Development of an intelligent assistant for selection of goods in the process of dialogue with the user
Abstract
This article is devoted to the development of methods for creating intelligent assistants. Intelligent assistants can be used in call centers to solve customer problems, to solve technical support tasks, to help people with disabilities, to help in choosing goods, etc. We consider intelligent assistants that engage in argumentative dialogue with users, aimed at finding goods and services that maximally satisfy users’ wants and needs. The development of the intelligent assistant is based on a four-level model of the subject domain and a semantic model of the user. The system under development automates the process of search and decision justification through the reuse of domain cases: accumulated knowledge about previous dialogues with users. This gives the system we developed an advantage over existing analogues, which are incapable of reusing knowledge about previous dialogues. The paper develops a case-based approach to building an intelligent system capable of reasoning about its responses. For this purpose, an argumentation graph is constructed, methods for structuring domain cases are developed, and ontological homomorphisms are used to transform the available domain cases into a finished solution. A description of model-theoretical methods for constructing intelligent assistants is presented. The cases of goods, users and dialogues of an intelligent assistant with users are formally described in the form of partial models. The transformation of domain cases and similarity of cases are formalized using ontological homomorphisms of partial models. The purpose of the developed dialogue system is not only to select a solution according to the user’s request, but also to find out the tasks that the user is going to solve, to analyze his argumentation, and then to justify the proposed solution to the user, to show that this particular product or service will be able to meet his needs.
Downloads
References
Toulmin S.E. (2003) The uses of argument. Cambridge University Press.
Reed C., Rowe G. (2004) Araucaria: Software for argument analysis, diagramming and representation. International Journal on Artificial Intelligence Tools, vol. 13, no. 4, pp. 961–979.
Walton D., Reed C., Macagno F. (2008) Argumentation schemes. Cambridge University Press.
Macagno F., Walton D. (2015) Classifying the patterns of natural arguments. Philosophy & Rhetoric, vol. 48, no. 1, pp. 26–53. https://doi.org/10.5325/philrhet.48.1.0026
Wagemans J. (2016) Constructing a periodic table of arguments. Argumentation, objectivity, and bias: Proceedings of the 11th international conference of the Ontario Society for the Study of Argumentation, Windsor, Ontario, Canada, pp. 1–12. https://doi.org/10.2139/ssrn.2769833
Walton D., Gordon T.F. (2017) Argument invention with the Carneades argumentation system. SCRIPTed, vol. 14, no. 2, pp. 168–207. https://doi.org/10.2966/scrip.140217.168
Wachsmuth H., Potthast M., Al-Khatib K., Ajjour Y. (2017) Building an argument search engine for the Web. Proceedings of the 4th Workshop on Argument Mining, pp. 49–59.
Slonim N. et al. (2021) An autonomous debating system. Nature, vol. 591, no. 7850, pp. 379–384. https://doi.org/10.1038/s41586-021-03215-w
Stab C., Miller T., Shiller B., Rai P., Gurevych I. (2018) Cross-topic argument mining from heterogeneous sources. Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pp. 3664–3674.
Naydanov Ch., Palchunov D., Sazonova P. (2015) Development of automated methods for the critical condition risk prevention, based on the analysis of the knowledge obtained from patient medical records. Proceedings of the International Conference on Biomedical Engineering and Computational Technologies, Novosibirsk, 28–30 October 2015, pp. 33–38. https://doi.org/10.1109/SIBIRCON.2015.7361845
Naydanov Ch., Palchunov D., Sazonova P. (2016) Development of automated methods for the prevention of risks of critical conditions, based on the analysis of the knowledge extracted from the medical histories. The Siberian Scientific Medical Journal, vol. 36, no. 1, pp. 105–113.
Naidanov Ch.A. (2019) Development of ontological model kernel, customisable for the subject domain. Vestnik of Novosibirsk State University. Series: Information technologies, vol. 17, no. 1, pp. 72–81.
OpenAI (2022) Introducing ChatGPT. Available at: https://openai.com/blog/chatgpt (accessed 26 January 2024).
McCloskey M., Cohen N.J. (1989) Catastrophic interference in connectionist networks: The sequential learning problem. Psychology of Learning and Motivation, vol. 24, pp. 109–165.
