Sherpa has launched its mobile personal assistant for Android in the UK, according to Pocket-lint. Sherpa is also available in the U.S. The personal assistant leverages natural language processing to interpret what the user is saying and to return helpful results. As with other personal assistant apps, Sherpa is integrated with your phone so that you can dictate text messages or have incoming messages read to you. It’ll also set up reminders for you, answer your questions about last night’s big sporting event, or make status updates to Facebook.
A very interesting feature offered by Sherpa is its ability to let you make payments through PayPal. It’ll be interesting to watch as future generations of mobile personal assistants add transactional processing capabilities. I’m hoping for a virtual agent assistant that will deposit checks, as that’s one of my least favorite tasks. Having the assistant pay non-recurring bills when instructed to do so would be helpful too.
Sherpa can be downloaded for free on Google Play.
Here’s yet another Kickstarter campaign that may be of interest to the chatbot and virtual agent crowd. The BlabDroid isn’t a real conversational agent. All it can do is ask questions in a child’s voice and then gleefully stand by and wait for an answer. But it has an uncanny way of connecting with people and pulling out their deepest, darkest secrets.
BlabDroid is outfitted with filmmaking tools and was originally built to shoot short documentaries. It uses the recorded voice of a 7-year old boy and its cuddly appearance to worm its way into the heart of subjects. It then makes a short movie about them as they respond to the questions, most of which are deeply personal.
If you pledge at the right level, you can get your very own BladDroid. It would be interesting to see the little robot outfitted with a more capable conversational system. At the very least, though, it shows the potential for new frontiers in human to computer interfaces and relationships.
Looking for a way to combine your enthusiasm for chatbot / virtual agent technologies and your addiction to Kickstarter? Well, you’re in luck! Mercer Engineering Research Center (MERC) has recently launched a Kickstarter campaign to gain funding for their Histochat project. The campaign is set to end in 23 days and they’re a long way from reaching their goal, so have a look and see if this is something that deserves your support.
Based on the Kickstarter videos, it looks like Histochat is an educational tool that will provide students with an interactive experience with real historical figures. The MERC team is looking to use ChatScript to build out conversational chatbots representing possibly five historical personalities: Albert Einstein, Amelia Earhart, Mahatma Gandhi, Martin Luther King, Jr., and Susan B. Anthony.
Students will apparently use a smartphone to access the chatbot agent representing one of these historical figures. They’ll be able to engage the historical personality in a conversation by asking questions about the person’s life and accomplishments. Check out the Kickstarter videos. The demo isn’t particularly exciting, but the idea of creating chatbots to bring history to life for students is a good one. Hopefully the Kickstarter campaign will get more momentum in the coming days.
Singularity Hub did an interview with Ray Kurzweil back in January, during which Kurzweil talked about his vision for an artificial intelligence that will act as a trusted personal assistant to humans. Kurzweil had only just started his stint at Google when the interview took place. He briefly shared his vision of constructing an artificially intelligent software system that mimics the hierarchical architecture of the human brain. It remains to be seen how successful Kurzweil and the team at Google will be in their endeavor. Whatever the outcome, the race to produce smarter and smarter digital entities is definitely underway. As Gary Marcus points out in his review of Kurzweil’s book on building a brain, there are many different machine learning techniques and cognitive systems that are being researched today in the public and private sector. Whether Kurzweil’s hierarchical approach pans out or not is really irrelevant. Advanced AI that can understand human intent and provide answers to human questions will happen. The progress made in this field is bound to influence commercially available virtual agent technologies, both in the mobile personal assistant and in the enterprise and customer support virtual agent domains.
Older conversational agent technologies will most likely be superseded by new ones. The work that Ray Kurzweil, the DeepQA team, and many other artificial intelligence researchers are engaged in today is producing techniques that far outpace the rudimentary pattern matching technology deployed in most simple chatbots. In the hands of dedicated and savvy bot masters, chatbot scripting languages such as AIML can be used to create impressive question answering agents. But unless it is combined with natural language processing, search, and machine learning algorithms, AIML by itself can’t produce a truly effective virtual agent. It’s sporty to make any predictions when it comes to the future of artificial intelligence, but one pretty safe prediction would seem to be this: the intelligent virtual agent that one day passes the Turing Test won’t have been created using basic AIML pattern matching technology.
