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

Negative sample generation method and device

A negative sample and sample technology, applied in the field of negative sample generation methods and devices, can solve the problems of low quality of negative samples and ignorance of knowledge graph community types.

Pending Publication Date: 2021-05-28
HEFEI UNIV OF TECH
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The embodiment of the present invention provides a negative sample generation method and device, to at least solve the technical problem that the quality of the generated negative samples is not high due to the lack of consideration of the community type of the knowledge map

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
  • Negative sample generation method and device
  • Negative sample generation method and device
  • Negative sample generation method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0023] 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.

[0024] 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 invention discloses a negative sample generation method and device. The method comprises the following steps: performing community division on a knowledge graph to obtain a plurality of communities; selecting two entities from the plurality of entities and a relationship between the two entities to form a target triple; determining a community where the target triple is located, and determining a community type of the community where the target triple is located; and according to the community type, selecting an entity of a community where a non-target triad is located or an entity of a community where a target triad is located, and replacing the entity in a target triad sample to obtain a negative sample. The technical problem that the quality of the generated negative sample is not high due to the fact that the community type of the knowledge graph is not considered is solved.

Description

technical field [0001] The present invention relates to the field of machine learning, in particular to a negative sample generation method and device. Background technique [0002] The knowledge representation model based on translation rules relies on the generation method of negative samples in the learning process, and negative samples play a key role in the knowledge representation learning model. There are currently five types of negative sample generation methods, which are completely random methods, probability-based methods, type-restricted methods, generative adversarial network-based methods, and batch negative sample generation methods. However, these methods do not take into account the community type information of the knowledge graph in the process of generating negative samples, so the quality of the generated negative samples is not high enough. [0003] For the above problems, no effective solution has been proposed yet. Contents of the invention [000...

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): G06F40/55G06F16/36G06F40/279
CPCG06F16/367G06F40/279G06F40/55
Inventor 吴信东单迎春洪炎卜晨阳
Owner HEFEI UNIV OF TECH
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