How Barbie’s manufacturers are using Big Data in practice
Hello Barbie responds realistically to a child by using natural language processing, machine learning and advanced analytics to parse what the child says and respond accordingly. The doll has a microphone concealed in her necklace that records what anyone says to her and transmits it to the servers at ToyTalk. There, the recording is parsed, analysed, and the correct response selected and sent back for Barbie to deliver — all in under a second.
Every one of Barbie’s potential conversations is mapped out, like the branches of a tree, with more than 8,000 lines of dialogue available to her as possible responses. Barbie also remembers what children say, storing answers for use in later conversation. If, for example, a child says their favourite musician is Taylor Swift, Barbie will remember that, and possibly bring it up in an exchange days or weeks later.
And unlike Siri or Cortana, who use automated voices, every line Barbie speaks is recorded by an actor, giving her a more lifelike sound. Updates will be recorded periodically so that Barbie is always up on the latest pop culture.
The technical details
On Barbie, there’s a “listen” button the child has to press to start recording what she says in order to get a response. When pressed, the child’s speech is recorded and sent to ToyTalk’s cloud-based servers for analysis. The conversations become part of a huge cache of data that Mattel and ToyTalk say will be used to help improve the technology in the future.
Ideas and insights you can steal
Hello Barbie is just the first in a long line of AI-enabled toys that will take advantage of deep learning algorithms to interact with us in more and more realistic ways. But toys aren’t the only inanimate objects that we “speak to” naturally – just think of Siri. In fact, Google is already predicting that we will eventually use voice commands more than typing on our mobile devices. This means manufacturers must start thinking about whether, and how, they can make their products smarter by building AI capabilities into them.
You can read more about how companies are using Big Data to drive success in Big Data in Practice: How 45 Successful Companies Used Big Data Analytics to Deliver Extraordinary Results.
Bernard Marr is a bestselling author, keynote speaker, and advisor to companies and governments. He has worked with and advised many of the world's best-known organisations. LinkedIn has recently ranked Bernard as one of the top 10 Business Influencers in the world (in fact, No 5 - just behind Bill Gates and Richard Branson). He writes on the topics of intelligent business performance for various publications including Forbes, HuffPost, and LinkedIn Pulse. His blogs and SlideShare presentation have millions of readers.