Tag Archives: Microsoft

Extending Chatbots with Azure Cognitive Services

Microsoft Bot Framework is an open source SDK and set of tools for developing chatbots. One of the advantages of building chatbots with the Bot Framework is that you can easily integrate your bot service with the powerful AI algorithms available through Azure Cognitive Services. This is a quick and easy way to give your chatbot super powers when you need them.

Microsoft Cognitive Services is an ever-growing collection of algorithms developed by experts in the fields of computer vision, speech, natural-language processing, decision assistance, and web search. The services simplify a variety of common AI-based tasks, which are then easily consumable through web APIs. The APIs are also constantly being improved and some are even able to teach themselves to be smarter based on the information you feed them.

Here is a quick highlight reel of some of the current Cognitive Services available to chatbot creators:


People have a natural ability to say the same thing in many ways. Intelligent bots need to be just as flexible in understanding what human beings want. The Cognitive Service Language APIs provide language models to determine intent, so your bots can respond with the appropriate action.

The Language Understanding Service (LUIS) easily integrates with Azure Bot Service to provide natural language capabilities for your chatbot. Using LUIS, you can classify a speaker’s intents and perform entity extraction. For instance, if someone tells your bot that they want to buy tickets to Amsterdam, LUIS can help identify that the speaker intends to book a flight and that Amsterdam is a location entity for this utterance.

While LUIS offers prebuilt language models to help with natural language understanding, you can also customize these models for particular language domains that are pertinent to your needs. LUIS also supports active learning, allowing your models to get progressively better as more people communicate with it.

Decision assist services

Cognitive Services has knowledge APIs that extend your bot’s ability to make judgments. Where the language understanding service helps your chatbot determine a speaker’s intention, the decision services help your chatbot figure out the best way to respond. Personalizer, currently in preview, uses machine learning to provide the best results for your users. For instance Personalizer can make recommendations or rank a chatbot’s optional responses to select the best one. Additionally, the Content Moderator service helps identify offensive language, images, and video, filtering profanity and adult content.

Speech recognition and conversion

The Speech APIs in Cognitive Services can give your bot advanced speech skills that leverage industry-leading algorithms for speech-to-text and text-to-speech conversion, as well as Speaker Recognition, a service that lets people use their voice for verification. The Speech APIs use built-in language models that cover a wide range of scenarios with high accuracy.

For applications that require further customization, you can use the Custom Recognition Intelligent Service (CRIS). This allows you to calibrate the language and acoustic models of the speech recognizer by tailoring it to the vocabulary of the application and to the speaking style of your bot’s users. This service allows your chatbot to overcome common challenges to communication such as dialects, slang and even background noise. If you’ve ever wondered how to create a bot that understands the latest lingo, CRIS is the bot enhancement you’ve been looking for.

Web search

The Bing Search APIs add intelligent web search capabilities to your chatbots, effectively putting the internet’s vast knowledge at your bot’s fingertips. Your bot can access billions of:

· webpages

· images

· videos

· news

· local businesses

Image and video understanding

The Vision APIs bring advanced computer vision algorithms for both images and video to your bots. For example, you can use them to recognize objects, people’s faces, age, gender, or even feelings.

The Vision APIs support a variety of image-understanding features. They can categorize the content of images, determining if the setting is at the beach or at a wedding. They can perform optical character recognition on your photo, picking out road signs and other text. The Vision APIs also support several image and video-processing capabilities, such as intelligently generating image or video thumbnails, or stabilizing the output of a video for you.


While chatbots are already an amazing way to help people interact with complex data in a human-centric way, extending them with web-based AI is a clear opportunity to make them even better assistants for people. Easy to use AI algorithms like the ones in Microsoft Cognitive Services remove language friction and give your chatbots super powers.

Creating a Chatbot with Microsoft Azure QnA Maker and Alexa

QnA Maker is Microsoft’s easy-to-use, cloud-based API for turning a public-facing FAQ page, product manuals, and support documents into a natural-language bot service. Because it takes in pre-vetted data to use as its “smarts,” it’s one of the easiest ways to build a powerful bot for your company.

Alexa, of course, is the world’s most pervasive host for conversational bots. It’s found in homes, corporate boardrooms, and anywhere else people want easy access to web-based information.

In this article, I will show you how to attach the plumbing to push the Q&A information your company wants users to know onto the conversational bot devices that they are most frequently using.

