Natural Language Recognition Technologies for the Development of a Voice Assistant

Yelena SPIRINA, Adilkhan ZHUMABEKOV, Nadezhda GORBUNOVA, Dinara Кazimova, Ruslana Selezneva

2022

DOI 10.52209/1609-1825_2022_4_443

Data confidence 70 medium

How this score is calculated

It is built from checkable properties of the record itself: whether the article has a DOI, how many independent sources confirmed its data, whether the required fields are filled in, and how recent the latest confirmation is. Disagreement between sources and a missing identifier lower it. A value of 80 or above means the record was published without further checking; 60 to 79 means it is published at reduced confidence, with a manual check advisable. A record verified by an editor by hand is never pushed below 90 by a recalculation. This scores our data about the article, not the article itself.

Abstract

The paper discusses the basic technologies of natural language recognition and the features of creating a voice assistant based on the DialogFlow cloud service. As an example, an application has been developed a voice assistant «IT-entrant», which answers entrants' questions about educational programs in the field of IT at Karaganda University named after E.A. Buketov. The article analyzes the principles of the popular voice assistants such as Google Assistant, Amazon Echo (Alexa), Microsoft Cortana, Yandex Alisa. It is revealed that the natural language recognition platform Google DialogFlow is a convenient tool for developing a dialog user interface in mobile applications. The algorithm for developing a voice assistant based on the DialogFlow cloud service is considered