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

Method and device for predicting first attribute of first node in graph network

A prediction method and node technology, applied in the computer field, can solve problems such as low accuracy, and achieve the effect of improving the accuracy of prediction

Pending Publication Date: 2022-07-01
ALIPAY (HANGZHOU) INFORMATION TECH CO LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] However, the accuracy of attribute prediction based on current graph networks is low

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
  • Method and device for predicting first attribute of first node in graph network
  • Method and device for predicting first attribute of first node in graph network
  • Method and device for predicting first attribute of first node in graph network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0026] As mentioned earlier, attribute prediction based on a node in a graph network is a commonly used prediction method. For example, merchants usually allocate manpower and reserve goods according to the forecast of possible future gross merchandise volume (Gross Merchandise Volume, GMV). Therefore, the prediction accuracy of the GMV of the merchants in a certain period of time in the future will directly affect the future business conditions of the merchants.

[0027] However, if figure 1 In the shown diagram of a graph network, any node does not exist independently, and there are more or less associations with other nodes. Therefore, when predicting the first attribute of one of the nodes, the accuracy of the obtained prediction result is bound to be lower if the correlation and dependency of the predicted node by other nodes are not considered.

[0028] For example, in an e-commerce scenario, there is often a close relationship between merchants and merchants in terms ...

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

Embodiments of the present specification describe a method and apparatus for predicting a first attribute of a first node in a graph network. According to the method of the embodiment, the time sequence representation of the first node and the time sequence representation of the second node are determined based on the historical value of the first attribute of the first node and the historical value of the first attribute of the second node serving as the neighbor of the first node, and then the time sequence representation of the second node is aggregated into the time sequence representation of the first node. A final characterization capable of reflecting the timing offset between the first attributes of the first node and the second node is obtained. A future value of the first attribute of the first node can be further predicted based on the final characterization. In this way, the relevance and dependency between the nodes are fully considered, so that the accuracy of predicting the first attribute of the first node can be improved.

Description

technical field [0001] One or more embodiments of this specification relate to the field of computer technology, and in particular, to a method and apparatus for predicting a first attribute of a first node in a graph network. Background technique [0002] Attribute prediction based on a node in a graph network is a common prediction method. For example, in an e-commerce scenario, a merchant's Gross Merchandise Volume (GMV) usually affects the allocation of manpower and the reserve of goods. Therefore, forecasting the GMV of a merchant in a certain period of time in the future can help guide the merchant to allocate manpower and reserve goods. [0003] However, the accuracy of attribute prediction based on graph networks is currently low. SUMMARY OF THE INVENTION [0004] One or more embodiments of this specification describe a method and apparatus for predicting a first attribute of a first node in a graph network, which can predict the accuracy of the attribute of a no...

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): G06F16/901G06Q10/04
CPCG06F16/9024G06Q10/04
Inventor 叶博睿杨硕胡斌斌张志强
Owner ALIPAY (HANGZHOU) INFORMATION TECH CO LTD
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