Audiovisual recommendations and systems based on information perception

An information perception and recommendation method technology, applied in the field of media recommendation, can solve the problems of relying on session data, lack of other layers of auxiliary information, and unable to capture user dynamic preferences, so as to alleviate the effect of interest drift

Active Publication Date: 2022-08-09
COMMUNICATION UNIVERSITY OF CHINA
View PDF3 Cites 0 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
  • Audiovisual recommendations and systems based on information perception
  • Audiovisual recommendations and systems based on information perception
  • Audiovisual recommendations and systems based on information perception

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0065] At present, in the field of film business, users' movie intentions are jointly affected by various factors, such as users' preferences for film types, users' preference for actors and directors, and film heat screenings. However, most of the existing session -based recommendation methods only depend on single -layer session data, lack of auxiliary information of other layers, and prone to cold startup and data sparse problems; and the current traditional recommendation algorithm (such as content -based recommendation algorithms 2. Recommended algorithm based on collaborative filtration) tend to use all historical interactive data to obtain the user's long -term and static preferences for the project. There is a potential assumption that all historical interaction data of the user is equally important for its current preferences. But in reality, users' choices of projects depend not only on his long -term preferences, but also on his recent interest preferences. For example,...

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 present invention provides an audiovisual recommendation method based on information perception. The audiovisual recommendation method and system based on information perception firstly preprocess user information, movie information and user on-demand record information to form standard input data; Obtaining the program global map from the on-demand related data, and augmenting the program global map to form a user-program interaction map; learning and processing the user-program interaction map to form movie feature vectors and user feature vectors; based on movie feature vectors and user features The vector obtains the user's short-term interest and long-term interest, obtains the user's interest vector based on the short-term interest and the long-term interest, and calculates the normalized probability according to the interest vector; from large to small, a preset number of normalized probabilities are taken as the large probability data, and use the items corresponding to the high probability data as the audio-visual recommendation list, thus realizing the fusion of various heterogeneous information.

Description

Technical field [0001] The present invention involves the field of media recommendation technology and is more specific, involving an information -based audiovisual recommendation method and system. Background technique [0002] With the advent of the Internet era, the content information on various websites has exploded. Users often cannot extract valid information from massive information or choose appropriate products. The emergence of the personalized recommendation system provides users with a more efficient decision -making environment. The work in the field of recommendation algorithms has made great progress, such as content -based recommendation algorithms, collaborative filtering recommendation algorithms and hybrid recommendation algorithms. These recommendation algorithms tend to use all historical interactive data to obtain users 'long -term and static preferences for the project. However, in the field of film business, users' preferences are often dynamic. In order ...

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): G06F16/435G06F16/901
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