Semantic Layer Construction in Data Warehouses Using GenAI for Contextualized Analytical Query Processing
DOI:
https://doi.org/10.63282/3117-5481/AIJCST-V7I4P108Keywords:
Data Warehouse, Generative Ai, Semantic Layer, Contextual Query Processing, Knowledge Graphs, Large Language Models, Metadata Management, Business Semantics, Vector Databases, Enterprise AnalyticsAbstract
Huge proliferation of enterprise data has fueled development of data warehouse (DW) architectures that have the capability of supporting big analytical workloads. But currently with the advent of the business user, they are demanding more and more semantic knowledge and query processing based on context and meaning, which the traditional metadata layer or OLAP cube simply does not offer. It is a study undertaken by proposing a Generative AI (GenAI)-friendly solution to build an intelligent semantic layer that allows the representation of contextual query comprehension, identification of semantic links, and knowledge grounding through the use of organized enterprise data. The proposed system combines Large Language Models (LLM) with semantic enrichment pipelines, which dynamic process business terminologies, reconcile queries with unified vocabularies, and convert them into optimized plans of DW execution. The model employs entity linking, embedding based schema matching, construction of knowledge graphs and contextual query rewrites to provide superior analytical accuracy. Furthermore, there is the introduction of a hybrid vector + relational index model that provides a better performance on natural-language query analysis. Complete comparisons on range of scenarios involving enterprise scale benchmark databases show substantial performance enhancements - an average accuracy of 38.6 in business query interpretation and 31.2 in latency reduction of semantic-driven workloads, compared to the traditional keyword-based systems. The architecture enables business glossaries to be adaptive, governance policy-enabled, and human-data collaboration, which is a very strong base on the topic of next-generation analytical ecosystems and enterprise decision intelligence. This paper includes: (1) An extensive literature review of semantic data warehousing, and AI based contextual analytics. (2) An elaborate procedure of GenAI-assisted weighted layer of semantics. (3) Usability, accuracy and performance experimental evaluations. (4) Major lessons and directions of future research on autonomous semantic data management. The results validate that GenAI technologies have the ability to turn data warehouses into smart analytical systems that are able to comprehend business intent, in turn, facilitating the rapidity of insights, decreasing the manual modeling task, and fostering the enterprise-wide democratisation of data among users
References
[1] Schneider, T., & Šimkus, M. (2020). Ontologies and data management: a brief survey. KI-Künstliche Intelligenz, 34(3), 329-353.
[2] Zhu, X., Li, Q., Cui, L., & Liu, Y. (2024). Large language model enhanced text-to-sql generation: A survey. arXiv preprint arXiv:2410.06011.
[3] Luo, Y., Li, G., Fan, J., Chai, C., & Tang, N. (2025). Natural language to sql: State of the art and open problems. Proceedings of the VLDB Endowment, 18(12), 5466-5471.
[4] Qin, B., Hui, B., Wang, L., Yang, M., Li, J., Li, B., ... & Li, Y. (2022). A survey on text-to-sql parsing: Concepts, methods, and future directions. arXiv preprint arXiv:2208.13629.
[5] Wang, J., Ng, P., Li, A. H., Jiang, J., Wang, Z., Nallapati, R., ... & Sengupta, S. (2022). Improving text-to-SQL semantic parsing with fine-grained query understanding. arXiv preprint arXiv:2209.14415.
[6] Sambath Narayanan, D. B. G. (2025). AI-Driven Data Engineering Workflows for Dynamic ETL Optimization in Cloud-Native Data Analytics Ecosystems. American International Journal of Computer Science and Technology, 7(3), 99-109. https://doi.org/10.63282/3117-5481/AIJCST-V7I3P108
[7] Jozashoori, S., & Vidal, M. E. (2019, October). MapSDI: A scaled-up semantic data integration framework for knowledge graph creation. In OTM Confederated International Conferences" On the Move to Meaningful Internet Systems" (pp. 58-75). Cham: Springer International Publishing.
