結合知識圖譜和大型語言模型的知識管理平台開發

以作者查詢圖書館館藏

、以作者查詢臺灣博碩士

、以作者查詢全國書目

、勘誤回報

、線上人數：20

、訪客IP：3.142.142.168

姓名

鄭珮慈(Pei-Tzu Cheng) 查詢紙本館藏

畢業系所

資訊工程學系

論文名稱

結合知識圖譜和大型語言模型的知識管理平台開發
(Development of a Knowledge Management Platform Combining Knowledge Graphs and Large Language Models)

相關論文

★ 整合GRAFCET虛擬機器的智慧型控制器開發平台	★ 分散式工業電子看板網路系統設計與實作
★ 設計與實作一個基於雙攝影機視覺系統的雙點觸控螢幕	★ 智慧型機器人的嵌入式計算平台
★ 一個即時移動物偵測與追蹤的嵌入式系統	★ 一個固態硬碟的多處理器架構與分散式控制演算法
★ 基於立體視覺手勢辨識的人機互動系統	★ 整合仿生智慧行為控制的機器人系統晶片設計
★ 嵌入式無線影像感測網路的設計與實作	★ 以雙核心處理器為基礎之車牌辨識系統
★ 基於立體視覺的連續三維手勢辨識	★ 微型、超低功耗無線感測網路控制器設計與硬體實作
★ 串流影像之即時人臉偵測、追蹤與辨識─嵌入式系統設計	★ 一個快速立體視覺系統的嵌入式硬體設計
★ 即時連續影像接合系統設計與實作	★ 基於雙核心平台的嵌入式步態辨識系統

檔案

[Endnote RIS 格式]

[Bibtex 格式]

[相關文章]

[文章引用]

[完整記錄]

[館藏目錄]

至系統瀏覽論文 (2029-7-22以後開放)

摘要(中)

數位轉型對於企業提升競爭力至關重要，但在管理數位化資源時也面臨多種挑戰，例如知識儲存分散與專家經驗難以傳承等。而大型語言模型（Large Language Model, LLM）雖然能有效提取並結構化知識，但其幻覺、安全性及缺乏可解釋性的問題也引發了擔憂。本研究提出DocuKMP系統，該系統結合知識圖譜（Knowledge Graph, KG）與LLM技術形成知識管理平台，系統內建知識圖譜建置工具鏈，解決了知識圖譜使用非結構化資料進行建置時的限制，並提供問答功能供使用者進行知識查詢，同時也設計使用者介面方便使用者與系統進行互動。而我們也分別針對知識圖譜建置工具鏈中的各個軟體工具進行實驗，並對DocuKMP系統所建置的知識圖譜進行四項品質標準評估，結果發現準確率為95.25%、一致性為100%、完整性為92.25%、冗餘度為99.95%，顯示知識圖譜具有相當高的品質。此外，DocuKMP系統在正確率上（82.35%）明顯優於RAG-Token和RAG-Sequence模型，且對硬體資源需求較低。綜上所述，DocuKMP系統在知識管理的正確性與資源效率方面均優於RAG模型，對企業數位轉型具有重要意義。

摘要(英)

Digital transformation is crucial for enhancing the competitiveness of enterprises, yet managing digital resources poses various challenges such as scattered knowledge storage and difficulty in transferring expert experience. Although Large Language Models (LLMs) can effectively extract and structure knowledge, concerns about hallucinations, security, and lack of interpretability have been raised. This study proposes the DocuKMP system, which integrates Knowledge Graph (KG) and LLM technologies to form a knowledge management platform. The system includes a built-in knowledge graph construction toolchain that addresses the limitations of using unstructured data for building knowledge graphs, and it provides a Q&A function for users to query knowledge. Additionally, a user interface is designed to facilitate user interaction with the system. We conducted experiments on various software tools in the knowledge graph construction toolchain and evaluated the knowledge graph built by the DocuKMP system based on four quality standards. The results show an accuracy of 95.25%, consistency of 100%, completeness of 92.25%, and redundancy of 99.95%, indicating a high-quality knowledge graph. Moreover, the DocuKMP system outperforms the RAG-Token and RAG-Sequence models in terms of accuracy (82.35%) while requiring fewer hardware resources. In summary, the DocuKMP system excels in both accuracy and resource efficiency for knowledge management, making it significant for enterprise digital transformation.

關鍵字(中)

★ 知識圖譜
★ 大型語言模型
★ 知識管理平台

關鍵字(英)

論文目次

摘要 I
Abstract II
誌謝 III
目錄 IV
圖目錄 VI
表目錄 VII
第一章、緒論 1
1.1 研究背景 1
1.2 研究目標 3
1.3 論文架構 4
第二章、文獻回顧 5
2.1 人工智慧從傳統到生成 5
2.1.1 生成對抗網路 5
2.1.2 Transformer 7
2.1.3 大型語言模型 8
2.2 緩解大型語言模型缺點的機制 9
2.2.1 檢索增強生成 10
2.2.2 知識圖譜 11
2.3 知識圖譜建置工具鏈 12
第三章、知識管理平台設計 14
3.1 DocuKMP系統架構 14
3.1.1 文本提取模組 16
3.1.2 知識圖譜建置模組 16
3.1.3 問答模組 17
3.2 DocuKMP系統離散事件建模 18
3.2.1 文本提取模組離散事件建模 21
3.2.2 知識圖譜建置模組離散事件建模 21
3.2.3 問答模組離散事件建模 22
3.3 DocuKMP系統使用者介面設計 23
第四章、系統實驗 25
4.1 實驗環境 25
4.2 DocuKMP系統軟體高階合成 26
4.2.1 文本提取 26
4.2.2 知識圖譜建置 28
4.2.3 問答 29
4.3 知識圖譜建置工具鏈的效能 31
4.3.1 PDF轉文字 31
4.3.2 語音轉文字 33
4.3.3 圖像轉文字 34
4.3.4 網頁轉文字 36
4.3.5 文本知識提取 37
4.3.6 知識圖譜建構 38
4.4 知識圖譜建置的品質 38
4.4.1 準確度 39
4.4.2 一致性 39
4.4.3 完整性 40
4.4.4 冗餘性 41
4.5 檢索增強生成與知識圖譜的比較 41
第五章、結論 43
5.1 結論 43
5.2 未來展望 44
第六章、參考文獻 46

