A Human Behavior Exploration Approach Using LLMs for Cyber-Physical Systems
Pages 578 - 586
Abstract
In the early phases of Cyber-Physical Systems (CPS) development, scoping human behavior plays a significant role, especially when interactions extend beyond expected behavior. Here, it is especially challenging to develop cases that capture the full spectrum of human behavior. Up to now, identifying such behavior of humans remains a task for domain experts. We explore how one can use Large Languages Models (LLMs) in the design phase of systems to provide additional information about human-CPS interaction. Our approach proposes a preliminary ontology describing a hierarchy of types of behavior and relevant CPS components as input for prompt templates. It uses them to generate parts of human behavior descriptions, as well as a canned prompt with one variable about behavior. For demonstration, we take a smart building with a Home Energy System as the use case.
An initial user evaluation shows that the behavior descriptions generated with standard and ontology-driven prompts complement each other and are useful when assisting humans. The discovered uncommon behaviors can be used to complete interaction scenarios that eventually result in a more robust CPS implementation.
References
[1]
2024. Github Repository. https://github.com/atenearesearchgroup/human-behavior-exploration.
[2]
Afsoon Afzal, Claire Le Goues, Michael Hilton, and Christopher Steven Timperley. 2020. A Study on Challenges of Testing Robotic Systems. In 2020 IEEE 13th Int. Conf. on Software Testing, Validation and Verification (ICST). 96--107.
[3]
Ian F Alexander and Neil Maiden. 2005. Scenarios, stories, use cases: through the systems development life-cycle. John Wiley & Sons.
[4]
Robert Arp, Barry Smith, and Andrew D. Spear. 2015. Building Ontologies with Basic Formal Ontology. The MIT Press, USA.
[5]
Shraddha Barke, Michael B. James, and Nadia Polikarpova. 2023. Grounded Copilot: How Programmers Interact with Code-Generating Models. Proc. ACM Program. Lang. 7, OOPSLA1 (2023).
[6]
Christoph Becker, Stefanie Betz, Ruzanna Chitchyan, Leticia Duboc, Steve M Easterbrook, Birgit Penzenstadler, Norbet Seyff, and Colin C Venters. 2015. Requirements: The key to sustainability. IEEE Software 33, 1 (2015), 56--65.
[7]
Angel Blanch, Roberto García, Jordi Planes, Rosa Gil, Ferran Balada, Eduardo Blanco, and Anton Aluja. 2017. Ontologies About Human Behavior. European Psychologist 22, 3 (2017), 180--197.
[8]
Paul Boutot, Mirza Rehenuma Tabassum, Abdul Abedin, and Sadaf Mustafiz. 2024. Requirements development for IoT systems with UCM4IoT. Journal of Computer Languages 78 (2024), 101251.
[9]
Fatma Bozyigit, Tolgahan Bardakci, Alireza Khalilipour, Moharram Challenger, Guus Ramackers, Önder Babur, and Michel RV Chaudron. 2024. Generating domain models from natural language text using NLP: a benchmark dataset and experimental comparison of tools. Software and Systems Modeling (2024), 1--19.
[10]
Marius Brinkmann and Axel Hahn. 2017. Testbed architecture for maritime cyber physical systems. In 2017 IEEE 15th Int. Conf. on Industrial Informatics (INDIN). 923--928.
[11]
Natalia Díaz Rodríguez, Manuel P. Cuéllar, Johan Lilius, and Miguel Delgado Calvo-Flores. 2014. A fuzzy ontology for semantic modelling and recognition of human behaviour. Knowledge-Based Systems 66 (2014), 46--60.
[12]
Madeline Endres, Sarah Fakhoury, Saikat Chakraborty, and Shuvendu K Lahiri. 2023. Formalizing Natural Language Intent into Program Specifications via Large Language Models. arXiv preprint arXiv:2310.01831 (2023).
[13]
Angela Fan, Beliz Gokkaya, Mark Harman, Mitya Lyubarskiy, Shubho Sengupta, Shin Yoo, and Jie M Zhang. 2023. Large language models for software engineering: Survey and open problems. arXiv preprint arXiv:2310.03533 (2023).
