Amazon Builds a Visual Conversation

 Conversation flow with a No-code environment

Amazon Is Adding Visual Conversation Builder for Amazon Lex

SEP 19, 2022   in Infoq.com

by  Daniel Dominguez

Amazon is introducing the Visual Conversation Builder for Amazon Lex, a drag and drop interface to visualize and build conversation flows in a no-code environment. The Visual Conversation Builder greatly simplifies bot design.

Amazon Lex is a fully managed artificial intelligence service with advanced natural language models to design, build, test, and deploy conversational interfaces in applications. Amazon Lex provides high-quality speech recognition and language understanding capabilities. The visual builder, allows to build and manage complex conversations with dynamic paths. By adding conditions directly to Lex bot, and managing the conversation path dynamically based on user input and business knowledge, all within a no-code environment.

According to Amazon, no machine learning expertise is necessary to use Amazon Lex. Developers can declaratively specify the conversation flow and Amazon Lex will take care of the speech recognition and natural language understanding functionality. Developers provide some sample utterances in plain English and the different parameters that they would like to collect from their user with the corresponding prompts. The language model gets built automatically.

To create a bot, you will first define the actions performed by the bot. These actions are the intents that need to be fulfilled by the bot. For each intent, you will add sample utterances and slots. Utterances are phrases that invoke the intent. Slots are input data required to fulfill the intent. Lastly, you will provide the business logic necessary to execute the action. An Amazon Lex bot can be created both via Console and REST APIs.

Chatbots are majorly incorporated into messaging applications, websites, mobile applications and other digital devices for interacting as digital assistants through text or text-to-speech functionalities. They offer various benefits, such as improved efficiency of business operations, customer engagement, branding and advertisement, data privacy and compliance, payment processing and automatic lead generation and qualification. Other visual chatbot builder alternatives are IBM Watson Chatbot Builder, Microsoft Bot Framework, Meta Bots for Workplace, among others.   ... '

Tips for Implementing Conversational AI

 Some useful thoughts.

Expert Tips and Best Practices for Implementing Conversational AI

Michael Hartsog   in CustomerThink

The chatbots of the past had limited capabilities. They could answer a predetermined set of questions, but no more—which often left customers frustrated. But conversational artificial intelligence (AI) changed all that.

Conversational AI gives bots a greater ability to understand human language, sentiment, and intention. AI-enhanced bots can customize messaging based on real-time data and complete complex tasks and transactions.

Today, conversational AI is the perfect addition to customer service teams, giving companies a competitive advantage by increasing agents’ productivity, delivering a better customer experience, and increasing customer satisfaction.

Want to add conversational AI to your customer communications but don’t know where to start?

On the Let’s Talk CX podcast with SKWeston, I sat down to discuss the impact conversational AI has on customer satisfaction and agent productivity, along with the best practices I’ve identified after being in the customer experience field for over fifteen years. Of course, understanding the trends and technologies that will deliver exceptional customer experiences is key. And that’s where our partner, SKWeston & Company, provides guidance on identifying the best path for our clients’ unique needs. They’ve identified and implemented innovative solutions in areas such as:

Conversational AI platforms

Omnichannel knowledge management system

A reimagined BPO with unbound agents and technology .... .     .... 

Closer to Conversation

 Better Conversation in Context

Model Moves Computers Closer to Understanding Human Conversation

Piotr Zelasko at the Johns Hopkins Center for Language and Speech Processing has developed a machine learning model that can differentiate speech functions in transcripts of conversations generated by language understanding (LU) systems. The model performs dialogue act recognition by identifying words' underlying intent, and assigns them to categories like "Statement," "Question," or "Interruption" in the final transcript. Zelasko sought to ensure his system could understand ordinary conversation, which may help with such tasks as summarization, intent recognition, and detection of key phrases. Zelasko said LU systems no longer need contend with "huge, unstructured chunks of text, which they struggle with when trying to classify things such as the topic, sentiment, or intent of the text. Instead, they can work with a series of expressions, which are saying very specific things."

