similarity and consumer feature similarity to obtain a comprehensive similarity and uses this to conduct the final personalized recommendation. Experiment results show that the algorithm not only optimizes the selection of nearest neighbors, but also alleviates the problem of data sparsity, and achieves good recommendation results.