Cold start recommendation method and system of television applet
A recommendation method and technology of recommendation system, applied in the field of cold start recommendation of TV mini-programs, can solve problems such as inapplicability of TV fixed products, inappropriate product recommendation, etc.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment
[0048] The present invention provides a cold-start recommendation scheme for TV applets. The scheme trains embeddings through user viewing behaviors, and then divides user embeddings into multiple categories through a clustering algorithm. Users in the same category have different family structures. There is a certain similarity in interest and hobbies, extracting the favorite applet of this type of user and recommending it to other users belonging to this type can be used as a cold start method for TV applet recommendation.
[0049] Such as figure 1 , including the following steps:
[0050] Step 1: Collect the behavior data of users using video on demand through data management on the TV side, such as viewing, favorite, cancel favorite of video content, as well as the name, duration, type and other information of the video, and store the data in the database .
[0051] Step 2: Collect the behavioral data of the user using the TV applet through data management on the TV side...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
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