Ray Kurzweil’s Ambition and Musings on The Future of Virtual Agent Technology

Digital BrainSingularity 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Older conversational agent technologies will most likely be superseded by new ones.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.

Out With the GUI. In with the Conversational UI.

Person Talking to SmartphoneThe 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.

Virtual Agents to Help Ease Transition to Arvest Bank

Intelligent Virtual Agent

IntelliResponse issued a press release today announcing Arvest Bank as a new customer of their virtual agent technology. Arvest Bank, one of the largest banks in Arkansas, has an interesting and compelling use case for virtual agents. With its history of rapid growth through the acquisition of other regional banks, Arvest often has the challenge of acclimating new customers. Virtual agent technology offers an effective approach to providing targeted support to these newly acquired customers.

Just about everyone finds change unsettling. It’s especially nerve wracking when the bank you’ve grown accustomed to is taken over and you’re forced to learn new systems and processes. Based on the press release, it looks like Arvest management has made a commitment to help ease the transition of these new customers by providing IntelliResponse virtual agent technology on the Arvest website.

According to the press release, banking customers will be able to interact with an intelligent virtual agent 24/7. I’m assuming that IntelliResponse will work with Arvest to prepare a knowledge base of frequently asked questions and perhaps provide the agent with access to existing data sources. Having a virtual agent available to walk them through the transition process will most likely be reassuring to many customers.

IntelliResponse has a patented core technology that apparently enables its virtual agents to understand the broader context of a question, even if the question is asked in different ways. This helps the agent return a more direct response that best addresses the real intent of the inquiry.

The press release also indicates that customers can be escalated to a live human support agent if the virtuel agent is unable to assist them. We look forward to seeing Arvest’s new virtual support agent in action.

Virtual Agent Wendy Offers Customer Support

VirtuOz WendyVirtuOz, Inc. issued a press release back at the beginning of the year announcing the launch of Wendy, a virtual agent support rep for Windstream Communications. According to the press release, Wendy offers 24/7 support to Windstream customers who may be experiencing problems with their high-speed Internet, digital TV, home phone, or other Windstream services.

Wendy doesn’t speak, but her avatar appears onscreen as a young professional clad in a Windstream branded polo. She is trained in basic troubleshooting. For example, if you let her know that you’re having trouble with your Internet connection, she’ll suggest that you try rebooting your modem and wireless router. If her suggestions don’t help you fix the problem, she can direct you to live support or to an appropriate email address. For just about any support question you can think to ask, Wendy offers up multiple links to relevant information that she thinks might address your issue.

Wendy seems to be a good example of a virtual customer support agent, offering customers another channel to get their problems resolved.

I’m Sorry You’re Upset

How Are You FeelingFeeling angry, depressed, or maybe happy as a clam? It may not be long before an intelligent virtual agent you’re conversing with is able to accurately gauge your emotional state. Advances in technology are enabling artificially intelligent software to pick up on subtle queues in human speech patterns. In the article Teaching Computers to Hear Emotions, IEEE reports on recent work by interns at Microsoft Research with spoken language software systems. Their work shows that software can have a surprising success rate at predicting a speaker’s emotional state by examining variations in the loudness and pitch of the speaker’s voice.

The implications for intelligent virtual agent technologies are just beginning to be explored. Obviously, a digital customer support agent that is able to sense when a customer is losing patience or becoming angry will be better equipped to serve the customer effectively. Recognizing the onset of negative emotions could prompt the virtual support agent to take a different approach with the customer. In some cases, a change in emotional state may be a signal to the virtual chatbot to escalate the conversation to a human support agent.

As speech recognition and spoken language systems become more sophisticated in picking up on human emotional queues, the applications in the realm of virtual agents, digital support representatives, and artificial intelligence in general are limitless.

Creating a Virtual Agent Chatbot for Your Business

Build Your ChatbotWhile it’s possible to develop a smart virtual agent from scratch, there are a number of software companies that provide easy-to-use and cost effective options for creating a customized virtual agent, or what is commonly referred to as a chatbot. I’m not affiliated with any of these companies. I’ve tried out some of the virtual agent products and I’ve chosen two at random to spotlight in this blog post so that you can get a feel for what’s involved in creating a conversational virtual agent for your business.

The chatbot companies we’re looking at in this post are MyCyberTwin and Chatbot4U.com.  At first glance, the companies seem quite different. MyCyberTwin presents itself as a virtual assistant vendor with products geared towards businesses. Chatbot4U looks more like a social site geared towards a younger crowd interested in creating and talking to chatbots impersonating popular teen idols. When I looked a bit further, though, I found that these two virtual agent providers have relatively similar business models, tools, and pricing structures.

