Research on Personalized Insurance Intelligent Customer Service Dialogue Generation Based on Large Language Models
Year: 2025
Type: conference-paper
Abstract: Artificial intelligence is challenging many areas, including insurance. Insurers who want to secure the highest customer satisfaction level and service quality can no longer ignore the necessity of personal intelligent customer service. But, on the flip side, these existing systems still have problems with comprehensive knowledge, human-like dialogue, and actual estimation. This paper presents a technique for developing personalized dialogue in intelligent customer service applications to the insurance business. Our model establishes an insurance knowledge base and utilizes the retrieval-augmented generation approach. In addition, we create dynamic memory by connecting the long short-term memory module, allowing the system to retrieve and modify customer's information while interacting with them in real time. As a result, intelligent models offer much more natural and engaging conversations, adjusting to specific tones and retaining individual emotions. These virtual assistants customize the responses according to the customer profiles. Hence, they give appropriate, professional, and personalized insurance advice.
Authors: Yuanhao Li, Huilin Zhao, Jiayu Lin, Zijun Zhou, Yuanchao Zhang
Institutions: Lanzhou University of Finance and Economics, Wuhan University
Language: English
Topic: Speech and dialogue systems
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
Funders: Lanzhou University, Wuhan University
OpenAlex ID: W4411010159