Implementation of Generative AI Technology in Modern Call Centers with the LLM Model
DOI:
https://doi.org/10.55927/marcopolo.v3i12.182Keywords:
Generative AI, Large Language Model, Call Center, Embedding, Vector Database, GPT-4Abstract
Modern call centers face challenges in providing fast, accurate, and personalized services to users. One innovative solution is the application of generative Artificial Intelligence (AI) technology based on Large Language Models (LLMs) such as GPT-4 or Mixtral. This study proposes an AI call center pipeline architecture that combines embedding technology, a vector database (FAISS), and LLMs to automatically generate natural language responses. The architecture utilizes Blazor (ASP.NET) on the front-end and Python on the back-end, enabling flexible integration between the user interface and intelligent server-side processing. With this approach, the system is expected to improve response speed, reduce human operator workload, and enhance user satisfaction.
References
Brown, T. B., Mann, B., Ryder, N., Subbiah, M., et al. (2020). Language Models are Few-Shot Learners. Advances in Neural Information Processing Systems, 33, 1877–1901.
Gunawan, D., & Sutopo, J. (2020). Penggunaan Chatbot untuk meningkatkan kualitas layanan pelanggan. Jurnal Teknologi dan Sistem Komputer, 8(1), 23-28.
Johnson, J., Douze, M., & Jégou, H. (2019). Billion-scale similarity search with GPUs. IEEE Transactions on Big Data, 7(3), 535–547.
Kusnadi, A., Setiawan, A., & Rahman, T. (2021). Implementasi teknologi chatbot pada layanan pelanggan berbasis kecerdasan buatan. Jurnal Teknologi Informasi dan Ilmu Komputer (JTIIK), 8(2), 215-222.
Reimers, N., & Gurevych, I. (2019). Sentence-BERT: Sentence embeddings using Siamese BERT-networks. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing (EMNLP), 3982–3992.
