blocks|key|311361|text|因此，如果没有更多关于你如何建立语言模型的细节，最基本的问题可能是，你要么在每个意图中没有足够的话语，而这些意图有足够的变化，显示出不同的表达方式可以用来表达特定的意图。|type|unstyled|depth|inlineStyleRanges|entityRanges|data|311362|变体是指不同的话语长度(字数)、不同的语序、时态、语法正确性等(医生来了)。|offset|length|311363|记住，每个意图应该在上至少有15个话语，。|style|BOLD|311364|此外，正如最佳实践中所述，您是否也确保在您的“无意图”中包括示例语句？最佳实践声明，您应该在应用程序的其他部分中，每10个语句中就有一个无语句。|311365|最终:构建你的应用程序，这样你的意图就足够清晰，你的意图中包含了不同的例子话语，这样当你测试其他的话语时，路易斯就更有可能与你的不同意图相匹配--如果你输入一个不遵循你不同意图的任何模式或上下文的话语，路易斯就会知道如何检测到你的“无”意图。|311366|如果您需要更具体的帮助，请张贴您的语言模型的JSON。|311367|entityMap|0|LINK|mutability|MUTABLE|url|https://learn.microsoft.com/en-us/azure/cognitive-services/luis/luis-quickstart-intents-only#getjobinformation-intent|1^0|0|W|4|0|0|A|A|0|H|A|Z|4|1|0|0|0^^$0|@$1|2|3|4|5|6|7|Y|8|@]|9|@]|A|$]]|$1|B|3|C|5|6|7|Z|8|@]|9|@$D|10|E|11|1|12]]|A|$]]|$1|F|3|G|5|6|7|13|8|@$D|14|E|15|H|I]]|9|@]|A|$]]|$1|J|3|K|5|6|7|16|8|@$D|17|E|18|H|I]]|9|@$D|19|E|1A|1|1B]]|A|$]]|$1|L|3|M|5|6|7|1C|8|@]|9|@]|A|$]]|$1|N|3|O|5|6|7|1D|8|@]|9|@]|A|$]]|$1|P|3|-4|5|6|7|1E|8|@]|9|@]|A|$]]]|Q|$R|$5|S|T|U|A|$V|W]]|X|$5|S|T|U|A|$V|W]]]]

So without more details on how you've built your language model, most likely the underlying issue is that you either don't have enough utterances in each intent that have enough variation displaying the different ways in which different utterances could be said for that particular intent.

And by variation I mean different lengths of the utterance (word count), different word order, tenses, grammatical correctness, etc. (<a href="https://learn.microsoft.com/en-us/azure/cognitive-services/luis/luis-quickstart-intents-only#getjobinformation-intent" rel="nofollow noreferrer">docs here</a>) 

And remember each intent should have at least 15 utterances.

Also, as stated in best practices, do did you also make sure to include example utterances in your None intent as well? <a href="https://learn.microsoft.com/en-us/azure/cognitive-services/luis/luis-quickstart-intents-only#getjobinformation-intent" rel="nofollow noreferrer">Best practices</a> state that you should have 1 utterances in None for every 10 utterances in the other parts of your app.

Ultimately: build your app so that your intents are distinct enough with varying example utterances built into the intent, so that when you test other utterances LUIS will be more likely able to match to your distinct intents--and if you enter an utterance that doesn't follow any sort of pattern or context of your distinct intents, LUIS will know to detect the utterance to your fallback "None" intent.

If you want more specific help, please post the JSON of your language model.

blocks|key|1840567|text|设置一个得分阈值，低于这个阈值，应用程序将不会显示对用户的任何响应(或者显示“对不起，我没有收到您”的消息)。这就避免了用LUIS不确定的内容来响应用户，这通常也会处理大量的“非主题”输入。|type|unstyled|depth|inlineStyleRanges|entityRanges|data|1840568|我建议将其设定为0.3至0.7之间，视主题的严重性而定。这不是LUIS中的配置选项，而是在您的代码中只需这样做：|1840569|if(result.score+>=0.5)+{+
++++//+show+response+based+on+intent.
}+else+{+
++++//+ask+user+to+rephrase
}|code-block|syntax|javascript|1840570|另外，你的意图似乎很不平衡。你想要尝试，并有大致相同的数量的每一个意图，在10到20之间，理想的。|1840571|entityMap^0|0|0|0|0^^$0|@$1|2|3|4|5|6|7|M|8|@]|9|@]|A|$]]|$1|B|3|C|5|6|7|N|8|@]|9|@]|A|$]]|$1|D|3|E|5|F|7|O|8|@]|9|@]|A|$G|H]]|$1|I|3|J|5|6|7|P|8|@]|9|@]|A|$]]|$1|K|3|-4|5|6|7|Q|8|@]|9|@]|A|$]]]|L|$]]