參考文獻

[1] W. Yun, X. Zhang, Z. Li, H. Liu, and M. Han, “Knowledge modeling: A survey of processes and techniques”, in International Journal of Intelligent Systems, vol. 36, no. 4, pp. 1686–1720, 2021.
[2] A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, et al., “Attention is all you need”, Advances in Neural Information Processing Systems 30, 2017, pp. 5998–6008.
[3] M. Shanahan, “Talking about large language models”, arXiv preprint arXiv:2212.03551, 2022.
[4] J. Achiam, S. Adler, S. Agarwal, L. Ahmad, I. Akkaya, F. L. Aleman, et al., “GPT-4 technical report”, arXiv preprint arXiv:2303.08774, 2023.
[5] H. Touvron, T. Lavril, G. Izacard, X. Martinet, M.-A. Lachaux, T. Lacroix, et al., “LLaMA: Open and Efficient Foundation Language Models”, arXiv preprint arXiv:2302.13971, 2023.
[6] R. Thoppilan, D. D. Freitas, J. Hall, N. Shazeer, A. Kulshreshtha, H.-T. Cheng, et al., “LaMDA: Language Models for Dialog Applications”, arXiv preprint arXiv:2201.08239, 2022.
[7] A. Chowdhery, S. Narang, J. Devlin, M. Bosma, G. Mishra, A. Roberts, et al., “PaLM: Scaling Language Modeling with Pathways”, Journal of Machine Learning Research, vol. 24, no. 240, pp. 1-113, 2023.
[8] A timeline of Google’s biggest AI and ML moments. Accessed: Jan. 23, 2024. [Online]. Available: https://blog.google/technology/ai/google-ai-ml-timeline/
[9] S. Mandvikar, “Augmenting Intelligent Document Processing (IDP) Workflows with Contemporary Large Language Models (LLMs)”, International Journal of Computer Trends and Technology, vol.71, no. 10, pp. 80-91, 2023.
[10] V. Bilgram and F. Laarmann, “Accelerating Innovation With Generative AI: AI-Augmented Digital Prototyping and Innovation Methods”, in IEEE Engineering Management Review, vol. 51, no. 2, pp. 18-25, 2023.
[11] Z. Ji, N. Lee, R. Frieske, T. Yu, D. Su, Y. Xu, et al., “Survey of Hallucination in Natural Language Generation”, in ACM Computing Surveys, vol. 55, no. 12, pp. 1-38, 2023.
[12] K. Liang, Z. Zhang, and J. F. Fisac, “Introspective Planning: Guiding Language-Enabled Agents to Refine Their Own Uncertainty”, arXiv preprint arXiv:2402.06529, 2024.
[13] A. Pal, L. K. Umapathi, and M. Sankarasubb, “Med-HALT: Medical Domain Hallucination Test for Large Language Models”, in Proceedings of the 27th Conference on Computational Natural Language Learning (CoNLL), 2023, pp. 314-334.
[14] Y. Yao, J. Duan, K. Xu, Y. Cai, Z. Sun and Y. Zhang, “A Survey on Large Language Model (LLM) Security and Privacy: The Good, the Bad, and the Ugly”, arXiv preprint arXiv:2312.02003, 2023.
[15] N. Carlini, F. Tramèr, E. Wallace, M. Jagielski, A. Herbert-Voss, K. Lee, et al., “Extracting training data from large language models”, in 30th USENIX Security Symposium (USENIX Security 21), 2021, pp. 2633-2650.
[16] H. Zhao, H. Chen, F. Yang, N. Liu, H. Deng, H. Cai, et al., “Explainability for Large Language Models: A Survey”, ACM Transactions on Intelligent Systems and Technology, vol.15, no.2, pp. 1-38, 2024.
[17] P. Lewis, E. Perez, A. Piktus, F. Petroni, V. Karpukhin, N. Goyal, et al., “Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks”, in 34th Conference on Neural Information Processing Systems (NeurIPS 2020), 2020, pp. 9459–9474.
[18] O. Ovadia, M. Brief, M. Mishaeli, and O. Elisha, “Fine-Tuning or Retrieval? Comparing Knowledge Injection in LLMs”, arXiv preprint arXiv:2312.05934, 2024.
[19] S. Barnett, S. Kurniawan, S. Thudumu, Z. Brannelly, and M. Abdelrazek, “Seven Failure Points When Engineering a Retrieval Augmented Generation System”, arXiv preprint arXiv:2401.05856, 2024.
[20] P. BehnamGhader, S. Miret, and S. Reddy, “Can Retriever-Augmented Language Models Reason? The Blame Game Between the Retriever and the Language Model”, arXiv preprint arXiv:2212.09146, 2022.
[21] J. Chen, H. Lin, X. Han, and L. Sun, “Benchmarking Large Language Models in Retrieval-Augmented Generation”, in AAAI, vol. 38, no. 16, pp. 17754-17762, 2024.
[22] Y. Gao, Y. Xiong, X. Gao, K. Jia, J. Pan, Y. Bi, et al., “Retrieval-Augmented Generation for Large Language Models: A Survey”, arXiv preprint arXiv:2312.10997, 2024.
[23] S. Ji, S. Pan, E. Cambria, P. Marttinen, and P. S. Yu, “A Survey on Knowledge Graphs: Representation, Acquisition and Applications”, in IEEE Transactions on Neural Networks and Learning Systems, vol. 33, no. 2, pp. 494-514, 2022.
[24] Z. Ji, Z. Liu, N. Lee, T. Yu, B. Wilie, M. Zeng, et al., “RHO (ρ): Reducing Hallucination in Open-domain Dialogues with Knowledge Grounding”, arXiv preprint arXiv:2212.01588, 2022.
