Communication of
Promobot robots

Promobot can chat and engage in the conversation with any person on any topic via its linguistic database. There are three operating principles of Promobot’s linguistic database: first it’s speech recognition, then processing the question and then searching for the answer.

What is a linguistic base?

The linguistic database (or the linguistic base) consists of numerous replies from both sides ― the person’s and the robot’s. These replies are combined under rules. For example:
icon-dialogue-1

— Hello, robot

icon-dialogue-2

— Hello. My name is Promobot.

Robot can give different responses to the same phrase:
icon-dialogue-3

— Hello, robot

icon-dialogue-2

— It’s a nice day for a good conversation!

Rule is a set of a robot’s replies which it uses to answer specific phrases.

One rule can contain several replies, as with the “Hello, robot” rule above. It can also contain just one reply. For example, when a robot is asked about the bathroom and the bathroom location is always the same, the robot will always give directions to that same location.

How the linguistic database works

Promobot’s linguistic base has 5 basic levels and numerous sublevels within the basic levels. In a matter of seconds robot searches across these levels to find an answer to the question – from first level to the last one.

1. First level contains the robot’s responses to its workplace. This level is created individually for each client: “Where to find X?”, “How to buy X?”, “What discounts do you have?”, “Where is the departure gate?”, etc.

2. Second level contains general questions to the robot. It is a unified base of all the robots: “How are you?”, “What are you doing?”, “Tell me a story”, “Who are you?”, etc.

3. Third level is the search engine on the Internet. If Promobot can’t find an answer at first two levels, it starts to look for it on the Internet: «“What is a synchrotron?”, “Who is the president of Turkey?”, “Weather today”

It’s important to note that the robot uses only relevant sources, not the very first related piece of data found on the Internet.

4. Fourth level contains low priority questions. If the robot can’t find answers on the Internet (usually that involves questions with no clear answer, absurd questions), it gives common answers highlighting basic words.
icon-dialogue-4

— How much does it cost to parachute jump on Jupiter?

icon-dialogue-2

— I think it is expensive.

A person can say something indistinctive. In this case the robot can change the topic or use additional phrase, adjusted by the owner:
icon-dialogue-5

— Yadda yadda yadda.

icon-dialogue-2

— What you said here is cute.
Have you heard about our discount system?

5. Fifth level contains all the requests that weren’t recognized by the robot. It can happen because of a person’s indistinct speech, language change or different external factors.
icon-dialogue-6

— fgjhrkkflkhwrgwjfsml.

icon-dialogue-2

— Please repeat your request.

Additional phrases and options

Additional phrases assist in operation, answering user’s questions, channeling the conversation, allow to engage with the person and add compliments, questions, jokes to the robot’s speech.
icon-dialogue-7

— Robot, do you know who is [person’s name]?

icon-dialogue-2

— Yes. And I’d love to give this person some of our store’s flowers.

The basic questions system (called anchor system) allows to form complex dialogues for the robot – for example, sales scripts.

It is also possible to add videos or photos to the linguistic base, as well as assign a set of movements and emotions to the robot’s replies. Different promotional phrases can be used and pronounced randomly by the robot even when there’s no person to talk to. These phrases can also be assigned to specific users: varied by ages, genders, etc.

Order now

Place your order

Fill out the form below. Our specialists will contact you shortly to inform on terms of purchase and delivery time for your Promobot. In “Message” area specify that you want to become a dealer or partner for Promobot.




    The humanoid project is over. We are no longer accepting any applications
    By submitting an application, you agree to the processing of personal data according to the privacy policy