{"id":1886,"date":"2020-08-21T16:10:57","date_gmt":"2020-08-21T14:10:57","guid":{"rendered":"https:\/\/www.codemotion.com\/magazine\/uncategorized\/conversation-ai-is-the-new-ux\/"},"modified":"2021-12-23T12:56:57","modified_gmt":"2021-12-23T11:56:57","slug":"conversational-ai-new-ux","status":"publish","type":"post","link":"https:\/\/www.codemotion.com\/magazine\/voice-digital-assistants\/conversational-ai-new-ux\/","title":{"rendered":"Conversational AI Is the New UX"},"content":{"rendered":"\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t\t\t\tTable Of Contents\t\t\t\t\t\t<\/div>\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t
\n\t\t\t\t\t\t
  1. Targeting the Internet of Things<\/a>
  2. Forget the past: you need a new mindset<\/a>
  3. API-based multi-channel AI solutions<\/a>
  4. Talking to the user<\/a>
  5. Want to launch a developer event despite the challenges of COVID-19?<\/a><\/ol>\t\t\t\t\t<\/div>\n\t\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\n\n\n

    The use of chatbots<\/span> is a fast-growing trend<\/span> that meets the needs of all stakeholders. According to recent research, 80% of customer<\/span> interactions can be resolved by well-designed bots<\/a> (Accenture), 60% of consumers want easier access to self-serve solutions for customer<\/span> service (Ovum), and 50% of enterprises will spend more on bots than on traditional app dev in 2021 (Gartner<\/span>). This makes chatbots<\/span> a great market for all developers<\/span>.<\/p>\n\n\n\n

    If you are interested in fully understanding the potential of this area and the positives and negatives of the existing technology, don\u2019t miss the opportunity to attend the Codemotion Online<\/span> Tech Conference<\/a><\/strong> in October 2020! <\/p>\n\n\n\n

    If your interest turns more towards knowing more about how modern technologies and tools can support you in the organisation of – and during – a virtual event, don’t miss this article showcasing the best tools used as we have hosted our online conferences<\/a> since the COVID-19 outbreak.<\/p>\n\n\n\n

    The conference will have many great speakers who will cover topics around designing UI<\/span> and UX<\/span> for chatbots<\/span>, based on voice input<\/span>. Check the website<\/a> for more information: attendance is free!<\/p>\n\n\n\n

    Chatbots<\/span> are becoming an increasingly powerful AI application<\/span>, issued by every AI-based development framework. They make users<\/span> happy, so they positively impact<\/span> every aspect of business.<\/p>\n\n\n\n

    Because chatbots<\/span> don\u2019t require the user<\/span> to understand the classification<\/span> logic used when content is presented through a text-based user interface<\/span>, they are being added in increasing numbers to classical websites, and showing very promising usage patterns. <\/p>\n\n\n\n

    Updated chatbots<\/span> are becoming the new User Interface<\/span>, often paired with the use of natural language and related technologies<\/span>.\u00a0 It seems clear that some online<\/span> activities will soon begin with a chatbot<\/span> instead of a website.\u00a0<\/p>\n\n\n\n

    Targeting the Internet of Things<\/h2>\n\n\n\n

    Many cars now have a natural-language chatbot as the preferred interface with their software<\/span>. That\u2019s logical when your hands are busy and you can\u2019t use tactile input devices. <\/p>\n\n\n\n

    We have already seen this in desktop computers<\/span> and smartphone<\/span> devices, and subsequently in separate hardware<\/span> such as Smart Speakers and Smart Displays<\/span> from many different suppliers. <\/p>\n\n\n\n

    All of these connect to one of three services: Alexa<\/span><\/a>, Google Assistant<\/span>, or Siri<\/span> (Apple<\/span> only). All of these devices, and many more, are part of the Internet of Things<\/span> (IoT<\/span>) – perhaps unsurprisingly, on its highest and most expensive level.<\/p>\n\n\n\n

    Lower levels exist and should be taken into account<\/span>. There are many competing brands for home, office, building, and neighborhood automation. All of them use infrastructure<\/span> to deploy<\/span> Cloud\/Edge\/5G<\/span> solutions based on AI<\/span> services. <\/p>\n\n\n\n

