Personalized courses recommendation technology is one of the hotspots in online education field. A good recommendation algorithm can stimulate learners’ enthusiasm and give full play to different learners’ learning personality. At present, the popular collaborative filtering algorithm ignores the semantic relationship between recommendation items, resulting in unsatisfactory recommendation results. In this paper, an algorithm combining knowledge graph and collaborative filtering is proposed. Firstly, the knowledge graph representation learning method is used to embed the semantic information of the items into a low-dimensional semantic space; then, the semantic similarity between the recommended items is calculated, and then, this item semantic information is fused into the collaborative filtering recommendation algorithm. This algorithm increases the performance of recommendation at the semantic level. The results show that the proposed algorithm can effectively recommend courses for learners and has higher values on precision, recall, and F1 than the traditional recommendation algorithm.

With the proposal of China’s “double carbon goal,” as a high energy-consuming industry, it is urgent for the mining industry to adopt a low-carbon development strategy. Therefore, in order to better provide reasonable suggestions and references for the low-carbon development of mining industry, referring to the methods and parameters of the 2006 IPCC National Greenhouse Gas Inventory Guidelines and China’s Provincial Greenhouse Gas Inventory Preparation Guidelines (Trial), a carbon emission estimation model is established to estimate the carbon emission of energy consumption of China's mining industry from 2000 to 2020. Then, using the extended Kaya identity, the influencing factors of carbon emission in mining industry are decomposed into energy carbon emission intensity, energy structure, energy intensity, industrial structure, and output value. On this basis, an LMDI model is constructed to analyze the impact of five factors on carbon emission from mining industry. The research shows that the carbon emission and carbon emission intensity of energy consumption in China’s mining industry first rise and then fall and then rise slightly. The carbon emission intensity in recent three years is about 2 tons/10000 yuan. The increase in output value is the main factor to increase carbon emission. The reduction in energy intensity is the initiative of carbon emission reduction. The current energy structure of mining industry is not conducive to carbon emission reduction.

With the world’s consensus on low-carbon emission reduction, all walks of life have formulated low-carbon development goals. As a high-energy consumption industry, it is urgent for mining industry to implement the development strategy of low-carbon emission reduction. Therefore, this study tries to provide reasonable suggestions and references for the low-carbon development of the mining industry. Firstly, this study analyzes the industry development, energy consumption, and carbon emission of mining industry from 2000 to 2020. Then, using the Tapio theory, this study constructs the analysis model of decoupling between carbon emission of mining industry and industry growth. The analysis method of decoupling state assignment is proposed for the first time in the model. At the same time, the energy efficiency decoupling index and energy structure decoupling index are introduced to explain the causes of carbon emission decoupling. The research shows that the carbon emission of energy consumption in China’s mining industry peaked in 2013, and the energy efficiency decoupling in 2001–2014 is the main driver of carbon emission decoupling. The sharp growth of industrial output value leads to the decoupling of energy efficiency. At present, the improvement of energy efficiency of China’s mining industry faces great resistance. At the same time, the inhibition effect of energy efficiency on carbon emissions is limited, and the energy structure will be the main factor to inhibit carbon emissions.