[14]
FINSENY 2024. FINSENY (Future INternet for Smart ENergY). http://www.finesce.eu/FINSENY.html
[15]
Samuel A Fricker, Rainer Grau, and Adrian Zwingli. 2014. Requirements engineering: best practice. In Requirements Engineering for Digital Health. Springer, 25--46.
[16]
Eva Geisberger and Manfred Broy. 2012. agendaCPS: integrierte forschungsagenda cyber-physical systems. Vol. 1. Springer-Verlag.
[17]
Rosa Gil, Jordi Virgili-Goma, Roberto García, and Cindy Mason. 2015. Emotions ontology for collaborative modelling and learning of emotional responses. Computers in Human Behavior 51 (2015), 610--617. Computing for Human Learning, Behaviour and Collaboration in the Social and Mobile Networks Era.
[18]
Nicola Guarino, Daniel Oberle, and Steffen Staab. 2009. What Is An Ontology? In Handbook on Ontologies. Springer, Chapter 1, 1--17.
[19]
Xinyi Hou, Yanjie Zhao, Yue Liu, Zhou Yang, Kailong Wang, Li Li, Xiapu Luo, David Lo, John Grundy, and Haoyu Wang. 2024. Large Language Models for Software Engineering: A Systematic Literature Review. arXiv:2308.10620 [cs.SE]
[20]
Jerome Hugues, Anton Hristosov, John J. Hudak, and Joe Yankel. 2020. TwinOps - DevOps meets model-based engineering and digital twins for the engineering of CPS. In 23rd ACM/IEEE Int. Conf. on Model Driven Engineering Languages and Systems: Comp. (MODELS '20). ACM.
[21]
Ivar Jacobson, Magnus Christerson, Patrik Jonsson, and Gunnar Overgaard. 1992. Object-Oriented Software Engineering: A Use Case Driven Approach. Addison Wesley.
[22]
Krzysztof Janowicz, Armin Haller, Simon J.D. Cox, Danh Le Phuoc, and Maxime Lefrançois. 2019. SOSA: A lightweight ontology for sensors, observations, samples, and actuators. Journal of Web Semantics 56 (2019), 1--10.
[23]
Devi Karolita, Jennifer McIntosh, Tanjila Kanij, John Grundy, and Humphrey O. Obie. 2023. Use of personas in Requirements Engineering: A systematic mapping study. Information and Software Technology 162 (2023), 107264.
[24]
C. Maria Keet. 2018. An introduction to ontology engineering. Computing, Vol. 20. College Publications, UK. 334p.
[25]
Shekoufeh Kolahdouz-Rahimi, Kevin Lano, and Chenghua Lin. 2023. Requirement Formalisation using Natural Language Processing and Machine Learning: A Systematic Review. arXiv preprint arXiv:2303.13365 (2023).
[26]
Ryan Languay, Nika Prairie, and Jörg Kienzle. 2023. Concern-Oriented Use Cases. Journal of Object Technology 22, 2 (July 2023), 2:1--14.
[27]
Christophe Lemaigre, Josefina Guerrero García, and Jean Vanderdonckt. 2008. Interface model elicitation from textual scenarios. In Human-Computer Interaction Symposium: IFIP 20th World Computer Congress, 1st TC 13 Human-Computer Interaction Symposium (HCIS 2008). Springer, 53--66.
[28]
Sachiko Lim, Aron Henriksson, and Jelena Zdravkovic. 2021. Data-driven requirements elicitation: A systematic literature review. SN Computer Science 2, 1 (2021), 16.
[29]
Jintao Liu, Zequn Zhang, Zhi Guo, Li Jin, Xiaoyu Li, Kaiwen Wei, and Xian Sun. 2023. KEPT: Knowledge Enhanced Prompt Tuning for event causality identification. Knowledge-Based Systems 259 (2023), 110064.
[30]
Daniel Lübke and Tammo van Lessen. 2017. BPMN-Based Model-Driven Testing of Service-Based Processes. In Enterprise, Business-Process and Information Systems Modeling. Springer International Publishing, Cham, 119--133.
[31]
Xianchang Luo, Yinxing Xue, Zhenchang Xing, and Jiamou Sun. 2022. Prcbert: Prompt learning for requirement classification using bert-based pretrained language models. In 37th Int. Conf. on Automated Software Engineering. 1--13.
