Hands-On Chatbots and Conversational UI Development
上QQ阅读APP看书,第一时间看更新

Managing context 

In any conversation, the context of conversation needs to be managed. Context can be maintained by creating a local cache where the information transferred between the two dialogue partners can be stored. For instance, the user may tell the chatbot their food preferences, and this information can be stored in context for future reference if not used immediately. Another instance is in a conversation where the user is asking questions about a story. These questions may be incomplete and may need to be interpreted in terms of the information available in the context. 

In this section, we will explore how context can be recorded and utilized during the conversation in Chatfuel. Let's take the task of finding a restaurant as part of your tour guide chatbot. The conversation between the chatbot and the user might go as follows:

User : Find a restaurant
Bot : Ok. Where?
User : City center.
Bot : Ok. Any cuisine that you fancy?
User : Indian
Bot : Ok. Let me see... I found a few Indian restaurants in the city center.
Here they are.

In the preceding conversation, up until the last bot utterance, the bot needs to save the information locally. When it has gathered all the information it needs, it can go off and search the database with appropriate parameters. Notice that it also needs to use that information in generating utterances dynamically. Let's explore how to do these two—dynamically generating utterances and searching the database.

First, we need to build the conversational flow to take the user through the conversation just as we discussed in the Next steps section. Let's assume that the user clicks the Find_a_restaurant button on the welcome block. Let's build the basic blocks with text messages and buttons to navigate through the conversation: