document/TranslateProject
2
0
Fork 0
mirror of https://github.com/LCTT/TranslateProject.git synced 2025-03-21 02:10:11 +08:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #20309 from alim0x/master

Browse Source 
[translated]20191118 Creating a Chat Bot with Recast.AI
This commit is contained in:
Xingyu.Wang 2020-12-01 17:39:09 +08:00 committed by GitHub
commit 4351ac78e0
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 179 additions and 181 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

181
sources/tech/20191118 Creating a Chat Bot with Recast.AI.md
View File

@ -1,181 +0,0 @@
[#]: collector: (lujun9972)
[#]: translator: (alim0x)
[#]: reviewer: ( )
[#]: publisher: ( )
[#]: url: ( )
[#]: subject: (Creating a Chat Bot with Recast.AI)
[#]: via: (https://opensourceforu.com/2019/11/creating-a-chat-bot-with-recast-ai/)
[#]: author: (Athira Lekshmi C.V https://opensourceforu.com/author/athira-lekshmi/)
Creating a Chat Bot with Recast.AI
======
[![][1]][2]
_According to a Gartner report from February 2018, “25 per cent of customer service and support operations will integrate virtual customer assistant (VCA) or chatbot technology across engagement channels by 2020, up from less than 2 per cent in 2017.” In the light of this, readers will find this tutorial on how the open source Recast. AI bot-creating platform works, helpful._
Chat bots, both voice based and others, have been in use for quite a while now. From chatbots that engage the user in a murder mystery game to bots which help in real estate deals and medical diagnosis, chatbots have traversed across domains.
There are many platforms which enable users to create and deploy bots. Recast.AI (now known as SAP Conversational AI after its acquisition by SAP) is a forerunner amongst these.
The cool interface, its collaborative nature and the analytics tools it provides, make it a popular choice.
As the Recast official site says, “It is an ultimate collaborative platform to build, train, deploy and monitor intelligent bots.”
![Figure 1: Setting the bot properties][3]
![Figure 2: Bot dashboard][4]
![Figure 3: Searching an intent][5]
**Building a basic bot in Recast**
Let us look at how to build a basic bot in Recast.
1. Create an account in _<https://cai.tools.sap>_. Signing up can be done either with an email ID or with a GitHub account.
2. Once you log in, you will land on the dashboard. Click on the + New Bot icon on the top right-hand side to create a new bot.
3. On the next screen, you will see that there is a set of predefined skills you can select. Select Greetings for the time being (Figure 1). This bot is already trained to understand basic greetings.
4. Provide a name for your bot. For now, since this is a very basic bot, you can have the bot crack some jokes, so let us name it Joke Bot and select the default language as English.
5. Select Non-personal data under the data policy since you won’t be dealing with any sensitive information; then select the Public bot option and click on Create a bot.
So that’s your bot created on the Recast platform.
![Figure 4: @joke intent][6]
![Figure 5: Predefined expressions][7]
**The five stages of developing a bot**
To use the words from the official Recast blog, there are five stages in a bot’s life.
* Training – Teaching your bot what it needs to understand
* Building – Creating your conversational flow with the Bot Builder tool
* Coding – Connecting your bot with external APIs or a database
* Connecting – Shipping your bot to one or several messaging platforms
* Monitoring – Training your bot to make it sharper and get insights on its usage
**Training a bot through intents**
You will be able to see the options to either search, fork or create an intent in the dashboard.
“An intent is a box of expressions that mean the same thing but which are constructed in different ways. Intents are the heart of your bot’s understanding. Each one of your intents represents an idea your bot is able to understand.” (from the _Recast.AI_ website)
As decided earlier, you need the bot to be able to crack jokes. So the base line is that the bot should be able to understand that the user is asking it to tell a joke; it shouldn’t be that even when the user just says, “Hi,” the bot responds with a joke – that would not be good.
So group the utterances that the user might make, like:
```
Tell me a joke.
Tell me a funny fact.
Can you crack a joke?
