将Watson Dialog服务转换为对话服务 [英] Watson Dialog service to Conversation service

问题描述

我们使用Bluemix Dialog服务创建了对话框，现在我们想将它们导入到新的Bluemix Conversation服务中. 导出导入失败. 你知道转移过程是否存在吗?

We created dialogs with Bluemix Dialog service and now we would like to import them into the new Bluemix Conversation service. The export-import failed. Do you know if an transfert process exists ?

谢谢

推荐答案

不幸的是，由于这两个系统非常不同，因此无法从Dialog迁移到对话".

Unfortunately the ability to migrate to Conversation from Dialog is not possible, as the two systems are very different.

意图与NLC相似.因此，如果您有现有的NLC服务，则可以将其导出并导入为CSV文件.

Intents in Conversation are similar to NLC. So if you have an existing NLC service, you can export that and import as a CSV file.

实体与Dialog中的完全不相关.

Entities in Conversation are not at all related to the same in Dialog.

对话本身是无状态的.所有会话状态，上下文变量都需要在应用程序层进行维护. Dialog通常将其保留在哪里.

Conversation itself is stateless. All conversational state, context variables need to be maintained at the application layer. Where as Dialog would normally maintain that.

在对话框中，您现在定义为INPUT + OUTPUT的节点现在是对话"中的单个节点.

In Dialog What you would define as an INPUT + OUTPUT nodes are now a single node in Conversation.

GOTO现在是Continue from.但是，continu from的行为会有所不同，具体取决于您是否将其挂钩为等待用户输入"，条件"或消息".

GOTO is now Continue from. But a continue from will have different behaviours depending if you hook it to "wait for user input", "condition" or "message".

现在，您可以通过在条件块中或在应用程序层进行编码来处理通常与变体形式相匹配的模糊匹配.

Fuzzy matching what you would normally do with Variations is now handled by coding in condition blocks, or at the application layer.

这篇关于将Watson Dialog服务转换为对话服务的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！