{"id":17680,"date":"2016-06-01T19:11:50","date_gmt":"2016-06-01T19:11:50","guid":{"rendered":"http:\/\/apidocs.kore.com\/?post_type=docs&p=1776"},"modified":"2023-02-07T11:55:13","modified_gmt":"2023-02-07T11:55:13","slug":"about-bots","status":"publish","type":"post","link":"https:\/\/developer.kore.ai\/v10-1\/docs\/bots\/chatbot-overview\/about-bots\/","title":{"rendered":"Virtual Assistant Concepts and Terminology"},"content":{"rendered":"
\r\n\t
\r\n\t\t
\r\n\t\t\t

This glossary lists the key terms and concepts related to the Kore.ai’s XO Platform.<\/span><\/p>\n\n\n\n
Note<\/em><\/strong>: “Virtual Assistant”, “VA” and “Bot” refer to the same concept and are used interchangeably throughout this glossary. Please see “Virtual Assistant” for the definition. <\/span><\/em><\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n
<\/div><\/div>\r\n\t
\r\n\t\t
\r\n\t\t\t\r\n\t\t<\/div>\r\n\t<\/div>\n

A<\/strong><\/span><\/h2>\n

Action task<\/strong> – <\/span>Action tasks<\/span><\/a> collect, modify, and post information in systems of record, such as scheduling an appointment, searching for a product, or updating critical information.<\/span><\/p>\n

Administration & analytics <\/strong>– The Kore.ai XO Platform provides enterprise grade visibility and control of all enterprise bots, user groups, and security, as well as a commitment to compliance in even the most highly regulated areas, including  healthcare and financial services. <\/span>Learn more.<\/span><\/a><\/p>\n

Alert task <\/strong>– <\/span>Alert tasks<\/span><\/a> Bots poll the system for user requested updates in real-time, to deliver timely, relevant, and personalized information to customers and employees directly from enterprise systems.
\n<\/span>API <\/strong>– An API, or Application Programming Interface, is a set of definitions, protocols, and tools for building software. It helps developers by essentially providing the building blocks for a program.<\/span><\/p>\n

Artificial Intelligence (AI)<\/strong> – AI is the development of computer systems that are able to perform tasks that normally require <\/span>human-like intelligence<\/span><\/a>, such as decision making, speech recognition and understanding, translation between languages, and more.  <\/span><\/p>\n

Auto-NLP<\/strong> – A term we use to describe our synonym-based approach to <\/span>natural language processing<\/span><\/a>. It allows VAs to communicate and understand intent variations right out of the gate, thus being speech enabled “automatically”<\/span><\/p>\n

Automatic Message Formatting<\/strong> – The pre-programmed responses for tasks built into Kore.ai’s XO Platform NL engines.<\/span><\/p>\n

Automated Speech Recognition (ASR)<\/strong> – Our Platform can integrate an <\/span>Automated Speech Recognition Engine<\/span><\/a> to enable bots to process voice-driven interactions and communicate outside of traditional text-based interfaces.<\/span><\/p>\n

Amazon Web Services (AWS)<\/strong> – A subsidiary of Amazon.com which provides on-demand cloud computing platforms to people and enterprises.<\/span><\/p>\n\r\n\t\t<\/div>\r\n\t<\/div>\r\n

<\/div><\/div>\r\n\t
\r\n\t\t
\r\n\t\t\t

B<\/strong><\/span><\/h2>\n

Bots (also see <\/strong>Chatbot <\/em><\/strong>and <\/strong>Virtual Assistant<\/em><\/strong>)<\/strong> – Short for a computer program that acts as an intelligent intermediary between people, digital systems, and Internet-enabled things<\/span><\/p>\n

Bot Builder Tool<\/strong> – A <\/span>web-based Bot Builder<\/span><\/a>, part of the Kore.ai XO Platform, that allows enterprises to customize VA use cases, channels, tasks, security, and more. It also provides a framework in which developers can design, test, and deploy VAs in a consistent process at scale.<\/span><\/p>\n

Bot context<\/strong> – <\/span>User or task information that is captured at the bot level<\/span><\/a> and can be used in context with some or all of the users of that bot.<\/span><\/p>\n\r\n\t\t<\/div>\r\n\t<\/div>\r\n

