Abstract
By controlling the benefits and drawbacks of informatization construction (IC) and development, evaluating the level of education informatization (EI) development can aid in university administration and decision-making. This work develops an evaluation method for the University Information Construction (UIC) based on the Analytical Hierarchy Process (AHP) and the Particle Swarm Optimization-based back-Propagation Neural Network (PSO-BPNN) algorithm to address the fuzziness issue in grade evaluation in the IC. Firstly, a set of data-driven evaluation index systems of the UIC effect is constructed with 16 second-class indicators and four first-class indicators of infrastructure, resource management, information management, and safeguard measures. The AHP method is used to determine the weight of the first-class indicators of the IC model. Secondly, from two perspectives of inertia weight and learning factor, the PSO-BPNN algorithm is designed to fit and analyze the level of UIC. The experimental findings demonstrate that the proposed model's training impact is better, reflecting UIC's effectiveness more accurately.