Scholarly record
RESEARCH AND DEVELOPMENT OF A CUSTOMIZABLE CHAT BOT FOR BANKS
Abstract
This article describes the peculiarities of developing a customizable chat bot. It reviews and compares approaches to developing a chat bot. It describes the features of using Software Development Kit (SDK), which can be easily implemented by a technician into a company's mobile application. Such a chat bot can be used in banks applications, as well as in any other applications which require assistance to the user in solving his/her problem. The chat bot will be able to solve typical user cases, but in more specific situations the presence of a technician-operator is required. It shows how to use neural networks to determine the topic of the dialog based on the user's message. At the same time, the possibility of the user to get support from the operator if necessary, if he chooses an appropriate action or explicitly asks the bot for it by writing, is described. The advantages of using a customized chat bot are shown, such as a reduction in the number of operators, reduced waiting time of the user, the ability of operators to focus on specific, narrow areas, small financial resources to obtain significant results, the simplicity of the vocabulary, the unity of the dialogue, etc. A separate figure demonstrates the work of the support department using a chat bot. Next steps to continue working with iOS devices are presented.
Publication Impact Profile
Publication details
References2
Tugusheva N.A., Chat-bot usage in various usage of everyday life, The Young Scientist, vol. 21, pp. 36-39, 2017. (in Russ.)
Kovrigina L.Y., Mouromtsev D.I., Understanding of natural language in dialog systems: syntactic analysis aspects, Young scientist's scientific works almanac, XLVII scientific educational and methodical conference of ITMO University, book 2, pp. 384-386, 2018. (in Russ.)
View or Download full articleAccess options
SWS access login
Login as SWS Scientific CommitteeLogin as SWS Scientific PartnerLogin as SWS AuthorAuthors and approved SWS contributors will read and export their own linked papers after identity matching by SWS profile, email and SGEM GlobalID.
For librarian assistance: [email protected]
Purchase Instant Access
- Article can be downloaded after successful payment.
- Article may be used according to SWS library access terms.
- Article cannot be redistributed.

