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

Personalized video recommendation method and system

A video recommendation and video technology, which is applied in the fields of instruments, computing, and electrical digital data processing, etc., can solve the problems of poor initial effect of the algorithm, low reliability of the results, and large storage consumption, etc., to achieve improved effects and generalization capabilities Strong, low computational complexity effect

Active Publication Date: 2020-02-28
HANGZHOU QUWEI SCI & TECH
View PDF8 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0011] However, the Bandit algorithm selects recommended results by accumulating user performance. When the data of this type is used up at the beginning, the reliability of the results is not high, so the initial effect of the algorithm is not good; in addition, when the explored category When there are too many, it is time-consuming to calculate the random number of each class each time; each class of each user needs to maintain a beta distribution parameter, which consumes a lot of storage

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
  • Personalized video recommendation method and system
  • Personalized video recommendation method and system
  • Personalized video recommendation method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0053] Such as figure 1 As shown, this embodiment proposes a personalized video recommendation method, including:

[0054] S1. Construct user vectors and video vectors, and store the vectors in Faiss;

[0055] In order to recommend videos to users, the present invention first constructs user vectors and video vectors, and performs video recommendation based on the user vectors and video vectors. Specifically:

[0056] S1.1. Use features to represent related attributes of users and videos;

[0057]The attributes of the user include basic attributes, behavioral attributes, etc., so the present invention can extract user features that characterize user attributes, such as ID class features (user name, etc.), basic attribute class features (such as gender, age, city, hobbies, etc.), statistics Class features (such as the time spent on the Internet in a week, the types of videos viewed, etc.). Correspondingly, video features used to characterize video attributes include ID feat...

Embodiment 2

[0082] Such as figure 2 As shown, this embodiment proposes a personalized video recommendation system, including:

[0083] Vector construction module, for constructing user vector, video vector, described vector is stored in Faiss;

[0084] In order to recommend videos to users, the present invention first constructs user vectors and video vectors, and performs video recommendation based on the user vectors and video vectors. Specifically include:

[0085] The feature representation module is used to use features to represent related attributes of users and videos;

[0086] The attributes of the user include basic attributes, behavioral attributes, etc., so the present invention can extract user features that characterize user attributes, such as ID class features (user name, etc.), basic attribute class features (such as gender, age, city, hobbies, etc.), statistics Class features (such as the time spent on the Internet in a week, the types of videos viewed, etc.). Corre...

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 personalized video recommendation method and system, and the method comprises the steps: S1, constructing a user vector and a video vector, and storing the vectors in Faiss;S2, judging whether the user needs to perform interest exploration or not, if so, executing the step S3, and if not, executing the step S4; S3, updating the user vector based on the user vector of theuser and the ID of the friend or the user in the same region; and S4, performing video recall in Faiss based on the user vector, and generating a recommended video for the user. According to the method, high recommendation efficiency can still be maintained while the problem that the recommended content type is fixed in the video recommendation process is avoided. Meanwhile, recommendation is performed in combination with the social relationship network and own characteristics, and the recommendation effect is good.

Description

technical field [0001] The invention relates to the field of content recommendation, in particular to a personalized video recommendation method and system. Background technique [0002] With the popularity of various applications, enterprises can collect more and more complete user data. How to use these data to increase revenue is a problem that all enterprises will face. The most common way is personalized recommendation, especially in e-commerce, video sites or other content platforms. Recommendation based on social network is a commonly used recommendation method. People with the same or similar interests are more likely to like the same content. Therefore, the recommendation based on the social network is based on the content liked by the friends you follow. However, in the recommendation process based on the social network, only the social relationship between users is considered, and the characteristics of the user itself are not considered, and it completely depen...

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): G06F16/735G06F16/783
CPCG06F16/735G06F16/7847
Inventor 李文杰范俊张智伟顾湘余
Owner HANGZHOU QUWEI SCI & TECH
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