The academic society is stepping into the age of scholarly big data, where finding suitable scholars for collaboration has become ever difficult. Scholarly recommendation approaches are designed to overcome the information overload problems. However, previous methods mainly consider network topology without considering scholars academic information and the manually designed similarity measurements may not have a good performance when applying to large-scale sparse networks. This paper designs a scholarly friend recommendation system using network embedding and scholar attributes. We first construct an attributed social network by extracting scholars academic attributes from digital libraries. Then, we perform an attributed random walk which can jointly model network structure and scholar attributes. Finally, a novel graph recurrent neural framework is adopted to embed attributed scholar interactions within the model for recommendations. Experimental results on two real-world scholarly datasets demonstrate the effectiveness of our proposed method.

Many oil fields are full of wind energy. At present, wind power generation technology has catered to oil fields. A larger wind turbine is used to supply power to several pumping units. As a result of the structural characteristics of the pumping unit, the efficiency of the electromotor is very low, which leads to a reduction in the utilization rate of wind energy. At the same time, considering the high cost of large wind turbines, the energy saving effect is not obvious in practical applications. This paper proposes an energy supply model of a pumping unit driven by a small wind turbine and a new wind-motor hybrid structure. Instead of wind power generation technology, wind energy drives the pumping unit directly via a mechanical–hydraulic transmission system. This new mechanical-hydraulic system can optimize the power confluence of wind and electric power. To enhance the efficiency of the motor, a mathematical model and a test station were established. The correctness of the energy conservation method and the mathematical model was verified, and the performance of the wind-motor system was studied.