Zendesk: Sentiment and Intent With AL

Powerful direction,  How well?

September 15, 2022

Zendesk Launches New Customer Sentiment and Intent Functionality Powered by ML

SAN FRANCISCO, Sept. 15, 2022 — Zendesk, Inc. today announced Intelligent Triage and Smart Assist, new AI solutions empowering businesses to triage customer support requests automatically and access valuable data at scale. By democratizing access to these solutions, companies can see value in minutes by understanding intent and sentiment through account-specific, data-driven models that are customized for individual use cases and drive faster resolutions.

Industry analysts predict that in the near term, AI will touch the majority of customer service interactions, but Zendesk research shows less than a third of companies are currently using AI to help their service teams become more efficient. That’s in part because even as AI technology has rapidly improved in the last five years, software vendors haven’t yet passed those improvements on to their customers and are still selling expensive AI solutions that are extremely time-consuming to set up.

Intelligent Triage and Smart Assist are the next step in Zendesk’s vision to create accessible CX AI for companies of all sizes. The technology uses proprietary industry expertise and insights from trillions of customer data points and applies a vertical lens. This creates models custom to each business capable of identifying the intent, language and sentiment of each customer interaction.

This unique approach to applying machine learning creates more personalized and informed interactions to better serve customers. For example, specific inquiries, such as “I’m having problems with payment”, can be automatically sent to an agent who is equipped to handle billing for a quicker resolution, while inquiries that include language written in all capital letters or in a sarcastic way will indicate a highly negative sentiment and be routed to the top of the queue. ... ' 

AI and the Curious Consideration of Autonomous Intent

Context, Autonomy Intent... for Autonomous AI.  Considerable piece on the difficult problem.  Has not come close to technical solution.

Home  AI Trends Insider on Autonomy  On Whether AI Can Form ‘Intent’ Including In The Case Of Autonomous...

On Whether AI Can Form ‘Intent’ Including In The Case Of Autonomous Cars
By Lance Eliot, the AI Trends Insider

These remarks all have something in common:

The devil made me do it
I didn’t mean to be mean to you
Something just came over me
I wanted to do it
You got what was coming to you
My motives were pure
What’s that all about?

You could say that those are all various ways in which someone might express their intent or intentions.

In some instances, the person is seemingly expressing their intent directly, while in other cases they appear to be avoiding being pinned down on their intentions and are trying to toss the intent onto the shoulders of someone or something else.

When we express our intent, there is no particular reason to necessarily believe that it is true per se.

A person can tell you their intentions and yet be lying through their teeth.

Or, a person can offer their intentions and genuinely believe that they are forthcoming in their indication, and yet it might be entirely fabricated and concocted as a kind of rationalization after-the-fact.  ... " 

Verified, Intentified Phone Calling is Advancing

Will we soon get the inferred reason for a phone call?  Its getting a start already, in IOS I get already get 'likely spam', and who it is likely to be from, but why not inferring reasonable intent?

Really a kind of machine learning, from calls, texts and Contact info, and call message text, the data is there and growing.

Verified Calls for the Google phone app will let you know why a business is calling

Another addition to make calls more simple and seamless  By Caleb Potts in Android Police

Even though we don't generally use our phones for calling as much these days, the actual phone part of your phone is still important. Google has long worked to make phone calls less annoying with features like automatic call screening and spam detection. Now, it looks like a new Verified Calls feature is rolling out to help consumers know why a business is calling them before they pick up.

According to Google's support page, Verified Calls is a feature that helps users learn more about incoming calls before answering. Unlike call screening, which can be initiated by the user on any incoming call, Verified Calls only come from businesses that have gone through Google's approval process. When a call that meets the criteria is placed from an approved business, the user will see the business name and logo, as well as the reason for the call.  ... "

Teaching AI to be Better at Second-Guessing

Intent is a element of context that humans frequently use in adapting to conversation.

How humans are teaching AI to become better at second-guessing
by Lachlan Gilbert, University of New South Wales

One of the holy grails in the development of artificial intelligence (AI) is giving machines the ability to predict intent when interacting with humans.

We humans do it all the time and without even being aware of it: we observe, we listen, we use our past experience to reason about what someone is doing, why they are doing it to come up with a prediction about what they will do next.

At the moment, AI may do a plausible job at detecting the intent of another person (in other words, after the fact). Or it may even have a list of predefined, possible responses that a human will respond with in a given situation. But when an AI system or machine only has a few clues or partial observations to go on, its responses can sometimes be a little… robotic.  .... "

Detecting Misinformation Intent

This gets closer to true intelligence in a machine.   Determining likely intent with AI methods.   But how well does it do, better than humans?  How well do humans do?

