Optimized Multi-Scale Mixed Dense Graph Convolution Network for Career Impression Management in College Students Based on Social Network Analysis

Abstract

This investigation attempts to increase success rate of employment, entrepreneurship by addressing the dangers that college students face when seeking work and starting their own businesses in rural areas. It offers a way of social environment analysis based on employment, entrepreneurship of college students in rural areas. This approach comprehends the employment and social environment of college students' rural employment, entrepreneurship as research goal. It thoroughly examines, detects component parts of the college students' rural employment, entrepreneurship environment. In this manuscript, Optimized Multi-Scale Mixed Dense Graph Convolution Network for Career Impression Management in College Students Based on Social Network Analysis (MSMDGCN-CIM-CS-SNA) is proposed. Initially input data are gathered from Xing social network Dataset. To execute this, input data is pre-processed using Distributed Adaptive Cubature Information Filtering(DACIF) and it removes the noise from collected data; then the Pre-processed data are fed to MSMDGCN for effectively categorize Career Impression Management in College Students. In general, MSMDGCN does not express adapting optimization strategies to determine optimal parameters to ensure accurate Career Impression Management in College Students. Hence, the Sand Cat swarms optimization(SCSOA) to optimize Quantum Conditional Generative Adversarial Network which accurately Career Impression Management in College Students based on Social Media.Then the proposed MSMDGCN-CIM-CS-SNA is implemented and the performance metrics like Student Origin; Proportion of Daily Living Expenses, Student’s Graduation Trend, Selection of Career Areas for College Students, Units of College Student’s Career Intention and Computation Time the World are analyzed. Performance of the MSMDGCN-CIM-CS-SNA approach attains 18.75%, 26.89% and 32.57% higher Student’s Graduation Trend; 16.87%, 24.57% and 32.94% lower Units of College Student’s Career Intention and 18.43%, 25.64% and 31.40% lower Computation Time when analyzed through existing techniques like analysis on social environment of college students’ rural employment with entrepreneurship (ASE-CS-REE), recommendation model for college career entrepreneurship projects depend on deep learning (RM-CCE-DL), group relationship mining of college students depend on predictive social network (GRM-CS-PSN) methods respectively.