Supercharge Your Innovation With Domain-Expert AI Agents!

Content recommendation method, device and system

A content recommendation and content technology, applied in the Internet field, can solve the problems of less click behavior and insufficient information, and achieve the effect of reasonable and effective content recommendation

Active Publication Date: 2019-08-27
ALIBABA (CHINA) CO LTD
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, for the random users who account for the majority of users, their click behavior is very small, and the amount of information contained in the click history data is insufficient, so it is difficult to make recommendations through the above methods

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
  • Content recommendation method, device and system
  • Content recommendation method, device and system
  • Content recommendation method, device and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0025] figure 1 A flowchart showing a content recommendation method according to an embodiment of the present invention. This embodiment can be implemented on the server side. Such as figure 1 As shown, the method mainly includes:

[0026] Step 101, recommending the content in the content collection to the user based on the average recommendation probability;

[0027] Step 102, collecting feedback information on the recommended content from the user's client;

[0028] Step 103: Determine a sequence of preferred content from the contents of the content collection according to the feedback information, so as to recommend content to the user based on the sequence of preferred content.

[0029] In this embodiment, content recommendation is performed based on user feedback, so that content recommendation can be reasonably and effectively performed for random users with few click behaviors.

[0030] The "content collection" herein refers to a collection composed of multiple con...

Embodiment 2

[0065] Figure 4 A flow chart of a content recommendation method according to another embodiment of the present invention is shown, and the embodiment can be implemented on the server side. Such as Figure 4 As shown, the method of this embodiment mainly includes: step 401, establishing a content pool, the content pool includes a plurality of content collections, and each content collection contains corresponding types of content; step 402, for each content collection in the content pool, Execute the method described in Embodiment 1 to generate a sequence of preferred content for each content collection.

[0066] In this embodiment, a content pool can be composed of multiple content collections, and each content collection can contain a type of content. It can be classified by business type, such as video content in the first content collection, advertising content in the second content collection, etc., or it can be classified according to more detailed classification princ...

Embodiment 3

[0069] Figure 5 A structural diagram of a content recommendation device according to an embodiment of the present invention is shown. The apparatus of this embodiment may be configured in a server device. Such as Figure 5As shown, the content recommending device 500 mainly includes: a first recommending component 501, configured to recommend the content in the content collection to the user based on the average recommendation probability; a collecting component 502, configured to collect feedback on the recommended content from the user's client Feedback information: a determining component 503, configured to determine a sequence of preferred content from the contents of the content collection according to the feedback information, so as to recommend content to the user based on the sequence of preferred content.

[0070] In this embodiment, content recommendation is performed based on user feedback, so that content recommendation can be reasonably and effectively performe...

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 relates to a content recommendation method, device and system. The method includes: recommending content in a content collection to users based on an average recommendation probability; collecting feedback information on the recommended content from the user's client, the feedback information including display Information and click information, wherein the display information includes the number of times and display time of the recommended content on the client, and the click information includes the number and time of the recommended content being clicked on the client; and according to the feedback information A sequence of preferred content is determined from the contents of the content collection, so as to recommend content to the user based on the sequence of preferred content. Various aspects of the present invention perform content recommendation based on user feedback, so that random users with few click behaviors can also reasonably and effectively perform content recommendation.

Description

technical field [0001] The present invention relates to the technical field of the Internet, in particular to a content recommendation method, device and system. Background technique [0002] For network platforms that provide users with various content such as video, audio, and advertisements, one of the focuses of their research is how to effectively estimate user needs and recommend content that may be of interest to users. [0003] Existing methods usually extract user interest tags and other information that reflects user preferences from user click history data to recommend content. However, for the random users who account for the majority of users, their click behavior is very small, and the amount of information contained in the click history data is insufficient, so it is difficult to make recommendations through the above methods. Contents of the invention [0004] In view of this, the present invention proposes a content recommendation method and device, which...

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): H04N21/258H04N21/25H04N21/45H04N21/466G06F16/9535
CPCG06F16/9535H04N21/252H04N21/25891H04N21/4532H04N21/4668H04L67/1396H04N21/258G06F16/00H04L67/01G06N7/01
Inventor 沈世星王必尧尹玉宗姚键潘柏宇王冀
Owner ALIBABA (CHINA) CO LTD
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com