Part 1: Creating a bot service with QnA Maker

To get started, I first created a free Azure account to play with. I then went to the QnA Maker portal page and clicked the Create a knowledge base tab at the top to set up the knowledge base for my bot. I then clicked the blue Create a QnA service button to make a new QnA service with my free Azure account.

I followed the prompts throughout the process, which made it easy to figure out what I needed to do at each step.

In step 2, I selected my Azure tenant, Azure subscription name, and Azure resource name associated with the QnA Maker service. I also chose the Azure QnA Maker service I’d just created in the previous step to host the knowledge base.

I then entered a name for my knowledge base and the URL of my company’s FAQ to use as the brains for my knowledge base. If you just want to test this part out, you can even use the FAQ for QnA Maker itself.

QnA Maker has an optional feature called Chit-chat that let me give my bot service a personality. I decided to go with “The Professional” for this, but definitely would like to try out “The Comic” at some point to see what that’s like.

The next step was just clicking the Create your KB button and waiting patiently for my data to be extracted and my knowledge base to be created.

Once that was done, I opened the Publish page in the QnA Maker portal, published my knowledge base, and hit the Create Bot button.

After filling out additional configuration information for Azure that was specific to my account, I had a bot deployed with zero coding on Microsoft Bot Framework v4. I could even chat with it using the built-in “Test in Web Chat” feature. You can find more details in this cognitive services tutorial.

Part 2: Making your bot service work on Alexa

To get the bot service I created above working with Alexa, I had to use an open-source middleware adapter created by the botbuilder community. Fortunately, the Alexa Middleware Adapter was available as a NuGet package for Visual Studio.

I went to the Azure portal and selected the bot I created in the previous section. This gave me the option to “Download Bot source code.” I downloaded my bot source code as a zip file, extracted it into a working directory, and opened it up in Visual Studio 2017.

When the bot is automatically generated, it’s created with references to the Microsoft.AspNetCore.App NuGet package and the Microsoft.AspNetCore.App SDK. Unfortunately, this had compatibility issues with the middleware package. To fix this, I right-clicked on the Microsoft.AspNetCore.App NuGet package in the Solution Explorer window and removed it. This automatically also removed the equivalent SDK. To get back all the DLLs I needed, I used NuGet Package Manager to install the Microsoft.AspNetCore.All (2.0.9) package instead. Be sure to install this specific version of the package to ensure compatibility.

After making those adjustments to the solution, I went to the Visual Studio menu bar and selected Tools -> Nuget Package Manager -> Manage Nuget Packages for Solution. I searched for Adapters.Alexa and installed the Bot.Builder.Community.Adapters.Alexa package.

If your downloaded app is missing its Program.cs or Startup.cs file, you will need to create these for you project in order to build and publish. In my case, I created a new Microsoft Bot Builder v4 project and copied these two files from there. In the Startup method of the Startup class I created a ConfigurationBuilder to gather my app settings.

Then in the ConfigureServices and Configure methods, I added a call to services.AddAlexaBot and UseAlexa in order to enable the Alexa middleware and set up a special endpoint for calls from Alexa.

Following these code changes, I published the Web App Bot back to my Azure account. The original QnA Bot Service now has an additional channel endpoint for Alexa. The Alexa address is the original Web App Bot root address with /api/skillrequests added to the end.

At this point, I was ready to go to my Amazon account and create a new Alexa skill. I went to: https://developer.amazon.com/alexa and signed in. (If you don’t already have a developer account, you will need to enter your information and agree to the developer EULA.) Next, I tapped the Alexamenu item at the top of the developer page and selected Alexa Skills Set. This took me to https://developer.amazon.com/alexa/console/ask, where I clicked the Create Skill button.

I wrote in a unique name for my skill, selected Custom for the model, and clicked Create skill. On the following screen, I selected Start from Scratchfor my template.

I selected JSON Editor.

Next, I opened another web browser and went to this source code, and copied the example JSON found in the README.md file.

I returned to the web browser that had the Amazon Alexa portal opened and pasted the JSON into the box. I change the invocationName to the name of my skill, clicked Save Model, and finally clicked Build Model.

After waiting patiently for the build to complete, I selected Endpoint in the left navigation window and clicked HTTPS. I then entered the address of the Azure App Service URL and added /api/skillrequests to the end.