What’s funny today?
```
…………………
Before going on to create the intent from scratch, let us explore the Search/fork option. Type _Joke_ in the search field (Figure 3). This gives a list of intents created by users of Recast around the globe, which is public, and this is why Recast is said to be collaborative in nature. So there’s no need to create all intents from scratch, one can build upon intents already created. This brings down the effort needed to train the bot with common intents.
* Select the first intent in the list and fork it into the bot.
* Click on the Fork button. The intent is now added to the bot (Figure 4).
* Click on the intent @joke, and a list of expressions which already exist in the intent will be displayed (Figure 5).
* Add a few more expressions to it (Figure 6).
![Figure 6: Suggested expressions][8]
![Figure 7: Suggested expressions][9]
Once a few expressions are added, the bot gives suggestions like shown in Figure 7. Select a few and add them to the intent (Figure 7).
You can also tag your own custom entities to detect keywords, depending on your bot’s context.
**Skills**
A skill is a block of conversation that has a clear purpose and that your bot can execute to achieve a goal. It can be as simple as the ability to greet someone, but it can also be more complex, like giving movie suggestions based on information provided by the user.
It need not be just a one query-answer set, but rather, skills running through multiple exchanges. For example, consider a bot which helps you learn about currency exchange rates. It starts by asking the source currency, then the target currency, before giving the exact response. Skills can be combined to create complex conversational flows.
Here’s how you create a skill for the joke bot:
* Go to the _Build_ tab. Click on the + icon to create a skill.
* Name the skill _Joke_ (Figure 8)
* Once created, click on the skill. You will see four tabs. _Read me, Triggers, Requirements and Actions_.
* Navigate to the Requirements tab. You should store the information only if the intent joke is present. So, add a requirement as shown in Figure 9.
![Figure 8: Skills dashboard][10]
![Figure 9: Adding a trigger][11]
Since this is a simple use case, you needn’t consider any specific requirements in the Requirement tab but consider a case for which a response needs to be triggered only if certain keywords or entities are present – in such a case you will need ‘requirements’.
Requirements are either intents or entities that your skill needs to retrieve before executing actions. Requirements are pieces of information that are important in the conversation and that your bot can use; for example, the user’s name or a location. Once a requirement is completed, the associated value is stored in the bot’s memory for the entire conversation.
Now let us move to the Action tab to set the responses (see Figure 10).
Click on Add _new message group_. Then select _Send message_ and add a text message, which can be any joke in this case. Also, since you don’t want your bot to crack the same joke each time, you can add multiple messages which will be randomly picked each time.
![Figure 10: Adding actions][12]
![Figure 11: Adding text messages][13]
![Figure 12: Setting up webchat][14]
**Channel integrations**
Well, the success of a bot also depends upon how easily it is accessible. Recast has built-in integrations with many messaging channels such as Skype for Business, Kik Messenger, Telegram, Line, Facebook Messenger, Slack, Alexa, etc. In addition to that, Recast also provides SDKs to develop custom channels.
Also, there is a ready-to-use Web chat provided by Recast (in the Connect tab). You can customise the colour schemes, headers, bot pictures, etc. It provides you with a script tag to be injected into the page. Your interface is now up (Figure 12).
The Web chat code base is open sourced, which makes it easier for developers to play around with the look and feel, the standard response types and much more.
The dashboard provides step-by-step procedures on how to deploy the bot on various channels. The joke bot was deployed in Telegram and in Web chat, as shown in Figure 13.
![Figure 13: Webchat deployed][15]
![Figure 14: Bot deployed in Telegram][16]
![Figure 15: Multi-language bot][17]
**And there is more**
Recast supports multiple languages, Select one language as the base while creating the bot, but then you also have the option to add as many languages as you want.
The example considered here is a simple static joke bot, but actual use cases will need interaction with various systems. Recast has a Web hook feature which allows users to connect with various systems to get responses. Also, there is detailed API documentation to help leverage each independent feature of the platform.
