Glossary & Definition
Platform
An application that allows users to visually create and manage multiple bots, and within each bot, build and maintain different conversation flows.
Agent
A virtual staff that can be used online independently and is capable of understanding natural human language through analysis. It takes the form of daily conversations to assist enterprises with various real business problems resolutions in an efficient, rigorous and cost-effective manner.
Intent
What the user wants to accomplish. For example, to get the weather condition, to get the method of handling affairs, to finish the affairs, etc.
Entity
An element of information in natural language, consisting of words or phrases. It includes the name of a person, organization, geographic location, time, date, etc.
Slot
The variable that stores the key information needed for intent, which can be inherited in a conversation, and the robot gives subsequent actions and feedback based on the value in the word slot.
Skill
A complete task that the bot accomplishes by talking to the user, and it can solve an independent need of the user through one or more rounds of conversation.
FAQ
Used in explicit single-round questioning scenarios, a knowledge question and answer consists of a user question and a response answer.
Dailogue Tree
A dailogue tree consists of hierarchical tree branches. A response is given based on the user's question and branch selection. In multiple rounds of questioning, the branches are refined and advanced to give a definitive answer.
Dailogue Flow
Used for more complex multi-round task scenarios, including but not limited to complex dialogue flows, data interaction with external interfaces, etc.
Channel
Channels are the medium through which bots interact with end users.
After creating a channel, you can use the send and receive message interface provided by the open platform to make calls and integrate the conversation bot capabilities in your own conversation scenarios for end-users to use.
Session
This is a record of a conversation between a user and a bot with a complete contextual relationship - a session starts when the user initiates a message to the bot, and ends when the user does not continue sending messages within 15 minutes of the last message.
Log
Logs show details of each message sent by the user and the corresponding bot reply, sorted in reverse chronological order of when the message occurred, with the later occurring first.
Label
Developer can educate the bot with the real conversation records after it goes live, helping the bot to continuously optimize its knowledge system and make itself more "smart".