In order to build an education information platform to support “industry-education dialogue” and at the same time serve the teaching and research of industry-education integration. In this paper, we use big data technology to construct a system of education management and resource optimization, supporting education construction in the context of industrial transformation and upgrading. For larger-scale WSNs, an energy-efficient data collection algorithm based on non-uniform clustering is proposed. To deal with large-scale optimization problems, a hybrid algorithm of genetic algorithms and particle optimization hierarchical collaboration is introduced. Then, the algorithm is applied to cluster WSNs, an adaptation function is constructed with the goal of equalizing energy consumption, and a data collection algorithm based on non-uniform clustering is proposed. The Apriori algorithm, which is based on the interest degree model, is used to mine the course evaluation data for the system design in the university industry-teaching fusion model. This system design does both course evaluation and resource optimization. The system’s total evaluation score is high, at 90.84 points. It also improves the efficiency of cooperation between the education industry and schools. It proves that the system’s design is effective and high-level and has a positive effect on teaching management and resource optimization in education.