A Conversation History-Based Q&A Cache Mechanism for Multi-Layered Chatbot Services
Source abstract
Abstract
Chatbot technologies have made our lives easier. To create a chatbot with high intelligence, a significant amount of knowledge processing is required. However, this can slow down the reaction time; hence, a mechanism to enable a quick response is needed. This paper proposes a cache mechanism to improve the response time of the chatbot service; while the cache in CPU utilizes the locality of references within binary code executions, our cache mechanism for chatbots uses the frequency and relevance information which potentially exists within the set of Q&A pairs. The proposed idea is to enable the broker in a multi-layered structure to analyze and store the keyword-wise relevance of the set of Q&A pairs from chatbots. In addition, the cache mechanism accumulates the frequency of the input questions by monitoring the conversation history. When a cache miss occurs, the broker selects a chatbot according to the frequency and relevance, and then delivers the query to the selected chatbot to obtain a response for answer. This mechanism showed a significant increase in the cache hit ratio as well as an improvement in the average response time.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: IoT and Edge/Fog Computing · Online Learning and Analytics · AI in Service Interactions
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Intelligent Things Lab, Department of Computer Science, Konkuk University, 120 Neungdong-ro, Gwangjin-gu, Seoul 05029, Korea
Funding
Ministry of Science and ICT, South Korea
References (25)
Show source-provided references
1. Makhkamova, O., Lee, K.-H., Do, K., and Kim, D. (2020, January 19–22). Deep Learning-based Multi-Chatbot Broker for Q&A Improvement of Video Tutoring Assistant. Proceedings of the 2020 IEEE International Conference on Big Data and Smart Computing (BigComp), Busan, Korea.10.1109/BigComp48618.2020.00-71 ↗
2. Making sense of MOOCs: Musings in a maze of myth, paradox and possibility10.5334/2012-18 ↗
3. Glusac, D., Karuović, D., and Milanov, D. (, January 27–30). Massive open online courses—Pedagogical overview. the Proceedings of the 2015 16th International Carpathian Control Conference (ICCC), Szilvasvarad, Hungary.10.1109/CarpathianCC.2015.7145063 ↗
4. Theresa, Z., and Meinel, C. (2021, January 14–18). Towards personalized, diaolgue-based system supported learning for MOOCs. Proceedings of the Learning Ideas Conference, New York, NY, USA.
5. Online learning in higher education: Exploring advantages and disadvantages for engagement10.1007/s12528-018-9179-z ↗
6. Park, K., Kim, D., Makhkamova, O., and Baatarzorig, J. (2019). Design of Chatbot System for Internet Lecture Video, The Korean Institute of Information Scientists and Engineers.
7. Cache memories10.1145/356887.356892 ↗
8. Sathiyamoorthi, V., and Bhaskaran, V.M. (2012, January 19–21). Web caching through modified cache replacement algorithm. Proceedings of the 2012 International Conference on Recent Trends in Information Technology, Chennai, India.10.1109/ICRTIT.2012.6206749 ↗
9. Boyanov, M., Koychev, I., Nakov, P., Moschiti, A., and Martino, G.D.S. (2017, January 4–6). Building chatbots from forum data: Model selection using question answering metrics. Proceedings of the International Conference Recent Advances in Natural Language Processing RANLP, Varna, Bulgaria.10.26615/978-954-452-049-6_018 ↗
10. Rana, M. (1994). EagleBot: A Chatbot Based Multi-tier Question Answering System for Retrieving Answers from Heterogeneous Sources Using BERT. [Master’s Thesis, Georgia Southern University].
11. Analyzing feedback processes in an online teaching and learning environment: An exploratory study10.1007/s10734-009-9247-4 ↗
12. Feng, W., Tang, J., Liu, T.X., Zhang, S., and Guan, J. (February, January 27). Understanding dropouts in MOOCs. Proceedings of the 33rd AAAI Conference on Artificial Intelligence (AAAI’19), Hilton Hawaiian Village, Honolulu, HI, USA.
