有没有人知道这三者之间的具体差异和特征,或者如果有更多功能/更灵活地用作开发人员?
答案 0 :(得分:92)
vs
api.ai vs
luis.ai ╔══════════════════════════════════════════════════════════════════════════════════════════════════════════════════════════════╗
║ wit.ai vs api.ai vs luis.ai ║
╠══════╦════════════════════════════════════╦═════════════════════════════════════════════╦════════════════════════════════════╣
║ S.No ║ Wit.ai ║ Api.ai ║ Luis.ai ║
╠══════╬════════════════════════════════════╬═════════════════════════════════════════════╬════════════════════════════════════╣
║ 1 ║ Wit.ai API is completely free ║ Api.ai Has a paid enterprise option ║ LUIS is in beta and free to use ║
║ ║ with no limitations on ║ which allows for this to be run on a ║ 10K transactions per month ║
║ ║ request rates. ║ private cloud internally and more ║ and up to 5 requests per second ║
║ ║ ║ from their services team., After google ║ for each account. ║
║ ║ ║ acquisition they are providing free ║ ║
║ ║ ║ services by integrating google cloud ║ ║
║ ║ ║ services. ║ ║
╠══════╬════════════════════════════════════╬═════════════════════════════════════════════╬════════════════════════════════════╣
║ 2 ║ Provides a nice combination ║ Speech to Text and Text to Speech ║ LUIS uses machine learning ║
║ ║ of both voice recognition and ║ capabilities, along with machine ║ based methods to analyze ║
║ ║ machine learning for developers. ║ learning. ║ sentences. To perform machine ║
║ ║ ║ ║ learning, LUIS breaks an ║
║ ║ ║ ║ utterance into "tokens". ║
╠══════╬════════════════════════════════════╬═════════════════════════════════════════════╬════════════════════════════════════╣
║ 3 ║ Has two main elements to it ║ Support of Intents, Entities, actions ║ Supports Intents, Entities ║
║ ║ that you set up within your ║ and one key focus area is its “Domains”. ║ and actions. ║
║ ║ app – intents and entities. ║ ║ ║
║ ║ Actions are separated to ║ ║ ║
║ ║ use as a combined operations. ║ ║ ║
╠══════╬════════════════════════════════════╬═════════════════════════════════════════════╬════════════════════════════════════╣
║ 4 ║ Has pre-build entities like ║ Has pre-build entities like @sys.date, ║ Has pre-build entities ║
║ ║ temperature, number, URLs, ║ @sys.color, @sys.unit-currency… etc. ║ builtin.intent.alarm, ║
║ ║ emails, duration… etc. ║ ║ builtin.intent.calendar, ║
║ ║ ║ ║ builtin.intent.email… etc. ║
╠══════╬════════════════════════════════════╬═════════════════════════════════════════════╬════════════════════════════════════╣
║ 5 ║ Doesn’t have integration module ║ Has integration module to connect ║ Has integration to Microsoft ║
║ ║ to directly communicating with ║ directly to Facebook messenger and ║ Azure and other services, can be ║
║ ║ Facebook messenger or other ║ other messenger api’s. Has support for ║ deployable in any supported ║
║ ║ messenger APIs. but has web ║ deploying in to heroku server, enterprise ║ servers. ║
║ ║ service api to hook services. ║ paid environment. ║ ║
╠══════╬════════════════════════════════════╬═════════════════════════════════════════════╬════════════════════════════════════╣
║ 6 ║ Early in 2015, joined Facebook ║ Created by a team who built personal ║ LUIS was introduced together with ║
║ ║ and opened up the entire platform ║ assistant app for major mobile platforms ║ Microsoft Bot Framework and Skype ║
║ ║ to be free for both public and ║ with speech and text enabled conversations. ║ Developer Platform which can be ║
║ ║ private instances. ║ acquired by google (sept 2016). ║ used to create Skype Bots. ║
╠══════╬════════════════════════════════════╬═════════════════════════════════════════════╬════════════════════════════════════╣
║ 7 ║ Wit.ai API for developers of iOS, ║ Api.ai has SDKs for Android, iOS, ║ LUIS allow building applications ║
║ ║ Android, Node.js, Raspberry Pi, ║ the Apple Watch, Node.js, Cordova, ║ by using the LUIS web interface. ║
║ ║ Ruby, Python, C, Rust and ║ Unity, C#, Xamarin, Windows Phone, ║ No coding needed other than the ║
║ ║ Windows Phone. It even ║ Python and JavaScript. It also can be ║ ability to interpret and use the ║
║ ║ has a JavaScript plugin for ║ integrated with Amazon’s Echo and ║ returned JSON in application. ║
║ ║ front end developers. ║ Microsoft’s Cortana. ║ It is also possible to use the ║
║ ║ ║ ║ LUIS REST API for ║
║ ║ ║ ║ automation of applications. ║
╚══════╩════════════════════════════════════╩═════════════════════════════════════════════╩════════════════════════════════════╝
<强>更新强> API.AI现在是Dialogflow。 Learn more here.
