Conversational UI Briefing Paper
Conversational user Interfaces attempt to bridge the gap between natural spoken and written human language and devices. Communication between humans and computers through graphical user interfaces (GUI) requires the individual to have to learn how use the GUI. Conversational UI allows the user to communicate with a device more efficiently without needing to understand specific syntax in order to perform certain tasks.
In today’s market Conversational UI are produced in two forms, voice assistants, and chatbots. Voice assistants allow for audio communication between user and devices while chatbots can be typed to as well. The functional use of voice assistants and chatbots is quite vast. Since most voice assistants and chatbots can interface with different applications, this greatly improves problem resolution when the user encounters an issue within the application. With all major technology companies developing either voice assistants or chatbots to which can be linked and to all most commonly used applications or devices, conversational UI will continue to progress and secure a crucial role in all internet of things (IoT) devices moving forward.
Conversational UI function by having the user input naturally spoken language (either audio or written). The input is then processed by Artificial Intelligence (AI) systems and a response is given. Several voice assistants including Apple’s Siri, Google Assistant, Samsung’s Bixby, and Amazon’s Alexa, all use cloud-based technology to process the input speech given by the user. The advantage of this is the ability to construct large databases of audio allowing the voice assistant to process the input faster as well as predict what the individual will say. In this manner it allows for a more fluid conversation between humans and devices. Since the processing of input speech is not done on the device this can create an issue of privacy, as concerns may arise due to all user-device interactions being stored.
Chatbots function in a similar manner and can be divided into two broad categories. They are generally scripted (basic user interaction) or structured (engaging virtual assistants). They may also be involved with collaboration tools and messaging applications. Chatbots that are scripted tend to be more hard-coded, meaning they are expecting questions and interactions from a set of use cases and formulate their response accordingly. Scripted bots can be thought of as providing a guided conversation. Although the implementation of these is less involved it also provides stricter limitations on the level of communication that can be performed. Structured chatbots rely on AI and more specifically cloud based Natural Language Understanding NLU to generate machine actionable data from user input. Unlike their scripted counterparts these types of chatbots are more complex and require more effort to properly implement. However the end user is able to be less rigid in the way questions and interactions are structured.
Conversational UI provide an easier and more fluid way for humans to interact with devices. Since computers are very reliant on the structure and syntax of their input conversational UI’s eliminate the complexity by allowing the user to input normal conversation. Conversational interfaces can be found on nearly all smart devices now, using both voice-activated assistants and chatbots. These interfaces allow for better service delivery and allocation resources in the service industry. For example, KLM the Dutch airline has begun using a chatbot that interfaces with Facebook’s messenger app. This allows individuals to check their flight details and even modify certain travel aspects, without having to contact a KLM representative directly. This is a great advantage as more serious issues can be delegated to human representatives.
Sephora, a popular makeup retailer in the U.S., has a successful bot on Kik. Today, the bot engages users with a number of questions about makeup preferences and serves up content and offers relevant to the responses. While it doesn’t sound like a highly sophisticated process – the more the consumer engages with the bot over time, the smarter the bot (and the brand) get about consumer preferences and the better it can serve personalized content and offers.
Several major technology companies including Amazon, Google, Apple, and Samsung have already released voice-activated assistants. There are also many platforms developed in combination with NLU platforms, to facilitate the construction of chatbots. Some of these include API.ai (Google), Wit.ai (Facebook), and Microsoft Bot Framework. Designing chatbots for specific using these platforms allow individuals to interface with their applications and in turn communication is established among a plethora of applications. For example, building an agent using Google’s API.ai automatically create a Google cloud platform for the agent. Using the Google cloud platform then provides a secure and high-performance infrastructure which is maintained by Google.
Canadian Government Use
The use of conversational UI can provide several benefits to the Government of Canada. Since conversational UI’s increases the quality of interaction between human and device, the GC can benefit from its use in delivery of Service . For example, if conversational UI were used to handle basic technical problems encountered by employees in the GC, this would ease the workload of IT support staff allowing them to deal with more complex issues that the conversational UI cannot handle.
Conversational UI’s could also be used on GC websites. This would aid Canadian citizens accessing the websites to quickly obtain information they are seeking through natural language requests with a chatbot. It would also be beneficial when an individual is required to fill out forms or applications, and is then given immediate feedback on whether the data they have entered is valid or what needs to be modified to do so.
Implications for Departments
Shared Services Canada could gain value from conversational UI’ internally, by allowing it to deal with employee technical issues. It can also allow external individuals to gain information quickly about the SSC.
The launch of Conversational UI’s in the GC provides a few challenges. Using either voice-activated assistants or chatbots designed using platforms like API.ai and Wit.ai means that the GC will be using Google’s or any other companies cloud computing network to process the information inputted to the conversational UI. Shared Services Canada will need to assess the security and privacy implications this brings forth. If the Conversational UI were to be designed without the use of these platforms then that would mean a sizable investment into designing one as well as maintaining it.
Content to be added by each departments