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

Personnel recommendation method based on heterogeneous graph nerves

A recommendation method and heterogeneous graph technology, applied in the field of recommendation, can solve problems such as factors that do not give specific results of intelligent allocation events, and achieve the effects of improving multi-dimensional processing capabilities, avoiding backlogs, and speeding up processing efficiency.

Pending Publication Date: 2022-01-04
NORTHEASTERN UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Many scholars have conducted research on how to achieve the optimal matching of events and personnel, but the current research is only at the stage of qualitative analysis. In addition to listing the specific goals that intelligent distribution events need to accomplish, they have not specifically given the impact of intelligence. What are the factors that assign event outcomes

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
  • Personnel recommendation method based on heterogeneous graph nerves
  • Personnel recommendation method based on heterogeneous graph nerves
  • Personnel recommendation method based on heterogeneous graph nerves

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0045] The specific implementation manners of the present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. The following examples are used to illustrate the present invention, but are not intended to limit the scope of the present invention.

[0046] A person recommendation method based on heterogeneous graph neural, such as figure 1 shown, including the following steps:

[0047]Step 1: Establish a training data set for the personnel and their handling events, preprocess the characteristics of the events in the training data set and the capability feature vectors of the personnel, and represent the events and personnel with vectors of the same dimension through feature dimensionality reduction;

[0048] The preprocessing is to use the principal component analysis algorithm (PCA) to reduce the dimensionality of event features and personnel capability portrait features. PCA is the most commonly used feature dimen...

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 provides a personnel recommendation method based on heterogeneous graph nerves, and relates to the technical field of recommendation methods. According to the method, the event characteristics of the event and the ability characteristics of the personnel are combined, the heterogeneous graph of the event and the personnel is constructed, and through training of the heterogeneous graph neural network, a plurality of to-be-recommended personnel can be recommended for the new event finally. The event allocation strategy is used for allocating events to a large number of new events, so that the event handling efficiency can be effectively improved, and the event overstock is avoided. Meanwhile, the system provides potential handling ability of mining personnel, and can perform priority allocation under certain conditions for event types which are never handled or less handled by the personnel, so that the learning enthusiasm of the personnel is effectively aroused, and the multi-dimensional handling ability of the personnel is improved.

Description

technical field [0001] The present invention relates to the technical field of recommendation methods, in particular to a person recommendation method based on heterogeneous graph neural. Background technique [0002] The event distribution system is an important system for event management and distribution. The random distribution event mode is to randomly distribute the event to specific undertakers according to certain random distribution event rules after the event is established; the designated distribution event mode is established by the According to the specific circumstances of the event, special personnel assign the event to specific undertakers. The former has the advantage of being open and transparent in the process of assigning events, and the results of the assigning events are objective and random. It can eliminate the possible impact of human factors on the process of assigning events. It is simple, fast, objective and fair, but cannot flexibly identify the ...

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): G06Q10/06G06Q50/26G06N3/04G06N3/08G06K9/62
CPCG06Q10/063112G06Q50/26G06N3/08G06N3/045G06F18/2135
Inventor 栗伟闵新谢维冬陈强
Owner NORTHEASTERN UNIV
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