Set a score threshold, below which your app won't show any response to the user (or could show a "sorry I didn't get you" message instead). This avoid responding to users with anything LUIS is unsure about, which usually takes care of a lot of "off topic" input too.

I would suggest setting it your threshold between 0.3 and 0.7, depending on the seriousness of your subject matter. This is not a configuration option in LUIS, rather in your code you just do:

<pre><code>if(result.score &gt;=0.5) { 
 // show response based on intent.
} else { 
 // ask user to rephrase
}
</code></pre>

On a separate note, it looks like your intents are very imbalanced. You want to try and have roughly the same number of utterances for each intent, between 10 and 20 ideally.

I am facing an issue whereby words that does not match with any intents, it will assume it belongs to intent with the most labeled utterances.

Example: if

<ul>
<li>Intent A consists of utterances such as Animals</li>
<li>Intent B consists of utterances such as Fruits</li>
<li>Intent C consists of utterances such as Insects</li>
<li>Intent D consists of utterances such as People Name</li>
</ul>

Desired: If the random word(s) does not fit into any of the luis intent, it will fit into none luis intent. Example of desired: If word such as "emotions" or "clothes" were entered, it will match as "None" intent.

Actual: When user type random word(s), it match with luis intent with highest number of labeled utterances. If word such as "emotions" was entered, it will match as "A" intent as intent A consist of highest number of labeled utterances.

Please advise on the issue. 

<a href="https://i.stack.imgur.com/GRbUk.png" rel="nofollow noreferrer"><img src="https://i.stack.imgur.com/GRbUk.png" alt="enter image description here"></a>

Map to the wrong LUIS intent

翻译质量差，导致语言生硬或混乱。

没有提供实际的解决方法或示例。

解答不清晰，无法理解或解决问题。

页面排版不美观，阅读体验差。

文章

问答

视频

教程

学习中心

腾讯云实验室

直播

竞赛

腾讯云代码分析专区

腾讯iOA零信任安全管理系统专区

腾讯云架构师技术同盟交流圈

腾讯云数据库专区

腾讯云智能顾问专区

腾讯云原生专区

腾讯混元专区

腾讯云TCE专区

腾讯云Lighthouse专区

腾讯云HAI专区

腾讯云Edgeone专区

腾讯云存储专区

腾讯云智能专区

腾讯轻联专区 

腾讯云开发专区

TAPD专区

腾讯轻量云游戏服专区

腾讯云最具价值专家

腾讯云架构师技术同盟

腾讯云创作之星

腾讯云开发者先锋

腾讯云代码助手

云原生构建

TAPD 敏捷项目管理

Cloud Studio

SDK中心

API中心

命令行工具

涵盖代码开发、场景应用、自动测试全流程，助你从零构建专属AI助手

一站式MCP教程库，解锁AI应用新玩法

聚焦“写作效率、视觉美观与运行性能”三方面进行全面升级，为您提供更高效、稳定的创作环境

社区富文本&Markdown编辑器全新改版上线，欢迎大家体验!

诚挚邀请您参与本次调研，分享您的真实使用感受与建议。您的反馈至关重要，感谢您的支持与参与！

社区新版编辑器体验调研

我正面临一个问题，在这个问题上，不符合任何意图的话，它将认为它属于意图与标签最多的话语。示例:如果意图A由诸如动物之类的话语组成意图B由诸如水果之类的话语组成。意图C由诸如昆虫之类的话语组成意图D由诸如人的名字之类的话语组成理想的：如果随机词不符合任何路易斯意图，它将符合无路易斯意图。想要的例子:如果输入诸如“情感”或...

问映射到错误的路易斯意图
EN

Stack Overflow用户

社区

活动

圈层

关于

腾讯云开发者

热门产品

热门推荐

更多推荐

问映射到错误的路易斯意图EN