如何在Watson Assistant的技能之间切换? [英] How to switch between skills on Watson Assistant?

问题描述

当前，在IBM Watson Assistant中，您只能将一种技能分配给助手.如何以编程方式交换助手的主要技能?

Currently in IBM Watson Assistant you can only assign one skill to an assistant. How can I programatically swap the main skill of an assistant?

推荐答案

将来的计划是让Assistant支持多种技能以及自定义技能.就如 data_henrik 所述，您可以使用V1 API调用每种技能.

The plan in the future is to have Assistant support multiple skills as well as custom skills. For the moment as data_henrik mentioned, you can use the V1 API to call each skill.

但是拥有多种技能仍然面临挑战，这可能会给您带来一些见识.

But having multiple skills still has its challenges, and this might give you some insights.

这些是您可以采用的一些方法(名称在某些情况下是组成的:).

These are some approaches you can take (names are made up in some cases :).

通过这种方法，您可以将用户的话语发送到所有工作空间，并获得最高的得分.

In this method you send your user utterance to all workspaces and take the highest scoring one.

如果您有大量意图(> 1,000)并且这些意图之间有明显区别，则需要使用此选项.这也是通话中最昂贵的.

This one is needed if you have a large number of intents (>1,000) and you have distinct differences between those intents. It's also the most costly in calls.

在此设置中，您具有高级技能.这试图了解将每个问题路由到何处的意图.然后，您将其暗示的第二种技能称为其返回的意图.

In this set up you have a top level skill. This attempts to understand the intent of where each question should be routed to. You then call the second skill it suggests as the intent it returns.

如果您的意图很多但主题相似，但又不足以组合为一项技能，则此方法有效.

This works if you have a large number of intents but similar topics, but not similar enough to group to a single skill.

类似于网关，除非一旦您确定了路由到您的最终技能，然后就只能使用该技能.如果该技能无法理解后面的问题，则将其路由回顶级技能，以找出应该去的地方.

Similar to the gateway, except once you have determined the final skill to route to you then only ever go to that skill. If that skill does not understand a later question, then it routes it back to the top level skill to figure out where it should go.

如果您的客户明确了他们要去的路，则此方法效果很好.因为他们倾向于在同一地区提出所有问题.

This one works well if you have customers with a clearly defined path of where they want to go. As they will tend to ask all their questions in the same area.

类似于路由器，除了当子技能不了解对方要求的内容时，而是回到顶层，它试图找出其他哪些子技能与其自身具有共同的关系(如果有的话)不能回到顶部).

Similar to the router, except when a sub-skill doesn't understand what the person asked, rather then going back to the top level it tries to figure out what other sub-skill has a common relationship with itself (if it can't it hands back to top).

这在多种技能可能具有相似意图的地方会有所帮助，但是在已经提出其他问题的情况下，您会选择一种技能而不是另一种.

This helps where multiple skills may have similar intents, but in the context of other questions already asked you would pick one skill over another.

在链设置中，您尝试以第一技巧回答用户问题.如果不能，那么您将学习第二种技能，依此类推.

In the chain setup you attempt to answer the user question in the first skill. If you can't, then you go to your second skill, then so on.

在这种情况下，您的意图按照已知频率的顺序进行映射.

Your intents in this case are mapped in order of known frequency.

如果您的意图非常相似，但是您知道人们提出的最常见问题，则此方法效果很好.但是，它是实施和维护中较难的一种.

This method works well if you have intents are very similar, but you know the most common questions people ask. It's one of the harder ones to implement and maintain though.

• 首先，每个技能都需要一个上下文对象.您无法跨技能共享上下文对象的系统部分.如果您使用的是Premium或Watson Assistant Plus，则将在技能本身内进行照管(因此您只需要存储对话ID).

• First, every skill needs a context object. You can't share the system part of the context object across skills. If you are using Premium or Watson Assistant Plus, then this is looked after within the skill itself (so you only need to store conversation IDs).

网关"，祈祷与祈祷"和连锁"失去了进行复杂对话的能力，而无需进行认真的工作.

"Gateway", "Spray and pray" and "chain" lose the ability to have complex conversational flows without serious work.

如果您计划一次从一项技能到另一项技能的通话，则可以使用云功能来实现.它降低了复杂性，并将逻辑带到了应用程序层之外.我通过我的语言翻译来实现例子.

If you plan a one-time call from one skill to another, you can use cloud functions to achieve this. It reduces the complexity, and takes the logic outside of the application layer. I achieve something like this with my language translation example.

通过使用技能而不是助手，您将失去进行基于版本控制的部署的能力.您可以创建多个助手来解决此问题，但这会使事情变得更加混乱.

By using the skills instead of the assistant, you lose the ability to do version control based deployments. You can create multiple assistants to get around this, but this makes things more messy.

这篇关于如何在Watson Assistant的技能之间切换?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！