Course recommendation method based on deep session interest interaction model
A recommendation method and technology of interest, applied in data processing applications, instruments, calculations, etc., can solve the problems that the recommendation model cannot recommend personalized courses for users, cannot fully express user interests, and does not consider the impact of user noise items, etc.
Pending Publication Date: 2022-05-31
GUILIN UNIV OF ELECTRONIC TECH
View PDF1 Cites 1 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] What the present invention aims to solve is that in the current course recommendation method based on the interest extraction process of the user session, the influence of noise items in the interaction process between the user and the item is not considered; at the same time, a static and low-rank vector cannot fully express the user's interest. interest, and the user's interest is not static, but changes with time, which leads to the failure of the generated recommendation model to recommend personalized courses for users, etc., and provides a course recommendation method with an in-depth conversational interest interaction model
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0024] In order to make the purpose, technical solution and advantages of the present invention clearer, the present invention will be further elaborated below in combination with specific examples and with reference to the accompanying drawings.
[0025] The present invention describes the specific implementation process of the method of the present invention by taking the course recommendation based on the deep conversational interest interaction model as an example. The model framework of the present invention is as figure 1 As shown, the overall process of course recommendation based on the deep conversational interest interaction model is as follows: figure 2 shown. Combined with the schematic diagram to illustrate the specific steps:
[0026] Step 1. Download the MOOCCube dataset from the MOOCData official website, and preprocess the data after screening.
[0027] Step 2. After obtaining the screened data from step 1, arrange the student data in chronological order, ...
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
Login to View More Abstract
The invention discloses a course recommendation method based on a deep session interest interaction model, which is characterized by mainly comprising the following steps of: screening and preprocessing user data, sorting behavior information of users and items according to time, and dividing sessions by taking one day as a time interval; in order to describe the dynamically changing interests of the user and enrich the interest representation of the user, the GRU is applied to capturing the dynamic preference of the user; next, inputting the recent behavior data and the dynamic interest representation of the user into a second-layer Attention network to obtain a multi-angle interest representation of the user; and finally, performing inner product on the multi-angle interest representation of the user and the course vector representation, and selecting each candidate item with a high score to recommend for the student. The problems that the influence of a noise item exists in the interaction process of the user and the item and the interest of the user cannot be fully expressed by a static and low-rank vector are not considered.
Description
(1) Technical field [0001] The invention relates to technical fields such as machine learning, deep learning, and data mining, and specifically relates to a course recommendation method that captures user preferences from multiple perspectives. (2) Background technology [0002] In recent years, the traditional offline education model has been under the pressure of soaring labor costs. At the same time, the individual needs of consumers have not been met. Against this background, offline education is facing more and more challenges such as high costs and low profits. stand out. With the rapid development of the Internet and artificial intelligence, the online education network environment has been greatly improved and enhanced. Online education refers to a method of rapid learning and content dissemination through Internet technology. Currently existing online education platforms such as MOOC and Netease Cloud Classroom are very popular. Compared with the traditional educ...
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
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G06F16/9535G06Q50/20
CPCG06F16/9535G06Q50/205
Inventor 刘铁园吴琼古天龙常亮
Owner GUILIN UNIV OF ELECTRONIC TECH