As for analytics, Recast has a monitoring dashboard which helps you understand the accuracy of the bot and train it further.
![Avatar][18]
[Athira Lekshmi C.V][19]
The author is an open-source enthusiast.
[![][20]][21]
--------------------------------------------------------------------------------
via: https://opensourceforu.com/2019/11/creating-a-chat-bot-with-recast-ai/
作者：[Athira Lekshmi C.V][a]
选题：[lujun9972][b]
译者：[译者ID](https://github.com/译者ID)
校对：[校对者ID](https://github.com/校对者ID)
本文由 [LCTT](https://github.com/LCTT/TranslateProject) 原创编译，[Linux中国](https://linux.cn/) 荣誉推出
[a]: https://opensourceforu.com/author/athira-lekshmi/
[b]: https://github.com/lujun9972
[1]: https://i0.wp.com/opensourceforu.com/wp-content/uploads/2019/04/Build-ChatBoat.jpg?resize=696%2C442&ssl=1 (Build ChatBoat)
[2]: https://i0.wp.com/opensourceforu.com/wp-content/uploads/2019/04/Build-ChatBoat.jpg?fit=900%2C572&ssl=1
[3]: https://i1.wp.com/opensourceforu.com/wp-content/uploads/2019/11/Figure-1-Setting-the-bot-properties.jpg?resize=350%2C201&ssl=1
[4]: https://i1.wp.com/opensourceforu.com/wp-content/uploads/2019/11/Figure-2-Setting-the-bot-properties.jpg?resize=350%2C217&ssl=1
[5]: https://i0.wp.com/opensourceforu.com/wp-content/uploads/2019/11/Figure-3-Searching-an-intent.jpg?resize=350%2C271&ssl=1
[6]: https://i0.wp.com/opensourceforu.com/wp-content/uploads/2019/11/Figure-4-@joke-intent.jpg?resize=350%2C214&ssl=1
[7]: https://i0.wp.com/opensourceforu.com/wp-content/uploads/2019/11/Figure-5-Predefined-expressions-350x227.jpg?resize=350%2C227&ssl=1
[8]: https://i2.wp.com/opensourceforu.com/wp-content/uploads/2019/11/Figure-6-Suggested-expressions-350x197.jpg?resize=350%2C197&ssl=1
[9]: https://i1.wp.com/opensourceforu.com/wp-content/uploads/2019/11/Figure-7-Suggested-expressions-350x248.jpg?resize=350%2C248&ssl=1
[10]: https://i0.wp.com/opensourceforu.com/wp-content/uploads/2019/11/Figure-8-Skills-dashboard.jpg?resize=350%2C187&ssl=1
[11]: https://i0.wp.com/opensourceforu.com/wp-content/uploads/2019/11/Figure-9-Adding-a-trigger.jpg?resize=350%2C197&ssl=1
[12]: https://i0.wp.com/opensourceforu.com/wp-content/uploads/2019/11/Figure-10-Adding-actions.jpg?resize=350%2C175&ssl=1
[13]: https://i1.wp.com/opensourceforu.com/wp-content/uploads/2019/11/Figure-11-Adding-text-messages.jpg?resize=350%2C255&ssl=1