Complete Article

Paradox Olivia Recruiting

Pointed out to me:

Paradox software firm hits unicorn status with new $200M capital raise

By Andy Blye - Reporter,   December 27, 2021, 09:37am MST

Paradox, a Scottsdale company that makes conversational recruiting software, announced Monday that it had raised $200 million in series C financing that includes a company valuation of $1.5 billion, vaulting it to unicorn status.

The funding came from a bevy of investors, co-led by Stripes, Sapphire Ventures, and Thoma Bravo with participation from Workday Ventures, Indeed, Willoughby Capital, Twilio Ventures, Blue Cloud Ventures, Geodesic, Principia Growth, DLA Piper Venture Fund and current investor Brighton Park Capital.... ' 

Conversica Conversational AI

Blog: How Conversational AI Helps Revenue Teams Hit Q4 Goals

  Conversica Blog

As we get closer and closer to marking two years of COVID-19, the pandemic continues to affect how we all interact with each other, both in our personal lives and at work. That means Sales, Marketing, and Customer Success are again adapting methods of engaging with customers and potential customers. With the economy still recovering, businesses and people are generally more cautious about making purchases. That means revenue teams looking to hit their end-of-year goals will need to put more focus on working with existing customers and fostering those relationships—no easy task, as Customer Success and Sales teams know.

Whether you want to grow your customer base or further engage your current client base, AI is a trend that’s worth exploring. Sales, Marketing, and Customer Success teams are increasingly turning to Conversational AI technology to automate some of the mundane but critical tasks and fill the gaps in the buyer journey. Looking at Q3 and Q4, these are the four most promising trends we see for revenue teams. 

Email Engagements

Email has long been a bread-and-butter channel for engaging customers, but blending a targeted AI approach with in-email purchases is breathing new life into the old standard. In-email purchases streamline the buying process, making it so that the customer doesn’t have to click links that could look like malware. The added convenience for the customer can make marketing campaigns considerably more successful.

The more customers you have, the more difficult it is to conduct a successful outreach program. It can be more of a challenge to engage customers over email, and phone calls only have a slightly higher success rate. Using AI to engage customers through these media means Sales and Marketing can focus their time and energy where they can make the greatest impact, rather than spending hours putting together low-engagement messages.

Conversational AI for a Customized Approach

People want to be treated like people, not a number. A personalized approach goes a long way towards making your customers feel like you’re working to genuinely improve their experience. With people feeling more isolated again, that customized approach also helps to create a greater sense of connectivity. Personalization in marketing campaigns can create a sense of camaraderie, which can ultimately boost your results. 

Conversational AI offers an easy way of adding that customization and personalized connection. We’re not just talking about auto-filling the customer’s name at the beginning of an email. This technology can develop a personal message that focuses on products and services that could better serve the buyer’s individual needs. Conversational AI analyzes recent buyer behavior to target buyers and potential customers when they’re more likely to make a purchase or need something in addition to a product they’re actively considering.  ..... 

AI Talks Decisions and their Completeness.

Good approach.   There is I recall a way to rate how good an explanation of a decision is in healthcare.  How well was this done? Also, since should be a complete conversation, a give and take set of statements and questions, how well was that done?   Further, its important to note which questions were not asked, and how they relate to that complete 'explanation'.    Overall,  conversation correctness and completeness and how they relate to future decisions.  

AI Matches Cardiologists' Expertise, While Explaining Its Decisions

University of California, San Francisco News, Elizabeth Fernandez, August 26, 2021

Scientists at the University of California, San Francisco and the University of California, Berkeley designed an artificial intelligence (AI) algorithm that diagnosed cardiovascular ailments as well as expert cardiologists, while explaining its reasoning. The researchers trained the convolutional neural network on commonly accessible electrocardiogram (ECG) data. The researchers said the algorithm performed strongly across 38 different diagnoses in five broad diagnostic categories. Because the researchers incorporated "explainability" into the algorithm, it highlighted ECG segments critical for each diagnosis, which may boost physicians' confidence in using it. The researchers said their results “offer strong support for AI algorithms like neural networks to be incorporated into existing commercial ECG algorithms, since they perform better for many diagnoses, can improve over time and provide additional insights through explainability.”