[32]
Lezhi Ma, Shangqing Liu, Yi Li, Xiaofei Xie, and Lei Bu. 2024. SpecGen: Automated Generation of Formal Program Specifications via Large Language Models. arXiv preprint arXiv:2401.08807 (2024).
[33]
M. M. Marques, A. J. Wright, E. Corker, M. Johnston, R. West, J. Hastings, L. Zhang, and S. Michie. 2023. The Behaviour Change Technique Ontology: Transforming the Behaviour Change Technique Taxonomy v1 [version 1; peer review: 4 approved]. Wellcome Open Research 8 (2023), 308.
[34]
C. Masolo, S. Borgo, A. Gangemi, N. Guarino, and A. Oltramari. 2003. Ontology Library. WonderWeb Deliverable D18 (ver. 1.0, 31-12-2003). http://wonderweb.semanticweb.org.
[35]
Sonali Mathur and Shaily Malik. 2010. Advancements in the V-Model. International Journal of Computer Applications 1, 12 (2010), 29--34.
[36]
Judith Michael and Heinrich C. Mayr. 2013. Conceptual Modeling for Ambient Assistance. In Conceptual Modeling - ER 2013 (LNCS, Vol. 8217). Springer, 403--413.
[37]
Judith Michael, Maike Schwammberger, and Andreas Wortmann. 2024. Explaining Cyberphysical System Behavior with Digital Twins. IEEE Software 41, 1 (Jan 2024), 55--63.
[38]
Judith Michael and Volodymyr Shekhovtsov. 2024. A Model-Based Reference Architecture for Complex Assistive Systems and its Application. Journal Software and Systems Modeling (SoSyM) (2024).
[39]
Shervin Minaee, Tomas Mikolov, Narjes Nikzad, Meysam Chenaghlu, Richard Socher, Xavier Amatriain, and Jianfeng Gao. 2024. Large language models: A survey. arXiv preprint arXiv:2402.06196 (2024).
[40]
OMG. 2013. Business Process Model and Notation (BPMN), Version 2.0.2. Technical Report. Object Management Group.
[41]
Oleksandr Palagin, Vladislav Kaverinskiy, Anna Litvin, and Kyrylo Malakhov. 2023. OntoChatGPT Information System: Ontology-Driven Structured Prompts for ChatGPT Meta-Learning. International Journal of Computing (July 2023), 170--183.
[42]
Omid Rajabi Shishvan, Daphney-Stavroula Zois, and Tolga Soyata. 2018. Machine Intelligence in Healthcare and Medical Cyber Physical Systems: A Survey. IEEE Access 6 (2018), 46419--46494.
[43]
Doruk Sahinel, Cem Akpolat, Orhan Can Görür, Fikret Sivrikaya, and Sahin Albayrak. 2021. Human modeling and interaction in cyber-physical systems: A reference framework. Journal of Manufacturing Systems 59 (1 April 2021), 367--385.
[44]
Shane Sendall and Alfred Strohmeier. 2000. From Use Cases to System Operation Specifications. In UML 2000 - The Unified Modeling Language. Springer.
[45]
Claude E Shannon. 1951. Prediction and entropy of printed English. Bell system technical journal 30, 1 (1951), 50--64.
[46]
Neelam Soundarajan and Stephen Fridella. 1999. Modeling exceptional behavior. In 2nd International Conference on The Unified Modeling Language: Beyond the Standard (Fort Collins, CO, USA) (UML'99). Springer-Verlag, 691--704.
[47]
J. A. Turner, G. Frishkoff, and Laird A. R. 2011. Ontology harmonization between fMRI and ERP: CogPO and NEMO. In 41th Annual Meeting of the Society for Neuroscience. Washington D.C., USA.
[48]
Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Łukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems 30 (2017).
[49]
Jules White, Sam Hays, Quchen Fu, Jesse Spencer-Smith, and Douglas C Schmidt. 2024. Chatgpt prompt patterns for improving code quality, refactoring, requirements elicitation, and software design. In Generative AI for Effective Software Development. Springer, 71--108.
