Обзор технологий, применяемых в интеллектуальных диалоговых системах
Ключевые слова:
чат-бот, диалоговая система, телефонный робот, голосовой помощник, машинное обучение, искусственный интеллект, обработка естественного языка
Аннотация
Целью исследования является обзор существующих интеллектуальных систем обеспечения клиентского сервиса. Рассматриваются голосовые ассистенты для поддержки клиентов по телефону и текстовые чат-боты. Метод исследования — анализ и обобщение информации из открытых российских и зарубежных источников. Результаты. Был проведён обзор существующих технологий машинного обучения, применяемых в диалоговых системах, предназначенных для обслуживания клиентов в различных сферах коммерческой деятельности. Приведены методы, на которых базируются данные технологии. Описаны сферы деятельности, в которых применяются такие программные продукты. В статье обсуждаются проблемы предметной области, а также перспективы развития интеллектуальных диалоговых систем. В статье приводятся результаты психологических исследований на тему взаимодействия робота и человека, а также проблемы безопасности при использовании интеллектуальных систем, такие как утечка персональных данных или сведений, составляющих коммерческую тайну. Одним из направлений является защита пользователей от телефонного спама. Заключение. В ходе работы было выявлено, что подходы к реализации диалоговых систем могут быть различными: системы с ограниченным набором готовых ответов; гибридные системы «машина-человек»; системы, основанные на глубоком обучении, способные удерживать контекст диалога; системы, ориентированные на извлечении из речи или текста побуждающих слов. При всём многообразии методов и методик, у всех диалоговых систем есть общие черты. Приведена схема декомпозиции диалоговой системы. Статья будет полезна разработчикам голосовых диалоговых систем и текстовых чат-ботов, в которых происходит взаимодействие человека с машиной.
Скачивания
Данные скачивания пока не доступны.
Литература
1. Badamshin R. A., Il’iasov B. G. and Cherniakhovskaia L. R. (2003) Problems of control of complex dynamic objects in critical situations based on knowledge. Moskva : Mashinostroenie. 239 p. (in Russian).
2. Larichev O. I. (2002) Theory and methods of decision making. Moskva : Logos. 392 p. (in Russian).
3. Colby K. M., Hilf F. D., Weber S. and Kraemer H. C. (1972) Turing-like indistinguishability tests for the validation of a computer simulation of paranoid processes. Artificial Intelligence. Vol. 3. P. 199–221. DOI
4. Weizenbaum J. (1966) ELIZA — a computer program for the study of natural language communication between man and machine. Communications of the ACM. Vol. 9, No 1. P. 36–45.
5. Colby K., Weber S., Hilf F. D. (1971) Artificial paranoia. Vol. 2, No 1. P. 1–25.
6. Gary G. Hendrix, Earl D. Sacerdoti, Daniel Sagalowicz and Jonathan Slocum (1978) Developing a natural language interface to complex data. ACM Trans. Database Syst. 3, 2 (June 1978). P. 105– 147. DOI
7. Al-Amin Md, Ali Mohammad, Salam Abdus, Khan Arif, Ali Ashraf, Ullah Ahsan, Alam Md Nur and Chowdhury Shamsul (2024). History of generative Artificial Intelligence (AI) chatbots: past, present, and future development. DOI
8. Bhattad H. and Geeta Atkar M. (2021) Review on different types of chatbots. International Research Journal of Modernization in Engineering. 3. DOI
9. Nam HI, Boon Patrick Lee C. and Lian Z. (2019) Journal of Information Technology Management A Publication of the Association of Management comments about the SIRI chatbot: a sentiment analysis of the postings at a microblogging site. Comments about the SIRI chatbot. Journal of Information Technology Management.
10. Radford Alec, Narasimhan Karthik, Salimans Tim and Sutskever Ilya (2018) Improving language understanding by generative pre-training.
11. Maksimova A. S. (2019) Information service user experience: interaction with human and robot operator. Journal of Sociology and Social Anthropology. Vol. 22, No 6. P. 44–68. DOI
12. Karibov A. Ju. (2019) Analysis of algorithms of voice assistants. Journal Bulletin of Science. Vol. 4, No 5(14). P. 492–495. EDN XTXJXA (in Russian).
