Media content recommendation method and related device

A technology of media content and target characteristics, applied in the computer field, can solve problems such as inaccurate content recommendation, affecting the accuracy of media content recommendation, reducing the click-through rate and conversion rate of media content, etc., to avoid inaccurate recommendation, improve click-through rate and Conversion rate, effect of improving accuracy

Pending Publication Date: 2020-07-17
TENCENT TECH (SHENZHEN) CO LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, the needs of users are not static. The content of interest may be different in different scenarios. Pushing media content to users through fixed user portraits cannot meet the needs of us

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
  • Media content recommendation method and related device
  • Media content recommendation method and related device
  • Media content recommendation method and related device

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0086] The embodiments of the present application provide a method and related device for recommending media content, which can be applied to a system or program that includes a media content recommendation function in a terminal device. The first media content browsed by the user is acquired, and then based on the first preset Rule extraction of candidate regions in the first media content, wherein the first preset rule is set based on at least two image features of the first media content, and the feature dimensions indicated by the image features are different; and the candidate regions are determined according to the second preset rule Screening is performed to obtain the target area, where the second preset rule is set based on the character feature of the first media content; and then the second media content is obtained based on the target area to perform media content recommendation. In this way, a dynamic recommendation process based on user browsing content is realized...

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 media content recommendation method and a related device, and the method comprises the steps: obtaining first media content browsed by a user, and extracting a candidate region in the first media content based on image features; screening the candidate regions according to the character features to obtain a target region; and obtaining the second media content based on the target area so as to recommend the media content. Therefore, a dynamic recommendation process based on user browsing content is realized, inaccurate media content recommendation caused by scene change is avoided, and through a multi-aspect screening process of image features and character features, the accuracy of media content recommendation is further improved, and the click rate and conversion rate of media content are improved.

Description

technical field [0001] The present application relates to the field of computer technology, and in particular to a method for recommending media content and related devices. Background technique [0002] With the development of mobile terminal-related technologies, more and more smart devices appear in people's lives. Among them, media content recommendation through smart devices is one of the main applications, such as the push of advertisements. Attractiveness requires targeted push of relevant media content to users. [0003] Generally, current advertising systems recommend advertisements to users based on information such as user portraits, user equipment, or content tags, for example, generating highly relevant advertisements based on user portraits. [0004] However, the needs of users are not static, and the content of interest may be different in different scenarios. Pushing media content to users through fixed user portraits cannot meet the needs of users in differ...

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): G06F16/48G06F16/9535G06Q30/02
CPCG06F16/48G06F16/9535G06Q30/0271
Inventor 卢建东余衍炳张发喜
Owner TENCENT TECH (SHENZHEN) CO LTD
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap