Nothing Special   »   [go: up one dir, main page]

skip to main content
rapid-communication

Retrieval augmented generation using engineering design knowledge

Published: 18 November 2024 Publication History

Abstract

Aiming to support Retrieval Augmented Generation (RAG) in the design process, we present a method to identify explicit, engineering design facts – {head entity:: relationship:: tail entity} from patented artefact descriptions. Given a sentence with a pair of entities (selected from noun phrases) marked in a unique manner, our method extracts their relationship that is explicitly communicated in the sentence. For this task, we create a dataset of 375,084 examples and fine-tune language models for relation identification (token classification task) and relation elicitation (sequence-to-sequence task). The token classification approach achieves up to 99.7% accuracy. Upon applying the method to a domain of 4,870 fan system patents, we populate a knowledge base of over 2.93 million facts. Using this knowledge base, we demonstrate how Large Language Models (LLMs) are guided by explicit facts to synthesise knowledge and generate technical and cohesive responses when sought out for knowledge retrieval tasks in the design process.

References

[1]
B. Chandrasekaran, Representing function: Relating functional representation and functional modeling research streams. Artificial intelligence for engineering design, Anal. Manuf. 19 (2005) 65–74,.
[2]
Chang, C., Zhou, J., Weng, Y., Zeng, X., Wu, Z., Wang, C.-D., Tang, Y., 2023. KGTN: Knowledge Graph Transformer Network for explainable multi-category item recommendation. Knowledge-Based Systems 278, 110854. https://doi.org/10.1016/j.knosys.2023.110854.
[3]
C. Chen, Y. Tao, Y. Li, Q. Liu, S. Li, Z. Tang, A structure-function knowledge extraction method for bio-inspired design, Comput. Ind. (2021),.
[4]
J. Chen, C. Liu, L. Xuan, Z. Zhang, Z. Zou, Knowledge-based turbomachinery design system via a deep neural network and multi-output Gaussian process, Knowl. Based. Syst. 252 (2022),.
[5]
W.G. Cochran, Sampling Techniques, Wiley Series in Probability and Statistics, Wiley, 1977.
[6]
N. Díaz-Rodríguez, J. Del Ser, M. Coeckelbergh, M. de Prado, E. Herrera-Viedma, F. Herrera, Connecting the dots in trustworthy Artificial Intelligence: From AI principles, ethics, and key requirements to responsible AI systems and regulation, Inf. Fusion 99 (2023),.
[7]
S. Dimassi, F. Demoly, C. Cruz, H. Qi, K. Kim, J. André, S. Gomes, An ontology-based framework to formalize and represent 4D printing knowledge in design, Comput. Ind. 126 (2021),.
[8]
N. Fatfouta, J.S. le-Cardinal, An ontology-based knowledge management approach supporting simulation-aided design for car crash simulation in the development phase, Comput. Ind. (2021),.
[9]
Z. Feng, C. Jin, H. Kim, X. Cui, Time-aware approximate collective keyword search in traffic networks, Knowl. Based. Syst. 229 (2021),.
[10]
Geng, R., Chen, Y., Huang, R., Qin, Y., Zheng, Q., 2023. Planarized sentence representation for nested named entity recognition. Information processing & management 60. https://doi.org/10.1016/j.ipm.2023.103352.
[11]
H. Jang, Y. Jeong, B. Yoon, TechWord: Development of a technology lexical database for structuring textual technology information based on natural language processing, Expert. Syst. Appl. (2021),.
[12]
J. Li, A. Sun, J. Han, C. Li, A survey on deep learning for named entity recognition, IEEe Trans. Knowl. Data Eng. 34 (2022) 50–70,.
[13]
X. Liu, K. Tan, S. Dong, Multi-granularity sequential neural network for document-level biomedical relation extraction, Inf. Process. Manage 58 (2021),.
[14]
Luo, J., Sarica, S., Wood, K., 2021. Guiding data-driven design ideation by knowledge distance. Knowledge-based systems 218. https://doi.org/10.1016/j.knosys.2021.106873.
[15]
Y. Qin, W. Lu, Q. Qi, X. Liu, M. Huang, P.J. Scott, X. Jiang, Towards an ontology-supported case-based reasoning approach for computer-aided tolerance specification, Knowl. Based. Syst. 141 (2018) 129–147,.
[16]
S. Quintana-Amate, P. Bermell-Garcia, A. Tiwari, Transforming expertise into knowledge-based engineering tools: a survey of knowledge sourcing in the context of engineering design, Knowl. Based. Syst. 84 (2015) 89–97,.
