Audio-visual recommendation method and system based on information perception

A recommendation method and information-aware technology, applied in the field of media recommendation, can solve problems such as dependence on session data, failure to capture user dynamic preferences, lack of other layers of auxiliary information, etc., and achieve the effect of alleviating interest drift

Active Publication Date: 2022-04-15
COMMUNICATION UNIVERSITY OF CHINA
View PDF3 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In view of the above problems, the purpose of the present invention is to provide an audio-visual recommendation method based on information perception to solve the problem that most of the recommendation methods in the prior art can only obtain the user's long-term and static preferences for items, and cannot capture the user's dynamic preferences. And most of the existing methods only rely on single-layer session data, lack of auxiliary information from other layers, and are prone to cold start and data sparse problems

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
  • Audio-visual recommendation method and system based on information perception
  • Audio-visual recommendation method and system based on information perception
  • Audio-visual recommendation method and system based on information perception

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0065] At present, in the field of movie business, users’ viewing intentions are affected by many factors, such as user preferences for movie genres, users’ preferences for actors and directors, and popular movie releases. However, most of the existing session-based recommendation methods only rely on single-layer session data, lack of auxiliary information from other layers, and are prone to cold start and data sparse problems; and, the current traditional recommendation algorithms (such as content-based recommendation algorithms , recommendation algorithms based on collaborative filtering) tend to use all historical interaction data to obtain users' long-term and static preferences for items. There is an underlying assumption in this approach that all historical interaction data of users are equally important to their current preferences. But in reality, the user's choice of items depends not only on his long-term preferences, but also on his recent interest preferences. For...

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 an audio-visual recommendation method based on information perception and an audio-visual recommendation system based on information perception. The audio-visual recommendation method based on information perception comprises the steps that firstly, user information, movie information and user on-demand record information are preprocessed to form standard input data; obtaining a program global map according to the global film and television data and the user on-demand related data, and amplifying the program global map to form a user-program interaction map; performing learning processing on the user-program interaction diagram to form a movie feature vector and a user feature vector; obtaining short-term interests and long-term interests of the user based on the movie feature vectors and the user feature vectors, obtaining interest vectors of the user based on the short-term interests and the long-term interests, and calculating a normalization probability according to the interest vectors; and sequentially taking a preset number of normalization probabilities from large to small as large probability data, and taking an item corresponding to the large probability data as an audiovisual recommendation list, so that fusion of various heterogeneous information is realized.

Description

technical field [0001] The present invention relates to the technical field of media recommendation, and more specifically, to an audio-visual recommendation method and system based on information perception. Background technique [0002] With the advent of the Internet age, the content information on various websites has exploded. Users are often unable to extract effective information of interest or choose suitable products from massive amounts of information. The emergence of personalized recommendation systems provides users with a more efficient decision-making environment. Great progress has been made in various areas of recommendation algorithm research, such as content-based recommendation algorithms, collaborative filtering-based recommendation algorithms, and hybrid recommendation algorithms. These recommendation algorithms tend to use all historical interaction data to obtain users' long-term and static preferences for items. However, in the field of movie busin...

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): G06F16/435G06F16/901
Inventor 蔡娟娟王璐青李传珍刘民桥王晖
Owner COMMUNICATION UNIVERSITY OF CHINA
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