Qubot NLU

Introduction

If you want your bot to be up-to-date and able to process natural text input, then use our innovative technology - Natural Language Processing (NLP). It is NLP that allows your bot to understand the meaning of users' messages and generate appropriate responses. Whether the client wants “two Margherita pizzas and cola” or “cola and cheesecake for two”, the bot will understand and place the correct order.

How NLP works. General information

The essence of the work of NLP comes down to the analysis of the main components of any sentence - entities and intents.

• Entities are any real world objects, e.g. cola (drink), Ukraine (country), 2022 (number), Dmitry (name).

• Intents are the client's wishes described as a sentence, for example, I would like a cola (want), how to get to the theater (finding a way), hello (greeting).

To recognize intentions, machine learning methods are used based on prepared phrases as examples for each class. These methods range from a simple bag-of-words to neural networks of fairly complex architecture. Words, n-grams of words, n-grams of letters (combating typos), the presence of a question mark and others are used as features.

Using combinations of recognized entities and intents, we can confidently state what the client wants and take appropriate actions.

There are some simple examples from a pizzeria bot in the table below:

Message 👩	Entities	Intents	Reply 💻
Hi	-	greet	Hello
Hi, I'm Margo	$NAME = Margaret	greet	Nice to meet you, Margaret!
I would like two Margheritas and a cola	$NUMBER = 2 $NAME = Margherita $DRINK = cola	want	Would you like to place an order for: 2 Margherita pizzas and one cola?
I would like	-	want	What would you like?
I would like to go to Ukraine	$COUNTRY = Ukraine	want	The distance from you to Ukraine is 4768.95 km. It will be most convenient to fly by plane.

The bot gives meaningful answers in every given example despite similar intentions and recognized entities. In the intent greet, we understand that $NAME is the customer's name, while in the intent want we understand that $NAME is the name of the pizza.

Improving bot's intellectual development

Описанные ранее общие сведения применяются для работы NLP у многих компаний, это довольно простая схема, только у неё есть недостаток - бот не способен ориентироваться в контексте. Это значит что во всех примерах из таблицы 1 всегда будет один и тот же ответ.

Для предоставления боту большего интеллекта в NLP от QuData используются забываемые намерения, а также механизм сохраняющий историю общения с клиентом.

Забываемые намерения - это такие намерения, которые происходят вне основного направления бота и забываются при первом же обычном намерении.

Благодаря этому Вам бот может ориентироваться в контексте, а также обрабатывать более сложные цепочки диалогов, например, такие:

Желтым выделены забываемые намерения.

Message 👩	Entities	Intents	Reply 💻
I want fanta	$DRINKS = fanta	want	How many bottles of fanta do you want?
How much does it cost?	-	[ want, what-is-the-price ]	Its price is 20 UAH.
Then 3	$NUMBER = 3	[ want, number ]	I added 3 bottles of fanta to the order

Message 👩	Entities	Intents	Reply 💻
/start	-	start	Hello. My name is Bot. What is your name?
My name is Katya	$NAME = Katherine	[start, my name is]	ОIt's nice to meet you, Katherine.
Hi	-	greet	Always happy to say hello again.
My name is Masha	$NAME = Maria	my name is	I see... So your name is Maria?
No.	-	deny	What is your name then?
Dasha	$NAME = Daria	name	I see... So your name is Daria?
Yes	-	yes	Okay, Daria, I'll remember that.
My name is Dasha	$NAME = Daria	my name is	Yes, Daria, I know.
I want fanta	$DRINKS = fanta	want	How many bottles of fanta do you want?