Get started
Work

Big Data-Driven Model for Industry-Education Integration Quality Evaluation and Optimization

Year: 2025
Type: conference-paper
Abstract: This study builds a model for quality evaluation and optimization of industry-education integration based on big data tech. It aims to address the limitations of traditional evaluation methods, which are overly simplistic, subjective, and static. First, we made a multi-level indicator system covering policy environment, resource inputs, integration process, and output benefits, and used hierarchical analysis and expert consultation to determine indicator weights. Second, we developed multi-source data fusion and feature extraction, integrating five data sources: education management systems, company information systems, government open data, surveys and social media. Third, we designed an evaluation model with three modules: basic evaluation, dynamic monitoring, and smart diagnosis, creating innovative evaluation that combines static evaluation with dynamic monitoring, and problem finding with cause diagnosis. The experiment used 10 vocational colleges from east, central, and west regions for verification and comparison. Results show our model matches reality 23.2 percentage points better than traditional methods; it performs great in stability (0.911) and adaptability (0.900); and works well for schools of different sizes and regions. Based on evaluation results, we suggested strategies in four areas: policy environment optimization, resource input optimization, integration process optimization, and outcome optimization. This research not only expands theory but also provides useful evaluation tools and optimization methods for government, schools, and companies, which is important for improving industry-education integration quality and promoting vocational education.
DOI: 10.1145/3764206.3764337
Language: English
Subfield: Education
Open Access status: hybrid
OpenAlex ID: W4416844166
FWCI:
Cites: 7
Cited by:
Related to: 10