Results in Taskbot Challenge

Instructive piece on the competitive challenge.     Like the idea. Would be interesting to track any of the contributions to actual public applications.  Nice to see one of my universities was a winner.  Will try to look at some of the entries/results for a later piece.

Amazon Picks Alexa TaskBot Challenge Finalists  in Voicebot.ai

ERIC HAL SCHWARTZ   By Eric Hal Schwartz

Amazon has chosen the 10 finalists for the Alexa Prize TaskBot Challenge https://voicebot.ai/2021/03/11/amazon-starts-new-alexa-prize-taskbot-challenge/  the newest contest run by the voice assistant developer. The chosen teams are based in universities in the U.S., Europe and Asia, each with a voice app designed to handle multi-step, complex tasks conceived in a conversation with a user.

TAKING ON TASKBOTS

Each team’s entry is supposed to be able to perform as an aide for carrying out cooking and home construction and repair projects. The idea is to develop an AI that goes beyond the limited, single task per order system most voice assistants use. A TaskBot is supposed to extend the conversation and gain enough information from a user to complete a longer, more varied project. In this case, those tasks relate to home improvement and cooking. Both are good examples of sometimes long lists of tasks hidden in a brief request like “cook a meal” or “repair a chair.” The challenge is also multi-modal, so the teams will need visual components to go with the voice app.

“Alexa already assists millions of customers in goal-directed interactions, such as ‘Alexa, play ‘Your Power’ by Billie Eilish’, or ‘Alexa, what’s the weather forecast for the weekend? With this new Alexa Prize challenge, we are now turning to multi-step and multi-modal task completion that can span hours if not days,” Alexa Shopping vice president of research and science Yoelle Maarek said in a statement. “I am delighted to see that so many quality university teams have expressed interest in addressing this hard AI challenge. This is a wonderful example of our customer-obsessed science approach where we join forces with academia to push the boundaries of science with the goal of delighting our customers.”

The 10 winning teams are from: Carnegie Mellon University, National Taiwan University (NTU), NOVA School of Science and Technology (Portugal), Ohio State University, Texas A&M University, University College London, University of California Santa Barbara, University of Glasgow, University of Massachusetts (Amherst), and the University of Pennsylvania.  ...  

Search is not a Conversation Yet

Search as AI,  and fundamentally conversation, putting it all together.    Google started with search, while the assistant providers started with the conversation.  Moving in the right direction. 

Google isn’t ready to turn search into a conversation

Despite Google’s whizzy AI demos at I/O, search is still served best by text  By James Vincent 

The future of search is a conversation — at least, according to Google.

It’s a pitch the company has been making for years, and it was the centerpiece of last week’s I/O developer conference. There, the company demoed two “groundbreaking” AI systems — LaMDA and MUM — that it hopes, one day, to integrate into all its products. To show off its potential, Google had LaMDA speak as the dwarf planet Pluto, answering questions about the celestial body’s environment and its flyby from the New Horizons probe.

GOOGLE’S DREAM IS TO SPEAK AND THE MACHINE WILL ANSWER

As this tech is adopted, users will be able to “talk to Google”: using natural language to retrieve information from the web or their personal archives of messages, calendar appointments, photos, and more.

This is more than just marketing for Google. The company has evidently been contemplating what would be a major shift to its core product for years. A recent research paper from a quartet of Google engineers titled “Rethinking Search” asks exactly this: is it time to replace “classical” search engines, which provide information by ranking webpages, with AI language models that deliver these answers directly instead?

There are two questions to ask here. First is can it be done? After years of slow but definite progress, are computers really ready to understand all the nuances of human speech? And secondly, should it be done? What happens to Google if the company leaves classical search behind? Appropriately enough, neither question has a simple answer.  ...