AI-Enhanced Semantic Knowledge Retrieval for Scalable and Intelligent Enterprise Information Systems
Abstract
Enterprise information systems can construct and process massive volumes of heterogenous data within purposeful databanks, papers, body of knowledge, communication channels and business software. Conventional key-word retrieval approaches are weak in understanding contextual affiliation, semantic location and developing information requirements that result in composing part and less discerning learning. The paper below develops an AI-Scaffolded Semantic Knowledge Retrieval Framework to scaffold scaled-up and smart enterprise information systems. It contains a fusion of natural language processing, semantic representation, knowledge graph, knowledge discovery with a bunch of vectors and AI-oriented ranking to discover knowledge and interpret the knowledge in the context of the enterprise. A single processing pipeline is used to process the data ingestion, preprocessing, entity and relation extraction, semantic embedding, knowledge indexing, query interpretation and relevancy aware retrieval. The model also is refined based on feedback to maintain high standard quality of retrieval and keep pace with the continually changing knowledge in the organization. It boasts a modular architecture enabling the integration with heterogeneous enterprise data sources without jeopardizing the scalability, interoperability and responding efficiently. The framework assessment considers the relevance of retrieval, semantic matching, efficient response, scalability and coverage of the knowledge to various situations of enterprise information. The proposed solution proposes a context-based knowledge discovery, intelligent information retrieval and decision making solution that enables organizations to transform distributed enterprise information into information, which may be acted upon, intelligently interrelated
Article Information
Journal |
International Journal of Science, Research and Technology |
|---|---|
Volume (Issue) |
Vol. 8 No. 4 (2025): International Journal of Science, Research and Technology (IJSRAT) |
DOI |
|
Pages |
14669-14679 |
Published |
July 21, 2025 |
| Copyright |
All rights reserved |
Open Access |
This work is licensed under a Creative Commons Attribution 4.0 International License. |
How to Cite |
Dr.M.Sunil Kumar (%2025). AI-Enhanced Semantic Knowledge Retrieval for Scalable and Intelligent Enterprise Information Systems. International Journal of Science, Research and Technology , Vol. 8 No. 4 (2025): International Journal of Science, Research and Technology (IJSRAT) , pp. 14669-14679. https://doi.org/10.15662/IJSRAT.2025.0804011 |
References
[2] R. Jain, “The vector database gap: A production blueprint for embedding-based enterprise search,” Int. J. Future Innovative Sci. Technol. (IJFIST), vol. 4, no. 4, pp. 6706–6713, 2021.
[3] F. Petroni, T. Rocktäschel, P. Lewis, A. Bakhtin, Y. Wu, and S. Riedel, “Language models as knowledge bases?,” in Proc. Conf. Empirical Methods Natural Lang. Process. (EMNLP), 2019, pp. 2463–2473, doi: 10.18653/v1/D19-1250.
[4] L. Zhong, J. Wu, Q. Li, H. Peng, and X. Wu, “A comprehensive survey on automatic knowledge graph construction,” ACM Comput. Surv., 2023, doi: 10.1145/3618295.
[5] J. Zhang, B. Chen, L. Zhang, X. Ke, and H. Ding, “Neural, symbolic and neural-symbolic reasoning on knowledge graphs,” AI Open, vol. 2, pp. 14–35, 2021, doi: 10.1016/j.aiopen.2021.03.001.
[6] B. Abu-Salih, “Domain-specific knowledge graphs: A survey,” J. Netw. Comput. Appl., vol. 185, Art. no. 103076, 2021, doi: 10.1016/j.jnca.2021.103076.
[7] J. Devlin, M.-W. Chang, K. Lee, and K. Toutanova, “BERT: Pre-training of deep bidirectional transformers for language understanding,” 2018, arXiv:1810.04805.
[8] Y. Liu, M. Ott, N. Goyal, J. Du, M. Joshi, D. Chen, O. Levy, M. Lewis, L. Zettlemoyer, and V. Stoyanov, “RoBERTa: A robustly optimized BERT pretraining approach,” 2019, arXiv:1907.11692.
[9] W. X. Zhao et al., “A survey of large language models,” 2023, arXiv:2303.18223.
[10] J. Yang et al., “Harnessing the power of LLMs in practice: A survey on ChatGPT and beyond,” 2023, doi: 10.1145/3649506.
[11] Z. Ji et al., “Survey of hallucination in natural language generation,” ACM Comput. Surv., vol. 55, no. 12, pp. 1–38, 2023, doi: 10.1145/3571730.
[12] X. Qiu, T. Sun, Y. Xu, Y. Shao, N. Dai, and X. Huang, “Pre-trained models for natural language processing: A survey,” Sci. China Technol. Sci., vol. 63, no. 10, pp. 1872–1897, 2020, doi: 10.1007/s11431-020-1647-3.
[13] L. Yao, C. Mao, and Y. Luo, “KG-BERT: BERT for knowledge graph completion,” 2019, arXiv:1909.03193.
[14] C. Raffel et al., “Exploring the limits of transfer learning with a unified text-to-text transformer,” J. Mach. Learn. Res., vol. 21, no. 1, pp. 5485–5551, 2020.