[25] S. Pan, L. Luo, Y. Wang, C. Chen, J. Wang, and X. Wu, “Unifying Large Language Models and Knowledge Graphs: A Roadmap”, in IEEE Transactions on Knowledge and Data Engineering, 2024.
[26] C. Peng, F. Xia, M. Naseriparsa, and F. Osborne, “Knowledge Graphs: Opportunities and Challenges”, Artif. Intell. Rev., vol. 56, pp. 13071-13102, 2023.
[27] F. Kitsios and M. Kamariotou, “Artificial Intelligence and Business Strategy towards Digital Transformation: A Research Agenda”, Sustainability, vol. 13, no. 4, pp. 2025, 2021.
[28] Y. Xu, X. Liu, X. Cao, C. Huang, E. Liu, S. Qian, et al., “Artificial intelligence: A powerful paradigm for scientific research”, Innovation, vol. 2, no. 4, 2021.
[29] D. Mhlanga, “Industry 4.0 in Finance: The Impact of Artificial Intelligence (AI) on Digital Financial Inclusion”, International Journal of Financial Studies, vol. 8, no. 3, pp. 45, 2020.
[30] Introducing ChatGPT. Accessed: Apr. 09, 2024. [Online]. Available: https://openai.com/blog/chatgpt
[31] I. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, et al., “Generative Adversarial Networks”, in Proc. Int. Conf. Neural Inf. Process. Syst., pp. 2672-2680, 2014.
[32] S. Islam, H. Elmekki, A. Elsebai, J. Bentahar, N. Drawel, G. Rjoub, et al., “A Comprehensive Survey on Applications of Transformers for Deep Learning Tasks”, in Expert Systems with Applications, vol. 241, pp. 122666, 2023.
[33] G. Iglesias, E. Talavera, and A. Díaz-Álvarez, “A survey on GANs for computer vision: Recent research, analysis and taxonomy”, in Computer Science Review, vol. 48, pp. 100553, 2023.
[34] A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, et al., “Attention is all you need”, Advances in Neural Information Processing Systems 30, pp. 5998–6008, 2017.
[35] R. Bommasani, D. Hudson, E. Adeli, R. Altman, S. Arora, S. v. Arx, et al., “On the Opportunities and Risks of Foundation Models”, arXiv preprint arXiv:2108.07258, 2021.
[36] W. X. Zhao, K. Zhou, J. Li, T. Tang, X. Wang, Y. Hou, et al., “A Survey of Large Language Models”, arXiv preprint arXiv:2303.18223, 2023.
[37] S. Bubeck, V. Chandrasekaran, R. Eldan, J. Gehrke, E. Horvitz, E. Kamar, et al., “Sparks of Artificial General Intelligence: Early experiments with GPT-4”, arXiv preprint arXiv:2303.12712, 2023.
[38] OpenAI (2023), “GPT-4 Technical Report”, arXiv preprint arXiv:2303.08774, 2023.
[39] Z. Xu, S. Jain, and M. Kankanhalli, “Hallucination is Inevitable: An Innate Limitation of Large Language Models”, arXiv preprint arXiv:2401.11817, 2024.
[40] Introducing the Knowledge Graph: things, not strings. Accessed: Mar. 05, 2024. [Online]. Available: https://blog.google/products/search/introducing-knowledge-graph-things-not/
[41] Neo4j. Accessed: Mar. 06, 2024. [Online]. Available: https://neo4j.com/
[42] P. Liu, Y. Huang, P. Wang, Q. Zhao, J. Nie, Y. Tang, et al., “Construction of typhoon disaster knowledge graph based on graph database Neo4j”, in 2020 Chinese Control And Decision Conference (CCDC), pp. 3612-3616, 2020.
[43] 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(PMLR), Honolulu, Hawaii, USA. vol.202, pp. 28492-28518, 2023.
[44] 司法院裁判書系統. Accessed: Apr. 05, 2024. [Online]. Available: https://judgment.judicial.gov.tw/FJUD/default.aspx
[45] Introducing Meta Llama 3: The most capable openly available LLM to date. Accessed: Jun. 07, 2024. [Online]. Available: https://ai.meta.com/blog/meta-llama-3/
[46] C.-H. Chen, M.-Y. Lin, and X.-C. Guo, “High-level modeling and synthesis of smart sensor networks for Industrial Internet of Things”, Computers & Electrical Engineering, vol. 61, pp. 48-66, 2017.
[47] The world’s most walkable cities revealed (and they aren’t in the US). Accessed: Jun. 10, 2024. [Online]. Available: https://edition.cnn.com/travel/travel-news-walkable-cities
[48] Z. Fan and C. Chen. “CuPe-KG: Cultural perspective–based knowledge graph construction of tourism resources via pretrained language models”, Information Processing & Management, vol.61, no.3, 2024.
[49] X. Wang, L. Chen, T. Ban, M. Usman, Y. Guan, S. Liu, et al., “Knowledge graph quality control: A survey”, Fundamental Research, vol.1, no.5, pp. 607-626, 2021.
[50] B. Xue and L. Zou, “Knowledge Graph Quality Management: A Comprehensive Survey”, in IEEE Transactions on Knowledge and Data Engineering, vol. 35, no. 5, pp. 4969-4988, 2023.

指導教授

陳慶瀚(Ching-Han Chen)

審核日期

2024-7-23

推文