Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Depth learning method, device and system

A deep learning and scheduling platform technology, applied in the field of deep learning, can solve problems such as poor matching between recommended products and user interests, and achieve the effect of accurate in-depth prediction

Active Publication Date: 2018-01-23
阿里巴巴(中国)网络技术有限公司
View PDF4 Cites 33 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The embodiment of the present invention provides a deep learning method, device and system, which can solve the problem of poor matching between recommended products and user interests

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
  • Depth learning method, device and system
  • Depth learning method, device and system
  • Depth learning method, device and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0064] Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited by the embodiments set forth herein. Rather, these embodiments are provided for more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0065] Embodiments of the present invention provide a deep learning system, such as figure 1 As shown, the system includes: computing nodes 11 and scheduling platform 12, wherein:

[0066] The scheduling platform 12 is configured to send the deep learning model and prediction samples to the computing nodes 11.

[0067] The scheduling platform 12 assigns forecast tasks to computing nodes 11 for calculation according to the actual f...

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 depth learning method, device and system, which belongs to the technical field of Internet. The problem of poor matching of recommended products and the interest of a user issolved. The method comprises the steps that a scheduling platform sends a depth learning model and a prediction sample to a computing node; the computing node extracts a sample feature in the form ofone-dimensional vector from the prediction sample, and converts the sample feature in the form of one-dimensional vector into a sample feature in the form of two-dimensional array; based on the depthlearning model, the sample feature in the two-dimensional array is generalized in the unit of two-dimensional sub-array to acquire a processing result; and the scheduling platform receives the processing result sent by the computing node, and outputs a learning result according to the processing result. The depth learning method, device and system are mainly used by a shopping website to recommend products to the user.

Description

technical field [0001] The present invention relates to the field of Internet technologies, in particular to a deep learning method, device and system. Background technique [0002] The product recommendation function is an information exposure method often used by shopping websites. This function can recommend other products of the same category or used in combination to the user based on the operation records of a single user's browsing, collection or purchase of products. Collect or purchase statistical data to recommend popular online products to users. From the user's point of view, the product recommendation function can provide richer product information, which is convenient for users to compare different products horizontally and make rational purchase decisions; from the perspective of shopping websites, the product recommendation function can increase the traffic guidance of product pages , Improve the conversion rate of commodity transactions. Due to its many ad...

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 Applications(China)
IPC IPC(8): G06Q30/06G06N3/04G06N3/08
Inventor 张斌刘忠义
Owner 阿里巴巴(中国)网络技术有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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