Intellectual system ELIS

My name is Oleg Andreev, I am 32 years old, engaged in repair and development of electronics, as well as programming (more than 10 years). Always fond of artificial intelligence and robotics.

A long time ago I had an idea in my head, to create an AI or something like that, which would be able to manage something. But it was not possible to do this, although there were some ideas. Now is the time of technology, now any child can assemble a robot or some complicated device on the Arduino platform, etc.

When in 2012, the free recognition of Russian speech from Google appeared, I set about trying to create a system that could speak like a person. Then I was engaged in PHP programming, but for writing a program, I had to learn something else, I found an environment for writing programs for PHP, it was interesting, but not for long, because to create a program I needed C #, C ++.
')
After studying C #, I wrote a simple client, and I did all the logic in the cloud in PHP. But soon Google made a restriction on requests for recognition and then put its project for a long time in the box. When free time and finance appeared, I decided to finalize the system, created a group in the VC, which grew.

But at one point all the sources of the initial system were destroyed and then it all started ...



I created an interesting intellectual system from scratch, which, of course, is being finalized. Many will think that this is a voice assistant such as Cortana, Siri, Dusya and the like. No, I do not create a voice assistant, but something more, since the emphasis is on developing a humanoid system that can learn as a child and conduct a conscious dialogue. Speech recognition at the moment I use from Yandex, but I am already engaged in my speech recognition technology, because I want to create Latvian speech recognition as well.

Alice can, for example, start a dialogue herself and learn by asking questions and different phrases.

Plans: I want to create a free and affordable intellectual system that will work in the house, in the car, help people with disabilities, or just become your friend.

In this video, there is a dialogue where you can see how the system responds and responds.



Here the dialogue begins with a person, then a pause is made so that the system stops the dialogue. Then the system itself starts the first dialogue several times, it already distinguishes it from voice assistants, who work on the structure of the question - the answer. Also, the video demonstrates training and context support, when the system makes a decision after what exactly the person will say further and if he does not know, it can be trained.



The system is fully compatible with the Arduino platform, so you can control any device. This demonstrates simple control of the light with context support, then - having asked to turn on the light, the system will ask where to turn it on, but you can ask to turn on the light immediately in a certain place, then it will not ask again.



How can you teach a program for yourself and not only. The video shows the memorization of one answer to one question, but the system is able to memorize several answers to one or many questions and have several questions to one or many answers. With the support of dialogue, the system learns itself.



This is the first video where context support was demonstrated, when asked to tell the news, the system will want to understand whether it is still interested in something else.



Anyone who wants to try out such a system: download

Thanks for attention!