In today’s data-driven business environment, small and medium-sized enterprises (SMEs) struggle to implement effective knowledge management (KM) due to limited financial, technical, and human resources. This study proposes an intelligent KM framework that integrates large language models (LLMs), that is, BERT-based models and knowledge graphs (KGs) to support accounting and supply chain decision-making in SMEs. Using a medical device manufacturer as a case enterprise, unstructured texts from accounting vouchers, ERP operation logs and supply chain records are collected, cleaned, anonymised, and manually annotated with entities and relations via Doccano. An end-to-end architecture based on BERT is adopted: for named entity recognition (NER) two models (BERT + CRF and BERT + BiLSTM + CRF) are trained, while for relation extraction (RE) two models (BERT and BERT + BiLSTM) are compared. Experimental results show that BERT + BiLSTM + CRF achieves the best NER performance (Precision 0.73, Recall 0.76, F1-score 0.74), and BERT attains superior RE performance (Precision 0.69, Recall 0.80, F1-score 0.74). The optimal models are then used to automatically construct RDF-like entity-relation-entity triples, which are stored and visualized in the Neo4j Aura cloud graph database via Py2neo. The resulting enterprise KG supports semantic querying, knowledge discovery, and interactive Q&A for accounting and supply chain tasks, and can be further leveraged for personalized training and internal audit support. The findings demonstrate that an LLM-enabled KG approach can provide a cost-effective, scalable KM solution for SMEs, while also highlighting challenges related to data quality, computational resources, and ongoing KG maintenance.
References
[1]
Al Koliby, I. S., Noor, N. H. M., Al-Swidi, A. K., Al-Hakimi, M. A., & Mehat, N. A. B. (2025). Enhancing Sustainable Performance among Manufacturing SMEs: The Interplay of Knowledge Management and Organizational Structure. DiscoverSustainability,6, 1-16. https://doi.org/10.1007/s43621-025-01351-1
[2]
Chen, W., & Sun, T. (2024). Application of Artificial Intelligence with Knowledge Graph Technology in Enterprise Financial and Tax Knowledge Management. Financial Super-vision, 5, 101-104.
[3]
Chen, S. S., & Wang, M. (2025). Construction and Application Prospect of Accounting Knowledge Graph Based on Large Language Model. Friends of Accounting, 5, 152-161.
[4]
Dehshiri, S. J. H., Amiri, M., Mostafaeipour, A., Pamučar, D., & Le, T. (2024). Enhancing Supply Chain Performance by Integrating Knowledge Management and Lean, Agile, Resilient, and Green Paradigms. JournalofManagementAnalytics,11, 738-769. https://doi.org/10.1080/23270012.2024.2408527
[5]
Devlin, J., Chang, M., Lee, K., & Toutanova, K. (2019). BERT: Pre-Training of Deep Bidirectional Transformers for Language Understanding. North American Chapter of the Association for Computational Linguistics.
[6]
Du Plessis, T., & du Toit, A. S. A. (2006). Knowledge Management and Legal Practice. InternationalJournalofInformationManagement,26, 360-371. https://doi.org/10.1016/j.ijinfomgt.2006.06.003
[7]
Durst, S., Edvardsson, I. R., & Foli, S. (2023). Knowledge Management in SMEs: A Follow-Up Literature Review. JournalofKnowledgeManagement,27, 25-58. https://doi.org/10.1108/jkm-04-2022-0325
[8]
Eslami, M. H., Achtenhagen, L., Bertsch, C. T., & Lehmann, A. (2023). Knowledge-Sharing across Supply Chain Actors in Adopting Industry 4.0 Technologies: An Exploratory Case Study within the Automotive Industry. TechnologicalForecastingandSocialChange,186, Article ID: 122118. https://doi.org/10.1016/j.techfore.2022.122118
[9]
Galkin, M., Auer, S., Vidal, M.-E., & Scerri, S. (2017). Enterprise Knowledge Graphs: A Semantic Approach for Knowledge Management in the Next Generation of Enterprise Information Systems. In Proceedings of the 19th International Conference on Enterprise Information Systems (Volume 2, pp. 88-98). SCITEPRESS-Science and Technology Publications. https://doi.org/10.5220/0006325200880098
[10]
Giorgi, J., Wang, X. D., Sahar, N., & Shin, W. Y. (2019). End-to-End Named Entity Recognition and Relation Extraction Using Pre-Trained Language Models. 1-12.
[11]
Halimuzzaman, M., & Sharma, J. (2023). The Evolution of Accounting Information Systems (AIS) and Enterprise Resource Planning (ERP): A Review of Literature. Episteme: An Online Interdisciplinary, Multidisciplinary & Multi-Cultural Journal, 12, 170-190.
[12]
Hu, X., Liu, A., & Dai, Y. (2024). Combining ChatGPT and Knowledge Graph for Explainable Machine Learning-Driven Design: A Case Study. Journal of Engineering Design,36, 1479-1501. https://doi.org/10.1080/09544828.2024.2355758
[13]
Huang, Z.H., Xu, W., & Yu, K. (2015). Bidirectional LSTM-CRF Models for Sequence Tagging.