To distribute my Alexa skill so people can use it on their own Amazon devices, I clicked the Distribution link in the Alexa developer console and followed the instructions from there.

And before I knew it, I was able to have a conversation with my company’s FAQ page, using the QnA Maker’s professional chit-chat personality, from my living room.

Microsoft’s convergence of chatbots and mixed reality

One of the biggest trends in mixed reality this year is the arrival of chatbots on platforms like HoloLens. Speech commands are a common input for many XR devices. Adding conversational AI to extend these native speech recognition capabilities is a natural next steps toward a future in which personalized virtual assistant backed by powerful AI accompany us in hologram form. They may be relegated to providing us with shopping suggestions, but perhaps, instead, they’ll become powerful custom tools that help make us sharper, give honest feedback, and assist in achieving our personal goals.

If you have followed the development of sci-fi artificial intelligence in television and movies over the years, the move from voice to full holograms will seem natural. In early sci-fi, such as HAL from the movie 2001: A Space Odyssey or the computer from the original Star Trek, computer intelligence was generally represented as a disembodied voice. In more recent incarnations of virtual assistance, such as Star Trek Voyager and Blade Runner 2049, these voices are finally personified by full holograms of the Emergency Medical Hologram and Joi.

In a similar way, Cortana, Alexa, and Siri are slowly moving from our smartphones, Echos, and Invoke devices to our holographic headsets. These are still early days, but the technology is already in place and the future incarnation of our virtual assistants is relatively clear.

The rise of the chatbot

For Microsoft’s personal digital assistant Cortana, who started her life as a hologram in the Halo video games for Xbox, the move to holographic headsets is a bit of a homecoming. It seems natural, then, that when Microsoft HoloLens was first released in 2016, Cortana was already built into the onboard holographic operating system.

Then, in a 2017 article on the Windows Apps Team blog, Building the Terminator Vision HUD in HoloLens, Microsoft showed people how to integrate Azure Cognitive Services into their holographic head-mounted display in order to provide smart object recognition and even translation services as a Terminator-like HUD overlay.

The only thing left to do to get to a smart virtual assistant was to tie together the HoloLens’s built-in Cortana speech capabilities with some AI to create an interactive experience. Not surprisingly, Microsoft was able to fill this gap with the Bot Framework.

Virtual assistants and Microsoft Bot Framework

Microsoft Bot Framework combines AI backed by Azure Cognitive Serviceswith natural-language capabilities. It includes a set of open source SDKs and tools that enable developers to build, test, and connect bots that interact naturally with users. With the Microsoft Bot Framework, it is easy can create a bot that can speak, listen, understand, and even learn from your users over time with Azure Cognitive Services. This chatbot technology is sometimes referred to as conversational AI.

There are several chatbot tools available. I am most familiar with the Bot Framework, so I will be talking about that. Right now, chatbots built with the Bot Framework can be adapted for speech interactions or for text interactions like the UPS virtual assistant example above. They are relatively easy to build and customize using prepared templates and web-based dialogs.

One of my favorite ways to build a chatbot is by using QnA Maker, which lets you simply point to an online FAQ page or upload product documentation to use as the knowledge base for your bot service. QnA Maker then walks you through applying a chatbot personality to your knowledge base and deploying it, usually with no custom coding. What I love about this is that you can get a sophisticated chatbot rolled out in about half a day.

Using the Microsoft Bot Framework, you also have the ability to take full control of the creation process to customize your bot in code. Bot apps can be created in C#, JavaScript, Python or Java. You can extend the capabilities of the Bot Framework with middleware that you either create yourself or bring into your code from third parties. There are even advanced capabilities available for managing complex conversation flows with branches and loops.

Ethical chatbots

Having introduced the idea above of building a Terminator HUD using Cognitive Services, it’s important to also raise awareness about fostering an environment of ethical AI and ethical thinking around AI. To borrow from the book The Future Computed, AI systems should be fair, reliable and safe, private and secure, inclusive, transparent, and accountable. As we build all forms of chatbots and virtual assistants, we should always consider what we intend our intelligent systems to do, as well as concern ourselves with what they might do unintentionally.

The ultimate convergence of AI and mixed reality

Today, chatbots are geared toward integrating skills for commerce like finding directions, locating restaurants, and providing help with a company’s products through virtual assistants. One of the chief research goals driving better chatbots is to personalize the chatbot experience. Achieving a high level of personalization will require extending current chatbots with more AI capabilities. Fortunately, this isn’t a far-future thing. As shown in the Terminator HUD tutorial above, adding Cognitive Services to your chatbots and devices is easy to do.

