Back to Search Start Over

Talent Management Recommendation Technology Based on Deep Learning.

Authors :
Huo, Yingying
Source :
Mathematical Problems in Engineering; 9/7/2022, p1-7, 7p
Publication Year :
2022

Abstract

Nowadays, with the vigorous development of information management technology, talent management has become a hot field that scholars pay attention to. The flow of talent between companies has become increasingly frequent. A large number of cooperative behaviors have produced a large number of cooperative results and subsequently brought a large amount of data on what to do. A huge network of collaborators has also been quietly formed, and how to mine valuable information from it has become a research hotspot, among which talent recommendation is one of the most important topics. Talent recommendation, when an enterprise introduces high-quality talents, provides valuable reference suggestions and selects candidates. When introducing talents, enterprises should not only consider the ability level of talents but also consider the cooperative relationship between them and enterprise personnel. Therefore, it is necessary to analyze the network of partners to find out the rules. There are only author nodes in the isomorphic collaborator network, and the connection between nodes is the cooperative relationship. On this basis, this paper constructs a heterogeneous collaborator network; that is, there are multiple types of nodes and connections in the network. The main research problem of this paper is to find an indicator to measure the strength of association between scholars in the collaborator network and to recommend potential academic talents for enterprises. Based on the data of academic research cooperation network, we carried out sufficient experiments to demonstrate the effectiveness of the heterogeneous cooperation network model proposed in this paper. [ABSTRACT FROM AUTHOR]

Details

Language :
English
ISSN :
1024123X
Database :
Complementary Index
Journal :
Mathematical Problems in Engineering
Publication Type :
Academic Journal
Accession number :
158956701
Full Text :
https://doi.org/10.1155/2022/7697192