Engineers develop new way to know liars' intent
in Tech Xplore 

Dartmouth engineering researchers have developed a new approach for detecting a speaker's intent to mislead. The approach's framework, which could be developed to extract opinion from "fake news," among other uses, was recently published as part of a paper in Journal of Experimental & Theoretical Artificial Intelligence.

Although previous studies have examined deception, this is possibly the first study to look at a speaker's intent. The researchers posit that while a true story can be manipulated into various deceiving forms, the intent, rather than the content of the communication, determines whether the communication is deceptive or not. For example, the speaker could be misinformed or make a wrong assumption, meaning the speaker made an unintentional error but did not attempt to deceive.  ... "

Referenced paper:

More information: Deqing Li et al, Discriminating deception from truth and misinformation: an intent-level approach, Journal of Experimental & Theoretical Artificial Intelligence (2019). https://www.tandfonline.com/doi/full/10.1080/0952813X.2019.1652354

Natural Language and Intent with Ambiguity

Good simple explanation from Tableau on Intent.   Have used the concept now in several projects, and of course there is ambiguity, beyond dictionary-definition,  in the use of many terms within a company.   The ambiguity in context is important to consider.

Machine learning, natural language meet to understand intent
 By Mark Jewett, VP of Marketing, Tableau

Machine learning and natural language processing promise to better translate human curiosity into pertinent answers. If true, these smart capabilities will broaden the use of analytics and reach people who are less comfortable dealing with data. It will all start with helping machines learn to interpret human intent. The key is semantics.

Sometimes intent is simple and explicit, like asking Siri or Alexa if a flight is delayed. This question has clear intention and a simple response—returning the flight status answers the question. Such simplicity is seldom the case when it comes to data analysis. Questions are usually more nuanced, making it hard to correctly assume what the user is really looking for. Natural language is even more tricky where ambiguous terms are common.

It’s also difficult for a machine to understand our intent within a limited context. The machine has the data itself but doesn’t grasp the bigger picture in the same way a person with domain expertise can. Asking “How are my sales doing in the Northeast?” is a lot more ambiguous than the flight status example above.

Ambiguity isn’t a new challenge in data analysis. Different groups within an organization may have different definitions or calculations for the same words: for example, the term “profitability”. Some organizations use central dictionaries (also called data catalogs) to reduce ambiguity and create consistency across the organization. These tools can help provide users with the context they need to understand more deeply. .... " 

Machine Learning and Intent

Deriving intent,  goals is still hard.  Especially in multiple component conversations.

Machine Learning, Natural Language Meet to Understand Intent     By Mark Jewett, VP, product marketing, Tableau Software in InformationWeek

Machine learning and natural language capabilities will bring the power of analytics to more people through semantics.

Machine learning and natural language processing promise to better translate human curiosity into pertinent answers. If true, these smart capabilities will broaden the use of analytics and reach people who are less comfortable dealing with data. It will all start with helping machines learn to interpret human intent. The key is semantics.

Sometimes intent is simple and explicit, like asking Siri or Alexa if a flight is delayed. This question has clear intention and a simple response -- returning the flight status answers the question. Such simplicity is seldom the case when it comes to data analysis. Questions are usually more nuanced, making it hard to correctly assume what the user is really looking for. Natural language is even more tricky where ambiguous terms are common.

It’s also difficult for a machine to understand our intent within a limited context. The machine has the data itself but doesn’t grasp the bigger picture in the same way a person with domain expertise can. Asking “How are my sales doing in the Northeast?” is a lot more ambiguous than the flight status example above..... "

Nuance Project Pathfinder

Back to still the biggest problem for assistant AI.   How do we create and manage context rich, memory enabled conversations between people and machines?  Here the claim it is not best done by developing all possible scripts, but about 'intent discovery'.

Nuance's AI uses real interactions to make chat bots smarter in Engadget by By Rachel England, 

Project Pathfinder draws on human conversation, not service scripts.

 "... Instead of using specially trained "conversation designers" to create dialog patterns, Project Pathfinder leverages machine learning and AI to read existing transcripts of conversations between human service agents and customers, and creates a new workflow based on that data. Using what Nuance calls "intent discovery," the system is able to build a comprehensive conversation map to build a visual representation of all the different avenues its customer service conversations take -- from first question to each follow-up-- to reveal the best paths to resolution, as well as unknown problem areas. ... " 

More on Nuance Communications.
See their blog in Intent Discovery.

Intent, Devices and Marketing Funnels

In Think with Google. Nothing is linear anymore.  Our devices can change our intent, based on changing context, anytime.    So how do we use this?

Intent and Marketing Funnels

How intent is redefining the marketing funnel     ... 

Forget everything you know about the marketing funnel. Today, people are no longer following a linear path from awareness to consideration to purchase. They are narrowing and broadening their consideration set in unique and unpredictable moments. People turn to their devices to get immediate answers. And every time they do, they are expressing intent and reshaping the traditional marketing funnel along the way.   ... 

