Please enable JavaScript.
Coggle requires JavaScript to display documents.
Chatbots - Coggle Diagram
Chatbots
-
Dialogflow
Natural Language Processing (NLP) is how we can train computers to understand and process the natural human language.
-
Dialogflow allows you to (1) build, (2) test, (3) launch and (4) improve your chatbot
Agents, Intents and Entities
-
Two different customers may ask the same thing differently, but their intent is the same
For example, if User A asks the chatbot "What time do you open on Saturday?", and User B asks "What are the opening hours on weekends?", both have the same intent of finding out the opening hours.
-
system entities
dates, times, numbers, email addresses, etc. You can also create your own custom entities. For example, you could define a vegetable entity that can match the types of vegetables available for purchase with a grocery store agent.
Many commercial chatbots are trained and tested, hence abling to hit an accuracy of about 80% or more.Thus 70-100% accurate
chatbots are consistent in their response (but whether it is "consistently right" or "consistently wrong" is another issue altogether).