What is Cognitive Engage

Nexright Cognitive Engage is a Customer Experience platform built for Enterprises leveraging IBM’s Watson. It provides rich features needed to build Digital Assistant and Chatbot solutions.

Cognitive Engage platform
— integrates with Enterprise structured, unstructured and real-time data
— rich engagement to choose from including voice, social, web, mobile
— rich visual and UX for a variety of conversational experience development
— leverages meaningful insights in the unstructured text without writing any code.
— custom NLP domain model development
— rich analytics and continuous experience improvement
— built-in security and privacy for information and data protection

Cognitive engage provides
— Customer support automation with FAQ, Knowledge-based advisory
— Lead generation leveraging product recommendation and promotion

Chatbot for Superannuation

Chatbot as a Super Coach to improve member engagement

While chatbot development is in its infancy relative to other digital communications, the majority of consumers who use bots to connect with a business are left with a positive impression.  It’s clear that the digital experience is evolving, and brands that want to stay ahead of the curve need to know two things: how best to employ this new technology and what their most coveted demographics are doing with it.

This technology offers a new human interface, which is particularly interesting since much of the current human interaction with technology is through a screen, a very old-fashioned approach. The fact that the economically powerful millennial generation has such a strong interest in chatbot and messaging means that they are here to stay, and will doubtless improve over time.

In context to Super industry, a simple chat window is all you need to interact with your new Super coach. If you previously needed a separate application for managing your Super, understanding Super that aligns with your Goals, planning for retirement and investment portfolio now you can perform all these actions without leaving the chat window.

From the functional standpoint, a Conversational experience will be able to issue voice and text commands and receive responses in the form of a text in simple user interfaces. While most people consider chatbots text-only interfaces, we are already using various UX models that can be used in bots solutions. The interactions are at the forefront of UX and UI design.

There are a tremendous opportunity and interest in creating holistic Conversational solutions that can strengthen the ability to improve Super member experience in mobile and connected devices.

 

 

Recently, the maturity of chatbot applications, natural language processing, and machine learning has given us an entirely new angle to approach real-time, personalized member experiences. Chatbots are the ultimate culmination of universal content accessibility and the personalization effort.

The Bots Are Here to Stay. Let’s Feed them Content:

Members or new users sometimes find it difficult to find information and understand how Super and retirement planning is relevant to their situation.

Without realizing it, content marketers have been progressively working to make Super content behave more like a chatbot for years. Think about it. Every personalization, automation, customization, and segmentation innovation has been enacted to deliver engaging, personally-tailored content directly to the member. Strategies, tools, platforms, and architectures have been moving more and more towards real-time content suited to exactly what our member needs to experience right now.

How Can You Make Sure Your Chatbot Is Actually Intelligent: 

In an interactive dialog process, Chatbot can help in setting up goals for retirement and guide users through an easy, actionable steps towards achieving those goals.

Whether it is reviewing contributions or assessing investment profile,  chatbot needs to have a better context. This relates it to having access to member information. This will not only smooth the onboarding process but also impress and reassure the user that they are dealing with a fund that knows what it is doing – and cares.

 

 

 

 

What is Conversational commerce

Conversational commerce is a term coined by Uber’s Chris Messina.

What is Conversational commerce: conversational commerce largely pertains to utilizing chat, messaging, or other natural language interfaces (i.e. voice) to interact with people, brands, or services and bots that before have had no real place in the bidirectional, asynchronous messaging context.

The net result is that you and I will be talking to brands and companies over Facebook Messenger, WhatsApp, Telegram, Slack, and elsewhere before year’s end, and will find it normal. Indeed, there are several examples of this phenomenon already, but those examples are few and far between and fit in a Product Hunt collection rather than demand an entire App Store

Conversational commerce refers to the intersection of messaging apps and shopping. Meaning, the trend toward interacting with businesses through messaging and chat apps like Facebook Messenger, WhatsApp, Talk, and WeChat. Or through voice technology, like Amazon’s Echo product, which interfaces with companies through voice commands.

Consumers can chat with company representatives, get customer support, ask questions, get personalized recommendations, read reviews, and click to purchase all from within messaging apps. With conversational commerce, the consumer engages in this interaction with a human representative, chatbot, or a mix of both.

