Please enable JavaScript.

Coggle requires JavaScript to display documents.

CHATBOT - Coggle Diagram

- - - - Agent
      - A Dialogflow agent is a virtual agent with the mission to handle conversations with your customers. Once a user sends a text message to the Dialogflow agent, Google uses artificial intelligence to translate the message into structured data with the aid of NLP.
      - Customers reach out to chatbot agent to acquire certain information. Hence, the Dialogflow agent needs to be built to handle the conversation.
      - A Dialogflow agent is similar to a human call centre agent. Whether it is a Dialogflow agent or a human agent, both need to be trained to handle conversational scenarios. Training does not need to be overly explicit.
    - - Intent
      - Customers reach out to chatbot agent to acquire certain information. 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.
      - An intent categorises the customer's intention for a conversation turn. You can define mutiple intents for a single agent, just like how a call centre agent can decide if you need basic troubleshooting, make an appointment, or redirect your phone calls based on what you say.
      - What a customer types to the chatbot is referred to as an "end-user expression". Dialogflow matches the end-user expression to the best intent in your agent. Matching an intent is also known as intent classification.
    - - Entity
      - When an intent is matched, Dialogflow can extract specific information from the end-user expression. The extracted data is called a parameter or entity type. Parameters and entity types are structured data that can help us make better sense of what the user is trying to find out.
      - In Dialogflow, there are system entities - e.g. 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.
- - - - Bots Can Retrieve Information and Respond Quickly
      - Unlike a human being who may need to search through manuals before they can provide a reasonable reply, bots are programmed and can retrieve information and respond within milliseconds. Customers can now be served in a shorter period of time.
      - Bots Can Relieve Workload of Human Agents
      - What was a 10-minute interaction between a customer and a service agent, is now a 2-minute conversation between the customer and a chatbot with a name and face. The service agent is now able to focus on other tasks.
      - Chatbot Data can be Analysed
      - All the chat conversations can be saved and analysed. We can find out what customers are frequently asking, and better attend to their needs.