    The current wave of AI<\/span> services is becoming a commodity, so the competitive value needed to excel will demand new proprietary algorithms. Edge-server<\/span> solutions will help most proximity services to deliver the best possible output in a specific geographic area. <\/p>\n\n\n\n

    The 5G<\/span> paradigm, once correctly deployed, will reduce latency<\/span> to match the human capacity to perceive reality, pushing the UI<\/span> approach to something no tactile interface can match.<\/p>\n\n\n\n

    Voice-based approaches have existed since the 1950s, but they didn’t historically work that well. In more recent times, IoT<\/span> has become a key element in this field.  We now interact with so many devices, from coffee machines, washing machines, voice and home assistants to cars. <\/p>\n\n\n\n

    This paradigm switch needs to be considered when designing conversational approaches to customer<\/span> care. New interfaces must also be fully integrated with the overall business software of a company and within the larger boundaries of the extended enterprise, including suppliers and, where possible, customers<\/span>.<\/p>\n\n\n\n

    The number of IoT<\/span> devices connected to an AI<\/span>-based solution will rapidly increase – eventually they may challenge the AC plug for numerical supremacy. <\/p>\n\n\n\n

    This scenario is not as impossible as it may seem, because many off-grid IoT<\/span> devices increasingly solve the power problem by drawing their operational current from photovoltaic cells or energy-harvesting techniques.<\/p>\n\n\n\n

    More skills are needed to maintain relevance in the current environment. Basic requirements include knowledge of Python<\/span>, an understanding<\/span> of AI<\/span> and ML at a high level<\/span> and of natural language processing<\/span><\/a>. Serverless<\/span> functions<\/span> are also something to learn for those backend<\/span> calls<\/span> to a database or 3rd party API<\/span>.<\/p>\n\n\n\n

    Forget the past: you need a new mindset<\/h2>\n\n\n\n

    This is a brand new world to conquer and the appropriate tools are still under development. The main issue is following new mental pathways without falling back on past mindsets.<\/p>\n\n\n\n

    The normal approach has always followed a dead-end path. Flowcharts<\/span> are disappointing when it comes to describing the conversation<\/span>, so a quantum leap is needed. Many aspects need to be accounted for using AI<\/span> and bots, and software code<\/span> must be written a long time after the bot<\/span> begins its analysis.<\/p>\n\n\n\n

    \u2018Artificial intelligence<\/span>\u2019 itself is a catchphrase that comprises many different components<\/span>. Let\u2019s look at some of the basic elements required to approach a solution. AI<\/span> is still not that accessible as a whole and what’s needed here is something that doesn’t easily fit into a simple box. <\/p>\n\n\n\n

    The field of AI<\/span> encompasses the Machine Learning<\/span> (ML) zone that in turn incorporates the Deep Learning<\/span> (DL) sphere: conversational AI<\/span> can’t be confined to one of these areas, but asks for solutions that can be thought of as coming from all three zones (AI<\/span>, ML, and DL).<\/p>\n\n\n\n

    Returning to bots, they classically try to handle too many things at once, and don’t often communicate with existing business systems. A proper bot solution is integrated with existing software<\/span> in a multi-channel solution.<\/p>\n\n\n\n

    Any voice chatbot<\/span> must implement<\/span> Natural Language<\/span> Understanding<\/span> (NLU), today an easily-managed undertaking. AI<\/span> and bot communication are technological problems that can be easily solved with correct analysis and a related business plan.<\/p>\n\n\n\n

    The largest part of the overall conversational user<\/span> interface is thus outside technology<\/span>. Finding the right approach to designing a solution is essential. Current use cases<\/span> are not particularly strong: some bots lack transparency, they often don’t understand<\/span> context, and they lack proper human escalation protocols.<\/p>\n\n\n\n

    API-based multi-channel AI solutions<\/h2>\n\n\n\n

    How can we untie all these knots? A strategy is required.<\/p>\n\n\n\n

    What is needed to develop a solution? At least three elements must be clear: intent, entities, and context.<\/p>\n\n\n\n