On the business side, companies can use chatbots to automate customer service messages. It’s how companies are enabling consumers to buy from them without ever leaving the messaging app they are using. Now companies can send order confirmations in Facebook Messenger, as well as shipping and delivery notifications. Using chatbots, businesses can resolve customer service issues, provide recommendations, create wishlists, and interact with buyers in real-time.

How businesses can adopt this technology

  • Product recommendation e.g. helping customers in selecting a financial product like Loan, Health Insurance, Promotions.
  • Complement existing E-commerce platform with new User Experience.
  • Customer experience improvement: Buyers are changing how they buy: Educate and enable buyers to make an informed decision before they purchase.

 

What is Conversational commerce

 

 

According to Havard Business review published article, “To Keep Your Customers, Keep It Simple“.

Consider the marketing activities of two digital camera brands. Brand A’s search engine strategy is to pick up any consumers who are searching common digital camera terms and direct them to the company website. There they find extensive technical and feature information and 360-degree rotatable product photos, all organized and sortable by model. In stores, shelf labels list key technical attributes, such as megapixel rating and memory, and provide a QR code that takes consumers to a mobile version of the brand’s website, where they can dig more deeply into product specifications.

Brand B’s search engine strategy is to first understand the consumer’s intent and wherein the search process she is likely to be. Why does she want a camera? Is she just starting to look, or is she ready to buy? The company guides those in the early stages of investigation to third-party review sites (where its cameras get good marks) and directs consumers who are actively shopping to its own website.

User reviews and ratings are front and center there, and a navigation tool lets consumers quickly find reviews that are relevant to their intended use of the camera (family and vacation photography, nature photography, sports photography, and so on). In stores, Brand B frames technical features in nontechnical terms. Instead of emphasizing megapixels and memory, for example, it says how many high-resolution photos fit on its memory card. The QR code on shelf displays leads to a simple app that simulates one of the camera’s key differentiators, a photo-editing feature.

The highly detailed information Brand A provides at every step on the purchase path may instruct the consumer about a given camera’s capabilities, but it does little to facilitate an easy decision. Brand B simplifies decision making by offering trustworthy information tailored to the consumer’s individual needs, thus helping her traverse the purchase path quickly and confidently. Our research shows that customers considering both brands are likely to be dramatically more “sticky” toward Brand B.

Every brand can create their own buyer’s cognitive profile, to provide personalized recommendations based on various criteria, for example, pricing, color, fit, style preferences, digital engagement patterns, and prior shopping history—online or in-store.This will drive massive jumps in conversion and engagement rates.

We have released Conversational Commerce capability as part of our Cognitive Engage platform today. Some of the features underlying this include Ubiquitous Natural Language Understanding, Leverage Customer Structured and Unstructured dark data, Virtual Assistants and Virtual Advisors, Co-Existence of Short-form and Long-form Dialogs, Personalization Drive Innovation & Customer experience, Customers Taking Control.

Let’s discuss how this can help your brand in driving new customer experience strategies.

Custom NLP by integrating Amazon Alexa with IBM Watson

Amazon is winning the smart home speaker battle.

New data from Strategy Analytics suggest that Amazon’s Alexa smart assistant is beating Google in the home. Strategy Analytics found that Amazon Alexa will be on 68 percent of all smart speakers by the end of the fourth quarter of 2017. This includes Echos built by Amazon and other products built by third parties that also run Alexa. Sonos will soon launch a speaker running Alexa, for example.

Amazon’s Echo home speaker and the device’s built-in Alexa voice-activated assistant spring into action any time you call out, “Alexa.” You can cue up music, call an Uber, or play games. If you have Internet-connected home devices you can turn on the lights with your arms full of groceries, or adjust the thermostat without lifting a finger. It’s incredibly handy.

Alexa is really cool because it’s extensible, via what Amazon calls “Skills.” The Echo is pretty cool too, mainly because it has a great audio input system, consisting of seven “far field” microphones. It enables the Echo and Alexa to pick up voice when other systems wouldn’t.

Once you have an Amazon developer account, creating an unreleased, private-to-you Alexa skill is really easy. There’s an option to create one within the Amazon Developer Console, and it’s a few simple steps:

  1. Set the Skill name and its “Invocation Name”. The invocation name is what the user says to start your skill from Alexa’s “root menu.”
  2. Create the Interaction Model. This is Amazon’s term for the data that will be used to train its Natural Language Processing (NLP) system with the terms and questions unique to your Skill.
  3. Connect to either an AWS Lambda function or an HTTPS endpoint. This is the programmatic logic that controls how your skill responds to the user.
  4. Test it! You can submit text via the console, or you can use an Echo linked to the Amazon developer account.