[14]: https://i2.wp.com/opensourceforu.com/wp-content/uploads/2019/11/Figure-12-Setting-up-webchat.jpg?resize=350%2C326&ssl=1
[15]: https://i0.wp.com/opensourceforu.com/wp-content/uploads/2019/11/Figure-13-Webchat-deployed.jpg?resize=350%2C425&ssl=1
[16]: https://i2.wp.com/opensourceforu.com/wp-content/uploads/2019/11/Figure-14-Bot-deployed-in-Telegram.jpg?resize=350%2C269&ssl=1
[17]: https://i1.wp.com/opensourceforu.com/wp-content/uploads/2019/11/Figure-15-Multi-language-bot.jpg?resize=350%2C419&ssl=1
[18]: https://secure.gravatar.com/avatar/d24503a2a0bb8bd9eefe502587d67323?s=100&r=g
[19]: https://opensourceforu.com/author/athira-lekshmi/
[20]: https://opensourceforu.com/wp-content/uploads/2019/11/assoc.png
[21]: https://feedburner.google.com/fb/a/mailverify?uri=LinuxForYou&loc=en_US

179
translated/tech/20191118 Creating a Chat Bot with Recast.AI.md Normal file
View File

@ -0,0 +1,179 @@
[#]: collector: (lujun9972)
[#]: translator: (alim0x)
[#]: reviewer: ( )
[#]: publisher: ( )
[#]: url: ( )
[#]: subject: (Creating a Chat Bot with Recast.AI)
[#]: via: (https://opensourceforu.com/2019/11/creating-a-chat-bot-with-recast-ai/)
[#]: author: (Athira Lekshmi C.V https://opensourceforu.com/author/athira-lekshmi/)
用 Recast.AI 创建一个聊天机器人
======
[![][1]][2]
_据 Gartner 2018 年 2 月的报告，“到 2020 年，25% 的客户服务和支持业务将在参与渠道中整合虚拟客户助理（VCA）或聊天机器人技术，而 2017 年只有不到 2%。”鉴于此，读者会发现本教程对理解开源的 Recast.AI 机器人创建平台的工作原理很有帮助。_
聊天机器人，包括基于语音的以及其他技术的，已经实际使用了有一阵子了。从让用户参与谋杀解密游戏，到帮助完成房地产交易和医疗诊断，聊天机器人已经跨越了多个领域。
有许多平台可以让用户创建和部署机器人。Recast.AI（在被 SAP 收购之后现在是 SAP Conversational AI）是其中的先行者。
酷炫的界面、协作性以及它所提供的分析工具，让它成为流行的选择。
正如 Recast 官方网站说的，“它是一个创建、训练、部署和监控智能机器人的终极协作平台。”
![图 1: 设置机器人属性][3]
![图 2: 机器人面板][4]
![图 3: 搜索一个意图][5]
**创建一个基础的机器人**
让我们来看看如何在 Recast 创建一个基础的机器人。
1. 在 _<https://cai.tools.sap>_ 创建一个账户。注册可以使用电子邮箱或者 Github 账户。
2. 在你登录之后，你会进入仪表板。点击右上角 + 新建机器人图标新建一个机器人。
3. 在下一个界面，你会看到一系列可选的预定义技能。暂时选择问候（图1）。这个机器人已经经过训练，来理解基本的问候。
4. 给机器人提供一个名字。目前来说，你可以让机器人讲一些笑话，所以我们将它命名为 Joke Bot，选择英语作为默认语言。
5. 因为你不会处理任何敏感信息，所以在数据策略下选择非个人数据。然后选择公共机器人选项并点击创建一个机器人。
所以这就是你在 Recast 平台创建的机器人。
![Figure 4: @joke 意图][6]
![Figure 5: 预定义表达][7]
**开发一个机器人的五个阶段**
用 Recast 官方博客的话说，在机器人的生命中有五个阶段。
* 训练——教授机器人需要理解的内容
* 构建——使用机器人构建工具创建你的对话流
* 编写代码——将机器人连接到外部 API 或数据库
* 连接——将机器人发布到一个或多个消息平台
* 监控——训练机器人让它更敏锐，并且了解其使用情况
**通过意图训练机器人**
你可以在仪表板上看到搜索、分叉或创建一个意图的选项。“意图是一系列含义相同但构造不同的表达。意图是你的机器人理解能力的核心。每个意图代表了机器人可以理解的一种想法。”（摘自 _Recast.AI_ 网站）
