Journal of Applied Science and Engineering

Published by Tamkang University Press

ESCI jase impact factor scopus logo open access rate of Scopus journal

Optimization and Implementation Path of Enterprise System Deep Learning Algorithm for Unstructured Data Processing

 2026

 Volume 35

Songyan Cui, Qian Yang

School of Pharmacy and Business, Zhejiang Pharmaceutical University, Ningbo, Zhejiang Province 315500, China

Received: May. 12, 2026
Accepted: July 24, 2026
Publication Date: September 16, 2026

上傳圖片

Complete Workflow of the Proposed EDO-TEGRU Framework for Unstructured Data Processing

 Copyright The Author(s). This is an open access article distributed under the terms of the Creative Commons Attribution License (CC BY 4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are cited.

Download Citation: BibTeX | http://dx.doi.org/10.6180/jase.202612_35.047

Download PDF

Enterprise system management involves coordinating multiple interdependent processes and stakeholders while optimizing resource allocation. This complexity often leads to inefficiencies and increased operational costs. To address these challenges, this research proposes a deep learning (DL) framework for optimizing and automating enterprise system management by effectively processing unstructured and semi-structured data commonly found in organizational workflows. The Efficient Dandelion Optimizer-driven Transformer Encoder Gated Recurrent Unit (EDO-TEGRU) model is designed to reduce manual effort, minimize errors, and improve resource allocation. The proposed framework processes heterogeneous enterprise data, including structured, semi-structured, and unstructured sources, through a unified representation learning mechanism, enabling effective integration of numerical operational metrics and textual contextual information within a single deep learning architecture for improved decision-making. The experimental evaluation was conducted using the publicly available Enterprise Operational Logs with Resource Dataset obtained from Kaggle. The dataset contains 1,000 enterprise operational log records comprising structured attributes and unstructured textual log messages. The model analyzes complex operational dependencies and provides context-aware decision support through preprocessing, customized model architecture, iterative training, and deployment tailored to enterprise requirements. Experimental results demonstrate an overall accuracy of 97%, confirming the reliability of the proposed framework in enterprise environments. Scalability and resource utilization evaluations indicate substantial reductions in manual effort, resource consumption, and operational costs while improving workflow efficiency. These findings validate the effectiveness of the optimized DL framework for processing heterogeneous enterprise data and demonstrate its practical applicability in supporting intelligent decision-making and efficient enterprise system management.

Keywords: Enterprise System Management, Unstructured Data Processing, Resource Allocation, Organizational Workflows, Efficient Dandelion Optimizer-Driven Transformer Encoder Gated Recurrent Unit (EDO-TEGRU)

  1. [1] E. de Haan, M. Padigar, S. El Kihal, R. Kübler, and J. E. Wieringa, (2024) “Unstructured Data Research in Business: Toward a Structured Approach” Journal of Business Research 177: 114655. DOI: https://doi.org/10.1016/j.jbusres.2024.114655.
  2. [2] F. Li and J. Xu, (2025) “Revolutionizing AI-Enabled Information Systems Using Integrated Big Data Analytics and Multi-modal Data Fusion” IEEE Access 13: DOI: https://doi.org/10.1109/ACCESS.2025.3552039.
  3. [3] Z. Rehman, N. Tariq, S. A. Moqurrab, J. Yoo, and G. Srivastava, (2024) “Machine Learning and Internet of Things Applications in Enterprise Architectures: Solutions, Challenges, and Open Issues” Expert Systems 41(1): e13467. DOI: https://doi.org/10.1111/exsy.13467.
  4. [4] K. H. Rolland and O. Hanseth, (2021) “Managing Path Dependency in Digital Transformation Processes: A Longitudinal Case Study of an Enterprise Document Management Platform” Procedia Computer Science 181: 765–774. DOI: https://doi.org/10.1016/j.procs.2021.01.229.
  5. [5] M. Joshi and V. K. Madisetti, (2025) “Intelligent ETL for Enterprise Software Applications Using Unstructured Data” Journal of Software Engineering and Applications 18(1): 44–65. DOI: https://doi.org/10.4236/jsea.2025.181003.
  6. [6] Z. Zhang, (2024) “Energy System Optimization Based on Fuzzy Decision Support System and Unstructured Data” Energy Informatics 7(1): 82. DOI: https://doi.org/10.1186/s42162-024-00396-2.
  7. [7] P. Li and L. Zhang, (2025) “Application of Big Data Technology in Enterprise Information Security Management” Scientific Reports 15(1): 1022. DOI: https://doi.org/10.1038/s41598-025-85403-6.
  8. [8] M. Zheng, (2022) “Advanced Artificial Intelligence Model for Financial Accounting Transformation Based on Machine Learning and Enterprise Unstructured Text Data” Mobile Information Systems 2022(1): 5708652. DOI: https://doi.org/10.1155/2022/5708652.
  9. [9] P. M. Mah, I. Skalna, and J. Muzam, (2022) “Natural Language Processing and Artificial Intelligence for Enterprise Management in the Era of Industry 4.0” Applied Sciences 12(18): 9207. DOI: https://doi.org/10.3390/app12189207.
  10. [10] S. Singh and S. Hooda, (2023) “A Study of Challenges and Limitations to Applying Machine Learning to Highly Unstructured Data” In: Proceedings of the 2023 7th International Conference on Computing, Communication, Control and Automation (ICCUBEA). DOI: https://doi.org/10.1109/ICCUBEA58933.2023.10392115.
  11. [11] L. Zeng, N. Xing, S. Cai, G. Chen, B. C. Ooi, J. Pei, and Y. Wu, (2024) “Powering In-Database Dynamic Model Slicing for Structured Data Analytics” arXiv Preprint: DOI: https://doi.org/10.48550/arXiv.2405.00568.
  12. [12] H. Zhao, H. Chen, T. A. Ruggles, Y. Feng, D. Singh, and H. J. Yoon, (2024) “Improving Text Classification with Large Language Model-Based Data Augmentation” Electronics 13(13): 2535. DOI: https://doi.org/10.3390/electronics13132535.
  13. [13] A. Lakhan, Q. U. A. Mastoi, M. Elhoseny, M. S. Memon, and M. A. Mohammed, (2022) “Deep Neural Network-Based Application Partitioning and Scheduling for Hospitals and Medical Enterprises Using IoT Assisted Mobile Fog Cloud” Enterprise Information Systems 16(7): 1883122. DOI: https://doi.org/10.1080/17517575.2021.1883122.
  14. [14] A. Abuhamdah, (2021) “Adaptive Elitist-Ant System for Solving Combinatorial Optimization Problems” Applied Soft Computing 105: 107293. DOI: https://doi.org/10.1016/j.asoc.2021.107293.
  15. [15] R. Y. Wang, J. S. Pan, S. C. Chu, B. S. Lin, and N. Zhong, (2026) “A Multi-Strategy Population-Free Particle Swarm Optimization Algorithm under Gamma Distribution in a Fixed Sample Domain and Its Comprehensive Analysis” Applied Soft Computing 193: 114578. DOI: https://doi.org/10.1016/j.asoc.2026.114578.