简体繁体 English

沃森会话引擎并行意图处理

[英]Watson Conversation Engine Parallel Intents Processing

原文 2016-11-23 03:43:06 9 1 ibm-watson/ watson-conversation/ watson-dialog

I have a conversation service with intents and entities. 我有意图和实体的对话服务。 I don't really have a dialog flow as my conversation agent would have to respond to a query which is not tiered or rather have a cadence. 我没有真正的对话流，因为我的会话代理必须响应一个没有分层或更有节奏的查询。

For eg 例如

Intent1 Intent1

Intent2 Intent2

... ...

Intent n 意图

These are parallel intents which could respond to a question. 这些是可以回答问题的平行意图。 What I get on dialog service is a tiered workflow, Start ->Intent 1 -> Intent2 我得到的对话服务是一个分层的工作流程，开始 - >意图1 - > Intent2

Without Intent1, I cannot go beyond any of the flows. 没有Intent1，我不能超越任何流程。

Kindly advice if I am missing anything here. 如果我在这里遗漏任何东西，请提供建议。

Another query related is does natural language classifier service scale to return a response similar to conversation engine? 另一个相关的查询是自然语言分类器服务规模返回类似于会话引擎的响应吗？ What I wanted was "what is weather in Los Angeles" and it gives me back information as "Temperature" =>Intent and Entity @City=Los Angeles. 我想要的是“什么是洛杉矶的天气”，它给了我回信息“温度”=>意图和实体@City =洛杉矶。 Assuming that I have list of cities in my Entity City. 假设我的实体城市中有城市列表。

1 个解决方案

Resolved: RTFM . 解决： RTFM 。 Dialog indeed has the ability to setup parallel intents. Dialog确实具有设置并行意图的能力。 Clicking on + at the bottom kind of setsup parallel intents. 单击底部类型的设置并行意图。 CLicking on + sign on the right corner allows you to setup intent cadence. 点击右上角的+号可以设置意图节奏。 I observe that IBM did a good job of copying of what Microsoft did with Luis here. 我观察到IBM在复制微软对Luis的处理方面做得很好。 Looks clean with the User interface. 用户界面看起来很干净。 When parallel intents are setup, you text responds back with a % match and with that you can make a genuine decision. 设置并行意图时，文本会以％匹配回复，并且您可以做出真正的决定。