Because holographic headsets have many external sensors, AI will also be useful for analyzing all this visual and location data and turning it into useful information through the chatbot and Cognitive Services. For instance, cameras can be used to help translate street signs if you are in a foreign city or to identify products when you are shopping and provide helpful reviews.

Finally, AI will be needed to create realistic 3D model representations of your chatbot and overcome the uncanny valley that is currently holding back VR, AR, and MR. When all three elements are in place to augment your chatbot — personalization, computer vision, and humanized 3D modeling — we’ll be that much closer to what we’ve always hoped for — personalized AI that looks out for us as individuals.

Here is some additional reading on the convergence of chatbots and MR you will find helpful:

Increasing Business Reach with Azure Bot Service Channels

Where do bots live? It’s a common misconception that bots live on your Echo Dot, on Twitter, or on Facebook. To the extent bots call anywhere their home, it’s the cloud. Objects and apps like your iPhone and Skype are the “channels” through which people communicate with your bot.

Azure Bot Service Channels

Out of the box, Azure Bot Service supports the following channels (though the list is always growing):

  • Cortana
  • Email
  • Facebook
  • GroupMe
  • Kik
  • LINE
  • Microsoft Teams
  • Skype
  • Skype for Business
  • Slack
  • Telegram

Through middleware created by the Bot Builder Community, your business’s bots can reach additional channels like Alexa and Google.

With Direct Line, your developers can also establish communications through your bots and your business’s custom apps on the web and on devices.

Companies like Dixons Carphone, BMW, Vodafone, UEI, LaLiga, and UPS are already using Microsoft Azure Bot Service support for multiple channels to extend their Bot reach.

UPS Chatbot, for instance, delivers shipping information and answers customer questions through voice and text on Skype and Facebook Messenger. UPS, which invests more than $1 billion a year in technology, developed its chatbot in-house and plans to continue to update its functionality, including integration with the UPS My Choice® platform using Direct Line. In just the first eight months, UPS Bot has already had more than 200,000 conversations over its various channels.

LaLiga, the Spanish football league, is also reaching its huge and devoted fan base through multiple channels with Azure Bot Service. It is estimated that LaLiga touches 1.6 billion fans worldwide on social media.

Using an architecture that combines Azure Bot Service, Microsoft Bot Framework and multiple Azure Cognitive Services such as Luis and Text Analysis, LaLiga maintains bots on Skype, Alexa and Google Assistant that use natural language processing. NLP allows their chatbots to understand both English and Spanish, their regional dialects, and even the soccer slang particular to each dialect. They are even able to use a tool called Azure Monitor anomaly detection to identify new player nicknames created by fans and then match them to the correct person. In this and similar ways, LaLiga’s chatbots are always learning and adapting over time. LaLiga plans to deploy its chatbots to almost a dozen additional channels in the near future.


Because social media endpoints are always changing, developing for a single delivery platform is simply not cost-effective. Channels provide businesses with a way to develop a bot once but deploy it to new social media platforms as they appear on the market and gain influence. At the same time, your core bot features can constantly be improved, and these improvements will automatically benefit the pre-existing channels people use to communicate with you.

Top 21 HoloLens Ideas


The image above is a best guess at the underlying technology being used in Microsoft’s new HoloLens headset. It’s not even that great a guess since the technology appears to still be in the prototype stage. On the other hand, the product is tied to the Windows 10 release date, so we may be seeing a consumer version – or at the very least a dev version – sometime in the fall.

Here are some things we can surmise about HoloLens:

a) the name may change – HoloLens is a good product name but isn’t quite where we might like it to be, in a league with Kinect, Silverlight or Surface for branding genius. In fact, Surface was such a good name, it was taken from one product group and simply given to another in a strange twist on the build vs buy vs borrow quandary. On the other hand, HoloLens sounds more official than the internal code name, Baraboo — isn’t that a party hippies throw themselves in the desert?

