The Application of the Depth Model of Precise Matching between People and Posts Based on Ability Perception in Human Resource Management

To revitalize talents and give full play to the maximum utility of HR (human resources), it is not enough to accumulate talents alone. HR must be effectively allocated to realize the matching of people and posts. Competency is a personal characteristic of an organization that distinguishes its perfo...

Full description

Saved in:
Bibliographic Details
Published in:Journal of function spaces 2022, Vol.2022, p.1-9
Main Author: Cao, Hui
Format: Article
Language:English
Subjects:
Algorithms
Depth perception
Economists
Employees
Employment
Human performance
Human resource management
Management by objectives
Matching
Neural networks
Perception
Performance management
Recommender systems
Regeneration
System theory
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:To revitalize talents and give full play to the maximum utility of HR (human resources), it is not enough to accumulate talents alone. HR must be effectively allocated to realize the matching of people and posts. Competency is a personal characteristic of an organization that distinguishes its performance level in a specific job and organizational environment. In order to solve the problem that job seekers’ job-seeking ability is difficult to match the job requirements, this paper combines neural network with traditional HRM (human resource management) algorithm based on ability perception and designs a depth model of accurate matching of people and posts in HR field, which can improve the quality of data training of traditional algorithm. The results show that compared with other algorithms, the F1 value of the proposed algorithm is obviously improved, and the proposed algorithm performs best, with the F1 value of 0.829. In this paper, the method of global network plus local network is used, which can effectively improve the hidden features of data and then improve the matching degree and recommendation accuracy of the algorithm.
ISSN:2314-8896
2314-8888
DOI:10.1155/2022/5495437