<\/div><\/div>\r\n\t
\r\n\t\t
\r\n\t\t\t

C<\/strong><\/span><\/h2>\n

Channel <\/strong>– A <\/span>channel<\/span><\/a> is another word for any of the various communication platforms where a VA can be implemented, such as SMS, email, mobile apps, websites, messaging apps and more. <\/span>With the Kore.ai’s XO Platform, you can design VA tasks once, and deploy across channels simply by checking a box. You can also differentiate cross-channel experiences by altering message responses or leveraging channel-specific UI elements, such as  date selectors, carousels, and more.<\/span><\/p>\n

Chatbot <\/strong>– Short for a computer program that acts as an intelligent intermediary between people, digital systems, and Internet-enabled things. Find out more about VAs with our <\/span>Bots 101 guide<\/span><\/a>.<\/span><\/p>\n

Chat logs<\/strong> – Histories of all recorded human-to-bot interactions.<\/span><\/p>\n

Cisco Spark<\/strong> – Cisco’s <\/span>all-in-one communication platform,<\/span><\/a> which is also a supported channel for bots and an integration partner for VA development.<\/span><\/p>\n

Cloud (or Cloud computing)<\/strong> – Internet-based computing that provides shared computer processing resources and data to computers and other devices, on demand.<\/span><\/p>\n

Cloud Connector<\/strong> – Provides an agent that runs behind your enterprise firewall that acts as a bridge to facilitate secure data exchanges between on-prem systems and Kore.ai’s cloud based infrastructure.<\/span><\/p>\n

Component reusability<\/strong> – The ability for developers to use components they’ve already built in the Bot Builder, such as APIs, synonyms, tasks, etc. and apply them to other bots.<\/span><\/p>\n

Context (see also, Bot Context, Enterprise Context, Session Context, User Context)<\/strong>  – <\/span>The information that a VA pulls from a conversation<\/span><\/a> with a user that it can leverage when performing tasks. Contextual data can vary in importance, utility, and lifespan.<\/span><\/p>\n

Conversational Commerce<\/strong> – A term coined by <\/span>Chris Messina in 2016<\/span><\/a>, which is another way of describing how digital economies will be driven by text and voice based interfaces and experiences.<\/span><\/p>\n

Conversational UI<\/strong> – Another way of describing text and voice-based interfaces, which don’t require graphical elements for use, such as Amazon’s Alexa or Apple’s Siri.<\/span><\/p>\n

Cognitive Services (aka Conversational and Cognitive Services)<\/strong> – A collection of separate APIs, SDKs, and services (that run on a cloud infrastructure like Azure) which developers can use to build intelligence into apps and\/or to construct a VA that can leverage AI capabilities. Unlike a <\/span>platform<\/span><\/a>, charge is typically separate for each service and each bot created.<\/span><\/p>\n\r\n\t\t<\/div>\r\n\t<\/div>\r\n

<\/div><\/div>\r\n\t
\r\n\t\t
\r\n\t\t\t

D<\/strong><\/span><\/h2>\n

Data retention<\/strong> – The continued storage of an organization’s data for compliance or business matters.<\/span><\/p>\n

Deep learning<\/strong> – An area of Machine Learning that is based on learning data representations as opposed to task specific algorithms.<\/span><\/p>\n

Deployment <\/strong>– The process of publishing a bot to a communication channel where it will be engaged by users.<\/span><\/p>\n

Dialog task<\/strong> – <\/span>Dialog tasks<\/span><\/a> are advanced tasks that developers design with logic-driven business processes and pre-established workflows. Bots key off the primary request intent to accomplish the task at hand, then go above and beyond to execute sub-intents and additional workflows. This way, VAs can handle complex multi-turn conversational experiences that replicate the natural back and forth exchanges people have every day.<\/span><\/p>\n

Dialog Builder<\/strong> – <\/span>The Dialog Builder<\/span><\/a> gives designers and developers the flexibility to manipulate the entire dialog process of a bot interaction and string together complex workflows in a GUI-based tool.<\/span><\/p>\n\r\n\t\t<\/div>\r\n\t<\/div>\r\n

<\/div><\/div>\r\n\t
\r\n\t\t
\r\n\t\t\t

E<\/strong><\/span><\/h2>\n

E-commerce <\/strong>– Any monetary transaction conducted on the internet.<\/span><\/p>\n

E-discovery <\/strong>– Any process in which electronic data is sought, located, secured, and searched with the intent of legal use. The Kore.ai XO Platform supports e-discovery.<\/span><\/p>\n

