High-dimensional power enterprise employee clustering based on convolutional neural network and mini-batch K-means algorithm

Ziheng Wang; Bowei Duan; Qian Zhang; Chuan Li; Xiaozhen Li

doi:10.1117/12.2661055

16 December 2022 High-dimensional power enterprise employee clustering based on convolutional neural network and mini-batch K-means algorithm

Ziheng Wang, Bowei Duan, Qian Zhang, Chuan Li, Xiaozhen Li

Author Affiliations +

Proceedings Volume 12500, Fifth International Conference on Mechatronics and Computer Technology Engineering (MCTE 2022); 125005Q (2022) https://doi.org/10.1117/12.2661055
Event: 5th International Conference on Mechatronics and Computer Technology Engineering (MCTE 2022), 2022, Chongqing, China

Abstract

With the gradual promotion of the use of mobile portal APPS in various enterprises and the rapid increase of users, the demand for personalized recommendation applications for different categories of users is gradually put forward. In actual application scenarios where users have no clear labels in advance, effective clustering algorithm is of great significance to realize personalized recommendation for users. Most of the traditional clustering algorithms are not suitable for enterprise application scenarios with millions of users, and the algorithm mainly focuses on the calculation process, with little consideration for the improvement of features. This paper focuses on the situation of employees of State Grid Corporation of China using "iGuoWang" mobile portal APP, proposes a clustering method based on hybrid deep learning for employees of electric power enterprises, counts the number of employees using each application, screens effective clustering features from the perspective of statistical analysis, and obtains effective clustering data sets. A "convolutional neural network + Mini-Batch K-means" clustering model was designed, and experiments were carried out based on the model and other traditional clustering algorithms. The results show that the clustering effect of the proposed model is significantly improved compared with other traditional algorithms under the evaluation indexes of contour coefficient and Calinski-Harabasz value. In view of the clustering results, this paper briefly analyzes the statistical indicators of various categories and proves that the clustering model has certain reference significance for personalized application recommendation.

Citation Download Citation

Ziheng Wang, Bowei Duan, Qian Zhang, Chuan Li, and Xiaozhen Li "High-dimensional power enterprise employee clustering based on convolutional neural network and mini-batch K-means algorithm", Proc. SPIE 12500, Fifth International Conference on Mechatronics and Computer Technology Engineering (MCTE 2022), 125005Q (16 December 2022); https://doi.org/10.1117/12.2661055

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
10 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Evolutionary algorithms

Convolutional neural networks

Data modeling

Statistical analysis

Dimension reduction

Convolution

Data centers

Show All Keywords

Keywords/Phrases

Search In:

Publication Years