Recognizing the discipline category of the abstract text is of great significance for automatic text recommendation and knowledge mining. Therefore, this study obtained the abstract text of social science and natural science in the Web of Science 2010-2020, and used the machine learning model SVM and deep learning model TextCNN and SCI-BERT models constructed a discipline classification model. It was found that the SCI-BERT model had the best performance. The precision, recall, and F1 were 86.54%, 86.89%, and 86.71%, respectively, and the F1 is 6.61% and 4.05% higher than SVM and TextCNN. The construction of this model can effectively identify the discipline categories of abstracts, and provide effective support for automatic indexing of subjects.

With the development and progress of the era, digital construction has become an important topic for enterprise development in the new era. Practice has shown that by actively carrying out corresponding digital construction work, enterprises can more comprehensively and systematically analyze the industry development and market prospects, which helps to promote the reasonable adjustment
of internal and external management work modes and the improvement of management efficiency, and has a positive guiding role for the healthy development cycle of enterprises. In this article, the author combines a large amount of research cases to conduct research on the effect of digital construction on enterprise development in the new era and proposes corresponding optimization measures, hoping to further promote the full play of information technology value, in order to safeguard the development of enterprises.