Algorithmic support of a chatbot for consulting potential applicants

Abstract

Algorithmic support of a chatbot for consulting potential applicants

Kushchiy D.N.

Incoming article date: 10.06.2023

The relevance of creating a chatbot for advising applicants, promoting the university brand and raising awareness about the university is considered. The basic principles of the chatbot functioning are determined. Modeling of the sequence of processes using IDEF0 and UML is performed. The article contains a description of the chatbot algorithm. Activity and state diagrams are used to visualize this algorithm. The graphical interpretation of the logic of the interaction of the system elements is performed at the IDEF3 documentation level. A physical model for storing the data necessary for consultation is presented; the purpose of the tables obtained is described. The issues of fuzzy search by keywords are considered. The article describes the error correction process using the n-gram distance metric and the Damerau-Levenshtein metric. The functioning of the chatbot in the consultation mode when searching for keywords with errors in the user's message is demonstrated.

Keywords: chatbot, dialog system, messenger, natural language processing, fuzzy search, Damerau-Levenstein distance, n-gram