Unlock instant, AI-driven research and patent intelligence for your innovation.

Method and device for training relational network embedding model and determining use probability

A technology of relational networks and models, applied in the computer field, can solve the problem of low accuracy of the probability of use, and achieve the effect of improving accuracy

Active Publication Date: 2020-01-17
ADVANCED NEW TECH CO LTD
View PDF2 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] At present, the user's usage probability of each resource share is determined mainly based on the user's own characteristics. When there are few user's own characteristics that can be obtained, the accuracy of determining the usage probability 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 training relational network embedding model and determining use probability
  • Method and device for training relational network embedding model and determining use probability
  • Method and device for training relational network embedding model and determining use probability

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0066] The solutions provided in this specification will be described below in conjunction with the accompanying drawings.

[0067] As mentioned above, in various resource distribution scenarios, it is often difficult to accurately determine the user's usage probability of each resource share due to incomplete and rich user data. In order to determine the probability of use more accurately, according to the embodiment of this specification, the user's relationship network is used to increase its data richness. The relationship network reflects the relationship between users, resource shares and geographical locations. By training the embedded model of the relationship network The user's group characteristics are learned, so that the embedding model is used to determine the probability of use with high accuracy.

[0068] Based on the above considerations, according to one or more embodiments of this specification, a comprehensive relationship network is constructed to determine...

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 embodiment of the invention provides a method and device for training a relational network embedding model and determining the use probability. The method comprises the steps of determining a primary iterative node embedding vector of each node and a primary iterative edge embedding vector of each connecting edge based on node features, edge features and a first parameter set in a relational network; executing multi-stage vector iteration to determine an edge embedding vector of the multi-stage iteration of each connecting edge, each stage of vector iteration comprising, for each connecting edge, determining an edge embedding vector of the current stage of iteration of the connecting edge at least based on the second parameter set; for each first-class connection edge, determining a prediction value of the connection edge based on the edge embedding vector of the multi-level iteration of the connection edge and the prediction parameter set; parameter values in the first parameter set, the second parameter set and the prediction parameter set are adjusted so that a predefined loss function is minimized, and the loss function is determined based on the prediction value and the label value of each first type of connection edge. Enhanced determination accuracy.

Description

technical field [0001] One or more embodiments of this specification relate to the computer field, and in particular to a method for training an embedded model of a relational network, and a method and device for determining a usage probability by using an embedded model of a relational network. Background technique [0002] In various resource distribution scenarios, since the total amount of resources is limited, the resource share distributed to each user is usually determined according to the usage probability of each resource share by each user, so as to realize the effective use of resources. [0003] Currently, the user's usage probability of each resource share is mainly determined based on the user's own characteristics. When there are few user's own characteristics that can be obtained, the accuracy of determining the usage probability is low. [0004] Therefore, it is desirable to have an improved solution that can improve the accuracy of determining the usage pro...

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): G06K9/62G06F16/2458
CPCG06F16/2465G06F18/214
Inventor 李茜茜向彪周俊
Owner ADVANCED NEW TECH CO LTD