
Тема выпуÑкной квалификационной работы: «Прототип чат-бота Ð´Ð»Ñ Ð¾Ð±Ñ€Ð°Ð·Ð¾Ð²Ð°Ñ‚ÐµÐ»ÑŒÐ½Ð¾Ð³Ð¾ учреждениÑ». Ð”Ð°Ð½Ð½Ð°Ñ Ñ€Ð°Ð±Ð¾Ñ‚Ð° поÑвÑщена разработке чат-бота Ð´Ð»Ñ Ð¼ÐµÑÑенджера, раÑÑмотрены возможноÑти Ð¾Ð±ÑƒÑ‡ÐµÐ½Ð¸Ñ Ñ‡Ð°Ñ‚-бота Ñ Ñ†ÐµÐ»ÑŒÑŽ ÑƒÐ»ÑƒÑ‡ÑˆÐµÐ½Ð¸Ñ ÐµÐ³Ð¾ коммуникативных навыков, раÑширение функционала, чтобы Ñотрудники, Ñтуденты и абитуриенты могли узнавать вÑÑŽ необходимую информацию об универÑитете. Задачи, которые решалиÑÑŒ в ходе иÑÑледованиÑ: 1. ПоÑтановка и формальное опиÑание задачи работы. 2. ОпиÑание Ñтруктуры нейронных Ñетей. 3. Обзор методов обучениÑ. 4. Ðнализ результатов обучениÑ. 5. Обзор библиотек глубокого обучениÑ.6. ОпиÑание предварительной обработки еÑтеÑтвенного Ñзыка. 7. ОпиÑание предобработки текÑта. 8. Ð ÐµÐ°Ð»Ð¸Ð·Ð°Ñ†Ð¸Ñ Ð¿Ñ€Ð¾Ñ‚Ð¾Ñ‚Ð¸Ð¿Ð° чат-бота. Ð’ работе раÑÑматриваетÑÑ Ð¼Ð¾Ð´ÐµÐ»Ð¸Ñ€Ð¾Ð²Ð°Ð½Ð¸Ðµ работы чат-бота Ñ Ð¿Ñ€Ð¸Ð¼ÐµÐ½ÐµÐ½Ð¸ÐµÐ¼ Ñзыка программированиÑ PythonÂ Ð´Ð»Ñ Ð¾ÑущеÑÑ‚Ð²Ð»ÐµÐ½Ð¸Ñ Ð´Ð¸Ð°Ð»Ð¾Ð³Ð° между чат-ботом и клиентом, который должен быть макÑимально приближен к разговору между Ð´Ð²ÑƒÐ¼Ñ Ð»ÑŽÐ´ÑŒÐ¼Ð¸. ПрименÑÑŽÑ‚ÑÑ Ð¸Ð½Ñ„Ð¾Ñ€Ð¼Ð°Ñ†Ð¸Ð¾Ð½Ð½Ñ‹Ðµ технологии Ð´Ð»Ñ Ð±Ð°Ð»Ð°Ð½Ñировки нагрузки и ÑÐ¾Ð·Ð´Ð°Ð½Ð¸Ñ Ð¾Ñ‚ÐºÐ°Ð·Ð¾ÑƒÑтойчивой ÑиÑтемы.
Topic of the final qualification work: "Prototype of a chat-bot for an educational institution". This work is devoted to the development of a chat bot for a messenger, the possibilities of teaching a chat bot to improve its communication skills, expanding the functionality so that employees, students and applicants can find out all the necessary information about the university are considered. Tasks that were solved in the course of the study: 1. Statement and formal description of the task of the work. 2. Description of the structure of neural networks. 3. Review of teaching methods. 4. Analysis of learning outcomes. 5. Overview of deep learning libraries. 6. Description of natural language preprocessing. 7. Description of text preprocessing. 8. Implementation of the chatbot prototype. The work deals with modeling the work of a chat bot using the Python programming language to carry out a dialogue between a chat bot and a client, which should be as close as possible to a conversation between two people. Information technologies are used to balance the load and create a fault-tolerant system.
ÐнÑоÑмаÑионнÑе ÑиÑÑемÑ, text classification, меÑÑенджеÑ, ÑаÑ-боÑ, messenger, ÐÑогÑаммиÑÐ¾Ð²Ð°Ð½Ð¸Ñ ÑзÑки, обÑабоÑка еÑÑеÑÑвенного ÑзÑка, classification algorithms, клаÑÑиÑикаÑÐ¸Ñ ÑекÑÑа, ÐейÑоннÑе ÑеÑи, chat-bot, virtual assistant, алгоÑиÑÐ¼Ñ ÐºÐ»Ð°ÑÑиÑикаÑии, natural language processing, виÑÑÑалÑнÑй помоÑник
ÐнÑоÑмаÑионнÑе ÑиÑÑемÑ, text classification, меÑÑенджеÑ, ÑаÑ-боÑ, messenger, ÐÑогÑаммиÑÐ¾Ð²Ð°Ð½Ð¸Ñ ÑзÑки, обÑабоÑка еÑÑеÑÑвенного ÑзÑка, classification algorithms, клаÑÑиÑикаÑÐ¸Ñ ÑекÑÑа, ÐейÑоннÑе ÑеÑи, chat-bot, virtual assistant, алгоÑиÑÐ¼Ñ ÐºÐ»Ð°ÑÑиÑикаÑии, natural language processing, виÑÑÑалÑнÑй помоÑник
| selected citations These citations are derived from selected sources. This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | 0 | |
| popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network. | Average | |
| influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | Average | |
| impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network. | Average |
