-->

Video: How to Train Virtual Agents to Recognize Customer Needs

Learn more about virtual agents at the next SpeechTEK conference.

Read the complete transcript of this clip:

Brett Knight: I want to level-set on interaction types. First, there's just understanding the need that they have. That means taking in questions. It's not just the text of what they ask for or what they say or speak, it's any other data we have about them to help influence what the understanding is, where they launched from, what products they have, things like that. Taking that data and then coming up, here's what we understand your need is.

Then on the response side of things, we call it simple, that counts for the navigation. Let’s say you need an auto quote, click here or tap here to do that. So that's just simple, doesn't require any account lookups, data, services, or even any significant dialogue.

Complex account: This one's not much dialogue at all, but I need data. So even if you’re looking for USAA's routing number, which is still the number one question asked despite making it more prominent in doing different things. What's USAA's routing ABA, routing number? Because we actually have two different banks, so there's two possible routing numbers we could surface up. So we want to provide the right answer. We don't want to, just for that question, we don't want to ask, "Well, do you have accounts at more than one bank?" Because most don't actually. Most just have the one routing number that's applicable. But we do a data lookup. We look up the member's account information.

Now if they do happen to have both, that does lead into a bit of a dialogue. But again, it requires data. Now a complex dialogue that is, one that may or may not have data needs—it might be, “I would like insurance.” As I said earlier, we have life insurance, auto, home, all these things, so we need to create some dialogue to do that. It's just another form of complex.

And then transactional is all that—say, “I need to replace a card.” Well, why do you need to replace a card? There's a dialogue that has to happen. In that case, we've deemed having a conversation is actually better-performing than just clicking buttons and drop-downs and things like that. But it requires a transaction and, depending on the services that are available, you may need to incorporate rules, fraud rules and all kinds of other things. It's not just a “here's a question, here's an answer” type of interaction.

SpeechTek Covers
Free
for qualified subscribers
Subscribe Now Current Issue Past Issues
Related Articles

The Downside of Directed Dialogue NLU (Video)

Omilia's Quinn Agen discusses the value of context and memory in delivering human-like interactions in self-service contact centers in this clip from SpeechTEK 2018.

Video: The Downside of Directed Dialogue NLU

Omilia's Nikos Kolivas discusses the value of context and memory in delivering human-like interactions in self-service contact centers in this clip from SpeechTEK 2018.

How Conversational Self-Service Improves the Contact Center Experience (Video)

Omilia's Quinn Agen discusses the way an an end-to-end conversational approach in machine-to-human interaction helps deliver satisfying contact center experiences in this clip from SpeechTEK 2018.

How Machine Learning and AI Can Enhance Virtual Agent Training (Video)

USAA's Brett Knight discusses how USAA has used machine learning and AI in virtual agent training at the enterpise level in this clip from SpeechTEK 2018.

Why Customers Prefer Conversational Self-Service (Video)

Omilia's Quinn Agen discusses the advantages of taking a conversational approach in automated contact center customer care in this clip from SpeechTEK 2018.

How to Assemble a Conversational Development Team for Virtual Agents (Video)

USAA's Brett Knight describes all the players enterprises should assemble when planning conversational development for virtual agents in this clip from SpeechTEK 2018.

Video: Rules-Based Chatbot Design, Part 2: Visual Representation and Support

Aspect's Andreas Volmer discusses the value of visually representing conversational flow logic in chatbot design, and explores the advantages of a language-based approach over a statistically based approach in this clip from SpeechTEK 2018.

Video: How Amazon Connect Leverages AI in the Contact Center

Amazon Connect General Manager Pasquale DeMaio demos Amazon Connect AI-driven Lex chatbot in this clip from his keynote at SpeechTEK 2018.

Video: How Do You Build Engaging Contact Center Experiences?

AWS Head of Product, Language Tech Vikram Anzabhagan outlines 4 essential strategies for leveraging technology to make contact center interactions more personal, conversational, agile, and engaging in this clip from his SpeechTEK 2018 keynote.

Video: How Hardware Advances Have Transformed NLP

O'Reilly Media's Paco Nathan discusses the explosive growth in CPUs and GPUs that have opened new vistas for natural-language processing applications and rendered old approaches obsolete in this clip from his SpeechTEK 2018 keynote.

Video: What Can NLP Do for Your Converted Text?

Paco Nathan of O'Reilly Media's R & D Group discusses the benefits of natural-language processing (NLP) when working with text converted from video in this clip from his SpeechTEK 2018 keynote.

Video: How to Improve UX and User Rating for Your Alexa Skill

Witlingo Product Manager Navya Nayaki Yelloji discusses the successful product development and QA strategy Witlingo created for its Motley Fool Alexa Skill in this presentation from SpeechTEK 2018.

Video: Are Chatbots Here to Stay?

You can hardly visit a company website without a chatbot popping up to offer you help these days. But these days, chatbots are helping with everything from mental health to identifying possible online predators. Is this trend here to stay? We asked Michael McTear, Allyson Boudousquie, Debra Cancro, and Crispin Reedy at SpeechTEK 2018.