Building Your Custom Chatbot

Both MyCyberTwin and Chatbot4U.com offer fairly straightforward user interfaces that allow you to program, or ‘train’, your chatbot without having to write any code or markup.  Both offer chatbots that you communicate with via typed input. You don’t speak directly to the virtual agent, but rather talk to it via text messages. Once you’ve created your free user account, you can create a blank virtual agent chatbot and then start filling its knowledge base with input (questions) and output (response) phrases.

With MyCyberTwin, you can start by specifying a website that you want your chatbot to reference to see if it can find answers to questions. This is a great feature, because it means that your chatbot will have at least some limited ability to successfully respond to questions that you might not be able to predict, or exactly replicate, in advance. For example, if someone asks the chatbot how to contact you, but you didn’t think to include this question in the chatbot’s knowledge base, there’s a good chance the chatbot may be able to point the person to your website’s “Contact Us” page, since it will use keywords to locate the appropriate content.

MyCyberTwin allows you to select one of several very life-like avatars to represent your virtual chatbot. When you embed the chatbot code into your website, the animated avatar appears in a separate window and invites the visitor to engage in conversation by typing in messages.

With Chatbot4U, you can set your virtual agent’s avatar by uploading a photo. The avatar is not animated. As you train your chatbot, you have the ability to add multiple layers, or ‘go backs’, to an ongoing conversation. For example, if the visitor types in the question “How are you?,” you can train the chatbot to respond “Fine. And how are you?” Then you can have the chatbot say something more or less appropriate when the visitor responds. These types of meaningful threads are typical and essential to human dialog. They’re difficult to recreate with current chatbot technology, however, because a chatbot has a very limited memory and can’t remember what it said beyond its last utterance.

Another useful feature of the Chatbot4U platform is that it allows you to add knowledge modules to your virtual agent. These modules endow your chatbot with the ability to tell jokes, to provide current weather information for any location, and search Wikipedia.

Training your chatbot is a simple procedure on both of these platforms, but it’s a time consuming endeavor. I recommend that you pick an area of your business that you want to concentrate on, such as your FAQs. You can also use my blog post Does Your Business Need a Virtual Agent? for some ideas on how to train your virtual assistant. You’ll want to create as many possible questions as you can think of and provide the best answer to the question. Training the virtual agent is simply a means of defining what the chatbot will say in response to pre-defined questions. To liven things up a bit, you can provide more than one answer to the same question and the virtual agent will randomly vary which response it uses.

Testing Your Chatbot Trial Version

MyCyberTwin and Chatbot4U.com both offer a free, personal version of their chatbot technology that you can try out with no time limit. The personal version lacks some of the features of the business version. Starting with a personal virtual agent will give you practice in using the platform and help you get a feel for creating conversational inputs and outputs.

Both vendors also offer you the option of running a 30-day trial of the full business chatbot. You can take advantage of the complete functionality available for training your virtual agent, including providing it access to web-based information sources, adding apps, and creating go-backs for more realistic conversations. I recommend that you converse with your chatbot at least a dozen times before you publish it to your website. Make a note of any questions you can think of that the virtual agent can’t answer. Converse with the agent as you would with an actual person and make sure that it has good responses for typical greetings and questions. You can also train the chatbot to direct the conversation towards its preferred topics about your business.

How Much Will Your Chatbot Cost?

At the time I’m writing this post, both MyCyberTwin and Chatbot4U.com offer basic, introductory chatbot solutions at the low-end of the price range for intelligent digital agents. Both will host your chatbot for around $25 a month. The fee includes some level of reporting, which will allow you to track conversations and train your virtual assistant to answer questions that it missed.

In future posts, we’ll look at the process for coding your own customized chatbot from scratch.  We also recommend that you visit Chatbots.org if you’re interested in seeing a thorough listing of virtual agent vendors available on the market today.

When the Virtual Debt Collector Comes Knocking

Virtual Agent Collecting on DebtIn my last post Does Your Business Need a Virtual Agent, I provided a couple of examples of how local businesses might leverage intelligent virtual assistants ton their websites to gain competitive advantage. Today I ran across a company that has an even more targeted use for virtual agents. InterProse offers  the Ammina Virtual Agent that is specially geared towards collecting from your delinquent customers.

This is a pretty clever use of non-human intelligent agents. It seems to make intuitive sense that when you’re behind in your payments, you’d rather avoid talking to a real person about it. The interaction is awkward and a human agent is more likely than not going to try to pressure you into paying. There’s something less threatening about a machine that refrains from judging you, but that’s simply there to state company policy and maybe even offer you some settlement options to consider. It’s also somewhat comforting to know that you’re not going to be subject to human emotions. Even if you lose your cool, the virtual agent is guaranteed to treat you with the same dispassionate politeness.

Check out the Interpro debt collection virtual agent for yourself.