What is Artificial Intelligence?
Artificial Intelligence (AI) is an ambiguous and opaque word.
Here we want to explain a little what does it mean and how we use it. 🔦
Artificial Intelligence is a new way of programming computers. Instead of putting in the code with a lot of if-this-then-that you use techniques to let the machine learn. That’s why it’s called „machine learning“. Machine learning is the technique that creates artificial intelligence.
Our parents probably never told us that snow is cold or the taste of chocolate. We learned it and they let us learn it. The same principle applies to machine learning.
Be smart: The brain is unparalleled. Applying the same principles doesn’t mean that you get somewhere close to what our brains are doing every day. Still, that new approach produces astonishing results and solves unsolved problems like image recognition, self-driving cars and many more.
One of this unsolved problems is to understand what a user wants if he is just sending a text message.
What we are doing: Understanding the user
At Spectrm we try to understand the user. We try to make sense of the words and sentences the user wrote to us.
The ability of a computer to do that is called Natural Language Processing.
Computers are able to „read“ numbers and words for decades, but not natural languages like English or German. Using just a predefined keyword like a command is something that chatbots have been already used in the 1980s.
Natural language processing tries to understand the language in their full complexity. There is sometimes thousands way of saying the same. Natural language processing wants to understand all of them.
Here are some techniques how this works:
From grammar lessons, we know that a sentence has different parts: subject, object, verb.
Entity recognition works similarly.
The computer tries to break the sentence into different parts to abstract it. The parts here are called entities. Entities can be eg. locations, persons or organizations.
Having entities abstracted is a good start, but without the connections between them, we don’t really understand what the user what. A semantic parser is there to make that connection by analyzing the semantic structure of a sentence.
80% of communication in a conversation is non-verbal. The feelings of the other person are important to understand what he wants to say.
For chatbots that is similar, but written language is of course much more difficult. Sentiment analysis solves that problem. It tries to abstract the usage of certain words and then calculate a score to decide whether it’s positive or negative. Instead of words, you can also analyze emojis. 🙌
We built our own – so you can do too
At Spectrm we built our own natural language processing algorithm.
We believe that every brand has their own voice and has to understand language differently.
What set’s us apart?
We enable brands to create a unique experience.
With our algorithm brands can completely tailor their understanding of words and meanings.
That flexibility separates the good from the bad experiences. A very obvious example: “Monster” is for Redbull something else then for Unity3D (a gaming company) – as a brand you want to respond accordingly.
We enable brands to be in charge – about their data and the training of the algorithm.
Brands can supervise the algorithm without being an AI scientist to create something your company has never seen before.
We make it brand safe.
Brands can either use our fuzzy matching or switch for some parts of the conversation to a strict rule-based approach to be absolutely sure that there is no misunderstanding.
So exciting …
With the help and financial support of the Google DNI we started on our mission to enable our customers to speak to every user individually. A meaningful conversation that helps both to get the most out of their connection. We are thrilled to be on this mission.
If you have questions, drop us a line.