johnny mnemonic

b) this is augmented reality rather than virtual reality. Facebook’s Oculus Rift, which is an immersive fully digital experience, is an example of virtual reality. Other fictional examples include The Oasis from Ernest Cline’s Ready Player One, The Mataverse from Neal Stephenson’s Snow Crash, William Gibson’s Cyberspace and the VR simulation from The Lawnmower Man. Augmented reality involves overlaying digital experience on top of the real world. This can be accomplished using holography, transparent displays, or projectors. A great example of projector based AR is the RoomAlive project by Hrvoje Benko, Eyal Ofek and Andy Wilson at Microsoft Research. HoloLens uses glasses or a head-rig – depending on how generous you feel – to implement AR. Magic Leap – with heavy investment from Google – appears to be doing the same thing. The now dormant Google Glass was neither AR nor VR, but was instead a heads-up display.


c) HoloLens uses Kinect technology under the plastic covers. While the depth sensor in the Kinect v2 has a field of view of 70 degrees by about 60 degrees, the depth capability in HoloLens is reported to include a field of view of 120 degrees by 120 degrees. This indicates that HoloLens will be using the Time-of-Flight technology used in Kinect v2 rather than the structured light from Kinect v1. This set up requires both an IR emitter as well as a depth camera combined with a sophisticated timing and phase technology to efficiently and relatively inexpensively calculate depth.


d) the depth camera is being used for multiple purposes. The first is for gesture detection. One of the issues that faced both Oculus and Google Glass was that they were primarily display technologies. But a computer monitor is useless without a keyboard or mouse. Similarly, Oculus and Glass needed decent interaction metaphors. Glass relied primarily on speech commands and tapping and clicking. Oculus had nothing until their recent acquisition of the NimbleVR . NimbleVR provides a depth camera optimized for hand and finger detection over a small range. This can be mounted in front of the Oculus headset. Conceptually, this allows people to use hand gestures and finger manipulations in front of the device. A virtual hand can be created as an affordance in the virtual world of the Oculus display, allowing users to interact with virtual objects and virtual interactive menus in virtro.

The depth sensor in HoloLens would work in a similar way except that instead of a virtual hand as affordance, it’s just your hand. You will use your hand to manipulate digital objects displayed on the AR lenses or to interact with AR menus using gestures.

An interesting question is how many IR sensors are going to be on the HoloLens device. From the pictures that have been released, it looks like we will have a color camera and a depth sensor for each eye, for a total of two depth cameras and two RGB cameras located near the joint between the lenses and the headband.


e) HoloLens is also using depth data for 3d reconstruction of real world surfaces. These surfaces are then used as virtual projection surfaces for digital textures. Finally, the blitted image is displayed on the transparent lenses.



This sort of reconstruction is a common problem in projection mapping scenarios. A great example of applying this sort of reconstruction can be found in the Halloween edition of Microsoft Research’s RoomAlive project. In the first image above, you are seeing the experience from the correct perspective. In the second image, the image is captured from a different perspective than the one that is being projected. From the incorrect perspective, it can be seen that the image is actually being projected on multiple surfaces – the various planes of the chair as well as the wall behind it – but foreshortened digitally and even color corrected to make the image appear cohesive to a viewer sitting at the correct position. One or more Kinects must be used to calibrate the projections appropriately against these multiple surfaces. If you watch the full video, you’ll see that Kinect sensors are used to track the viewer as she moves through the room and the foreshortening / skewing occurs dynamically to adjust to her changing position.

The Minecraft AR experience being used to show the capabilities of HoloLens requires similar techniques. The depth sensor is required not only to calibrate and synchronize the digital display to line up correctly with the table and other planes in the room, but also to constantly adjust the display as the player moves around the room.


f) are the display lenses stereoscopic or holographic? At this point no one is completely sure, though indications are that this is something more than the stereoscopic display technique used in the Oculus Rift. While a stereoscopic display will create the illusion of depth and parallax by creating a different image for each lens, something holographic would actually be creating multiple images per lens and smoothly shifting through them based on the location of each pupil staring through its respective lens and the orientation and position of the player’s head.

One way of achieving this sort of holographic display is to have multiple layers of lenses pressed against each other and using interference shift the light projected into each pupil as the pupil moves. It turns out that the average person’s pupils typically move around rapidly in saccades, mapping and reconstructing images for the brain, even though we do not realize this motion is occurring. Accurately capturing these motions and shifting digital projections appropriately to compensate would create a highly realistic experience typically missing from stereoscopic reconstructions. It is rumored in the industry that Magic Leap is pursuing this type of digital holography.