Blenderbot AI (2022) BlenderBot 3: A Conversational AI Prototype. Available at: https://blenderbot.ai (accessed 26 January 2024).
Shuster K. et al. (2022) Blenderbot 3: A deployed conversational agent that continually learns to responsibly engage. arXiv:2208.03188. https://doi.org/10.48550/arXiv.2208.03188
Higashinaka R. et al. (2017) Argumentative dialogue system based on argumentation structures. Proceedings of the 21st Workshop on the Semantics and Pragmatics of Dialogue, pp. 154–155.
Lippi M., Torroni P. (2016) Argumentation mining: State of the art and emerging trends. ACM Transactions on Internet Technology, vol. 16, no. 2, pp. 1–25. https://doi.org/10.1145/2850417
Fazzinga B., Galassi A., Torroni P. (2021) An argumentative dialogue system for COVID-19 vaccine information. International Conference on Logic and Argumentation. Cham: Springer International Publishing, pp. 477–485.
Chalaguine L.A., Hunter A. (2020) A persuasive chatbot using a crowd-sourced argument graph and concerns. IOS Press E-books Series Frontiers in Artificial Intelligence and Applications, vol. 326: Computational Models of Argument, pp. 9–20. https://doi.org/10.3233/FAIA200487
Palchunov D., Yakobson A. (2022) Automated methods for conducting an argumented dialogue with the user. 2022 IEEE International Multi-Conference on Engineering, Computer and Information Sciences (SIBIRCON), pp. 880–885. https://doi.org/10.1109/SIBIRCON56155.2022.10016975
Palchunov D.E., Yakobson A.A. (2022) Software system “ArgumentDialogue”. Certificate of state registration of computer programme No. 2022664041, registered 22.07.2022.
Carnap R. (1956) Meaning and necessity. A study in semantics and modal logic. Chicago.
Palchunov D.E. (2006) Modelling of thinking and formalization of reflexion I: Theoretical-model formalization of ontology and reflexion. Philosophy of Science, vol. 4(31), pp. 86–114.
Palchunov D.E. (2022) Methodological aspects of the application of model theory in knowledge engineering and artificial intelligence. 2022 Ural-Siberian Conference on Computational Technologies in Cognitive Science, Genomics and Biomedicine (CSGB), pp. 210–215. https://doi.org/10.1109/CSGB56354.2022.9865602
Palchunov D.E. (2008) Modelling of thinking and formalization of reflexion. Part 2: Ontologies and formalisation of concepts. Philosophy of Science, vol. 2(37), pp. 62–99.
Palchunov D.E. (2008) Solution of the information search task on the basis of ontologies. Business-informatics, vol. 1(3), pp. 3–13 (in Russian).
Orlovsky A., Palchunov D. (2021) Development of automated methods for the domain ontology population with the help of a virtual assistant. 2021 IEEE 22nd International Conference of Young Professionals in Electron Devices and Materials (EDM), pp. 537–541. https://doi.org/10.1109/EDM52169.2021.9507641
Makhina E.D., Palchunov D.E. (2018) Software system to determine speech actions in natural language texts. Vestnik of Novosibirsk State University. Series: Information technologies, vol. 16, no. 4, pp. 95–106. https://doi.org/10.25205/1818-7900-2018-16-4-95-106
Galitsky B., Ilvovsky D., Kuznetsov S. (2018) Detecting logical argumentation in text via communicative discourse tree. Journal of Experimental and Theoretical Artificial Intelligence, vol. 30, no. 5, pp. 637–663. https://doi.org/10.1080/0952813X.2018.1467492
Galitsky B., Ilvovsky D., Kuznetsov S.O. (2015) Text integrity assessment: Sentiment profile vs rhetoric structure. Computational Linguistics and Intelligent Text Processing (eds. A. Gelbukh). CICLing 2015. Lecture Notes in Computer Science, vol. 9042. Springer, Cham, pp. 126–139. https://doi.org/10.1007/978-3-319-18117-2_10
Galitsky B., Ilvovsky D., Kuznetsov S.O. (2015) Rhetoric map of an answer to compound queries. Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing, Beijing, China, vol. 2: Short Papers, pp. 681–686. https://doi.org/10.3115/v1/P15-2112