就像先前定的，你需要一个讲笑话的机器人。所以底线是这个机器人可以理解用户在要求它讲笑话，它不应该在用户仅仅说了“Hi”的情况下回复一个笑话——这可不妙。把用户可能说的话进行分组，比如：
```
Tell me a joke.（给我讲个笑话。）
Tell me a funny fact.（告诉我一个有趣的事实。）
Can you crack a joke?（你可以讲个笑话吗？）
What’s funny today?（今天有什么有趣的？）
```
…………………
在继续从头开始创建意图之前，让我们来看看搜索/分叉选项。在搜索框输入 _Joke_（图 3）。系统给出了全球的 Recast 用户创建的公开的意图清单，这就是为什么说 Recast 天然就是协作性质的。所以其实没有必要从头开始创建所有的意图，可以在已经创建的基础上进行构建。这就降低了训练具有常见意图的机器人所需的投入。
* 选择列表中的第一个意图并将其分叉到机器人上。
* 点击分叉（Fork）按钮。这个意图就添加到了机器人中（图 4）。
* 点击意图 @joke，会显示出这个意图中已经存在的表达列表（图 5）。
* 向其添加更多的表达（图 6）。
![图 6: 建议的表达][8]
![图 7: 建议的表达][9]
添加了一些表达之后，机器人会给出一些建议，像图 7 展示的那样。选择几个将它们添加到意图中（图 7）。你还可以根据机器人的上下文，标记你自己的自定义实体来检测关键词。
**技能**
技能是一块有明确目的的对话，机器人可以据此运行并达到目标。它可以像打招呼那么简单，也可以更复杂，比如基于用户提供的信息提供电影建议。
技能需要的不能只是一对问答，它需要多次交互。比如考虑一个帮你学习汇率的机器人。它一开始会问原货币，然后是目标货币，最后给出准确回应。结合技能可以创建复杂的对话流。
下面是如何给笑话机器人创建技能：
* 去到 _构建（Build）_ 页。点击 + 图标创建技能。
* 给技能命名 _Joke_（图 8）
* 创建之后，点击这个技能。你会看到四个标签。_Read me，Triggers（触发器），Requirements（需求）和 Actions（动作）。_
* 切换到 Requirements 页面。只有在笑话意图存在的时候，你才应该存储信息。所以，像图 9 那样添加一个 requirement（需求）。
![图 8: 技能面板][10]
![图 9: 添加一个触发器][11]
由于这个简单的使用范例，你不需要在需求选项卡中考虑任何特定的需求，但可以考虑只有当某些关键字或实体出现时才需要触发响应的情况——在这种情况下你需要“需求”。
需求是某个技能执行动作之前需要检索的意图或实体。需求是对话中机器人可以使用的重要信息。例如用户的姓名或位置。一旦一个需求完成，相关的值就会存储在机器人的内存中，供整个对话使用。
现在让我们转到动作页面设置回应（参见图 10）。
点击添加 _新消息组_。然后选择 _发送新消息_ 并添加一条文本消息，在这个例子中可以是任何笑话。当然，你肯定不想让你的机器人每次都说一样的笑话，你可以添加多条消息，每次从中随机选择一条。
![图 10: 添加动作][12]
![图 11: 添加文本消息][13]
![图 12: 设置网络聊天][14]
**频道集成**
一个成功的机器人还依赖于它的易得性。Recast 有不少的内置消息频道集成，如 Skype for Business、Kik Messenger、Telegram、Line、Facebook Messenger、Slack、Alexa 等等。除此之外，Recast 还提供了 SDK 用于开发自定义的频道。
此外，Recast 还提供一个可立即使用的网页聊天（在连接页面中）。你可以自定义颜色主题，标题，机器人头像等。它给你提供了一个可以添加到页面的脚本标签。你的界面现在就可以使用了（图 12）。
网页聊天的代码是开源的，开发者可以更方便地定制外观，标准回应类型等等。面板提供了如何将机器人部署到各种频道的逐步过程说明。这个笑话机器人部署在 Telegram 和网页聊天上，就像图 13 展示的那样。
![图 13: 网页聊天部署][15]
![图 14: Telegram 中开发的机器人][16]
![图 15: 多语言机器人][17]
**还有更多**
Recast 支持多语言，创建机器人的时候选择一个语言作为基础，但之后你有选项可以添加更多你想要的语言。
这里的例子是一个简单的静态笑话机器人，实际使用中可能需要更多的和不同系统的交互。Recast 有 Web 钩子功能，用户可以连接到不同的系统来获取回应。同时它还有详细的 API 文档来帮助使用平台的每个独立功能。
至于分析，Recast 有一个监控面板，帮助你了解机器人的准确度以及更加深入地训练机器人。
![Avatar][18]
[Athira Lekshmi C.V][19]
作者是一名开源爱好者。
[![][20]][21]
--------------------------------------------------------------------------------
via: https://opensourceforu.com/2019/11/creating-a-chat-bot-with-recast-ai/
作者：[Athira Lekshmi C.V][a]
选题：[lujun9972][b]