[50]
Hongbin Ye, Ningyu Zhang, Shumin Deng, Xiang Chen, Hui Chen, Feiyu Xiong, Xi Chen, and Huajun Chen. 2022. Ontology-enhanced Prompt-tuning for Fewshot Learning. In ACM Web Conference 2022 (WWW '22). ACM, 778--787.
[51]
Tao Yue, Shaukat Ali, and Lionel Briand. 2011. Automated Transition from Use Cases to UML State Machines to Support State-Based Testing. In Modelling Foundations and Applications. Springer, 115--131.
[52]
Jianzhang Zhang, Yiyang Chen, Nan Niu, and Chuang Liu. 2023. A preliminary evaluation of chatgpt in requirements information retrieval. arXiv preprint arXiv:2304.12562 (2023).
[53]
Man Zhang, Tao Yue, Shaukat Ali, Bran Selic, Oscar Okariz, Roland Norgre, and Karmele Intxausti. 2018. Specifying uncertainty in use case models. JSS 144 (2018), 573--603.
[54]
Simiao Zhang, Jiaping Wang, Guoliang Dong, Jun Sun, Yueling Zhang, and Geguang Pu. 2024. Experimenting a New Programming Practice with LLMs. arXiv preprint arXiv:2401.01062 (2024).
[55]
Kai Zheng, Qingfeng Sun, Yaming Yang, and Fei Xu. 2022. Knowledge Stimulated Contrastive Prompting for Low-Resource Stance Detection. In Findings of the Association for Computational Linguistics: EMNLP 2022. Assoc. for Computational Linguistics, 1168--1178.
[56]
Miriam Zia, Sadaf Mustafiz, Hans Vangheluwe, and Jörg Kienzle. 2007. A Modelling and Simulation Based Process for Dependable Systems Design. Software and Systems Modeling (April 2007), 437 -- 451.
Index Terms
- A Human Behavior Exploration Approach Using LLMs for Cyber-Physical Systems
Recommendations
Human models in human-in-the-loop control systems
Understanding the collaboration between physical systems and human is an essential task in man-machine systems. This area of research has been significantly explored in the recent years with the focus on the machine side. Much less attention has been ...
Towards Independent In-Cloud Evolution of Cyber-Physical Systems
CPSNA '14: Proceedings of the 2014 IEEE International Conference on Cyber-Physical Systems, Networks, and ApplicationsThe capabilities of Cyber-Physical Systems (CPSs) are increasingly being extended towards new composite services deployed across a range of smart sensing and controlling devices. These services enable the emergence of multiple end-to-end cyber-physical ...
Exploring Human Behaviour in Cyber-Physical Systems with Multi-modelling and Co-simulation
Formal Methods. FM 2019 International WorkshopsAbstractDefinitions of cyber-physical systems often include humans within the system boundary, however design techniques often focus on the technical aspects and ignore this important part of the system. Multi-modelling and co-simulation offer a way to ...
Comments
Information & Contributors
Information
Published In
September 2024
1261 pages
ISBN:9798400706226
DOI:10.1145/3652620
- Chairs:
- Manuel Wimmer,
- Alexander Egyed,
- Program Chairs:
- Benoit Combemale,
- Marsha Chechik
Copyright © 2024 Copyright is held by the owner/author(s). Publication rights licensed to ACM.
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].
Sponsors
- SIGSOFT: ACM Special Interest Group on Software Engineering
- Johannes Kepler University Linz
- IEEE CS
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 31 October 2024
Check for updates
Author Tags
Qualifiers
- Research-article
Funding Sources
- Universidad de Málaga
- Junta de Andalucía
- Ministerio de Ciencia e Innovación - AEI
Conference
MODELS Companion '24
Sponsor:
MODELS Companion '24: ACM/IEEE 27th International Conference on Model Driven Engineering Languages and Systems
September 22 - 27, 2024
Linz, Austria
Acceptance Rates
Overall Acceptance Rate 144 of 506 submissions, 28%
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 62Total Downloads
- Downloads (Last 12 months)62
- Downloads (Last 6 weeks)10
Reflects downloads up to 12 Feb 2025
Other Metrics
Citations
View Options
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in