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

Video recommendation method and system

A video recommendation and video technology, applied in special data processing applications, instruments, electrical digital data processing, etc., can solve problems that affect the quality of recommendations, and achieve the effect of improving the quality of recommendations

Active Publication Date: 2014-11-19
STARTIMES SOFTWARE TECH CO LTD
View PDF9 Cites 48 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In view of this, the present invention provides a video recommendation method and system to overcome the traditional implicit scoring method in the prior art that does not comprehensively consider the video's own playing time, user ratings and time interval factors on the user's interest. Influence, which seriously affects the quality of the final 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
  • Video recommendation method and system
  • Video recommendation method and system
  • Video recommendation method and system

Examples

Experimental program
Comparison scheme
Effect test

example 1

[0104] In the collaborative filtering recommendation system, the normal distribution factorization method assumes that the number of users is M and the number of videos is N, and further assumes that the latent factor random vector Q for a given user u and video i u and P i After that, user u’s final implicit rating R for video i ui is a random variable whose mean is R = QP T ≈ Σ f = 1 F Q uf P if , Variance is normal distribution of , where And F The normal distribution of the latent factor vector Q satisfies the mean value of 0 and the variance of is normally distributed, and the latent factor vectors P and Q are independent of each other.

[0105] But in reality, some inherent attributes of a scoring system have nothing to do ...

example 2

[0161] There are many similarity algorithms used in collaborative filtering recommendation algorithms, such as cosine similarity algorithm, Pearson similarity algorithm and Euclidean similarity algorithm. Preferably, this solution adopts the Pearson similarity algorithm to calculate the similarity between video and video, and its calculation formula is as follows:

[0162] S ( x , y ) = Σ x i y i - N xy ‾ NΣ x i 2 - ( Σ x i ...

example 3

[0175] Example 3: Top-N recommended implementation method

[0176] Preferably, the final video recommendation score of user u can be calculated by the following formula:

[0177] SR u = Sim ( x , y ) × R u T - - - ( 28 )

[0178] Among them: SR u is the recommendation score vector of user u for each video finally calculated by the recommendation system, Sim(x,y) is the improved video-video similarity matrix based on video tags and viewing history information, R u is the rating vector of user u for each video after matrix decomposition of social normal distribution factorization method,

[0179] The resulting vector SR u It can be sorted according to the recommendation score from high to low, recommend ...

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 discloses a video recommendation method and system. The method comprises the steps that an initial score of a user on a video is calculated according to the length of time of the video and the length of time spent by the user in watching the video; the initial score is standardized in a minimum-maximum standardization mode to obtain a standardization score of the user on the video; according to the difference value between a current moment and the moment when the user watches the video last time, calculating a final score of the user on the video. According to the video recommendation method and system, the influences of the playing time of the video, the user watching frequency and time interval factors on user interestingness are comprehensively considered, and the final recommendation quality is improved.

Description

technical field [0001] The present invention relates to the technical field of personalized recommendation, in particular to a video recommendation method and system. Background technique [0002] The recommendation system is a system that establishes a binary relationship between a user and an item (such as video, audio, product, etc.), mines potential objects of interest for each user through historical information or similarity relationships, and then performs personalized recommendations. [0003] Among the existing large-scale recommendation systems, collaborative filtering recommendation (Collaborative Filtering Recommendation) is currently the hottest personalized recommendation technology. The collaborative filtering recommendation system is a system that studies the user's interest preferences, performs personalized calculations, and discovers the user's points of interest by the system, thereby guiding the user to discover their own information needs. Collaborativ...

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
CPCG06F16/735H04N21/25891
Inventor 胡玉婷袁昊程曹江辉
Owner STARTIMES SOFTWARE TECH CO LTD
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com