An open unified protocol for a smart, connected IoT

Here is a situation that I found myself in, and I’m sure other smart-home users can relate to it. A couple of weeks ago, while on a business trip in China, my smart doorbell (such as ring) rang. I picked up my smartphone to see who was at the door. To my surprise, it was my daughter standing outside our house. Although it was daytime in my location, she was standing in the dark, back at home. I turned on the intercom to ask her why she wasn’t inside, and she explained that she had misplaced her key. Now, I have a smart doorbell, a smart lock, and smart lighting system. But, instead of simply giving a command to unlock the door and turn on the light, I had to exit the doorbell app, open the smart lock app and only then could my daughter safely enter the house. Instead of having full control of my smart home at my fingertips, I have an assortment of different apps with different interfaces that I need to manage separately. I don’t think that this is the best we can get out of the Internet of Things (IoT).

Now, of course, there are some smart doorbells that could combine some of these functions, but that’s still not enough. It only solves this one scenario. But, what about smart climate control, home irrigation systems, and all the other appliances and services that are becoming smart and connected? Each of these has a different interface, as well as different communication protocols: Wi-Fi, Bluetooth, ZigBee, Z-Wave, and fairly soon also various LTE machine-type categories, NB-IoT, LoRa, Sigfox, and more. For a home to be truly smart and connected, all these devices should be able to communicate with each other, and enrich the user experience.

Amazon, Google and others are heavily investing in Artificial Intelligence (AI), and bringing exciting new products to the consumer domain, so why not harness the power of AI to enable deep linking of the smart home IoT environment? The above scenario could have been made more “intelligent” by the smart doorbell camera recognizing and authenticating my daughter’s face automatically, turning on the light in the doorway, unlocking the door for her and texting me that she is safely home. Mission accomplished!

A recent piece posted on wired.com claims that it’s crazy to buy into the internet of things. This claim is backed by examples of “smart” products and services that have been shut down or went out of business, rendering the devices virtually useless. In other words, once you buy a smart IoT device for your home, you are dependent on the service that supports the device, and therefore at risk of it becoming an expensive brick. But, perhaps this risk could be averted by a very simple solution: deep linking.

Deep linking the Internet of Things

Deep linking is simply a unified protocol or interface that allows applications to trigger and communicate to one another behind the scenes. In smartphone applications, this is what allows your calendar to team up with your navigation app. Together, they can suggest when you should depart, so that you avoid traffic, and get to your meetings on time. At home, smart irrigation systems (like GreenIQ) already know when it is about to rain and avoid activating my garden sprinklers. So, why shouldn’t smart home devices be linked in a similar fashion? Maybe, when I wake up, my home could detect it via my wearable activity band and start a chain of events: the smart blinds will let in the sunlight, while the smart espresso machine gets the coffee started, and Uber would be asked to send me a cab if I happen to be car-less that day, to make it to my first meeting. By opening and standardizing the interfaces of these products, the user experience can be immensely enhanced. At the same time, an open interface can significantly reduce the risk of the product quickly becoming obsolete.

Today, the main solution for getting all your smart things on the same page is a central hub. There are physical hubs that plug into your home network, as well as applications that consolidate everything into one software interface. For example, Amazon is constantly declaring new capabilities of its highly popular Echo product line. In addition, Google showcased their new hub, simply titled ‘Home’, in the Google I/O conference several weeks ago. Amazon, Google, Apple, and others, from small startups to tech giants are all trying to get their products to be the one in control. In the end, the dominator of the market for smart home hubs will be the one that has the most open and robustly defined deep linking interface, and hence will have the richest set of compatible devices and applications.

Artificial Intelligence will really make the smart home smart

Until now, the type of home I’ve depicted would be better described as a connected home, rather than a smart home. To be smart, it needs to step beyond connectivity, into the realm of intelligence. If my home could learn my habits, recognize my family members, get to know how I do things, and what I need to get them done, then it could truly be called smart. This means making all the connected devices in my home aware of one another and utilizing the right one at the right time. Another important step towards intelligence is understanding natural language. Today, many hubs are already able to respond to various verbal commands, but the next step is a fully functional conversational assistant. Or, in other words, a hub that can actually carry on a conversation, including contextual references, like “play that song” or “let her in”. This requires deep learning, which is becoming prevalent in more and more devices. Exciting times are ahead, when we’ll be able to talk to our homes, and they’ll help us get things done faster and more conveniently. But in the end, the main reason I want everything to be smart and connected is so that I know my daughter is safe and warm at home.

Want to learn more?

Click here to learn about the CEVA-XC5, the highly powerful, multi-mode communication processor for IoT wireless applications.
Check out CEVA’s lowest power multi-microphone voice activation solution for conversational assistants.
Click here to find out about CDNN, CEVA Deep Neural Networks – the advanced, low-power, embedded solution for machine learning
Watch CEVA’s webinar about implementing machine vision in embedded systems, including a deep dive into CDNN.

#Deep Learning #Deep Linking #IoT #smart home

Posted By

Moshe Sheier

Moshe Sheier serves as our Vice President of Marketing. Mr. Sheier brings with him more than 20 years of experience in the semiconductor IP and chip industry in both development and managerial roles. Prior to this position, Mr. Sheier was the Director of Product Marketing at CEVA and before that he has managed Xilinx Inc. partner program in EMEA. Before joining CEVA, he was with the DSP Group since 1993, holding different engineering and R&D management positions, including the VLSI Department Manager. Mr. Sheier holds several US patents in the area of DSP architectures, a B.Sc. in Electrical Engineering and an M.B.A.