This article lists the key terms and concepts related to the Kore.ai Bots Platform.
A bot is a form of virtual assistant that acts as an intelligent intermediary between people, digital systems, and Internet-enabled things. Bots are intelligent with machine learning, natural language processing, and other forms of advanced software allowing them to handle complex human conversations and learn from past interactions, improving responses over time.
Anything that a user says to the chatbot is an utterance. For example, if the user types Book me a flight to Orlando for next Sunday, the entire sentence is considered as the user utterance.
The few essential words in the utterance that describe what the user wants the chatbot to do. It is usually a combination of a verb and a noun. For example, in the above user utterance Book me a flight to Orlando for next Sunday, the intent is Book me a flight.
To fulfill user intent, the Bot may require additional information or parameters. For example, to book a flight, it needs the source and destination city along with the travel date. In the above example, user utterance Book me a flight to Orlando for next Sunday, Orlando and next Sunday are entities.
Entities are the necessary fields, data, or words for a chatbot to complete the user’s request. With the required entities in hand, the Bots Platform can reach out to the web service and get the specific data or perform the action as per the user intent.
For more information about parameters and user input, see the particular task type parameters and fields at Defining Bot Tasks.
|Book me a flight to Orlando||Book flight||City: Orlando|
|Schedule a meeting with Bill this Sunday||Schedule a meeting||Person name: Bill
Date: April 22, 2018
|Add two bottles of red wine to the cart||Add to cart||Item: Red Wine
Natural Language Processing
The process by which a bot identifies the intent of the user extracts useful information from their utterance and maps that data (entities) to the relevant task. This allows bots to process requests in text or speech form, rather than complicated menus or programming language.
Kore.ai’s Platform uses a unique NLProcessing strategy. It combines Fundamental Meaning and Machine Learning Engines for optimal conversation accuracy. Bots built on Kore.ai’s Platform can understand and process the following:
- Multi-sentence messages
- Multiple intents
- Contextual references
- Patterns and idiomatic sentences, and more.
A machine’s ability to simulate human behavior and decision-making and perform tasks that normally require human-like intelligence, such as speech recognition and understanding, language translation, and more.
A machine’s ability to use algorithms, patterns, and training data to learn and find hidden insights, without being explicitly programmed.
The extraction of relevant and valuable data from a user’s utterance to complete a task. Bots can ensure they have all the data they need to complete the user tasks and, if not, can prompt the user for the missing information.
Tasks refer to different types of simple and complex “jobs” that are designated to the chatbot by the developer. These tasks are performed by the chatbot to fulfill the user intents.
For a Travel bot, task names might be to Book tickets, Find hotels, Provide weather forecast, and so forth, which cater to different user intents.
Once the bot understands a user intent, it is ready to perform a task, such as reaching out to a web service, extracting the current weather conditions report, parsing that response, and then delivering the data to the user.
Kore.ai provides 5 pre-defined task types that cover virtually all bot scenarios.
Bots can collect, modify, and post information in systems of record, like scheduling an appointment, searching for a product, or updating critical information.
Bots can deliver timely, relevant, and personalized notifications to customers and employees directly from the enterprise system by polling backend systems or by pulling information at regular intervals. Alerts can be configured by users or bot developers.
Bots can provide your users with answers to their most commonly asked questions by querying a predefined set of information. For example, a bot could answer customer questions regarding hours of operation while also answering questions about return policies.
Bots can provide users with data from back-end systems in the form of reports. These reports are formatted and organized based on user preferences and applicable filters, and they can be downloaded for later use. For example, a bot could provide a sales manager with a report detailing the top 10 sales reps last year by region, organized from most to least sales.
Bots can handle complex multi-turn conversational experiences that replicate the natural back and forth exchanges people have every day.
How chatbots come to recognize new intents and entities, how to answer questions correctly, and how to identify the important aspects of a user utterance. Learning can be manual or automatic. And, just like humans, bots need to know when they are wrong and what the right action, response, or answer should be.
A form of learning in which you have input variables (X) and an output variable (Y), and you use an algorithm to learn the mapping function from the input to the output. Here, the bot developer acts as a teacher and has virtually full control over what the bot learns. This means that the algorithm makes predictions based on the training data provided. The bot creator developer can manually correct these predictions by flagging the findings as correct or incorrect. Since the bot developer already knows what the bot should understand, learning can be stopped as soon as he or she decides or when the model reaches an acceptable level of performance.
A form of learning that doesn’t require bot developer oversight. Here, the bot learns from all successful utterances, meaning those utterances that were successfully recognized by the bot and the tasks that were completed, and uses these findings to automatically expand the model and retrain the bot, including user-provided confirmations of intents in case of conflicts. This form of training allows bots to expand their language capabilities and improve their accuracy – while excluding failed utterances – all without human intervention.
Channels refer to various communication platforms where a bot can live such as SMS, email, mobile apps, websites, messaging apps and more. With the Bot Builder, you can design chatbot tasks once, and deploy across channels by merely checking a box.
You can also differentiate cross-channel experiences by altering message responses or leveraging channel-specific UI elements like date selectors, carousels and more.
Variables, Context, and Session Data
When developers create and define tasks, they can access the following:
- Session variables provided by the Bots Platform
- Custom variables that they define
- The context that defines the scope of the variable
For example, some API requests may require you to set session variables before executing the task, or a Dialog task component may need to access a session variable to transition to the next node. Dialog tasks can also access the context object with additional system variables. These session and context variables allow you to persist data and store, for example, a user’s home address for commerce, transportation, and home delivery-focused services to be used by the bot when executing a task.