AI-Powered Organizational Knowledge Management Platform Using Large Language Models for Intelligent Meeting Understanding and Semantic Knowledge Retrieval

The proposed AI-Powered Organizational Knowledge Management Platform for Intelligent Meeting Understanding and Semantic Knowledge Retrieval provides an integrated solution for converting unstructured meeting recordings into structured and searchable organizational knowledge. The system combines Speech-to-Text transcription, Large Language Model-based knowledge extraction, relational data storage, semantic embeddings, vector retrieval, and Retrieval-Augmented Generation within a unified platform. The proposed workflow converts meeting audio into timestamped transcripts using Whisper and processes the transcripts using an LLM to extract executive summaries, topics, decisions, and action items. The transcript is also divided into chunks and converted into embeddings for storage in ChromaDB. This enables semantic retrieval of relevant meeting information when users submit natural-language queries. The RAG component uses the retrieved transcript context to generate context-grounded responses along with relevant meeting and timestamp references. The platform also incorporates JWT-based authentication and user-specific meeting filtering to maintain separation between users and their stored meeting information. The implemented system was evaluated through backend, AI-service, frontend build, and end-to-end testing. The results included 61/61 successful backend tests, 33/33 successful AI-service tests, and 9/9 successful end-to-end workflow stages. These results demonstrate the successful integration of the major components required for meeting transcription, knowledge extraction, semantic retrieval, and RAG-based question answering.   Overall, the proposed system transforms meeting recordings from passive stored files into structured, searchable, and reusable organizational knowledge. Future development can extend the platform through speaker diarization, multilingual processing, persistent cloud AI infrastructure, improved retrieval techniques, and integration with platforms such as Google Meet, Zoom, and Microsoft Teams.

[1]     A. Radford, J. W. Kim, T. Xu, G. Brockman, C. Mcleavey, and I. Sutskever, “Robust Speech Recognition via Large-Scale Weak Supervision,” in Proceedings of the 40th International Conference on Machine Learning (ICML), vol. 202, pp. 28492–28518, 2023. Available: https://proceedings.mlr.press/v202/radford23a.html   [2]     N. Reimers and I. Gurevych, “Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks,” in Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pp. 3982–3992, 2019. doi: 10.18653/v1/D19-1410. Available: https://aclanthology.org/D19-1410/   [3]    P. Lewis, E. Perez, A. Piktus, F. Petroni, V. Karpukhin, N. Goyal, H. Küttler, M. Lewis, W.-t. Yih, T. Rocktäschel, S. Riedel, and D. Kiela, “Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks,” Advances in Neural Information Processing Systems (NeurIPS), vol. 33, pp. 9459–9474, 2020. Available: NeurIPS paper   [4]    Y. Gao, Y. Xiong, X. Gao, K. Jia, J. Pan, Y. Bi, Y. Dai, J. Sun, M. Wang, and H. Wang, “Retrieval-Augmented Generation for Large Language Models: A Survey,” arXiv preprint arXiv:2312.10997, 2023. doi: 10.48550/arXiv.2312.10997. Available: https://arxiv.org/abs/2312.10997   [5]     V. Rennard, G. Shang, J. Hunter, and M. Vazirgiannis, “Abstractive Meeting Summarization: A Survey,” Transactions of the Association for Computational Linguistics, vol. 11, pp. 861–884, 2023. doi: 10.1162/tacl_a_00578. Available: https://aclanthology.org/2023.tacl-1.49/   [6]    S. Sadia, F. Adeeba, S. Shams, and S. Hussain, “Leveraging LLMs for Action Item Identification in Urdu Meetings: Dataset Creation and Comparative Analysis,” Information Processing & Management, vol. 62, no. 2, Art. 104071, 2025. doi: 10.1016/j.ipm.2025.104071. Available: https://www.sciencedirect.com/science/article/pii/S0306457325000135   [7]     M. Alavi and D. E. Leidner, “Knowledge Management and Knowledge Management Systems: Conceptual Foundations and Research Issues,” MIS Quarterly, vol. 25, no. 1, pp. 107–136, 2001. Available: https://aisel.aisnet.org/misq/vol25/iss1/6/   [8]     Chroma, “Chroma Documentation,” Chroma, Open-source AI application database. Available: https://docs.trychroma.com/   [9]      Spring Boot, “Spring Boot Documentation,” Spring. Available: https://docs.spring.io/spring-boot/documentation.html