13. Kovtun O. S. and Srebnyj A. A. (2017) Robotization of banks: on the way to self-service. Scientific-practical researches journal. No 9(9). P. 54–56. EDN YLYRLV (in Russian).
14. Chujko D. V., Majorova E. V. (2020) “Are you a robot?”: ways to respond to robot recognition in a telephone conversation. Ethnopsycholinguistics Journal. No 3. P. 238–251. DOI
15. Romanov A. A. (2019) Dialogue system based on dynamic representation of knowledge graphs. Ekonomika: vchera, segodnia, zavtra. T. 9, No 8A. P. 453–461. DOI
16. Nguen T. M. Ch. (2022) Processing text data with diacritics in dialog decision support systems: dissertation for the degree of candidate of technical sciences. 151 p. EDN DVJYZF (in Russian).
17. Sun, Liangtai, Xingyu Chen, Lu Chen, Tianle Dai, Zichen Zhu and Kai Yu (2022) META-GUI: Towards Multi-modal Conversational Agents on Mobile GUI. Conference on Empirical Methods in Natural Language Processing. DOI
18. Tian Xie, Xinyi Yang, Angela S. Lin, Feihong Wu, Kazuma Hashimoto, Jin Qu, Young Mo Kang, Wenpeng Yin, Huan Wang, Semih Yavuz, Gang Wu, Michael Jones, Richard Socher, Yingbo Zhou, Wenhao Liu, Caiming Xiong (2022) Converse: A Tree-Based Modular Task-Oriented Dialogue System. arXiv preprint arXiv:2203.12187. DOI
19. Subendhu Rongali, Konstantine Arkoudas, Melanie Rubino and Wael Hamza (2022) Training naturalized semantic parsers with very little data. arXiv preprint arXiv:2204.14243. DOI
20. Taylor John Robert (1999) An Introduction to Error Analysis: The Study of Uncertainties in Physical Measurements. University Science Books. P. 128–129.
21. Yaoyuan Vincent Tan, Jason Roy (2019) Bayesian additive regression trees and the General BART model. Statistics in medicine. Т. 38, № 25. – С. 5048–5069. – DOI
22. Krivosheev N. A., Ivanova Ju. A., Spicyn V. G. (2021) Automatic generation of short texts based on the use of neural networks LSTM and SeqGAN. Bulletin of Tomsk State University. Management, Computing and Information Science. No 57. P. 118–130. DOI
23. Lantao Yu, Weinan Zhang, Jun Wang, Yong Yu (2017) SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient. AAAI’17: Proc. of the Thirty-First AAAI Conference on Artificial Intelligence. P. 2852–2858. DOI
24. Hochreiter S., Schmidhuber J. (1997) Long short-term memory. Neural Computation. V. 9, Iss. 8. P. 1735–1780. DOI
25. Chen B., Cherry C. (2014) A Systematic Comparison of Smoothing Techniques for Sentence-Level BLEU. Proc. of the Ninth Work-shop on Statistical Machine Translation. P. 362–367.
26. He Keqing, Jingang Wang, Chaobo Sun and Wei Wu (2022) Unified Knowledge Prompt Pre-training for Customer Service Dialogues. Proceedings of the 31st ACM International Conference on Information & Knowledge Management. P. 4009–4013. DOI
27. Devlin, Jacob, Ming-Wei Chang, Kenton Lee and Kristina Toutanova (2019) BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. Proceedings of NAACL-HLT. P. 4171–4186. DOI
28. Partha Pratim Ray (2023) ChatGPT: A comprehensive review on background, applications, key challenges, bias, ethics, limitations and future scope. Internet of Things and Cyber-Physical Systems. P. 121–154. DOI
29. What is it YandexGPT 5. Yandexс. URL
30. Model Card Claude 3 Addendumhttps. Anthropic. URL
31. Touvron H., Lavril T., Izacard G., Martinet X., Lachaux M. A., Lacroix T. and Lample G. (2023). Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971.
32. Guo D., Yang D., Zhang H., Song J., Zhang R., Xu R. and He Y. (2025). Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning. arXiv preprint arXiv:2501.12948.
