无法使用Actions SDK读取意图 [英] Unable to read intents using Actions SDK

问题描述

我的action.json文件中有以下操作，

I've got the following action in my action.json file,

{
    "description": "Recommend movies",
    "initialTrigger": {
        "intent": "GIVE_RECOMMENDATION",
        "queryPatterns": [
            {"queryPattern": "What should I watch?"},
            {"queryPattern": "Give me a recommendation"},
            {"queryPattern": "Tell me a good ($String:genre)? movie"}
        ]
    },
    "httpExecution": {
        "url":"my webhook URL here"
    }
}

在我的API上，我得到了：

On my API, I've got:

app.post('/', function(req, res){
    let assistant = new ActionsSdkAssistant({request: req, response: res});
    console.log('Current intent: ' + assistant.getIntent());
}

当我模拟自己的动作并说我应该看什么？，当前的意图始终是 assistant.intent.action.TEXT。为什么从来没有'GIVE_RECOMM

When I simulate my action, and say "What should I watch?", the current intent is ALWAYS 'assistant.intent.action.TEXT'. Why is it never 'GIVE_RECOMMENDATION', like its supposed to be?

推荐答案

我假设您正在测试自己的技能：

I'm assuming you're testing your skill as such:

打开操作名称

open ACTION NAME

我应该看什么？

您可能遇到了与我相同的问题，请查看对
的接受的答案和评论 ExpectedInputs /可能性_intents仅与 assistant.intent.action.TEXT一起使用？

Chances are you're having the same issue I had, see the accepted answer and comments to ExpectedInputs / possible_intents only works with "assistant.intent.action.TEXT"?

简而言之：最初的意图被触发后（即打开技能后），Actions SDK仅支持assistant.intent.action.TEXT意向，不再进行任何意向匹配。

In short: After the initial intent was triggered (i.e. after you opened your skill) the Actions SDK only supports the assistant.intent.action.TEXT intent and no longer does any intent matching.

意图匹配仅适用于操作的第一次调用：

Intent matching only works for the very first invocation of the action:

问ACTION_NAME我应该看什么？

ask ACTION_NAME What should I watch?

以上应该为您提供正确的意图名称。

The above should give you the correct intent name.

如果您没有自己的系统，建议使用 http://api.ai 自然语言处理，并且需要与用户进行基于意图的对话

Google recommends using http://api.ai if you do not have your own system in place for natural language processing and need to have intent-based dialog with your user

这篇关于无法使用Actions SDK读取意图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！