[8] Hur, A., Janjua, N., & Ahmed, M. (2021, December). A survey on state-of-the-art techniques for knowledge graphs construction and challenges ahead. In 2021 IEEE Fourth International Conference on Artificial Intelligence and Knowledge Engineering (AIKE) (pp. 99-103). IEEE.
[9] Mohamed, S. M., Farah, S., Lotfy, A. M., Rizk, K. A., Saeed, A. Y., Mohamed, S. H., ... & Arafa, T. (2025). Knowledge Graphs: The Future of Data Integration and Insightful Discovery. In Advanced Research Trends in Sustainable Solutions, Data Analytics, and Security (pp. 99-146). IGI Global Scientific Publishing.
[10] Zou, X. (2020, March). A survey on application of knowledge graph. In Journal of Physics: Conference Series (Vol. 1487, No. 1, p. 012016). IOP Publishing.
[11] Sambath Narayanan, D. B. G. (2025). Generative AI–Enabled Intelligent Query Optimization for Large-Scale Data Analytics Platforms. International Journal of Artificial Intelligence, Data Science, and Machine Learning, 6(2), 153-160. https://doi.org/10.63282/3050-9262.IJAIDSML-V6I2P117
[12] Oliveira, M. A., Manara, S., Molé, B., Muller, T., Guillouche, A., Hesske, L., ... & Berger, C. R. (2023). Semantic Modelling of Organizational Knowledge as a Basis for Enterprise Data Governance 4.0--Application to a Unified Clinical Data Model. arXiv preprint arXiv:2311.02082.
[13] Nebot, V., & Berlanga, R. (2012). Building data warehouses with semantic web data. Decision Support Systems, 52(4), 853-868.
[14] Bhupathi, S. (2025). Role of Databases in GenAI Applications. arXiv preprint arXiv:2503.04847.
[15] Shilaskar, S., Chakole, S., Samarth, A., & Shejole, P. (2025, March). GenAI based Data Extraction with Query-Based Insights. In 2025 International Conference on Emerging Smart Computing and Informatics (ESCI) (pp. 1-6). IEEE.
[16] Fernández, J. D., Arias, M., Martınez-Prieto, M. A., & Gutiérrez, C. (2013). Management of big semantic data. Big data computing, 131-167.
[17] Salmon, B., Schlosser, S. W., Cranor, L. F., & Ganger, G. R. (2009, February). Perspective: Semantic Data Management for the Home. In FAST (Vol. 9, pp. 167-182).
[18] Rau, L. F. (1987). Knowledge organization and access in a conceptual information system. Information Processing & Management, 23(4), 269-283.
[19] Singh, A., Shetty, A., Ehtesham, A., Kumar, S., & Khoei, T. T. (2025, January). A survey of large language model-based generative ai for text-to-sql: Benchmarks, applications, use cases, and challenges. In 2025 IEEE 15th Annual Computing and Communication Workshop and Conference (CCWC) (pp. 00015-00021). IEEE.
[20] Balaji, M. T. M., Balajiraja, N., UMA, M. P., & Nair, M. S. P. (2025). Generative AI Tools: Concepts, Applications, and Innovations. Academic Guru Publishing House.
[21] Weston, N., Chitchyan, R., & Rashid, A. (2009, August). A framework for constructing semantically composable feature models from natural language requirements. In Proceedings of the 13th International Software Product Line Conference (pp. 211-220).
[22] Sambath Narayanan, D. B. G. (2024). Data Engineering for Responsible AI: Architecting Ethical and Transparent Analytical Pipelines. International Journal of Emerging Research in Engineering and Technology, 5(3), 97-105. https://doi.org/10.63282/3050-922X.IJERET-V5I3P110
[23] Guo, J., Zhan, Z., Gao, Y., Xiao, Y., Lou, J. G., Liu, T., & Zhang, D. (2019). Towards complex text-to-sql in cross-domain database with intermediate representation. arXiv preprint arXiv:1905.08205.
[24] Yang, B., & Yang, M. (2022). Research on enterprise knowledge service based on semantic reasoning and data fusion. Neural Computing and Applications, 34(12), 9455-9470.