33. Oshrat Yaniv, Yonatan Aumann, Tal Hollander, Oleg Maksimov, Anita Ostroumov, Natali Shechtman and Sarit Kraus (2022) Efficient Customer Service Combining Human Operators and Virtual Agents. arXiv preprint arXiv:2209.05226. DOI
34. Zaid S., Malik A. and Fatima K. (2022) Jewelry Shop Conversational Chatbot. arXiv preprint arXiv:2206.04659. DOI
35. Yutaka Sasaki (2007) The truth of the F-measure. School of Computer Science, University of Manchester MIB, 131 Princess Street, Manchester, M1 7DN.
36. Gorbunova A. A. and Trunov A. S. (2021) Intelligent analysis of applications for technical problems in systems such as service desk, Proc. XV International Industry Scientific and Technical Conference Information Society Technologies, Moscow. P. 302–307. EDN MKMQVI (in Russian).
37. Li Feng-Lin, Minghui Qiu, Haiqing Chen, Xiongwei Wang, Xing Gao, Jun Huang, Juwei Ren, Zhongzhou Zhao, Weipeng Zhao, Lei Wang, Guwei Jin and Wei Chu (2017) Alime assist: An intelligent assistant for creating an innovative e-commerce experience. Proceedings of the 2017 ACM on Conference on Information and Knowledge Management. P. 2495–2498. DOI
38. Gao Y. [et al.] (2023) Retrieval-augmented generation for large language models: A survey // arXiv preprint arXiv:2312.10997. Т. 2.
39. Korbut A. (2018) “Sorry, I cannot understand”: ways of dealing with non-understanding in human-robot interaction, Laboratorium. Journal of Social Research. No 3. P. 57–78. DOI
40. Sharbani Pandit, Jienan Liu, Roberto Perdisci, Mustaque Ahamad (2020) Fighting Voice Spam with a Virtual Assistant Prototype. arXiv preprint arXiv:2008.03554. DOI
41. Yanyan Li, Sara Kim and Eric Sy (2021) A survey on amazon alexa attack surfaces. 2021 IEEE 18th Annual Consumer Communications & Networking Conference (CCNC). IEEE. P. 1–7. DOI
42. Julio Cesar Duarte, Sérgio Colcher (2021) Building a Noisy Audio Dataset to Evaluate Machine Learning Approaches for Automatic Speech Recognition Systems. arXiv preprint arXiv:2110.01425. DOI
43. Arindam Ghosh, Mark Fuhs, Deblin Bagchi, Bahman Farahani, Monika Woszczyna (2022) Low-resource Low-footprint Wake-word Detection using Knowledge Distillation. arXiv preprint arXiv:2207.03331. DOI
2. Larichev O. I. (2002) Theory and methods of decision making. Moskva : Logos. 392 p. (in Russian).
3. Colby K. M., Hilf F. D., Weber S. and Kraemer H. C. (1972) Turing-like indistinguishability tests for the validation of a computer simulation of paranoid processes. Artificial Intelligence. Vol. 3. P. 199–221. DOI
4. Weizenbaum J. (1966) ELIZA — a computer program for the study of natural language communication between man and machine. Communications of the ACM. Vol. 9, No 1. P. 36–45.
5. Colby K., Weber S., Hilf F. D. (1971) Artificial paranoia. Vol. 2, No 1. P. 1–25.
6. Gary G. Hendrix, Earl D. Sacerdoti, Daniel Sagalowicz and Jonathan Slocum (1978) Developing a natural language interface to complex data. ACM Trans. Database Syst. 3, 2 (June 1978). P. 105– 147. DOI
7. Al-Amin Md, Ali Mohammad, Salam Abdus, Khan Arif, Ali Ashraf, Ullah Ahsan, Alam Md Nur and Chowdhury Shamsul (2024). History of generative Artificial Intelligence (AI) chatbots: past, present, and future development. DOI
8. Bhattad H. and Geeta Atkar M. (2021) Review on different types of chatbots. International Research Journal of Modernization in Engineering. 3. DOI
9. Nam HI, Boon Patrick Lee C. and Lian Z. (2019) Journal of Information Technology Management A Publication of the Association of Management comments about the SIRI chatbot: a sentiment analysis of the postings at a microblogging site. Comments about the SIRI chatbot. Journal of Information Technology Management.