On the other hand, it has also been reported that HoloLens is equipped with eye-tracking cameras on the inside of the frames, apparently to aid with gestural interactions. It would be extremely interesting if Microsoft’s route to achieving true holographic displays involved eye-tracking combined with a high display refresh rate rather than coherent light interference display technology as many people assume. Or, then again, it could just be stereoscopic displays after all.


g) occlusion is generally considered a problem for interactive experiences. For augmented reality experiences, however, it is a feature. Consider a physical-to-digital interaction in which you use your finger/hand to manipulate a holographic menu. The illusion we want to see is of the hand coming between the player’s eyes and the digital menu. The player’s hand should block and obscure portions of the menu as he interacts with it.

The difficulty with creating this illusion is that the player’s hand isn’t really between the menu and the eyes. Really, the player’s hand is on the far side of the menu, and the menu is being displayed on the HoloLens between the player’s eyes and his hand. Visually, the hologram of the menu will bleed through and appear on top of the hand.

In order to re-establish the illusion of the menu being located on the far side of the hand, we need depth-sensors to accurately map an outline of the hand and arm and then cut a hand and arm shape out of the menu where the hand should be occluding it. This process has to be repeated as the hand moves in real-time and it’s kind of a hard problem.


h) misc sensors : best guess is that in addition to depth sensors, color cameras and eye-tracking cameras, we’ll also get a directional microphone, gyroscope, accelerometer and magnetometer. Some sort of 3D sound has been announced, so it makes sense that there is a directional microphone or microphone array to complement it. This is something that is available on both the Kinect v1 and Kinect v2. The gyroscope, accelerometer and magnetometer are also guesses – but the Oculus hardware has them to track quick head movements, head position and head orientation. It makes sense that HoloLens will need them also.


i) the current form factor looks a little big – bigger than the Magic Leap is supposed to be but smaller than the current Oculus dev units. The goal – really everyone’s goal, from Microsoft to Facebook to Google – is to continue to bring down the size of sensors so we can eventually have heavy glasses rather than light-weight head gear.

j) vampires, infrared sensors and transparent displays are all sensitive to direct sunlight. This consideration can affect the viability of some AR scenarios.

k) like all innovative technologies, the success of HoloLens will depend primarily on what people use it for. the myth of the killer app is probably not very useful anymore, but the notion that you need an app store to sell a device is a generally accepted universal constant. The success of the HoloLens will depend on what developers build for it and what consumers can imagine doing with it.



Top 21 Ideas

Many of these ideas are borrowed from other VR and AR technology. In most cases, HoloLens will simply provide a better way to implement these notions. These ideas come from movies, from art installations, and from many years working at an innovative marketing agency where we prototyped these ideas day in and day out.


1. Shopping


Amazon made one click shopping make sense. Shopping and the psychology of shopping changes when we make it more convenient, effectively turning instant gratification into a marketing strategy. Using HoloLens AR, we can remodel a room with virtual furniture and then purchase all the pieces on an interactive menu floating in the air in front of us when we find the configuration we want. We can try and buy virtual clothes. With a wave of the hand we can stock our pantry, stock our refrigerator … wait, come to think of it, with decent AR, do we even need furniture or clothes anymore?

2. Gaming


IllumiRoom was a Microsoft project that never quite made it to product but was a huge hit on the web. The notion was to extend the XBox One console with projections that reacted to what was occurring in the game but could also extend the visuals of the game into the entire living room. IllumiRoom (which I was fortunate enough to see live the last time I was in Redmond) also uses a Kinect sensor to scan the room in order to calibrate projection mapping onto surfaces like bookshelves, tables and potted plants. As you can guess, this is the same team that came up with RoomAlive. A setup that includes a $1,500 projector and a Kinect is a bit complicated, especially when a similar effect can now be created using a single unit HoloLens.


The HoloLens device could also be used for in-game Heads-Up notifications or even as a second screen. It would make a lot of sense if XBox integration is on the roadmap and would set XBox apart as the clear leader in the console wars.

3. Communication


‘nuff said.

4. Home Automation


Home automation has come a long way and you can now easily turn lights on and off with your smart phone from miles away. Turning your lights on and off from inside your own house may still involve actually touching a light switch. Devices like the Kinect have the limitation that they can only sense a portion of a room at a time. Many ideas have been thrown out to create better gesture recognition sensors for the home, including using wifi signals that go through walls to detect gestures in other rooms. If you were actually wearing a gestural device around with you, this would no longer be a problem. Point at a bulb, make a fist, “put out the light, and then put out the light” to quote the Bard.

