|
|
Bimonthly Since 1986 |
ISSN 1004-9037
|
|
|
|
|
Publication Details |
Edited by: Editorial Board of Journal of Data Acquisition and Processing
P.O. Box 2704, Beijing 100190, P.R. China
Sponsored by: Institute of Computing Technology, CAS & China Computer Federation
Undertaken by: Institute of Computing Technology, CAS
Published by: SCIENCE PRESS, BEIJING, CHINA
Distributed by:
China: All Local Post Offices
|
|
|
|
|
|
|
|
|
|
Abstract
With the advent of ChatGPT, the market for chatbot systems was revitalized. However, the existing chatbot system conducts scenario-based learning through vast open data. Therefore, generating an answer corresponding to a specific conversation takes time and effort. In this paper, we propose a chatbot system for civil complaint question and answer in a particular field. pa This per builds by converging topic modeling and sentence generation models to improve the performance of the chatbot system. In addition, it is made to enable natural conversation by learning daily conversation and emotional sentence datasets. Finally, in this paper, an individual database is provided to process the personal information of the civil complaint response service.
Keyword
Chatbot System, Topic extraction model, Generative Pre–Training (GPT), Database
PDF Download (click here)
|
|
|
|
|