Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Television product accurate recommendation method and system based on explicit and implicit potential factor model

A factor model and recommendation method technology, applied in the field of recommendation, can solve problems such as inability to recommend users, limited scope of use, and inability to explain

Active Publication Date: 2019-07-02
PLA STRATEGIC SUPPORT FORCE INFORMATION ENG UNIV PLA SSF IEU
View PDF7 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The content-based recommendation algorithm is to directly analyze the product content, and recommend products with similar content according to the past preferences of the target users. This recommendation algorithm is simple and direct, but the scope of use is limited, and it is only used for products with existing prominent labels.
The problem with this type of algorithm is that it cannot recommend products in categories that users have never touched
However, in the LFM model, the decomposed features cannot be explained, and these features are often obtained through mathematical calculations rather than artificially specified

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
  • Television product accurate recommendation method and system based on explicit and implicit potential factor model
  • Television product accurate recommendation method and system based on explicit and implicit potential factor model
  • Television product accurate recommendation method and system based on explicit and implicit potential factor model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0081] like figure 1 As shown in the figure, an accurate recommendation method for TV products based on an explicit and implicit latent factor model includes the following steps:

[0082] Step S101: processing the correct title of the TV product through regular expressions, comprehensively considering multiple anti-crawling mechanisms, designing a crawling strategy, and crawling the required external data;

[0083] Specifically, the step S101 includes:

[0084] Step S1011 : designing an anti-crawling mechanism, the anti-crawling mechanism includes actively initiating an asynchronous request to obtain the required data by simulating an Ajax request;

[0085] Step S1012: Design a web crawler algorithm according to the anti-crawler mechanism to crawl web page data:

[0086] Adopt the anti-crawler mechanism to continuously initiate Http requests, then receive Http responses, parse the HTML file obtained, and if it is a definite structure, directly match the data in the tag;

[...

Embodiment 2

[0131] like figure 2 As shown, another method for accurate recommendation of TV products based on the explicit and implicit latent factor model includes the following steps:

[0132] Step S201: Process the correct title of the TV product through regular expressions, comprehensively consider various anti-crawling mechanisms, design a crawler strategy, and crawl the required external data; the correct title of the TV product includes the TV series name and the number of episodes, variety show name TV program titles such as the number of episodes and the number of episodes, such as "Peacekeeping Infantry Battalion (19)", "October 19 Nature: A Bird's Eye View of the Earth (05)", etc. The correct title of the TV product can be obtained from the TV product information. The TV product information is mainly It consists of logo, proper title of TV product, date of creation, director, actor, year of production, content description, total number of episodes, category name, series catego...

Embodiment 3

[0270] like Figure 8 As shown, an accurate recommendation system for TV products based on an explicit and implicit latent factor model includes:

[0271] The automatic label labeling module 301 is used to process the correct title of the TV product through regular expressions, comprehensively consider a variety of anti-crawling mechanisms, design a crawling strategy, and crawl the required external data;

[0272] The automatic label labeling module 302 is used to establish a classification model for TV products and user groups according to different characteristics of TV products and user groups, and realize automatic label labeling of TV product information and user information through the classification model, and obtain labeling Labeled TV product information and labelled user information;

[0273] The explicit and implicit latent factor model building module 303 is used to obtain explicit latent factors according to the TV product information data tag table, the user vie...

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 the technical field of recommendation, and discloses a television product accurate recommendation method based on a explicit and implicit potential factor model, which comprises the following steps: processing a television product positive topic name through a regular expression, designing a crawler strategy, and crawling required external data; establishing classificationmodels aiming at the television products and the users according to different characteristics of the television products and the user groups, thereby realizing automatic label labeling of the different television products and the users in the crawled external data, and obtaining television product information after label labeling and user information after label labeling; obtaining a potential dominant factor, obtaining a potential recessive factor according to the potential dominant factor, and constructing a potential recessive factor model based on the potential dominant factor and the potential recessive factor; and recommending the television product based on the constructed explicit and implicit potential factor model. The invention also discloses a television product accurate recommendation system based on the explicit and implicit potential factor model. The recommendation accuracy is improved.

Description

technical field [0001] The invention relates to the technical field of recommendation, in particular to a method and system for accurate recommendation of television products based on an explicit and implicit latent factor model. Background technique [0002] With the rapid development of the Internet, information is showing an explosive growth trend, and countless information floods into thousands of households every day. The "Triple Play" under this situation has brought opportunities for the development of traditional radio and television media. Radio and television operators can obtain useful information from the historical information and real-time interactive information of each user, but find users from a large amount of information. Interesting information is very difficult. In order to solve this problem, the recommender system mines users' favorite preferences by analyzing the relevant data of users, including personal social attributes, browsing logs, etc., so as...

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): H04N21/258H04N21/25H04N21/845H04N21/81H04L29/08G06K9/62
CPCH04N21/25891H04N21/25866H04N21/251H04N21/252H04N21/8455H04N21/8133H04L67/02G06F18/2411
Inventor 奚琪桂智杰李创项永明杨萍
Owner PLA STRATEGIC SUPPORT FORCE INFORMATION ENG UNIV PLA SSF IEU
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products