[14]
Li, J., Qian, L., Liu, P., & Liu, T. (2024). Construction of Legal Knowledge Graph Based on Knowledge-Enhanced Large Language Models. Information,15, Article No. 666. https://doi.org/10.3390/info15110666
[15]
Lukyanova, I., Haddud, A., & Khare, A. (2022). Types of ERP Systems and Their Impacts on the Supply Chains in the Humanitarian and Private Sectors. Sustainability,14, Article No. 13054. https://doi.org/10.3390/su142013054
[16]
Mansfield, M., Tamma, V., Goddard, P., & Coenen, F. (2021). Capturing Expert Knowledge for Building Enterprise SME Knowledge Graphs. In Proceedings of the 11th Knowledge Capture Conference (pp. 129-136). Association for Computing Machinery. https://doi.org/10.1145/3460210.3493569
[17]
Mo, F., Rehman, H. U., Elshafei, B., Chaplin, J. C., Sanderson, D., Martínez-Arellano, G. et al. (2023). Efficient Decision-Making in SMEs: Leveraging Knowledge Graphs with Neo4j and AI Vision. IETConferenceProceedings,2023, 69-75. https://doi.org/10.1049/icp.2023.1736
[18]
Mukarram, S. S., Saleem, F., Alomair, A., & Al Naim, A. S. (2025). Knowledge Management and Sustainable Innovation for Green Finance: Evidence from Asia. HumanitiesandSocialSciencesCommunications,12, Article No. 1742. https://doi.org/10.1057/s41599-025-06022-0
[19]
Park, Y.-J., Lee, M.-A., Yang, G.-J., Park, S. J., & Sohn, C.-B. (2022). Biomedical Text NER Tagging Tool with Web Interface for Generating Bert-Based Fine-Tuning Dataset. AppliedSciences,12, Article No. 12012. https://doi.org/10.3390/app122312012
[20]
Pereira, N., & Fernandes, C. (2025). Knowledge Management in Health Organizations: A Systematic Literature Review. JournaloftheKnowledgeEconomy, 1-73. https://doi.org/10.1007/s13132-025-02760-3
[21]
Pisoni, G., Molnár, B., & Tarcsi, Á. (2024). Knowledge Management and Data Analysis Techniques for Data-Driven Financial Companies. JournaloftheKnowledgeEconomy,15, 13374-13393. https://doi.org/10.1007/s13132-023-01607-z
[22]
Puspita, M. E., & Pramono, J. (2019). Factors Affecting the Use of Accounting Information in Small and Medium Enterprises (SMEs): A Study on SMEs in Tingkir, Salatiga. TheIndonesianAccountingReview,9, 207-225. https://doi.org/10.14414/tiar.v9i2.1818
[23]
Schulze, M., Pelzer, M., Schröder, M., Jilek, C., Maus, H., & Dengel, A. (2022). Towards Knowledge Graph Based Services in Accounting Use Cases. In SEMANTICS 2022 EU: 18th International Conference on Semantic Systems (pp. 1-5). CEUR Workshop Proceedings.
[24]
Sima, X., Coudert, T., Geneste, L., & de Valroger, A. (2022). Knowledge Management in SMEs: Preliminary Ideas for a Dedicated Framework. IFAC-PapersOnLine,55, 1050-1055. https://doi.org/10.1016/j.ifacol.2022.09.528
[25]
Sutton, C., & McCallum, A. (2012). An Introduction to Conditional Random Fields. FoundationsandTrends®inMachineLearning,4, 267-373. https://doi.org/10.1561/2200000013
[26]
Theuma, A., Hayak, A. F., & Khdour, N. (2025). An Accounting Knowledge Management System That Fosters Innovation and Performance. InternationalJournalofKnowledgeManagement,21, 1-22. https://doi.org/10.4018/ijkm.365909
[27]
Wei, M., Xu, Z., & Hu, J. (2021). Entity Relationship Extraction Based on Bi-LSTM and Attention Mechanism. In 2021 2nd International Conference on Artificial Intelligence and Information Systems (pp. 1-5). ACM. https://doi.org/10.1145/3469213.3470701
[28]
Wu, S., & He, Y. (2019). Enriching Pre-Trained Language Model with Entity Information for Relation Classification. In Proceedings of the 28th ACM International Conference on Information and Knowledge Management (pp. 2361-2364). ACM. https://doi.org/10.1145/3357384.3358119
[29]
Zhao, X. J., Blum, M., Yang, R., Yang, B. M., Carpintero, L. M., Pina-Navarro, M., Wang, T., Li, X., Li, H. T., Fu, Y. R., Wang, R. R., Zhang, J. T., & Li, I. (2024). AGENTiGraph: An Interactive Knowledge Graph Platform for LLM-Based Chatbots Utilizing Private Data.
[30]
Zhong, H., Chen, S. S., & Wang, M. (2024). Exploration of the Accounting Vertical Do-main Reasoning Ability for Large Language Model. Finance and Accounting Monthly, 45, 17-25.
[31]
Zhou, P., Shi, W., Tian, J., Qi, Z., Li, B., Hao, H. et al. (2016). Attention-Based Bidirectional Long Short-Term Memory Networks for Relation Classification. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers) (pp. 207-212). Association for Computational Linguistics. https://doi.org/10.18653/v1/p16-2034
[32]
Zhu, J. H., Xia, Y. C., Wu, L. J., He, D., Qin, T., Zhou, W. G., Li, H. Q., & Liu, T. Y. (2020). Incorporating BERT into Neural Machine Translation. In 8th International Conference on Learning Representations (ICLR). (pp. 1-22). OpenReview.net.
