Abstract
There is a vast space of potentiality for inspiration in the design and engineering of technical systems that are poorly valorized; the cyberspace that stores and daily adds high volumes of global collective intelligence. This space could be more productively tackled with the assistance of Artificial Intelligence algorithms led by Natural Language Processing (NLP) models. We investigate the application of Structured Activation Vertex Entropy (SAVE) method in combination with Question Answering Machine (QAM) algorithms to explore information that is stored in big datasets, accessible within unstructured dataspaces. The SAVE method is transformed with the assistance of TRIZ into a set of searching meta-terms or meta-concepts. Taking off from a clear description of the problem, target results, and the current (eco)system, meta-terms, and concepts are incorporated into a spiral searching-answering process called ‘D-SIT-SIT-C’, driven by a Retrieval Augmented Generation (RAG) model to create an “intelligent” Natural Language Processing pipeline, with inserting the human in the loop at each iteration. We have found that the proposed pipeline based on a RAG model brings new valences to the creative thinking process and unleashes new dimensions of investigations that lead to higher quality solutions than those formulated with limited resources.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Friedl, J.: Mastering Regular Expressions, 3rd edn. O’Reilly, Sebastopol (2006)
Lane, H., Hapke, H., Howard, C.: Natural Language Processing in Action. Manning, New York (2019)
Dwyer, D.: Top 12 Best Search Engines in the World (2016). https://www.inspire.scot/blog/2016/11/11/top-12-best-search-engines-in-the-world238. Accessed 20 June 2022
Gadd, K.: TRIZ for Engineers. Wiley, Chichester (2011)
Schmidt, R., Montani, S., Bellazzi, R., Portinale, L., Gierl, L.: Cased-based reasoning for medical knowledge-based systems. Int. J. Med. Inform. 64, 355–367 (2001)
Lee, C.H., Chen, C.H., Li, F., Shie, A.J.: Customized and knowledge-centric service design model integrating case-based reasoning and TRIZ. Expert Syst. Appl. 143, 13062, 14 pp. (2020)
Dewulf, S., Childs, P.R.N.: Patent data driven innovation logic: textual pattern exploration to identify innovation logic data. In: Borgianni, Y., Brad, S., Cavallucci, D., Livotov, P. (eds.) TFC 2021. IAICT, vol. 635, pp. 170–181. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-86614-3_14
Ip.com: Why Non-Patent Literature Can Make or Break Your Business. https://ip.com/wp-content/uploads/2020/09/IQ_NPL_ebook_P2.pdf. Accessed 02 June 2022
Souilia, A., Cavallucci, D., Rousselot, F.: Natural Language Processing (NLP) - a solution for knowledge extraction from patent unstructured data. Proc. Eng. 131, 635–643 (2015)
Kaliteevskii, V., Deder, A., Peric, N., Chechurin, L.: Concept extraction based on semantic models using big amount of patents and scientific publications data. In: Borgianni, Y., Brad, S., Cavallucci, D., Livotov, P. (eds.) TFC 2021. IAICT, vol. 635, pp. 141–149. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-86614-3_11
Guarino, G., Samet, A., Cavallucci, D.: Patent specialization for deep learning information retrieval algorithms. In: Borgianni, Y., Brad, S., Cavallucci, D., Livotov, P. (eds.) TFC 2021. IAICT, vol. 635, pp. 162–169. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-86614-3_13
Boufeloussen, O., Cavallucci, D.: Bringing together engineering problems and basic science knowledge, one step closer to systematic invention. In: Borgianni, Y., Brad, S., Cavallucci, D., Livotov, P. (eds.) TFC 2021. IAICT, vol. 635, pp. 340–351. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-86614-3_27
Hanifi, M., Chibane, H., Houssin, R., Cavallucci, D.: Problem formulation in inventive design using Doc2vec and cosine similarity as artificial intelligence methods and scientific papers. Eng. Appl. Artif. Intell. 109, 104661 (2022)
Hugging Face: What is Question Answering?. https://huggingface.co/tasks/question-answering. Accessed 04 June 2022
Brad, S.: Domain analysis with TRIZ to define an effective “Design for Excellence” framework. In: Borgianni, Y., Brad, S., Cavallucci, D., Livotov, P. (eds.) TFC 2021. IAICT, vol. 635, pp. 426–444. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-86614-3_34
Wang, Z.J., Choi, D., Xu, S., Yang, D.: Putting humans in the natural language processing loop: a survey. https://arxiv.org/abs/2103.04044 (2021). Accessed 04 May 2022
Roy, A.: Progress and Challenges in Long-Form Open-Domain Question Answering. https://ai.googleblog.com/2021/03/progress-and-challenges-in-long-form.html. Accessed 03 Apr 2022
Jernite, Y.: ELI5 Model from Hugging Face Model Repository. https://huggingface.co/yjernite. Accessed 02 Feb 2022
Fan, A., Jernite, Y., Perez, E., Grangier, D., Weston, J., Auli, M.: ELI5: Long Form Question Answering. https://arxiv.org/abs/1907.09190 (2019). Accessed 20 Jan 2022
Wikipedia: User scripts/Snippets. https://en.wikipedia.org/wiki/Wikipedia:User_scripts/Snippets. Accessed 05 Apr 2022
Guo, M., Dai, Z., Vrandečić, D., Al-Rfou, R.: Wiki-40B: multilingual language model dataset. In: Proceedings of the 12th Language Resources and Evaluation Conference, pp. 2440–2452. European Language Resources Association, Marseille, France (2020)
Hugging Face Data Sets. https://github.com/huggingface/datasets. Accessed 05 Apr 2022
Cameron, G.: ARIZ Explored: A Step-by-Step Guide to ARIZ, the Algorithm for Solving Inventive Problems. Create Space, Scotts Valley (2015)
Wikipedia. Scrubber: https://en.wikipedia.org/wiki/Scrubber. Accessed 02 June 2022
Lewis, M., et al.: BART: denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. https://arxiv.org/abs/1910.13461 (2019). Accessed 04 May 2022
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 IFIP International Federation for Information Processing
About this paper
Cite this paper
Brad, S., Ștetco, E. (2022). An Interactive Artificial Intelligence System for Inventive Problem-Solving. In: Nowak, R., Chrząszcz, J., Brad, S. (eds) Systematic Innovation Partnerships with Artificial Intelligence and Information Technology. TFC 2022. IFIP Advances in Information and Communication Technology, vol 655. Springer, Cham. https://doi.org/10.1007/978-3-031-17288-5_15
Download citation
DOI: https://doi.org/10.1007/978-3-031-17288-5_15
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-17287-8
Online ISBN: 978-3-031-17288-5
eBook Packages: Computer ScienceComputer Science (R0)
