A content recommendation method and device based on deep reinforcement learning

A technology of intensive learning and content recommendation, applied in the Internet field, to stimulate browsing intentions and increase click-through rate

Active Publication Date: 2021-06-15
云南腾云信息产业有限公司
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In many application scenarios, it is necessary to provide users with multiple recommended content, that is, it is necessary to provide users with a combination of recommended content. If the single content recommendation method in the prior art is used, it is difficult to maximize the expected effect of the recommended content combination

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
  • A content recommendation method and device based on deep reinforcement learning
  • A content recommendation method and device based on deep reinforcement learning
  • A content recommendation method and device based on deep reinforcement learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0035] In order to enable those skilled in the art to better understand the solutions of the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only It is an embodiment of a part of the present invention, but not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts shall fall within the protection scope of the present invention.

[0036] It should be noted that the terms "first" and "second" in the description and claims of the present invention and the above drawings are used to distinguish similar objects, but not necessarily used to describe a specific sequence or sequence. It is to be understood that the data so used are interchangeable under appropriate ...

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 a content recommendation method and device based on deep reinforcement learning. The method includes: training the depth enhancement function to obtain the training result of the parameter set in the depth enhancement function; obtaining an ordered candidate set of recommended content and selecting The number of recommended content; based on the training results of the parameter set, use the depth enhancement function to calculate the comprehensive reward value of each recommended content in the candidate set; the comprehensive reward value of each recommended content is related to the recommended content and the ranking after the recommended content It is related to other recommended content; according to the calculation result, a piece of recommended content is selected as the selected recommended content and output in sequence. The present invention comprehensively considers the recommended content and the ranking of the recommended content by using the method of deep reinforcement learning, thereby obtaining a better recommendation result.

Description

technical field [0001] The present invention relates to the field of Internet technology, in particular to a content recommendation method and device based on deep reinforcement learning. Background technique [0002] In order to accurately locate target data of interest to users in massive data, various content recommendation methods are provided in the prior art. For example, Facebook adopts a hybrid sorting method of GBDT and logistic regression, Google adopts a wide and deep machine learning sorting method based on deep learning, and Netflix adopts a machine learning sorting method based on session information using RNN. However, the above methods for content recommendation all belong to the single content recommendation method of logistic regression. This single content recommendation method takes the maximization of the expected effect of the selected single recommended content as the recommendation goal, and does not take into consideration the relationship between t...

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): G06F16/9535G06F16/958G06N20/00
Inventor 王瑞夏锋林乐宇
Owner 云南腾云信息产业有限公司
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