5. Education


While cool visuals will make education more interesting, the biggest benefit of HoloLens for education is simple access. Children in rural areas in the US have to travel long distances to achieve a decent education. Around the world, the problem of rural education is even worse. What if educators could be brought to the children instead? This is one of the stated goals of Facebook’s purchase of Oculus Rift and HoloLens can do the same job just as well and probably better.

6. Medical Care


Technology can be used for interesting diagnostic and rehabilitation functions. The depth sensors that come with HoloLens will no doubt be used in these ways eventually. But like education, one of the great problems in medical care right now is access. If we can’t bring the patient to the doctor, let’s bring the GP to the patient and do regular check ups.

7. Holodeck


The RoomAlive project points the way toward building a Holodeck. All we have to do is replace Kinect sensors with HoloLens sensors, projectors with holographic displays, and then try now to break the HoloLens strapped to our heads as we learn Kung Fu.

8. Windows


Have you ever wished you could look out your window and be somewhere else? HoloLens can make that happen. You’ll have to block out natural light by replacing your windows with sheetrock, but after that HoloLens can give you any view you want.


But why stop at windows. You can digitize all your walls if you want, and HoloLens’ depth technology will take care of the rest.

9. Movies and Television


Oculus Rift and Samsung Gear VR have apps that let you watch movies in your own virtual theater. But wouldn’t it be more fun to watch a movie with your entire family? With HoloLens we can all be together on the couch but watch different things. They can watch Barney on the flatscreen while I watch an overlay of Meet the Press superimposed on the screen. Then again, with HoloLens maybe I could replace my expensive 60” plasma TV with a piece of cardboard and just watch that instead.

10. Therapy


It’s commonly accepted that white noise and muted colors relax us. Controlling our environment helps us to regulate our inner states. Behavioral psychology is based on such ideas and the father of behavioral psychology, B. F. Skinner, even created the Skinner box to research these ideas – though I personally prefer Wilhelm Reich’s Orgone box. With 3D audio and lenses that extend over most of your field of view, HoloLens can recreate just the right experience to block out the world after a busy day and just relax. shhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhh.

11. Concerts


Once a year in the Nevada desert a magical music festival is held called Baraboo. Or, I don’t know, maybe it’s held in Tennessee. In any case, getting to festivals is really hard and usually involves being around people who aren’t wearing enough deodorant, large crowds, and buying plastic bottles of water for $20. Wouldn’t it be great to have an immersive festival experience without all the things that get in the way. Of course, there are those who believe that all that other stuff is essential to the experience. They can still go and be part of the background for me.

12. Avatars


Gamification is a huge buzzword at digital marketing agencies. Undergirding the hype is the realization that our digital and RL experiences overlap and that it sometimes can be hard to find the seams. Vernor Vinge’s 2001 novella Fast Times at Fairmont High draws out the implications of this merging of physical and digital realities and the potential for the constant self reinvention we are used to on the internet bleeding over into the real world. Why continue with the name your parents gave you when you can live your AR life as ByteMst3r9999? Why be constrained by your biological appearance when you can project your inner self through a fun and bespoke avatar representation? AR can ensure that other people only see you the way that you want them to.

13. Blocking Other People’s Avatars


The flip side of an AR society invested in an avatar culture is the ability to block people who are griefing us. Parents can call a time out and block their children for ten minutes periods. Husbands can block their wives. We could all start blocking our co-workers on occasion. For serious offenses, people face permanent blocking as a legal sanction for bad behavior by the game masters of our augmented reality world. The concept was brilliantly played out in the recent Black Mirror Christmas special starring Jon Hamm. If you haven’t been keeping up with Black Mirror, go check it out. I’ll wait for you to finish.