Email <\/strong>– A supported communication channel for bots.<\/span><\/p>\n

Encryption <\/strong>– The process of converting information or data into a code, especially to prevent unauthorized access.<\/span><\/p>\n

End-to-end<\/strong> – A way of describing the Kore.ai XO Platform which signifies that it includes all the component features to take enterprises from the very beginning of the VA development process, through deployment and management.<\/span><\/p>\n

Enterprise analytics<\/strong> – The central dashboard within the Kore.ai XO Platform where <\/span>administrators can get visibility into key metrics, pull detailed reports, and track bot usage<\/span><\/a> (i.e. number of executed tasks, most popular channels, most active users, user enrollment, etc.)<\/span><\/p>\n

Enterprise bots store<\/strong> – A bot store that an enterprise sets up for a select group of users to access any custom built bots. The Store is where you can find prebuilt bot templates which you can use for different business scenarios.<\/span><\/p>\n

Enterprise-grade<\/strong> – A way of describing all of the <\/span>components and capabilities of the Kore.ai XO Platform<\/span><\/a> that are specifically designed to match the highest enterprise standards, including administration, analytics, security, compliance, and more.<\/span><\/p>\n

Enterprise context <\/strong>– Information that represents company-wide rules and standards that apply to all users and VAs, such as a company travel policy, or expense limits.<\/span><\/p>\n

Entity <\/strong>– <\/span>Entities are the necessary fields, data, or words for a VA to complete the user’s request: <\/span>be that a date, a time, a location, a description or any number of things.<\/span> With the required entities in hand, the VA can reach out to the web service and get the specific data or perform the action as per the user intent. For example, to book a flight, the VA needs the source and destination city along with the travel date. In this example, the user utterance “Book me a flight to Orlando for next Sunday<\/span>”, “<\/span><\/em>Orlando<\/span>”<\/span><\/em> and “next Sunday<\/span>”<\/span><\/em> are entities<\/span>. <\/span><\/em>For more information about parameters and user input, refer to the particular task type parameters and fields.<\/span><\/p>\n\n\n\n\n\n\n
SAMPLE UTTERANCE<\/strong><\/td>\nINTENT<\/strong><\/td>\nENTITY<\/strong><\/td>\n<\/tr>\n
Book me a flight to Orlando<\/span><\/td>\nBook flight<\/span><\/td>\nCity: Orlando<\/span><\/td>\n<\/tr>\n
Schedule a meeting with Bill this Sunday<\/span><\/td>\nSchedule a meeting<\/span><\/td>\n\n

Person name: Bill<\/span><\/p>\n

Date: April 22, 2018<\/span><\/td>\n<\/tr>\n

Add two bottles of red wine to the cart<\/span><\/td>\nAdd to cart<\/span><\/td>\n\n

Item: Red Wine<\/span><\/p>\n

Count: Two<\/span><\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n

 <\/p>\n

Entity extraction<\/strong> – This is <\/span>the process by which the NL engine identifies words<\/span><\/a> from a user’s utterance to ensure all available fields match the task at hand. If the VA needs an entity to complete the task after initial extraction, it will prompt the user for it.<\/span><\/p>\n\r\n\t\t<\/div>\r\n\t<\/div>\r\n

<\/div><\/div>\r\n\t
\r\n\t\t
\r\n\t\t\t

F <\/strong><\/span><\/h2>\n

Facebook Messenger<\/strong> – A <\/span>supported channel<\/span><\/a> for VAs built on Kore.ai’s XO Platform, primarily used when companies build bots for end customers.<\/span><\/p>\n

FAQ <\/strong>– One of the primary data source VAs use, along with the Knowledge Graph, to pull information to complete knowledge tasks. <\/span><\/p>\n

Framework <\/strong>– A framework is a structure that provides some basic building blocks and generic functionality for building VAs (like ML\/ NLP or a Dialog Builder), but requires additional user-written code or other third-party services (to match the functionality of an actual platform). Frameworks often are composed of piecemeal components from different vendors.<\/span><\/p>\n

Fundamental Meaning<\/strong> – Fundamental Meaning is an approach to NLP that’s all about understanding words themselves. Each user utterance is broken down word-for-word to search for intent (what the user is asking the VA to do) and entities (the necessary data needed to complete a task). <\/span>Learn more about this approach and the NL engine.<\/span><\/a><\/p>\n\r\n\t\t<\/div>\r\n\t<\/div>\r\n