For commercially viable virtual agents in the field of customer support, incorporating strong search capabilities would seem to be a must. Search can be combined with pattern matching against a broad database of known frequently asked questions to provide web or mobile users with basic self serve information. Text and/or speech recognition and natural language processing would also seem to be non-negotiable skills for a virtual customer service agent. User profiling and targeted recommendations are capabilities that advanced virtual agents should also have in their toolkit. We could go even farther and list attributes such as a sense of humor, the ability to detect human emotion, and empathy. All of these would be desirable qualities in a customer-facing virtual agent.
Perhaps as Kurzweil / Google and others work towards recreating the human brain in digital form, advancements in cognitive computing, speech recognition, natural language processing, and other interrelated fields will be the outcome. It will be hugely interesting to see how software vendors in the virtual agent and personal digital assistant space capitalize on these breakthroughs to improve and reshape their commercial offerings.
A Techcrunch article today reported that sources indicate Amazon has purchased Evi, a mobile personal assistant and rival to Apple’s Siri. Apparently the purchase happened several months ago, but has been kept under wraps. Evi was the creation of True Knowledge, a British startup connected with university labs focused on natural language processing. In January, Amazon made another interesting acquisition when it purchased Ivona Software, a text-to-speech and voice recognition technology company featured on Kindle Fire tablets.
What does Amazon have planned for these technologies? Is Amazon on a path to roll out its own Amazon-branded smartphone? Or perhaps their aim is to incorporate more interactive voice technologies into the Kindle reading platform. It would be interesting to see if a true conversational agent could be incorporated into the Kindle. It does seem like a platform where users could greatly benefit from the help of a smart virtual agent. Wouldn’t it be nice, for example, to be able to ask an intelligent virtual agent for book recommendations like the book you just finished? Sure, you can go to the Amazon store online to browse recommendations based on your past buying and browsing history. But wouldn’t it be more compelling to get recommendations from your own virtual personal assistant?
Or maybe a Kindle-based agent could answer questions like “how many pages does this book have compared to the last one I read?” or “how many review stars does this book have compared to the other one that I read by this same author?” or “I don’t want to finish this book, but would you please tell me who the murderer is?” Okay, that last question would be cheating. I’m definitely interested to find out more about what Amazon has planned for the Evi and Ivona capabilities.
The Graphical User Interface (GUI) has dominated user-facing computer applications for the past three decades. As revolutionary as the GUI might once have been, it has its shortcomings. Application complexity increases almost as quickly as computer processing power. Mobile devices force application designers to squeeze more and more functionality into ever diminishing screen space.
So what comes next? A few weeks ago, Ron Kaplan of Nuance Communications wrote an article for Wired on the Conversational User Interface, or “CUI.” What Kaplan describes is a transition toward intelligent applications that human users can talk to in order to get things done. The basic technologies to enable this transition are already in place. We may soon be witnesses to the tipping point where conversational user interfaces replace GUIs and become the norm.
Kaplan points at mobile personal assistants such as Apple’s Siri and Samsung’s S-Voice and describes them as primitive first-generation CUIs. These apps can certainly help us with simple tasks, but the scope of their comprehension and helpfulness is limited. New, more advanced generations of intelligent conversational agents are just around the corner, Kaplan predicts, and their capabilities will far exceed those of today’s speech recognition apps.
Kaplan suggests that as machine learning advances, perhaps along the lines of the framework provided by DeepQA research, conversational virtual agents will graduate from simply understanding what we’re saying, to actually grasping our intent. Such a sophisticated CUI will be able to show us the exact movie we want to see, even when we can’t remember the movie title or the name of the leading actress. It will also understand hypothetical objects and future events, enabling it to respond to instructions such as “Let me know when I’m close to a good Italian restaurant, but not a major chain.”
The possibilities for intelligent virtual agents, just one form of future Conversational User Interfaces, are limitless. It only remains to be seen how quickly this important transformation will occur.