Research on big data visualization in the talent cultivation guarantee system of social sports instruction and management oriented to the concept of OBE

Abstract How to evaluate the talent objectively, targeting to improve the quality of talent training and collocation efficiency, urgently need to think and solve. This paper carries out the analysis of social sports guidance and management professional talents through data mining and visualization. First of all, according to the talent portrait construction process for data collection, text analysis, talent portrait construction, and then apply the improved K-mean clustering for the visualization and analysis of talent cultivation. For the initial clustering center of traditional K-mean clustering algorithm, the density parameter is used to reduce the uncertainty generated by randomly selecting the clustering center. Finally, principal component analysis is used to derive the final classification evaluation results. After calculating the four clustering centers, the sample talent quality level is in the middle level, and the total score ranges from 63 points to 85 points. The second category of social sports guidance and management talents obtained by clustering is the best among all categories, and the overall physical and mental qualities are the highest in the sample, which are all above 78 points. Moreover, the highest scores for all indicators except the quality of specialized knowledge appeared in this part of the social sports guidance and management talents. The number of talents finally categorized as three stars is the highest, up to 121.