<\/div><\/div>\r\n\t
\r\n\t\t
\r\n\t\t\t

G<\/strong><\/span><\/h2>\n

Glip <\/strong>– A <\/span>supported channel<\/span><\/a> for VAs built on Kore.ai’s XO Platform.<\/span><\/p>\n

Graphic User Interface (GUI)<\/strong> – A visual way of interacting with an app or system, usually consisting of  buttons, images, windows, icons, menu forms, and more.<\/span><\/p>\n\r\n\t\t<\/div>\r\n\t<\/div>\r\n

<\/div><\/div>\r\n\t
\r\n\t\t
\r\n\t\t\t

H<\/strong><\/span><\/h2>\n

Hosting <\/strong>– Hosting refers to storing and allowing access to the XO Platform. Enterprises have the choice to host on-prem or in the cloud via AWS.<\/span><\/p>\n\r\n\t\t<\/div>\r\n\t<\/div>\r\n

<\/div><\/div>\r\n\t
\r\n\t\t
\r\n\t\t\t

I<\/strong><\/span><\/h2>\n

Information and Communication Technologies (ICT)<\/strong> – ICT refers to technologies that provide access to information through telecommunications. It is similar to Information Technology (IT), but focuses primarily on communication technologies. This includes the Internet, wireless networks, cell phones, and other communication media.<\/span><\/p>\n

Information task<\/strong> – <\/span>Information tasks<\/span><\/a> lookup data or pull reports based on specific parameters and quickly return easy-to-consume results that are convenient for users.<\/span> These reports are formatted and organized based on user preferences, applicable filters, and they can be downloaded for later use. For example, a VA can provide a sales manager with a report detailing the top 10 sales reps last year by region, organized from most to least sales.<\/span><\/p>\n

Interface <\/strong>– A shared boundary across which two or more separate components of a computer system exchange information.<\/span><\/p>\n

Intelligence (see also <\/strong>Platform Intelligence)<\/strong><\/a> – All the capabilities provided to developers who use the Kore.ai XO Platform to create AI-powered VAs including how to use contextual data, memory, NLP, machine learning (both supervised and unsupervised), sentiment analysis, and more.<\/span><\/p>\n

Intent <\/strong>– <\/span>A few essential words in the utterance that describe what the user wants the VA to do. It is usually a combination of a verb and a noun. For example, in <\/span>“Book me a flight to Orlando for next Sunday”<\/span><\/em>, the intent is <\/span>Book me a flight<\/span><\/em>.<\/span><\/p>\n

Intent recognition<\/strong> – <\/span>The process by which the NL engine analyzes the structure of a user’s command<\/span><\/a> to identify each word by meaning, position, conjugation, capitalization, plurality, and other factors to correctly match the user’s intent to the task at hand.<\/span><\/p>\n

Interaction <\/strong>– Any text-based or spoken communication between a human and a VA.<\/span><\/p>\n\r\n\t\t<\/div>\r\n\t<\/div>\r\n

<\/div><\/div>\r\n\t
\r\n\t\t
\r\n\t\t\t

J<\/strong><\/span><\/h2>\n

Javascript <\/strong>– A programming language that is dynamic and supports object-oriented, imperative, and functional programming styles.<\/span><\/p>\n\r\n\t\t<\/div>\r\n\t<\/div>\r\n

<\/div><\/div>\r\n\t
\r\n\t\t
\r\n\t\t\t

K<\/strong><\/span><\/h2>\n

Knowledge task<\/strong> \/ <\/span>Knowledge Graph <\/strong>– <\/span>Knowledge tasks<\/span><\/a> take user questions and query a predefined set of information to rapidly find the right answers, such as business hours of operation or specific policy questions.<\/span><\/p>\n

Kore.ai<\/strong> – Kore.ai is a software development company, founded in 2014 in Orlando, FL to help <\/span>enterprises build and use conversational, intelligent VAs for a variety of use cases. <\/span><\/a>Learn more about <\/span>Kore.ai<\/span><\/a><\/p>\n\r\n\t\t<\/div>\r\n\t<\/div>\r\n