10. Radford Alec, Narasimhan Karthik, Salimans Tim and Sutskever Ilya (2018) Improving language understanding by generative pre-training.
11. Maksimova A. S. (2019) Information service user experience: interaction with human and robot operator. Journal of Sociology and Social Anthropology. Vol. 22, No 6. P. 44–68. DOI
12. Karibov A. Ju. (2019) Analysis of algorithms of voice assistants. Journal Bulletin of Science. Vol. 4, No 5(14). P. 492–495. EDN XTXJXA (in Russian).
13. Kovtun O. S. and Srebnyj A. A. (2017) Robotization of banks: on the way to self-service. Scientific-practical researches journal. No 9(9). P. 54–56. EDN YLYRLV (in Russian).
14. Chujko D. V., Majorova E. V. (2020) “Are you a robot?”: ways to respond to robot recognition in a telephone conversation. Ethnopsycholinguistics Journal. No 3. P. 238–251. DOI
15. Romanov A. A. (2019) Dialogue system based on dynamic representation of knowledge graphs. Ekonomika: vchera, segodnia, zavtra. T. 9, No 8A. P. 453–461. DOI
16. Nguen T. M. Ch. (2022) Processing text data with diacritics in dialog decision support systems: dissertation for the degree of candidate of technical sciences. 151 p. EDN DVJYZF (in Russian).
17. Sun, Liangtai, Xingyu Chen, Lu Chen, Tianle Dai, Zichen Zhu and Kai Yu (2022) META-GUI: Towards Multi-modal Conversational Agents on Mobile GUI. Conference on Empirical Methods in Natural Language Processing. DOI
18. Tian Xie, Xinyi Yang, Angela S. Lin, Feihong Wu, Kazuma Hashimoto, Jin Qu, Young Mo Kang, Wenpeng Yin, Huan Wang, Semih Yavuz, Gang Wu, Michael Jones, Richard Socher, Yingbo Zhou, Wenhao Liu, Caiming Xiong (2022) Converse: A Tree-Based Modular Task-Oriented Dialogue System. arXiv preprint arXiv:2203.12187. DOI
19. Subendhu Rongali, Konstantine Arkoudas, Melanie Rubino and Wael Hamza (2022) Training naturalized semantic parsers with very little data. arXiv preprint arXiv:2204.14243. DOI
20. Taylor John Robert (1999) An Introduction to Error Analysis: The Study of Uncertainties in Physical Measurements. University Science Books. P. 128–129.
21. Yaoyuan Vincent Tan, Jason Roy (2019) Bayesian additive regression trees and the General BART model. Statistics in medicine. Т. 38, № 25. – С. 5048–5069. – DOI
22. Krivosheev N. A., Ivanova Ju. A., Spicyn V. G. (2021) Automatic generation of short texts based on the use of neural networks LSTM and SeqGAN. Bulletin of Tomsk State University. Management, Computing and Information Science. No 57. P. 118–130. DOI
23. Lantao Yu, Weinan Zhang, Jun Wang, Yong Yu (2017) SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient. AAAI’17: Proc. of the Thirty-First AAAI Conference on Artificial Intelligence. P. 2852–2858. DOI
24. Hochreiter S., Schmidhuber J. (1997) Long short-term memory. Neural Computation. V. 9, Iss. 8. P. 1735–1780. DOI
25. Chen B., Cherry C. (2014) A Systematic Comparison of Smoothing Techniques for Sentence-Level BLEU. Proc. of the Ninth Work-shop on Statistical Machine Translation. P. 362–367.
26. He Keqing, Jingang Wang, Chaobo Sun and Wei Wu (2022) Unified Knowledge Prompt Pre-training for Customer Service Dialogues. Proceedings of the 31st ACM International Conference on Information & Knowledge Management. P. 4009–4013. DOI
27. Devlin, Jacob, Ming-Wei Chang, Kenton Lee and Kristina Toutanova (2019) BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. Proceedings of NAACL-HLT. P. 4171–4186. DOI
28. Partha Pratim Ray (2023) ChatGPT: A comprehensive review on background, applications, key challenges, bias, ethics, limitations and future scope. Internet of Things and Cyber-Physical Systems. P. 121–154. DOI
29. What is it YandexGPT 5. Yandexс. URL
30. Model Card Claude 3 Addendumhttps. Anthropic. URL
31. Touvron H., Lavril T., Izacard G., Martinet X., Lachaux M. A., Lacroix T. and Lample G. (2023). Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971.