[17]
L. Siddharth, L. Blessing, J. Luo, Natural language processing in-and-for design research, Des. Sci. 8 (2022),.
[18]
L. Siddharth, L.T.M. Blessing, K.L. Wood, J. Luo, Engineering knowledge graph from patent database, J. Comput. Inf. Sci. Eng. 22 (2021),.
[19]
L. Siddharth, A. Chakrabarti, Evaluating the impact of Idea-Inspire 4.0 on analogical transfer of concepts. Artificial intelligence for engineering design, Anal. Manuf. 32 (2018) 431–448,.
[20]
L. Siddharth, A. Chakrabarti, R. Ranganath, Modeling and structuring design rationale to enable knowledge reuse, Syst. Eng. 23 (2020) 294–311,.
[21]
L. Siddharth, A. Chakrabarti, S. Venkataraman, QC Montreal, Canada V01BT02A039, Representing complex analogues using a function model to support conceptual design, in: Proceedings of ASME DETC/CIE, 2018,.
[22]
L. Siddharth, G. Li, J. Luo, Enhancing patent retrieval using text and knowledge graph embeddings: a technical note, J. Eng. Des. 33 (2022) 670–683,.
[23]
L. Soares, N. FitzGerald, J. Ling, T. Kwiatkowski, Matching the blanks: distributional similarity for relation learning, in: A. Korhonen, D. Traum, L. Màrquez (Eds.), Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, Association for Computational Linguistics, Florence, Italy, 2019, pp. 2895–2905,.
[24]
H. Sun, R. Grishman, Lexicalized dependency paths based supervised learning for relation extraction, Comput. Syst. Sci. Eng. 43 (2022) 861–870,.
[25]
Y. Sun, W. Liu, G. Cao, Q. Peng, J. Gu, J. Fu, Effective design knowledge abstraction from Chinese patents based on a meta-model of the patent design knowledge graph, Comput. Ind. 142 (2022),.
[26]
C.V. Trappey, A.J.C. Trappey, H.-Y. Peng, L.-D. Lin, T.-M. Wang, A knowledge centric methodology for dental implant technology assessment using ontology based patent analysis and clinical meta-analysis, Adv. Eng. Inf. (2014),.
[27]
R. Wang, C.F. Cheung, Knowledge graph embedding learning system for defect diagnosis in additive manufacturing, Comput. Ind. 149 (2023),.
[28]
J. Yang, E. Kim, M. Hur, S. Cho, M. Han, I. Seo, Knowledge extraction and visualization of digital design process, Expert. Syst. Appl. (2018),.
[29]
D. Ye, Y. Lin, P. Li, M. Sun, S. Muresan, P. Nakov, Packed Levitated marker for entity and relation extraction, in: A. Villavicencio (Ed.), Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics, 1, Association for Computational Linguistics, Dublin, Ireland, 2022, pp. 4904–4917,. Long Papers.
[30]
Z. Zhang, X. Han, Z. Liu, X. Jiang, M. Sun, Q. Liu, ERNIE: Enhanced language representation with informative entities, in: A. Korhonen, D. Traum, L. Màrquez (Eds.), Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, Association for Computational Linguistics, Florence, Italy, 2019, pp. 1441–1451,.
[31]
Z. Zhong, D. Chen, A frustratingly easy approach for entity and relation extraction, in: K. Toutanova, A. Rumshisky, L. Zettlemoyer, D. Hakkani-Tur, I. Beltagy, S. Bethard, R. Cotterell, T. Chakraborty, Y. Zhou (Eds.), Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Association for Computational Linguistics, Online, 2021, pp. 50–61,.
[32]
H. Zuo, Y. Yin, P. Childs, Patent-KG: patent knowledge graph extraction for engineering design, Proc. Des. Soc. 2 (2022) 821–830,.

Recommendations

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image Knowledge-Based Systems
Knowledge-Based Systems  Volume 303, Issue C
Nov 2024
408 pages

Publisher

Elsevier Science Publishers B. V.

Netherlands

Publication History

Published: 18 November 2024

Author Tags

  1. Knowledge graphs
  2. Retrieval-augmented generation
  3. Large-language models
  4. Engineering design knowledge
  5. Patent documents
  6. Graph neural networks

Qualifiers

  • Rapid-communication

Contributors

Other Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

  • 0
    Total Citations
  • 0
    Total Downloads
  • Downloads (Last 12 months)0
  • Downloads (Last 6 weeks)0
Reflects downloads up to 23 Dec 2024

Other Metrics

Citations

View Options

View options

Media

Figures

Other

Tables

Share

Share

Share this Publication link

Share on social media