Big Data Analysis and Modeling Method of College Student Employment Management Based on Deep Learning Model

Introduction

College students’ employability represents an important cornerstone to ensure the sustainable development of national education and is related to national economic development and social construction. Due to the expansion of university enrollment, the number of university students has continued to grow. In 2020, there will be as many as 8.74 million fresh graduates of domestic universities, while in 2021, the number will be 9.09 million—an increase of 350,000. In addition, affected by the COVID-19 pandemic, the demand for employment of enterprises has decreased, some posts are saturated, and the employment situation of college students is extremely pessimistic. At the same time, in order to improve their competitiveness, more and more college graduates have joined the ranks of the postgraduate entrance examination. Data shows that in just the ten years from 2009 to 2019, the number of graduate students admitted to colleges and universities has grown from 440,000 to 720,000. On February 28, 2020, the Ministry of Education in China plans to increase the enrollment of master’s students by 189,000. The continuous increase of the number of graduates, the employment of graduates is facing a complex and severe situation, and the difficulty of graduate employment is also increasing, representing a complex and serious situation (Dong, 2021). The state attaches great importance to employment, especially for college graduates. In the new era, colleges and universities should combine their own reality and carry out more targeted employment guidance services, formulate corresponding employment opportunities according to the student condition promote the innovation of an employment work system for college graduates, and optimize employment guidance.

With the popularization of higher education, the employment environment and situation of college students have become complicated, which hinders the rational and scientific employment of college students in the future. In this context, colleges and universities should strengthen the employment management of college students, give full play to the role of the employment management of college students, strengthen the employment guidance of college students so that college students know the direction of future development, and promote the good employment of college students in the future. Based on this, in the practice of college education, it is necessary to focus not only on the development of college students' employment management, but also on the innovation of college students' employment management, so as to improve the quality of college students, thereby improving the quality of college personnel training and realizing the practical significance of college students' employment management. Although college employment data management methods have achieved good development in recent decades, there are still shortcomings. Deep learning is a novel machine learning method proposed in the field of artificial intelligence in recent years. Deep learning can mine and capture the deep connections between big data by training big data and can improve the accuracy of classification and prediction (Cheng, 2022). It is an effective big data processing method. In addition, the training of deep learning models is faster, and with the increase of training samples, it can show better performance growth than general methods. The college student employment data management model based on deep learning can overcome the shortcomings of existing methods. The reasons are as follows:

• •

  Sufficient data can ensure the accuracy of the model.

• •

  The model can deeply mine the data relationship and establish an accurate proxy model between employment indicators and impact factors.

• •

  The deep learning model can avoid the defects and uncertainties of the single employment indicator model to a certain extent (Gugnani & Singh, 2022).

In order to study the big data of college students' employment, this paper takes the big data of college students' employment as the premise, analyzes the current employment data by establishing a deep belief network (DBN) model, and proposes relevant management measures, aiming to provide a scientific basis for the management of graduates' employment data.