Your browser doesn't support javascript.
loading
Discovering patterns and trends in customer service technologies patents using large language model.
Kim, Chaeyeon; Lee, Juyong.
Afiliação
  • Kim C; Department of Industrial and Systems Engineering, College of Engineering, Changwon National University, Changwondaehak-ro 20, Changwon-si, Gyeonsangnam-do, 51140, South Korea.
  • Lee J; Department of Industrial and Systems Engineering, College of Engineering, Changwon National University, Changwondaehak-ro 20, Changwon-si, Gyeonsangnam-do, 51140, South Korea.
Heliyon ; 10(14): e34701, 2024 Jul 30.
Article em En | MEDLINE | ID: mdl-39149018
ABSTRACT
The definition of service has evolved from a focus on material value in manufacturing before the 2000s to a customer-centric value based on the significant growth of the service industry. Digital transformation has become essential for companies in the service industry due to the incorporation of digital technology through the Fourth Industrial Revolution and COVID-19. This study utilised Bidirectional Encoder Representations from Transformer (BERT) to analyse 3029 international patents related to the customer service industry and digital transformation registered between 2000 and 2022. Through topic modelling, this study identified 10 major topics in the customer service industry and analysed their yearly trends. Our findings show that as of 2022, the trend with the highest frequency is user-centric network service design, while cloud computing has experienced the steepest increase in the last five years. User-centric network services have been steadily developing since the inception of the Internet. Cloud computing is one of the key technologies being developed intensively in 2023 for the digital transformation of customer service. This study identifies time series trends of customer service industry patents and suggests the effectiveness of using BERTopic to predict future trends in technology.
Palavras-chave

Texto completo: 1 Base de dados: MEDLINE Idioma: En Ano de publicação: 2024 Tipo de documento: Article

Texto completo: 1 Base de dados: MEDLINE Idioma: En Ano de publicação: 2024 Tipo de documento: Article