Journeys as unique as each consumer

So how has the marketing funnel changed exactly? In the last six months, Google looked at thousands of users’ clickstream data as part of an opt-in panel.1 And we found that no two customer journeys are exactly alike. In fact, even within the same category, journeys take multiple shapes.2 .... " 

Ford Looks for Common Car Language

Makes lots of sense.

Ford asks for a common language for self-driving cars
It wants every car to signal its intentions the same way.

Jon Fingas, @jonfingas in Engadget

Ford has been developing its own means for self-driving cars to communicate their intent, but it also knows that fragmentation could be a huge problem in the autonomous driving world. How are you supposed to know what cars are doing when each one has a different visual cue? Accordingly, Ford has issued a memorandum of understanding that asks the industry to create a signalling standard for cars capable of at least SAE Level 4 automation (that is, they can handle all driving tasks under some conditions). It hopes the exchange of standards will lead to a common language that human drivers and pedestrians will understand, regardless of where they live or how tech-savvy they may be.... " 

Cisco Talks Network Assurance with AI

Specific term was new to me.  But I do like the link to the business, the process, the goals.  Are the intents the same as in a simulation model of the business process?   Risks?  Reading more. 

Machine Learning for Analytics and Assurance
By Duval Yeager in Cisco Blog.  Network operation based in the intent of the business.  Goals?  Intriguing.

We are hearing amazing stories from our Cisco customers as they roll out intelligent analytics and assurance solutions in the form of Cisco DNA Center, Meraki insight, and Network Assurance Engine (NAE). The comments are on the accuracy and complexity of the analytical models that we have built, based on 30 years of Cisco networking leadership. You can read my blog post on how analytics works here. But, the back story to this is the approach of Machine Learning. When we add advanced machine learning algorithms to these products, the intelligence and system flexibility will be even more exciting. Let me explain…

Assurance in IP networking uses an analytics engine to verify that the network is operating based on the intents of the business. These intents are translated based on the network policies that IT configured when the system was set-up. The resulting model drives the decisions that an assurance solution makes to improve the network. This model is very good at network optimization, but every network is different, and network utilization is always changing as we change the way we use it  .... " 

Shiseido: Predicting Intent, Driving Beauty Growth

In Think with Google,  predicting future behavior.

How one beauty brand is predicting intent to drive growth

Alessio Rossi, global chief digital officer at Shiseido, says that to truly grow, brands must stop reacting to customer intent and start anticipating it.

Beauty shoppers today are passionate and curious. They spend hours researching product benefits and reading reviews before deciding what to buy. Even product aspects that were once low consideration, such as ingredients, now generate hours of research time.

Given how research-obsessed people are, we, as marketers, can’t afford to just react to in-the-moment behaviors. That would leave us one step behind. We have to anticipate what people might need and deliver it to them in meaningful ways.

At Shiseido, we’ve built our business around anticipating our customers’ needs, because it’s the best way to deliver strong results. Here’s what we’ve learned along the way  . .... 

We realized that we also needed to predict what other kinds of products might excite them. People can’t tell you exactly what they might want next, so we take cues from past actions to predict future intentions. We call it showing people “the right amount of wrong.” We may not always get it right, but we will continue to learn and provide value as we nurture these relationships.

Give value to get value

Our customers are willing to provide information about their preferences because we give them value in return. And the more information we have about our customers, the better we can infer their needs. As soon as we stop providing that value, we lose their trust. So we take this relationship seriously.  ... "

Bots in the Twittersphere

A quite interesting view of Bots in the twittersphere.  From PEW below.  Useful definitions.   Which points out that they are not close to mostly out to make mischief, but also a useful part of the infrastructure.   Call them automated accounts if you like.  Just like there are many, many automated systems out there,  which query their environment and some action:  assisting, adapting, counting, sensing .....  You could call it all an IOB  (internet of Bots)  Some human,  some machine, some sensor ...  simple and complex.  Makes me think about about the detection of intent.   Can we measure the intent of an automated bot?    By its actions, developers?

A considerable piece of work below that made methink ... read it all:

Bots in the Twittersphere
An estimated two-thirds of tweeted links to popular websites are posted by automated accounts – not human beings .... " 

      ... By Stefan Wojcik, Solomon, Messing  AAron Smith, Lee Arainie and Paul Hitlin

Fast and Automatic Translation

We spent lots of time using translation services to understand how consumers interacted with product.  Now we re not far away from automating the process.  My desktop assistants do it already.     Some aspects, like Intent analysis are already being installed in natural language analysis.

Soon Talking to Strangers will be even easier.    
 by David Pierce in Wired.When translation happens quickly and accurately, we’ll be able to experience places in an entirely new way.  ... "