13. Loghin, D., Ramapantulu, L., and Teo, Y.M. (2019, January 8–13). Towards Analyzing the Performance of Hybrid Edge-Cloud Processing. Proceedings of the 2019 IEEE International Conference on Edge Computing (EDGE), Milan, Italy.10.1109/EDGE.2019.00029 ↗
14. Borsci, S., Malizia, A., Schmettow, M., Velde, F., Tariverdiyeva, G., Balaji, D., and Chamberlain, A. (2021). The Chatbot Usability Scale: The Design and Pilot of a Usability Scale for Interaction with AI-Based Conversational Agents. Pers. Ubiquit. Comput., 1–25.10.1007/s00779-021-01582-9 ↗
15. Kowsher, M., Tahabilder, A., Sanjid, Z.I., Prottasha, N.J., and Sarker, M.H. (2020, January 26–29). Knowledge-Base Optimization to Reduce the Response Time of Bangla Chatbot. Proceedings of the 2020 Joint 9th International Conference on Informatics, Electronics & Vision (ICIEV) and 2020 4th International Conference on Imaging, Vision & Pattern Recognition (icIVPR), Kitakyushu, Japan.10.1109/ICIEVicIVPR48672.2020.9306602 ↗
16. The cache performance and optimizations of blocked algorithms10.1145/106974.106981 ↗
17. Meizhen, W., Yanlei, S., and Yue, T. (2013, January 14–16). The design and implementation of LRU-based web cache. Proceedings of the 2013 8th International Conference on Communications and Networking in China (CHINACOM), Guilin, China.
18. Estimating Instantaneous Cache Hit Ratio Using Markov Chain Analysis10.1109/TNET.2012.2227338 ↗
19. Tran, A.-T., Lakew, D.S., Nguyen, T.-V., Tuong, V.-D., Truong, T.P., Dao, N.-N., and Cho, S. (2021, January 2). Hit Ratio and Latency Optimization for Caching Systems: A Survey. Proceedings of the 2021 International Conference on Information Networking (ICOIN), Jeju Island, Korea.10.1109/ICOIN50884.2021.9334019 ↗
20. Shi, L., Wei, L., Ye, H.-Q., and Shi, Y. (2006, January 13–16). Measurements of Web Caching and Applications. Proceedings of the 2006 International Conference on Machine Learning and Cybernetics, Dalian, China.10.1109/ICMLC.2006.258834 ↗
21. Ma, H., Wang, S., Li, M., and Li, N. (2015, January 26–30). Enhancing Graph-Based Keywords Extraction with Node Association. Proceedings of the on the Move to Meaningful Internet Systems: OTM 2015 Workshops, Rhodes, Greece.
22. Marietto, M.D.G.B., Aguiar, R.V., Barbosa, G.D.O., Botelho, W.T., Pimentel, E., Franca, R.D.S., and Da Silva, V.L. (2013). Artificial Intelligence Markup Language: A Brief Tutorial. arXiv.10.5121/ijcses.2013.4301 ↗
23. Li, W., and Zhao, J. (2016, January 8–10). TextRank Algorithm by Exploiting Wikipedia for Short Text Keywords Extraction. Proceedings of the 2016 3rd International Conference on Information Science and Control Engineering (ICISCE), Beijing, China.10.1109/ICISCE.2016.151 ↗
24. Geetha, K., Gounden, N.A., and Monikandan, S. (2009, January 8–10). SEMALRU: An Implementation of modified web cache replacement algorithm. Proceedings of the 2009 World Congress on Nature & Biologically Inspired Computing (NaBIC), Bhubaneswar, India.10.1109/NABIC.2009.5393711 ↗
25. (2021, March 03). Google Code, AIML Foundation Archive. Available online: https://code.google.com/archive/p/aiml-en-us-foundation-alice/downloads.