Research on the Quality Improvement of Party School Education and Training in Newly-Built Applied Undergraduate Colleges and Universities Facing Intelligent Educational Technology

Abstract

With the continuous progress of intelligent education technology, the education and training of party schools in new applied undergraduate colleges and universities are facing the urgent need to improve the quality. In this study, we use Jieba Partition Technology to perform particual processing on training materials and use the TF-IDF algorithm to extract features from the particual results. A training management platform for party schools in colleges and universities that integrates intelligent education technology is built using the improved collaborative filtering recommendation model. Taking a university as an example, the performance test of this paper’s training platform is conducted, and finally, through regression analysis, the effect of improving the quality of party school education and training is assessed. The recommendation model in this paper performs better when the number of recommendations is 200, yielding precision and recall values of 0.55 and 0.51, respectively. The average degree of compliance of the party school trainees with the five indicators of effectiveness assessment is high, and the average score of “Satisfactory training results” is 4.035. The factors of the intelligent education platform, such as training content, training methods, instructor level and training materials, all have highly significant effects on the improvement of training quality at the level of p<0.001. All of them have a highly significant positive contribution to the improvement of training quality.

Keywords

• jieba participle
• tf-idf algorithm
• collaborative filtering recommendation
• party school training
• 97m80