Types of Chatbot Technology
This article is an excerpt of “Chatbots: The Definitive Guide 2020”.
In this article we’ll cover the different types of chatbot technology: linguistics, machine learning and a hybrid model approach. We’ll also look at chatbot development and integrations.
Chatbots Technology
The majority of chatbot development tools today are based on two main types of chatbots, either linguistic (rule-based chatbots) or machine learning (AI chatbot) models.
Linguistic Based (Rule-Based Chatbots)
Linguistic based — sometimes referred to as ‘rules-based’, delivers the fine-tuned control and flexibility that is missing in machine learning chatbots. It’s possible to work out in advance what the correct answer to a question is, and design automated tests to check the quality and consistency of the system.
Rule-based chatbots use if/then logic to create conversational flows.
Language conditions can be created to look at the words, their order, synonyms, common ways to phrase a question and more, to ensure that questions with the same meaning receive the same answer. If something is not right in the understanding it’s possible for a human to fine-tune the conditions.
However, chatbots based on a purely linguistic model can be rigid and slow to develop, due to this highly labor-intensive approach.
Though these types of bots use Natural Language Processing, interactions with them are quite specific and structured. These type of chatbots tend to resemble interactive FAQs, and their capabilities are basic.
These are the most common type of bots, of which many of us have likely interacted with — either on a live chat, through an e-commerce website, or on Facebook messenger.
Machine learning (AI Chatbots)
Chatbots powered by AI Software are more complex than rule-based chatbots and tend to be more conversational, data-driven and predictive.
These types of chatbots are generally more sophisticated, interactive and personalized than task-oriented chatbots. Over time with data they are more contextually aware and leverage natural language understanding and apply predictive intelligence to personalize a user’s experience.
Conversational systems based on machine learning can be impressive if the problem at hand is well-matched to their capabilities. By its nature, it learns from patterns and previous experiences.
But, to perform even at the most rudimentary level, such systems often require staggering amounts of training data and highly trained skilled human specialists. In addition, a machine learning chatbot functions as a black box. If something goes wrong with the model it can be hard to intervene, let alone to optimize and improve.
The resources required, combined with the very narrow range of scenarios in which statistical algorithms are truly excellent, makes purely machine learning-based chatbots an impractical choice for many enterprises.
Hybrid Model — The Ultimate Chatbot Experience
While linguistic and machine learning models have a place in developing some types of conversational systems, taking a hybrid approach offers the best of both worlds, and offers the ability to deliver more complex conversational AI chatbot solutions.
A hybrid approach has several key advantages over both the alternatives. When considered against machine learning methods, it allows for conversational systems to be built even without data, provides transparency in how the system operates, enables business users to understand the application, and ensures that a consistent personality is maintained and that its behavior is in alignment with business expectations.
At the same time, it allows for machine learning integrations to go beyond the realm of linguistic rules, to make smart and complex inferences in areas where a linguistic only approach is difficult, or even impossible to create. When a hybrid approach is delivered at a native level this allows for statistical algorithms to be embedded alongside the linguistic conditioning, maintaining them in the same visual interface.
Building conversational applications using only linguistic or machine learning methods is hard, resource intensive and frequently prohibitively expensive. By taking a hybrid approach, enterprises have the muscle, flexibility and speed required to develop business-relevant AI applications that can make a difference to the customer experience and the bottom line.
Here’s a video explaining the benefits of a hybrid approach using both linguistic and machine learning models:
Build better voice apps. Get more articles & interviews from voice technology experts at voicetechpodcast.com
Chatbot Development
There are no hard and fast rules but here are some top tips to developing chatbots to ensure success.
1. Define Goals
It’s essential to define business value and goals at the beginning of a project. By knowing the features needed to achieve the desired result it’s possible to shape the implementation, bearing in mind any business restrictions such as time or budget.
Whether it’s a proof of concept, pilot or full production project it’s important to stay true to these goals before moving on to other phases within the project. Otherwise it’s tempting to be distracted by cool features that aren’t necessary to achieve the end goal.
2. Think Big, Start Small
Enterprises are moving beyond short-term chatbot strategies that solve specific pain points, to using conversational interfaces as an enabler to achieve goals at a strategic level within the organization.
Consider the wider strategy but start with a smaller project in order to see the results and measure the success before deciding on the next phase. Ensure the technology used for chatbot development can scale to meet future needs.
3. Take Control of the Chatbot Landscape
In large enterprises it’s not uncommon for several proof of concept (PoCs) and pilot chatbot projects to be currently underway, unseen and often un-coordinated by the CIO. For businesses this poses two main concerns — a duplication of resources and potential security risks.
In recognition of the need to bring together teams tasked with delivering the innovative solutions that will drive the business forward globally, enterprises are forming Centers of Excellence.
Skillsets are no longer spread across the organization but focused on collaborating and developing chatbot solutions to solve problems, improve productivity and make the business stronger.
4. Collaborate With All Stakeholders
The combination of CIOs taking control of the chatbot landscape, the continued business-driven initiatives from departments looking to build their own applications, and the push from developers to build conversational systems at a ‘skunk work’ level is creating an interesting and dynamic set of stakeholders.
Choose a development technology that is advanced enough for developers to rapidly build a complex proof of concept that can still be easily understood by business users, even from day one.
5. Going Live Isn’t the End
Launching a chatbot is only the beginning. It can always do better and increase customer satisfaction even further.
Make provisions to provide continual and continuous improvement to the system. It doesn’t have to be time intensive, much of the process can be automated. At the same time, it’s also essential to have KPI reporting in place and to use the traditional measuring methods already used by the organization, such as first call resolutions rates.
By enabling the chatbot to continue to learn and improve, the value of overall solution will increase.
Chatbot Connectors
Chatbot connectors are pre-built libraries of intelligent connectors that span a range of business and AI assets including RPA (robotic process automation) and CPaaS (Communications Platform as a Service).
Connectors harness the power of back-office technology to deliver even greater intelligence and capabilities by integrating a chatbot into business systems, communication platforms and more. Reach users on any channel, deliver more personalized answers based on behind the scenes processes, and execute tasks on customers’ behalf.
People use a variety of channels and devices in communicating with others. Not only is it important for organizations to be available on all channels relevant to its audience, but the experience needs to be seamless across those channels too.
Ease of deployment onto a variety of channels should be a key consideration when planning a chatbot, alongside the ability for persistent chat.
For example, a person might use a Facebook Messenger chatbot on their smartphone to start a conversation on the commute home and want to continue it later that evening using a smart home hub, before moving to their smart speaker or watch to conclude it.
Channels often deployed for chatbot use include: Amazon Alexa, Android chat, Cortana, Discord, Facebook Messenger, Google Assistant, iOS Chat, IVR by Twilio, IVR by Nexmo, IVR by Cisco, LINE, Microsoft Teams, MS Bot Framework, Skype, Slack, SMS by Nexmo, Telegram, Twitter, Wechat, WhatsApp, or a custom app for mobile, in car or home.
Connectors can also include enterprise backend software, Live Chat, ASR/TTS and Knowledgebase such as: Blue Prism, UiPath, Salesforce.com, SAP, Amadeus, Bold360, Cention, Live Chat Inc., LivePerson, Google ASR, Amazon, Apple, Microsoft, Nuance, and RightNow.
Originally published on the Artificial Solutions website on November 27th.