答案 1 :(得分:43)
这个blogpost对Luis,Wit.ai,Api.ai,Amazon Alexa和IBM Watson服务进行了非常好的分析和比较。它还有一个很好的背景,说明为什么你想要首先构建一个会话机器人以及随之而来的一些挑战。它是由YumiBot背后的人写的(一个为您提供应用程序开发报价的机器人)。
一般的要点是 Wit.ai 和 Luis 是很好的选择,如果您正在尝试并且只是想免费获得一些东西。 Api.ai 拥有出色的服务和用户体验,但不是免费的。与 IBM Watson 相同,后者为企业工作定价更高。 Alexa的 API很棒,但只适用于Alexa(但鉴于他们拥有庞大的用户群,并不是一件坏事)。
他们的建议也是不要过分依赖一家提供商:
我们建议您以自己的代码存储库中的结构化方式存储模型所需的所有数据。因此,稍后您可以从头开始重新训练模型,甚至可以根据需要更改语言理解提供程序。当公司关闭他们的服务而你完全没有准备时,你只是不想处于这种情况。你还记得Parse吗?
我希望这有点帮助!我认为做出选择的最佳方式是试试这些服务。鉴于其中很多仍处于开发阶段且添加功能/更改定价模型,您应该尝试使用特定用例来查看它们,看看哪一个可以帮助您到达最快的地方。
答案 2 :(得分:8)
我们最近有published an evaluation study of seven NLU API-enabled services:API.ai,Amazon Lex,Microsoft LUIS,IBM Watson Conversation,wit.ai,Recast.ai和Snips.ai。
我们的调查结果摘要:
答案 3 :(得分:7)
这个问题的一个方面是这些工具在理解自然语言方面的效率如何。在刚刚发布的最近的基准测试中,我们(Snips,一家法国AI公司)刚刚发布,我们测试了Alexa(亚马逊),SiriKit(Apple),Luis(微软)和API.ai(谷歌)的内置自然语言引擎。
我们测试了他们理解自然查询的能力,例如“找到我可以参加午餐会的沙拉吧”,“为6人订购一辆出租车”,以及其他326个查询。
总的结论是所有解决方案都不完善。
更确切地说,他们的反应中都有相似的噪音水平(精确度在60%到90%之间),但他们可以支持的语言范围存在显着差异。从这个角度来看,Luis执行得最差:在我们测试的每个用例中,它只能理解不到14%的查询。 API.ai表现更好,但不是非常可靠:它可以理解我们测试的0到80%的查询,具体取决于用例。 Alexa(42%和82%的召回率)和Siri(召回率为61%)可以观察到最高的召回率。
更多详细信息以及这些结果背后的原始数据可以在我们的博文Benchmarking Natural Language Understanding Systems
中找到。答案 4 :(得分:1)
在我看来,Luis更强大,可以提取不同语言的实体。 我已经在api.ai进行了测试,而荷兰人并没有为我工作。 如果您只需要英语,那么其中任何一个都应该没问题,但如果您需要支持更多语言,那么在遇到一项服务之前,最好先测试这些语言。 Bing发言到文本是可以的,但我认为要获得更强大的解决方案,你需要另一个微软服务来清理语音和噪音。
答案 5 :(得分:1)
我将回答有关灵活性以及作为开发人员的问题的最后一部分,IMO,这最终取决于您在这些平台上的期望。
如果您是使用NodeJS或.Net的开发人员,则LUIS.ai拥有广泛的库和定义明确的代码段以及可以快速启动像样的机器人的示例。与Google相比,其意图和实体识别略低于标准水平,但是如果您是Microsoft Shop,则与O365,Teams,Skype,Cortana等都有很多一键式集成。LUIS.ai的缺点在于他们的服务非常不稳定,截至撰写本文时,他们的LUIS.ai网站无法拒绝连接,并且已经有一个多星期了,Cortana集成无法正常工作。因此,该平台仍在开发中。
Api.ai从纯粹的NLU角度来看要比Luis.ai更好,其后续意图非常容易设置,语音启动在很大程度上优于Luis.ai(即使在启动语音之后)。我要说的缺点是,建立机器人的可连接性和API比建立基于MSBot的聊天机器人要复杂一些。
另一个受到关注的平台开源平台是RASA NLU。 https://rasa.com/。相对而言,大型数据集的实体识别和排名仍然有些粗略,但是它的开放源代码,如果您想动手,可以使用他们的github平台进行改进。
从纯粹的开发角度来看,在MS平台上使用chatisbot(使用luis.ai或qnamaker.ai)更容易上手,但是在稳定平台时要准备面对挑战。
-Kartik
答案 6 :(得分:0)
我正在使用DialogFlow,但是我切换到LUIS。为什么?因为当您在DialogFlow中调用DetectIntent时,您会得到一个带有所选意图及其置信度的JSON,但是我需要获取一个意图列表,每个意图的置信度。 wit.ai和api.ai也会发生相同的情况。
另一方面,LUIS为您提供了意图列表作为响应。这样,我就可以对自己进行进一步处理。
当您搜索“飞往开罗的机票”时,这是LUIS的一个示例(LUIS示例的一部分):
{
"query": "Book me a flight to Cairo",
"topScoringIntent": {
"intent": "BookFlight",
"score": 0.9887482
},
"intents": [
{
"intent": "BookFlight",
"score": 0.9887482
},
{
"intent": "None",
"score": 0.04272597
},
{
"intent": "LocationFinder",
"score": 0.0125702191
},
{
"intent": "Reminder",
"score": 0.00375502417
},
{
"intent": "FoodOrder",
"score": 3.765154E-07
},
],
"entities": [
{
"entity": "cairo",
"type": "Location",
"startIndex": 20,
"endIndex": 24,
"score": 0.956781447
}
]
}
另一方面,用于配置DialogFlow的UI比您从LUIS获得的功能强大得多。