College course selection and repair mixed recommendation method and system based on attention mechanism

Abstract

The invention discloses a college course selection and repair mixed recommendation method and system based on an attention mechanism. The method comprises the steps that historical course selection behavior vectors of other students, historical course selection behavior vectors of professional courses of target students and candidate course selection vectors are constructed according to historicalcourse selection records of the target students and the other students; attention weighting is performed on the target student vectors according to the historical course selection behavior vectors and the candidate course selection vectors of the target student specialized courses, and student relationship vectors with student relationship weights are obtained according to the weighted target student vectors and student relationship pairs; and a target student preference vector is obtained according to the candidate course selection vector, the historical course selection behavior vectors ofother students and the student relationship vector, thus sorting the candidate course selection according to the target student preference vector, and selecting the first k course selection courses torecommend to the target student. According to the recommendation algorithm, course recommendation is carried out by using multi-party information, so that the memory ability and generalization ability of a recommendation effect can be effectively realized.

Description

technical field [0001] The invention relates to the technical field of social recommendation, in particular to an attention mechanism-based mixed recommendation method and system for elective courses in colleges and universities. Background technique [0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art. [0003] As the Internet course selection method is becoming more and more popular in the course selection of college students, students are often in a state of confusion about course selection. Due to unfamiliarity with unknown courses, it is difficult for students to choose elective courses that satisfy their own interests and are conducive to their professional development. In order to help students choose courses that suit them more effectively, the need for course recommendation is becoming more and more urgent in the course selection process. [0004] The existing cou...

AI Technical Summary

Problems solved by technology

[0007] In summary, the inventor believes that the existing recommendation methods are too single and the recommendation effect is poor; the traditional collaborative filtering algorithm cannot well represent a student's preference for courses, and some existing deep learning methods often use all the students' Historical behavior is used as a training sample, but all historical behaviors of students do not have a positive feedback effect on the prediction of students' course selection preferences; traditional social recommendation methods only predict freshmen's course selection preferences based on the relationship between classmates. The course selection preferences of students may only partially match, so simply using the course selection preferences of other students in social relationships to shape a student’s overall course selection preferences may be more one-sided

Images