A Conversation History-Based Q&A Cache Mechanism for Multi-Layered Chatbot Services

Chatbot technologies have made our lives easier. To create a chatbot with high intelligence, a significant amount of knowledge processing is required. However, this can slow down the reaction time; hence, a mechanism to enable a quick response is needed. This paper proposes a cache mechanism to impr...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Ozoda Makhkamova, Doohyun Kim
Formato: article
Lenguaje:EN
Publicado: MDPI AG 2021
Materias:
T
Acceso en línea:https://doaj.org/article/a35f0d76c0d94134a66ac8affe858a94
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:a35f0d76c0d94134a66ac8affe858a94
record_format dspace
spelling oai:doaj.org-article:a35f0d76c0d94134a66ac8affe858a942021-11-11T15:04:10ZA Conversation History-Based Q&A Cache Mechanism for Multi-Layered Chatbot Services10.3390/app112199812076-3417https://doaj.org/article/a35f0d76c0d94134a66ac8affe858a942021-10-01T00:00:00Zhttps://www.mdpi.com/2076-3417/11/21/9981https://doaj.org/toc/2076-3417Chatbot technologies have made our lives easier. To create a chatbot with high intelligence, a significant amount of knowledge processing is required. However, this can slow down the reaction time; hence, a mechanism to enable a quick response is needed. This paper proposes a cache mechanism to improve the response time of the chatbot service; while the cache in CPU utilizes the locality of references within binary code executions, our cache mechanism for chatbots uses the frequency and relevance information which potentially exists within the set of Q&A pairs. The proposed idea is to enable the broker in a multi-layered structure to analyze and store the keyword-wise relevance of the set of Q&A pairs from chatbots. In addition, the cache mechanism accumulates the frequency of the input questions by monitoring the conversation history. When a cache miss occurs, the broker selects a chatbot according to the frequency and relevance, and then delivers the query to the selected chatbot to obtain a response for answer. This mechanism showed a significant increase in the cache hit ratio as well as an improvement in the average response time.Ozoda MakhkamovaDoohyun KimMDPI AGarticlechatbotmulti-layer servicecache mechanismresponse timechatbot cacheTechnologyTEngineering (General). Civil engineering (General)TA1-2040Biology (General)QH301-705.5PhysicsQC1-999ChemistryQD1-999ENApplied Sciences, Vol 11, Iss 9981, p 9981 (2021)
institution DOAJ
collection DOAJ
language EN
topic chatbot
multi-layer service
cache mechanism
response time
chatbot cache
Technology
T
Engineering (General). Civil engineering (General)
TA1-2040
Biology (General)
QH301-705.5
Physics
QC1-999
Chemistry
QD1-999
spellingShingle chatbot
multi-layer service
cache mechanism
response time
chatbot cache
Technology
T
Engineering (General). Civil engineering (General)
TA1-2040
Biology (General)
QH301-705.5
Physics
QC1-999
Chemistry
QD1-999
Ozoda Makhkamova
Doohyun Kim
A Conversation History-Based Q&A Cache Mechanism for Multi-Layered Chatbot Services
description Chatbot technologies have made our lives easier. To create a chatbot with high intelligence, a significant amount of knowledge processing is required. However, this can slow down the reaction time; hence, a mechanism to enable a quick response is needed. This paper proposes a cache mechanism to improve the response time of the chatbot service; while the cache in CPU utilizes the locality of references within binary code executions, our cache mechanism for chatbots uses the frequency and relevance information which potentially exists within the set of Q&A pairs. The proposed idea is to enable the broker in a multi-layered structure to analyze and store the keyword-wise relevance of the set of Q&A pairs from chatbots. In addition, the cache mechanism accumulates the frequency of the input questions by monitoring the conversation history. When a cache miss occurs, the broker selects a chatbot according to the frequency and relevance, and then delivers the query to the selected chatbot to obtain a response for answer. This mechanism showed a significant increase in the cache hit ratio as well as an improvement in the average response time.
format article
author Ozoda Makhkamova
Doohyun Kim
author_facet Ozoda Makhkamova
Doohyun Kim
author_sort Ozoda Makhkamova
title A Conversation History-Based Q&A Cache Mechanism for Multi-Layered Chatbot Services
title_short A Conversation History-Based Q&A Cache Mechanism for Multi-Layered Chatbot Services
title_full A Conversation History-Based Q&A Cache Mechanism for Multi-Layered Chatbot Services
title_fullStr A Conversation History-Based Q&A Cache Mechanism for Multi-Layered Chatbot Services
title_full_unstemmed A Conversation History-Based Q&A Cache Mechanism for Multi-Layered Chatbot Services
title_sort conversation history-based q&a cache mechanism for multi-layered chatbot services
publisher MDPI AG
publishDate 2021
url https://doaj.org/article/a35f0d76c0d94134a66ac8affe858a94
work_keys_str_mv AT ozodamakhkamova aconversationhistorybasedqacachemechanismformultilayeredchatbotservices
AT doohyunkim aconversationhistorybasedqacachemechanismformultilayeredchatbotservices
AT ozodamakhkamova conversationhistorybasedqacachemechanismformultilayeredchatbotservices
AT doohyunkim conversationhistorybasedqacachemechanismformultilayeredchatbotservices
_version_ 1718437161537110016