Design and implementation of college student portrait system
Li, Zijing (2024)
Kandidaatintyö
Li, Zijing
2024
School of Engineering Science, Tietotekniikka
Kaikki oikeudet pidätetään.
Julkaisun pysyvä osoite on
https://urn.fi/URN:NBN:fi-fe2024051732273
https://urn.fi/URN:NBN:fi-fe2024051732273
Tiivistelmä
The construction of smart campus has been vigorously promoted with the rapid development of information technology and big data technology today. Colleges and universities can collect and store data such as students' basic information, academic performance and campus behavior through various ways. Because students' campus learning and daily life mainly depend on students' individual self-management, the occurrence of problems such as failure, partial course, and irregular life may not be timely attention, so that students have trouble and affect the normal area. Based on a large number of students' scores and consumption records collected, the main learning and consumption characteristics of students are extracted, and an intuitive student portrait is constructed. Through the classification and quantification of courses, the future development direction is evaluated and suggested, so that students can get targeted help on campus, and colleges and universities can optimize a more reasonable student management plan.
This thesis preprocesses the consumption data items obtained from the campus card and the student scores collected in the examination, such as data cleaning, desensitization and standardization. A label system is constructed based on the standardized student attributes, and the K-means algorithm is used to cluster the data such as student scores and consumption, and the clustered students are labeled. So as to form a complete student portrait. In this paper, PostgreSQL relational database is used to store original and factual data data, and Django+ReactJS technology is used to implement a Web-based student portrait system. The visual presentation of student portraits makes students have a clearer understanding of their own campus learning status and future development. After testing and verification, the various functions of the system can run accurately without failure, can run normally in the case of hundreds of concurrent login use, and maintain a millisecond fast response.
This thesis preprocesses the consumption data items obtained from the campus card and the student scores collected in the examination, such as data cleaning, desensitization and standardization. A label system is constructed based on the standardized student attributes, and the K-means algorithm is used to cluster the data such as student scores and consumption, and the clustered students are labeled. So as to form a complete student portrait. In this paper, PostgreSQL relational database is used to store original and factual data data, and Django+ReactJS technology is used to implement a Web-based student portrait system. The visual presentation of student portraits makes students have a clearer understanding of their own campus learning status and future development. After testing and verification, the various functions of the system can run accurately without failure, can run normally in the case of hundreds of concurrent login use, and maintain a millisecond fast response.
