When you create a custom Bot in Kore.ai, you should consider how your users of the custom Bot will access and interact with the Bot. The Kore.ai Bots Platform provides a Natural Language Processing, or NLP interpreter. With NLP, your users can get, authenticate, and interact with your custom Bot using simple, everyday language. For example, a user could enter text in a messaging window such as, “Get me a 3-day weather forecast for my zip code.” The NLP interpreter will process the user input, and offer to set up an appropriate Bot to get the weather forecast, such as the Kore.ai Weather Underground Bot.
To make sure your Bot is NLP-optimized, you can define, and refine names and terms used for your custom Bot to enhance the NLP interpreter accuracy and performance to recognize the right Bot task for the user. You begin by defining synonyms at the task level, and then manage and refine synonyms, and test at the Bot level.
To get started optimizing your bot and bot tasks, you need to open the Natural Language tab. In Bot Builder, select the bot that you want to optimize NLP settings for, and then on the Natural Language tab, select on of the following options shown in the illustration.
Training – In the Training section, you can test how the NLP interpreter recognizes and responds to user input for a Bot, and then if needed, train the interpreter to recognize the correct user intent.
Machine Learning – With Machine Learning, you can enhance Bot recognition of user utterances for better recognition and system performance for the user intent, which is the intended task that the user wants to access.
Synonyms – You can use the Synonyms section to optimize the NLP interpreter accuracy in recognizing the correct task and task field provided by the user for the names of your tasks and task fields.
Patterns – In the Patterns section, you can define slang, metaphors, or other idiomatic expressions for task names and task fields. For more information, see Managing Patterns.
Standard Responses – Standard responses are pre-defined text responses to users based on an event, condition, trigger, or user input. In the Standard Responses section, you can modify existing bot responses, or add additional responses for the same event.
Ignore Words & Field Memory – In this section, you can configure bot intelligence by persisting data for each task to pre-populate data fields in another related task for the same bot in the Field Memory settings for each task. You can also define words to ignore in user utterances to increase performance and intent recognition. For more information, see Managing Ignore Words & Field Memory.
Task Identification Settings – In this section, you can define the recognition confidence levels required for minimum recognition actions, the confidence range for asking a user to choose from a list of possible matches, and a recognition confidence level for a positive match for knowledge tasks.
Refer Developer topic on: Optimizing Bots for Natural Language Processing