We chose to use Lambda for the logic system since we are familiar with it. (Lambda is also one of the places developers can run their conversational app’s business and routing logic). Getting a basic Skill up and running was trivial. Amazon’s sample projects provide a decent starting point.

But we wanted to go beyond a simple Alexa skill. We wanted to talk back and forth with it to enable recommendation or advisory system.

Alexa isn’t really set up for interactive and longer conversation. Or more accurately, it is, but only to the extent that most bot building platforms and frameworks are today.

It looks something like this:

  1. Message comes in from user
  2. An NLP system classifies that message into an “intent,” and extracts relevant information into “slots.” An example of slot extraction would be extracting “SUV for Family” from the sentences “I am looking an SUV for my Family”, while the intent might be “Find a Car”.
  3. To recommend a car requires further qualification of user needs e.g. the budget, size, safety needs, brand preference etc. which can be very chatty and longer.
  4. The results from the NLP system get sent to the logic system — in this case, a Lambda function that Alexa is invoking — which then routes it.

The problem here is step 3. That’s because we wanted to go beyond basic question and answering with the Echo. We wanted to ask follow-up questions and recommend or advise.

Typically, handling followup messages mean tracking the conversation state in your bot or Skill’s logic system, then handling the intent from the NLP system in various ways depending on where the user is in the conversation flow. It’s a clumsy, but necessary technique in most systems.

But we know that conversations can be handled a little more elegantly than that.

So we addressed these limitations: Alexa meets IBM Watson

We made an Alexa app with custom NLP and business logic, using Alexa’s pre-built NLP system only as a channel. Using IBM Watson’s advanced Conversational and NLP system allowed best of both worlds.

Solution

 

Amazon’s strategy with Alexa is to allow the assistant to extend beyond just voice-controlled speakers it manufacturers. The company has also included the assistant in its Amazon mobile shopping app and has made it available to third-parties for use in their own hardware and software applications.

Is your brand ready to tap this market?

 

 

IHearYou : Empathy is the foundation in Conversation design

 

IHearYou is a human-centric design approach and a conversation framework that augments human intellect.

IHearYou are set of best practices developed by Nexright to design conversations. It is built with Empathy as the foundation. Realizing Empathy answers powerfully that we can and ought to have what we want. It is a humanistic map with a focus on relationship-focused interactions instead of technology-focused one.

Realizing Empathy signals a long-needed transition from technocratic paradigm to human bias. Simply put, we need to feel empowered enough to feel a sense of freedom in our relationship to computer technology. The kind that can help us engage in a dialogue with the machine.

To realize empathy in relation to another requires that we make new, meaningful, and coherent relationships where there previously were none considering the context of the other.

Continuous Automated Testing and Training Framework for Watson Conversation

For cognitive projects, a majority of the effort is spent on Conversation design.  It is usually is a continuous process as it needs to be. Continuous training and Continuous test data validation with End-user trials is key to a successful rollout.

So how do you ensure that a small change to your conversation design won’t break everything else? The key is regression testing.

How do you ensure that a continuous change in your re-training efforts is working as expected?

Following are some of the areas that need to be tested/validated on a continuous basis.

 

 

Below are some the challenges that need to be addressed to scale a Conversation centric application.

To support best UX Practices for building Chatbots, Human-centric dialog design is key so that the end user finds what it is looking for in a guided process. This means designing and testing multi-entity scenarios.

A conversation (or chat) is a chain of statements exchanged between two or more individuals. Mostly, conversations happen on a particular topic or in a situation. Whatever the topic or situation is, Context is very important to maintain the state of a conversation. Making sure your training process or validation of test data supports context is a challenge.

Nexright Watson Conversation testing/training framework

We have developed a testing and training framework to address some of the above needs. Nexright Watson Conversation testing/training framework support both technical and business users. For example

  • User Interface for Business users
  • Jenkins (open source continuous integration tool) for Technical developers

The framework supports some standard areas including Response accuracy, Intent identification, Entity Identification, Confidence level. The user interface allows business SME or Domain experts to identify all unmatched intent.