SciELO - Scientific Electronic Library Online

 
 número51Análisis comparativo de Técnicas de Machine Learning para la predicción de casos de deserción universitaria índice de autoresíndice de assuntosPesquisa de artigos
Home Pagelista alfabética de periódicos  

Serviços Personalizados

Journal

Artigo

Indicadores

Links relacionados

  • Não possue artigos similaresSimilares em SciELO

Compartilhar


RISTI - Revista Ibérica de Sistemas e Tecnologias de Informação

versão impressa ISSN 1646-9895

Resumo

IPARRAGUIRRE-VILLANUEVA, Orlando; OBREGON-PALOMINO, Luz; PUJAY-IGLESIAS, Wilson  e  CABANILLAS-CARBONELL, Michael. Intelligent agent for incident management. RISTI [online]. 2023, n.51, pp.99-115.  Epub 30-Set-2023. ISSN 1646-9895.  https://doi.org/10.17013/risti.51.99-115.

An intelligent agent uses artificial intelligence (AI) to dialogue with users; incidents are interruptions that arise and prevent users from making use of information technology (IT); Latin America has 15. 5% of customer incident responses; in Europe, each year IT security incidents have seen a 41% increase since 2019, which are classified as High and Very High severity. The purpose of this study was to implement an intelligent agent to improve Incident Management, reduce the number of unresolved incidents, reduce resolution time, and increase user satisfaction. To achieve this objective, a quantitative approach and a pre-experimental design were followed; questionnaires were used to collect data, and then all data were subjected to statistical analysis to validate the hypothesis. Experts verified the reliability and validity of the instruments used. In addition, the Scrum framework was used for the development of the intelligent solution. The achievement of the implementation was obtained through the incorporation of various technologies such as Dialogflow, Webhook, PostgreSQL; finally, an intelligent agent capable of attending incidents reported by users was obtained, assigning the task in an automated manner. The development of this study minimized the number of unresolved incidents per day by 14%, reduced the incident resolution time by 63% and increased user satisfaction to "Satisfied" to 43.3% and "Very Satisfied" to 57.7%. Finally, it can be concluded that this work provides an important contribution for future implementations of designs or developments related to the automation of incident management through intelligent agents.

Palavras-chave : Intelligent Chatbot; Agent; Incident; Management.

        · resumo em Espanhol     · texto em Espanhol     · Espanhol ( pdf )