32. Guo D., Yang D., Zhang H., Song J., Zhang R., Xu R. and He Y. (2025). Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning. arXiv preprint arXiv:2501.12948.
33. Oshrat Yaniv, Yonatan Aumann, Tal Hollander, Oleg Maksimov, Anita Ostroumov, Natali Shechtman and Sarit Kraus (2022) Efficient Customer Service Combining Human Operators and Virtual Agents. arXiv preprint arXiv:2209.05226. DOI
34. Zaid S., Malik A. and Fatima K. (2022) Jewelry Shop Conversational Chatbot. arXiv preprint arXiv:2206.04659. DOI
35. Yutaka Sasaki (2007) The truth of the F-measure. School of Computer Science, University of Manchester MIB, 131 Princess Street, Manchester, M1 7DN.
36. Gorbunova A. A. and Trunov A. S. (2021) Intelligent analysis of applications for technical problems in systems such as service desk, Proc. XV International Industry Scientific and Technical Conference Information Society Technologies, Moscow. P. 302–307. EDN MKMQVI (in Russian).
37. Li Feng-Lin, Minghui Qiu, Haiqing Chen, Xiongwei Wang, Xing Gao, Jun Huang, Juwei Ren, Zhongzhou Zhao, Weipeng Zhao, Lei Wang, Guwei Jin and Wei Chu (2017) Alime assist: An intelligent assistant for creating an innovative e-commerce experience. Proceedings of the 2017 ACM on Conference on Information and Knowledge Management. P. 2495–2498. DOI
38. Gao Y. [et al.] (2023) Retrieval-augmented generation for large language models: A survey // arXiv preprint arXiv:2312.10997. Т. 2.
39. Korbut A. (2018) “Sorry, I cannot understand”: ways of dealing with non-understanding in human-robot interaction, Laboratorium. Journal of Social Research. No 3. P. 57–78. DOI
40. Sharbani Pandit, Jienan Liu, Roberto Perdisci, Mustaque Ahamad (2020) Fighting Voice Spam with a Virtual Assistant Prototype. arXiv preprint arXiv:2008.03554. DOI
41. Yanyan Li, Sara Kim and Eric Sy (2021) A survey on amazon alexa attack surfaces. 2021 IEEE 18th Annual Consumer Communications & Networking Conference (CCNC). IEEE. P. 1–7. DOI
42. Julio Cesar Duarte, Sérgio Colcher (2021) Building a Noisy Audio Dataset to Evaluate Machine Learning Approaches for Automatic Speech Recognition Systems. arXiv preprint arXiv:2110.01425. DOI
43. Arindam Ghosh, Mark Fuhs, Deblin Bagchi, Bahman Farahani, Monika Woszczyna (2022) Low-resource Low-footprint Wake-word Detection using Knowledge Distillation. arXiv preprint arXiv:2207.03331. DOI
Опубликован
2025-09-02
Как цитировать
Варламов, А. С. (2025). Обзор технологий, применяемых в интеллектуальных диалоговых системах. Вестник ВГУ. Серия: Системный анализ и информационные технологии, (2), 139-156. https://doi.org/10.17308/sait/1995-5499/2025/2/139-156
Выпуск
Раздел
Современные технологии разработки программного обеспечения
- Авторы сохраняют за собой авторские права и предоставляют журналу право первой публикации работы, которая по истечении 6 месяцев после публикации автоматически лицензируется на условиях Creative Commons Attribution License , которая позволяет другим распространять данную работу с обязательным сохранением ссылок на авторов оригинальной работы и оригинальную публикацию в этом журнале.
- Авторы имеют право размещать их работу в сети Интернет (например в институтском хранилище или персональном сайте) до и во время процесса рассмотрения ее данным журналом, так как это может привести к продуктивному обсуждению и большему количеству ссылок на данную работу (См. The Effect of Open Access).