<\/div><\/div>\r\n\t
\r\n\t\t
\r\n\t\t\t

L<\/strong><\/span><\/h2>\n

Live agent handoff<\/strong> – A VAs ability to <\/span>seamlessly take a conversation from any channel and bring in a human agent<\/span><\/a>. This function is especially useful for areas such as service, support and ITSM.<\/span><\/p>\n

Learning <\/strong>– <\/span>Learning is about how <\/span>VAs<\/span><\/a> recognize new intents and entities, answer questions correctly, and identify the important aspects of a user utterance. Learning can be manual or automatic. And, like humans, VAs need to know when they are wrong and what the right action, response, or answer should be.<\/span><\/p>\n

Location Services<\/strong> – Location services identify a user’s physical location and can be used to build location dependent tasks for greater accuracy.<\/span><\/p>\n

Logic programming<\/strong> – A type of programming which is largely based on formal logic and is the building block for complex VA dialogs and workflows.<\/span><\/p>\n\r\n\t\t<\/div>\r\n\t<\/div>\r\n

<\/div><\/div>\r\n\t
\r\n\t\t
\r\n\t\t\t

M<\/strong><\/span><\/h2>\n

Machine Learning<\/strong> – Using algorithms, patterns, and training data, machine learning allows computers to find hidden insights without being explicitly programmed. Learn more about the way Kore.ai uses <\/span>machine learning for natural language enablement.<\/span><\/a><\/p>\n

Managed Services Provider (MSP)<\/strong> – Most often an IT provider that manages and assumes responsibility for providing a defined set of services to its clients either proactively or as the MSP determines that services are needed. They typically offer a range of services such as network maintenance, hardware repair, help-desk, email management, and anything else that requires a day-to-day administrator to keep running. They may need to purchase technology from a third-party provider, a cost which is bundled with their services and passed on to their end customer. MSPs operate on longer-term annual or multi-year contracts, and the tenure of their relationship is open-ended.<\/span><\/p>\n

Memory <\/strong>– Virtual Assistants can remember actions, data, and contextual details to maintain conversation continuity and take helpful actions. The developer can designate how long the bot remembers information as either short term or long term memory.<\/span><\/p>\n

Message Broker<\/strong> – A Kore.ai XO Platform component that consumes all user inputs and system outputs, standardizes for a common messaging paradigm, and redirects to the appropriate endpoints.<\/span><\/p>\n

Message Store<\/strong> – A Kore.ai XO Platform component that stores messages between users, bots, and systems and automatically logs and categorizes message successes and failures.<\/span><\/p>\n

Microsoft Teams<\/strong> – A <\/span>supported channel<\/span><\/a> for VAs built on Kore.ai’s XO Platform.<\/span><\/p>\n

Middleware <\/strong>– The Kore.ai XO Platform Middleware contains the Message Broker, Message Store, and built-in encryption to create a flawless conversational experience by ensuring messages are received, secured, and exchanged in real time.<\/span><\/p>\n

Mobile SDKs<\/strong> – A set of software development tools that allow developers to create applications for a variety of mobile devices. Mobile SDKs are also a supported channel for bots.<\/span><\/p>\n

Multi-layer authentication<\/strong> – A method of access control in which the user must provide several separate authentication factors before being granted access to data. The Kore.ai XO Platform supports multi-layer authentication for bot access.<\/span><\/p>\n

Multiple intents<\/strong> – When a user gives a complex request to a VA which requires the bot to process and prioritize two or more intents at once.<\/span><\/p>\n\r\n\t\t<\/div>\r\n\t<\/div>\r\n

<\/div><\/div>\r\n\t
\r\n\t\t
\r\n\t\t\t

N<\/strong><\/span><\/h2>\n

Natural Language (NL)<\/strong> – The method by which users can talk to systems in everyday language like text and speech, rather than programming language.<\/span><\/p>\n

Natural Language Processing (NLP)<\/strong> – The process by which a VA or any other system understands and processes requests in common language, rather than programming language. NLP is typically enabled via machine learning, but <\/span>Kore.ai uses a multi-engine  approach<\/span><\/a> which includes intent recognition and entity extraction. <\/span>NLP enables a VA to identify the user intents; extract useful information from their utterances and map the data(entities) to the relevant tasks. Kore.ai’s XO Platform uses a unique NLP strategy. It combines Fundamental Meaning, Machine Learning and Knowledge Graph Engines for optimal conversational accuracy. VAs built on the XO Platform can understand and process:<\/span><\/p>\n