Adding context awareness to chatbots with microservices: Case Forest Companion
Islam, Md Rayhan Al (2023)
Islam, Md Rayhan Al
2023
Master's Programme in Computing Sciences
Informaatioteknologian ja viestinnän tiedekunta - Faculty of Information Technology and Communication Sciences
This publication is copyrighted. You may download, display and print it for Your own personal use. Commercial use is prohibited.
Hyväksymispäivämäärä
2023-06-14
Julkaisun pysyvä osoite on
https://urn.fi/URN:NBN:fi:tuni-202306096641
https://urn.fi/URN:NBN:fi:tuni-202306096641
Tiivistelmä
Chatbots are now available on websites and apps where people are trying to sell some services or products. It makes the product owners’ life easier by serving the customers automatically with some questions and answers. The concept of context awareness in chatbots is common in the development sectors for increasing user engagement and better response by the bot. Obtaining complete context awareness is a challenge and needs different techniques such as natural language processing, intent recognition, etc. Also, when the chatbot has different modules like fetching some information from the backend and replying to the user or extracting intent from the conversation, the complete setup of the chatbot becomes complex and hard to maintain. There fore, a good integration structure is which keeps it manageable from time to time.
Developers face difficulties because the chatbots currently available do not exactly provide the whole code to the consumer, rather they sell it as a solution. Certain chatbot frameworks provide an open-source license but still, those need some planning and deployment procedures to make it a complete solution.
In this thesis, we have proposed an architecture model, based on microservices that shows how context awareness can be achieved using a Belief-desire-intention (BDI) model. Furthermore, it is also shown how an extra service can be added to the chatbot. For explaining this, a case study has been done where a location-based game database service is used to integrate with the BDI model and make the chatbot work as a whole. The main goal of this thesis is to explain how we can produce certain software architecture and make the integration process testable, scalable, and less complicated.
Developers face difficulties because the chatbots currently available do not exactly provide the whole code to the consumer, rather they sell it as a solution. Certain chatbot frameworks provide an open-source license but still, those need some planning and deployment procedures to make it a complete solution.
In this thesis, we have proposed an architecture model, based on microservices that shows how context awareness can be achieved using a Belief-desire-intention (BDI) model. Furthermore, it is also shown how an extra service can be added to the chatbot. For explaining this, a case study has been done where a location-based game database service is used to integrate with the BDI model and make the chatbot work as a whole. The main goal of this thesis is to explain how we can produce certain software architecture and make the integration process testable, scalable, and less complicated.