Collaborative filtering-based video program recommendation system and recommendation method

A recommendation system and collaborative filtering technology, which is applied in the fields of instruments, computing, and electronic digital data processing, etc., can solve problems such as difficulty in calculating similarity, complicated relationships, and no longer recommending columns

Active Publication Date: 2016-03-16
SHANDONG UNIV
View PDF4 Cites 36 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

First of all, video recommendation generally relies on videos that users have watched to recommend videos that users have not watched. However, it is impossible to no longer recommend the columns they have watched in the column recommendation. On the contrary, gen

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 filtering-based video program recommendation system and recommendation method
  • Collaborative filtering-based video program recommendation system and recommendation method
  • Collaborative filtering-based video program recommendation system and recommendation method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0057] A video column recommendation system based on collaborative filtering, including: user model creation module, user similarity calculation module, nearest neighbor set generation module, column score generation module and recommendation module, wherein:

[0058] The user model creation module is used to obtain column attribute information, and the attribute information includes user identification, column identification operated by the user, and historical operation information on the column by the user;

[0059] The user similarity calculation module calculates the similarity sim(u,v) between the target user and other users by establishing a similarity matrix M, where u∈1,2,...,n; v∈1,2 ,...,n;

[0060] The nearest neighbor set generation module ranks the interest similarity between the target user and other users, and obtains the K users with the largest value to obtain the nearest neighbor set of the target user, and the value of K is set according to the actual situa...

Embodiment 2

[0064] A kind of recommending method of recommending system as described in embodiment 1, comprises the steps:

[0065] Step S101: Create a user model

[0066] Use the number of user clicks on the column as the scoring value in the scoring table: the user clicks on any video in the column is considered to have completed a column click, and obtains all the columns clicked by the user within a long period of time from the user log file The name and the number of times each column has been clicked will be sorted out to generate a user viewing history table; the data format of each record is: {User: column 1 [number of clicks on column 1]; column 2 [number of clicks on column 2]; column 5[ column 5 click times]; ...; column i[column i click times]}; deduplicate the data recorded above and store it in database A;

[0067] Step S102: Calculate user similarity

[0068] The collaborative filtering algorithm analyzes and calculates the user's interest similarity through the similarit...

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 provides a collaborative filtering-based video program recommendation system, which comprises a user model creation module, a user similarity calculation module, a nearest neighbor set generation module, a columns score generation module and a recommendation module. The recommendation method comprises the steps of setting a reward item and increasing the effect of a dark-horse column on the user similarity. Based on the above recommendation method, the computational complexity is reduced by utilizing a user similarity matrix M. the rating of the above recommendation method is realized based on the weighted average of the nearest-neighbor similarity. In this way, the user preference is fully analyzed and the potential interest points of users can be found out.

Description

technical field [0001] The invention relates to a collaborative filtering-based video column recommendation system and recommendation method, and belongs to the technical field of smart TV recommendation systems. Background technique [0002] With the advent of the Internet era and the era of big data, and the rapid development of smart Internet TV, the TV programs people watch are not limited to live TV programs. Through the Internet, TV users can choose more conveniently and quickly according to their interests. shows or popular movies. The information overload problem caused by the rapid growth of the order of magnitude of movies has brought a lot of trouble to users, making it impossible for users to accurately and efficiently obtain the movies they are interested in. The rapid growth of the Internet scale has brought about the problem of information overload. The simultaneous presentation of excessive information makes it impossible for users to quickly and convenientl...

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
IPC IPC(8): G06F17/30
CPCG06F16/735
Inventor 许宏吉李文强季名扬许征征李石曹海波
Owner SHANDONG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap