Can you guess who has helped me research this topic? Google Assistant. I simply asked: “Tell me about the technologies behind Google Assistant” and it did not disappoint me. Before going any further, let me introduce you to Google Assistant; a virtual assistant developed using AI technologies and used in Android phones. If you are not aware how it works, you can mistakenly think that who answers your questions is a real human being, but that is incorrect. It is a technology invented to answer your questions and help you, maybe by simply setting your alarm or scheduling appointments. If you have not yet checked it out, I recommend you do so right away; it is fun to experience this wonderful new technology.

So, how does it exactly work? AI is at the core of Google Assistant; it is programmed to understand what a person is saying through tools like natural language processing and machine learning. Natural Language Processing is a field of AI responsible for programming computers and machines to understand human language and also translate (such as Google Translate). It benefits from many other fields, such as linguistics, computational linguistics, and machine learning. Linguistics is the field that studies how language functions, while computational linguistics combines computer science with linguistics.

Google Assistant instantly processes your words and understands exactly what you are saying. It then responds by constructing clear sentences as a human being would, based on what it has learnt. The sentences that Google Assistant utters are not saved responses; it is fed with the rules of linguistics that help it construct sentences.

Google Assistant processes inputs and comes up with an output—a search result or an answer to your question, just like how a human being would. However, unlike humans, it is supported by Google’s search engine. You can ask the Assistant: “Who won the Oscars this year?” and it will search the results and come up with the correct answer.

Google Assistant also benefits from machine learning technology, which focusses on systems that teach machines to learn from experience and make decisions accordingly, rather than being programmed for every single task. In other words, machine learning is about giving the machines the rules and leaving them to learn from trial and error without explicit instructions in their programming codes.

AI is an amazing field that cannot be fully covered in one article; what we offer here is merely a glimpse at AI and related disciplines. I advise you to look up all the terms used in this article; maybe one day you become an AI engineer who introduces better technologies for a better future.

References