loading page

Design of a large language model for improving customer service in telecom operators
  • +2
  • xiaol Ma,
  • RuQiang Zhao,
  • Liu Ying,
  • Congjian Deng,
  • Dequan Du
xiaol Ma
China Telecom Corporation Limited
Author Profile
RuQiang Zhao
Guangdong University of Technology
Author Profile
Liu Ying
China Telecom Corporation Limited

Corresponding Author:[email protected]

Author Profile
Congjian Deng
Xi'an University of Electronic Science and Technology
Author Profile
Dequan Du
China Telecom Corporation Limited
Author Profile

Abstract

For telecom operators, customer service is integral to their business. Traditional service systems, responsible for managing large amounts of data and complex knowledge bases, need more time retrieval processes and a lack of precision, hindering their ability to respond quickly to customer requests. To address these issues, this paper uses the LangChain programming framework to create a customized Large Language Model (LLM) specifically for the customer service context of telecom operators. It also uses reinforcement learning to improve the performance of the models and reduce the production of incorrect information. Experimental results show that the acceptance of our model’s recommended knowledge has increased from 15% to 70%, confirming its reliable operation in resource-constrained environments.
Submitted to Electronics Letters
19 Feb 2024Review(s) Completed, Editorial Evaluation Pending
25 Feb 2024Editorial Decision: Revise Major
21 Mar 2024Review(s) Completed, Editorial Evaluation Pending
12 Apr 2024Editorial Decision: Revise Minor
23 Apr 20242nd Revision Received
25 Apr 2024Submission Checks Completed
25 Apr 2024Assigned to Editor
25 Apr 2024Review(s) Completed, Editorial Evaluation Pending
28 Apr 2024Editorial Decision: Accept