14. Augmented Media


Augmented reality today typically involves a smart phone or tablet and and a fiducial marker. The fiducial is a tag or bar code that indicates to the app on your phone where an AR experience should be placed. Typically you’ll find the fiducial in a magazine ad that encourages you to download an app to see the hidden augmented content. It’s novel and fun. The problem involves having to hold up your tablet or phone for a period of time just to see what is sometimes a disappointing experience. It would be much more interesting to have these augmented media experiences always available. HoloLens can be always on and searching for these types of augmented experiences as you read the latest New Yorker or Wired. They needn’t be confined to ads, either. Why can’t the whole magazine be filled with AR content? And why stop at magazines? Comic books with additional AR content would change the genre in fascinating ways (Marvel’s online version already offers something like this, though rudimentary). And then imagine opening a popup book where all the popups are augmented, a children’s book where all the illustrations are animated, or a textbook that changes on the fly and updates itself every year with the latest relevant information – a kindle on steroids. You can read about that possibility in Neal Stephenson’s Diamond Age – only available in non-augmented formats for now.

15. Terminator Vision


This is what we thought Google Glass was supposed to provide – but then it didn’t. That’s okay. With vision recognition software and the two RGB cameras on HoloLens, you’ll never forget a name again. Instant information will appear telling you about your surroundings. Maps and directions will appear when you gesture for them. Shopping associates will no longer have to wing it when engaging with customers. Instead, HoloLens will provide them with conversation cues and decision trees that will help the associate close the sale efficiently and effectively. Dates will be more interesting as you pull up the publicly available medical, education and legal histories of anyone who is with you at dinner. And of course, with the heartbeat monitor and ability to detect small fluctuations in skin tone, no one will ever be able to lie to you again, making salary negotiations and buying a car a snap.

16. Wealth Management


With instant tracking of the DOW, S&P and NASDAQ along with a gestural interface that goes wherever you go, you can become a day trader extraordinaire. Lose and gain thousands of dollars with a flick of your finger.

17. Clippit


Call him Jarvis if it helps. Some sort of AI personal assistant has always been in the cards. Immersive AR will make it a reality.

18. Impossible UIs




cloud atlas floating computer

I don’t watch movies the way other people do. Whenever I go to see a futuristic movie, I try to figure out how to recreate the fantasy user experiences portrayed in it. Minority Report is an easy one – it’s a large area display, possibly projection, with Kinect-like gestural sensors. The communication device from the Total Recall reboot is a transparent screen and either capacitive touch or more likely a color camera doing blob recognition. The 3D touchscreen from Pacific Rim has always had me stumped. Possibly some sort of leap motion device attached to a Pepper’s Ghost display? The one fantasy UX I could never figure out until I saw HoloLens is the “Orison” computer made up of floating disks in Cloud Atlas. The Orison screens are clearly digital devices in a physical space – beautiful, elegant, and the sort of intuitive UX for which we should strive. Until now, they would have been impossible to recreate. Now, I’m just waiting to get my hands on a dev device to try to make working Orison displays.

19. Wiki World


Wiki World is a simple extension of terminator vision. Facts floating before your eyes, always available, always on. No one will ever have to look up the correct spelling for a word again or strain his memory for a sports statistic. What movie was that actor in? Is grouper ethical to eat? Is Javascript an object-oriented language? Wiki world will make memorization obsolete and obviate all arguments – well, except for edit wars between Wikipedia editors, of course.

20. Belief Circles


Belief circles are a concept from Vernor Vinge’s Hugo award winning novel Rainbows End. Augmented reality lends itself to self-organizing communal affiliations that will create inter-subjective realities that are shared. Some people will share sci-fi themes. Others might go the MMO route and share a fantasy setting with a fictional history, origin story, guilds and factions. Others will prefer football. Some will share a common religion or political vision. All of these belief circles will overlap and interpenetrate. Taking advantage of these self-generating belief circles for content creation and marketing will open up new opportunities for freelance creatives and entrepreneurs over the next ten years.

21. Theater of Memory


Giulio Camillo’s memory theater belongs to a long tradition of mnemonic technology going back to Roman times and used by orators and lawyers to memorize long speeches. The scholar Frances Yates argued that it also belonged to another Renaissance tradition of neoplatonic magic that has since been superseded by science in the same way that memory technology has been superseded by books, magazines and computers. What Frances Yates – and after her Ioan Couliano – tried to show, however, was that in dismissing these obsolete modes of understanding the world, we also lose access to a deeper, metaphoric and humanistic way of seeing the world and are the poorer for it. The theater of memory is like Feng Shui – also discredited – in that it assumes that the way we construct our surroundings also affects our inner lives and that there is a sympathetic relationship between the macrocosm of our environment and the microcosm of our emotional lives. I’m sounding too new agey so I’ll just stop now. I will be creating my own digital theater of memory as soon as I can, though, as a personal project just for me.