译者：[alim0x]](https://github.com/alim0x)
校对：[校对者ID](https://github.com/校对者ID)
本文由 [LCTT](https://github.com/LCTT/TranslateProject) 原创编译，[Linux中国](https://linux.cn/) 荣誉推出
[a]: https://opensourceforu.com/author/athira-lekshmi/
[b]: https://github.com/lujun9972
[1]: https://i0.wp.com/opensourceforu.com/wp-content/uploads/2019/04/Build-ChatBoat.jpg?resize=696%2C442&ssl=1 (Build ChatBoat)
[2]: https://i0.wp.com/opensourceforu.com/wp-content/uploads/2019/04/Build-ChatBoat.jpg?fit=900%2C572&ssl=1
[3]: https://i1.wp.com/opensourceforu.com/wp-content/uploads/2019/11/Figure-1-Setting-the-bot-properties.jpg
[4]: https://i1.wp.com/opensourceforu.com/wp-content/uploads/2019/11/Figure-2-Setting-the-bot-properties.jpg
[5]: https://i0.wp.com/opensourceforu.com/wp-content/uploads/2019/11/Figure-3-Searching-an-intent.jpg
[6]: https://i0.wp.com/opensourceforu.com/wp-content/uploads/2019/11/Figure-4-@joke-intent.jpg
[7]: https://i0.wp.com/opensourceforu.com/wp-content/uploads/2019/11/Figure-5-Predefined-expressions.jpg
[8]: https://i2.wp.com/opensourceforu.com/wp-content/uploads/2019/11/Figure-6-Suggested-expressions.jpg
[9]: https://i1.wp.com/opensourceforu.com/wp-content/uploads/2019/11/Figure-7-Suggested-expressions.jpg
[10]: https://i0.wp.com/opensourceforu.com/wp-content/uploads/2019/11/Figure-8-Skills-dashboard.jpg
[11]: https://i0.wp.com/opensourceforu.com/wp-content/uploads/2019/11/Figure-9-Adding-a-trigger.jpg
[12]: https://i0.wp.com/opensourceforu.com/wp-content/uploads/2019/11/Figure-10-Adding-actions.jpg
[13]: https://i1.wp.com/opensourceforu.com/wp-content/uploads/2019/11/Figure-11-Adding-text-messages.jpg
[14]: https://i2.wp.com/opensourceforu.com/wp-content/uploads/2019/11/Figure-12-Setting-up-webchat.jpg
[15]: https://i0.wp.com/opensourceforu.com/wp-content/uploads/2019/11/Figure-13-Webchat-deployed.jpg
[16]: https://i2.wp.com/opensourceforu.com/wp-content/uploads/2019/11/Figure-14-Bot-deployed-in-Telegram.jpg
[17]: https://i1.wp.com/opensourceforu.com/wp-content/uploads/2019/11/Figure-15-Multi-language-bot.jpg
[18]: https://secure.gravatar.com/avatar/d24503a2a0bb8bd9eefe502587d67323?s=100&r=g
[19]: https://opensourceforu.com/author/athira-lekshmi/
[20]: https://opensourceforu.com/wp-content/uploads/2019/11/assoc.png
[21]: https://feedburner.google.com/fb/a/mailverify?uri=LinuxForYou&loc=en_US