Research on self‐learning system with “Internet + Education” innovative talents education mode under big data background

Abstract

AbstractIn the “Internet + Education” mode, a big data analysis of innovative talents education model is conducted to improve the quantitative evaluation ability of innovative talent education and training, and the “Internet + Education” innovative talent education model under the background of big data is proposed based on segmented information fusion and regression statistical analysis. More and more attention is attracted by the continuous advancement of innovative talent training models. The resource data mining and information processing research of innovative talent education models are conducted in related literature and have achieved certain research results. A big data analysis model for the cultivation of innovative talents is constructed and a structured big data information reorganization method is adopted to conduct information fusion processing of the “Internet + Education” innovative talents education model. Features describing the associated information of the talent cultivation model are extracted and the segmented information fusion method is adopted for feature clustering processing. The autoregression analysis of innovative talents cultivation evaluation ability is conducted based on feature clustering results and a test statistic model is constructed for effective analysis of the “Internet + Education” innovative talents education model under big data background. As a result, comprehensive and fuzzy decision‐making on the talent education model is realized according to judgment statistics. Simulation results show that the accuracy of a quantitative assessment of the “Internet + Education” innovative talents education model is higher with this method and the convergence of regression analysis is better. This shows that this method can effectively instruct the innovation of the talent education model and novel technologies can be more utilized by the efficiency and performance of the method.