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

A kind of personalized video recommendation method and system

A video recommendation and video technology, applied in the fields of instrumentation, computing, electrical digital data processing, etc., can solve the problems of poor initial effect of the algorithm, low reliability of the results, high storage consumption, etc., and achieve the effect improvement and generalization ability. Strong, low computational complexity

Active Publication Date: 2022-07-22
HANGZHOU QUWEI SCI & TECH
View PDF8 Cites 0 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
  • A kind of personalized video recommendation method and system
  • A kind of personalized video recommendation method and system
  • A kind of personalized video recommendation method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

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

[0054] S1, construct a user vector, a video vector, and store the vector in Faiss;

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

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

[0057]User attributes include basic attributes, behavior attributes, etc., so the present invention can extract user characteristics that characterize user attributes, such as ID type characteristics (user name, etc.), basic attribute type characteristics (such as gender, age, city, hobby, etc.), statistics Class features (such as online time in a week, types of videos viewed, etc.). Correspondingly, video features used to characterize video attributes include ID-type features (video ad...

Embodiment 2

[0083] like figure 2 As shown, this embodiment proposes a personalized video recommendation system, including:

[0084] A vector building module for constructing a user vector and a video vector, and storing the vector in Faiss;

[0085] In order to recommend videos to users, the present invention first constructs a user vector and a video vector, and performs video recommendation based on the user vector and the video vector. Specifically include:

[0086] The feature representation module is used to use features to represent the relevant attributes of users and videos;

[0087] User attributes include basic attributes, behavior attributes, etc., so the present invention can extract user characteristics that characterize user attributes, such as ID type characteristics (user name, etc.), basic attribute type characteristics (such as gender, age, city, hobby, etc.), statistics Class features (such as online time in a week, types of videos viewed, etc.). Correspondingly, v...

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, wherein the method includes: S1, constructing a user vector and a video vector, and storing the vector in Faiss; S2, judging whether the user needs to conduct interest exploration, and if so, executing the steps S3, if no, perform step S4; S3, update the user vector based on the user vector of the user and the IDs of his friends or users in the same region; S4, perform video recall in Faiss based on the user vector, and generate a recommended video for the user. The present invention can maintain high recommendation efficiency while avoiding the fixed problem of the recommended content type in the video recommendation process. At the same time, the recommendation is made based on the social network and its 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 comprehensive user data. How to use this data to increase revenue is a problem that enterprises will face. The most common way is personalized recommendations, 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 that the friends who follow them like. However, in the recommendation process based on the social network, only the social relations among users are considered, but the characteristics of the users themselves are not considered, and the prefere...

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 Patents(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