Research and implementation of a full-process academic early warning and tracking evaluation system

Traditional academic warning systems usually focus more on terminal indicators such as students’ grades and attendance, and trigger warnings when these indicators meet specific conditions. The academic warning system studied in this paper adopts a whole-process monitoring and warning method, which n...

Full description

Saved in:
Bibliographic Details
Main Authors: Li Qipeng, Zeng Songwei
Format: Article
Language:zho
Published: National Computer System Engineering Research Institute of China 2025-02-01
Series:Dianzi Jishu Yingyong
Subjects:
Online Access:http://www.chinaaet.com/article/3000170292
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Traditional academic warning systems usually focus more on terminal indicators such as students’ grades and attendance, and trigger warnings when these indicators meet specific conditions. The academic warning system studied in this paper adopts a whole-process monitoring and warning method, which not only monitors conventional indicators such as students’ final grades, annual assessments, and attendance, but also comprehensively tracks, analyzes and evaluates students’ classroom performance, homework after class, team assessments, ideological and political assessments, and economic pressure, etc. Meanwhile, based on the implementation rules of the undergraduate tutor system, all tutors are encouraged to actively participate in academic warning activities. As important mentors in the learning process of students, they track and evaluate students’ academic performance, and provide timely, effective, and precise academic guidance, realizing the whole-process and closed-loop monitoring from issuing warnings to guiding effects. This paper uses Particle Swarm Optimization (PSO) to optimize Support Vector Machine (SVM), and combines Web and mini-program technology to implement a whole-process academic warning tracking and evaluation system, which effectively improves the accuracy and timeliness of warnings, filling in the gaps of traditional academic warning systems. This system is of great significance for improving the quality of students’ academic performance, and also provides a reference for academic warning support systems in other universities.
ISSN:0258-7998