Open AccessA Self-Organized Mapping Neural Network-based Intelligent Evaluation Model for Business Capacity in Enterprise Management
Author(s) -
Qi Zhang,
Jiale Zhang
Publication year - 2023
Publication title -
ieee access
Language(s) - English
Resource type - Journals
ISSN - 2169-3536
DOI - 10.1109/access.2023.3322320
Subject(s) - aerospace , bioengineering , communication, networking and broadcast technologies , components, circuits, devices and systems , computing and processing , engineered materials, dielectrics and plasmas , engineering profession , fields, waves and electromagnetics , general topics for engineers , geoscience , nuclear engineering , photonics and electrooptics , power, energy and industry applications , robotics and control systems , signal processing and analysis , transportation
In era of big data, the integration of deep learning with enterprise management has been an inevitable requirement. However, scenarios of enterprise management vary with ever-changing entities, without fixed problem format. This makes it difficult to form a universal golden dataset for training supervised models. To handle such challenge, this paper takes the “business capacity evaluation of human resources in the enterprise management” as the main situation, and explores unsupervised deep learning-based technical methods for solution. Specifically, this paper proposes a self-organized mapping neural network (SOMNN)-based intelligent evaluation model for business capacity in enterprise management. For one thing, the procedures of SOMNN are described using symbol representation. For another, the SOMNN is specifically embedded into the realistic situations of business capacity evaluation, so as to generate digital evaluation results. After that, we carry out a case study on data from a real-world enterprise, in order to make performance assessment for the proposed model. The simulation results show that the proposed model can make proper evaluation towards business capacity in enterprise management, under the unsupervised pattern.