Unlock instant, AI-driven research and patent intelligence for your innovation.

Collaborative course selection recommendation method based on scores and course teachers

A technology for teachers and scores, applied in data processing applications, electrical digital data processing, special data processing applications, etc., can solve problems such as lack of comparability, inappropriateness, and difficulty in obtaining historical information, and achieve reasonable models and accurate collaborative filtering , the reasonable effect of vector training

Inactive Publication Date: 2019-07-30
TIANJIN UNIV
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The key to this method is how to find the similar relationship between users. For newly enrolled students, it is relatively difficult to obtain historical information and lacks comparability, so it is not suitable for the scenario of course recommendation.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Collaborative course selection recommendation method based on scores and course teachers
  • Collaborative course selection recommendation method based on scores and course teachers
  • Collaborative course selection recommendation method based on scores and course teachers

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0036] Based on the traditional collaborative filtering algorithm and the principle of word2vec, the present invention proposes a course selection recommendation method for cooperative scores and teachers, emphatically introducing two features of scores and teachers. Substantive features of the present invention are as follows:

[0037](1) Calculate the similarity relationship between courses based on the principle of word2vec. Word2vec is a tool that Google open sourced in 2013 to represent words as vectors, and map the similarity between words through the cosine angle between vectors. In the present invention, all courses selected by each graduate are sorted in time series as an input text, and each course is regarded as a word. Due to the coherence between courses, each text can be regarded as a time series. Using the idea of ​​CBOW model to predict the central word through the context, the current course vector can be predicted according to the previous and subsequent co...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention relates to a collaborative course selection recommendation method based on scores and course teachers, and the method comprises the following steps: selecting all graduate courses and teacher and score information corresponding to the courses, carrying out the timing sequence arrangement, and serving as input data; respectively constructing two Huffman trees according to the statistical frequency of the course and the course teacher in the input data, thereby determining the Huffman code of each course and the course teacher thereof; randomly initializing parameters of all models, vectors of courses and vectors of course teachers; carrying out iteration. The closer the distance between the course vectors is, the higher the similarity between the two courses is, and when a course of interest is newly selected, other courses related to the course can be recommended, namely, the connection between the courses is considered, and the favor of students on teachers is also considered.

Description

technical field [0001] The invention belongs to the technical field of recommendation based on collaborative filtering, and in particular relates to a collaborative course selection recommendation method based on scores and teachers. Background technique [0002] With the diversification of education development, designing a complete, scientific and reasonable curriculum system according to the subject characteristics of students' majors has become the focus of education that major universities are paying more and more attention to. At present, the curriculum arrangement of major universities mostly adopts the way that students choose courses freely. Although designated professional courses are divided according to different grades, the coherence and cohesion between courses of different grades are determined by students themselves. When students choose courses, they usually face the problem of not knowing which courses are suitable for them and which teachers are suitable f...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06F16/9535G06Q50/20
CPCG06Q50/205G06F16/9535
Inventor 金志刚韩玥罗咏梅
Owner TIANJIN UNIV