使用 Python 构建聊天机器人

2020-04-13 08:00:00 · 飞浪

介绍对话式NLP或自然语言处理通过聊天机器人在文本分析中发挥着重要作用。聊天机器人是一种基于人工智能的工具，旨在用人类的母语与他们交谈。这些聊天机器人在各个行业都很受欢迎，被认为是自然

介绍

对话式NLP或自然语言处理通过聊天机器人在文本分析中发挥着重要作用。聊天机器人是一种基于人工智能的工具，旨在用人类的母语与他们交谈。这些聊天机器人在各个行业都很受欢迎，被认为是自然语言处理最有用的应用之一。

在本指南中，您将学习使用 Python 构建您的第一个聊天机器人。

基线库

您将在本指南中使用nltk库。NLTK 代表自然语言工具包，是处理文本数据的领先 Python 库。下面的第一行代码导入了该库，而第二行使用nltk.chat模块导入所需的实用程序。

      import nltk
from nltk.chat.util import Chat, reflections
    

下面的代码显示实用程序Chat是一个提供构建聊天机器人逻辑的类。

      print(Chat)

输出：

      <class 'nltk.chat.util.Chat'>

您上面导入的另一个文件是Reflections，它是包含一组输入文本及其对应输出值的字典。您可以使用下面的代码检查该字典。这是一个可选字典，您可以按照与下面相同的格式创建自己的字典。

      reflections

输出：

      {'i am': 'you are',
     'i was': 'you were',
     'i': 'you',
     "i'm": 'you are',
     "i'd": 'you would',
     "i've": 'you have',
     "i'll": 'you will',
     'my': 'your',
     'you are': 'I am',
     'you were': 'I was',
     "you've": 'I have',
     "you'll": 'I will',
     'your': 'my',
     'yours': 'mine',
     'you': 'me',
     'me': 'you'}
    

构建聊天机器人

第一步是创建用于训练聊天机器人的规则。下面的代码行创建了一组简单的规则。列表的第一个元素是用户输入，而第二个元素是来自机器人的响应。在 set_pairs 对象中创建了几个这样的列表。

      set_pairs = [
    [
        r"my name is (.*)",
        ["Hello %1, How are you doing today ?",]
    ],
    [
        r"hi|hey|hello",
        ["Hello", "Hey there",]
    ], 
    [
        r"what is your name?",
        ["You can call me a chatbot ?",]
    ],
    [
        r"how are you ?",
        ["I am fine, thank you! How can i help you?",]
    ],
    [
        r"I am fine, thank you",
        ["great to hear that, how can i help you?",]
    ],
    [
        r"how can i help you? ",
        ["i am looking for online guides and courses to learn data science, can you suggest?", "i am looking for data science training platforms",]
    ],
    [
        r"i'm (.*) doing good",
        ["That's great to hear","How can i help you?:)",]
    ],
    [
        r"i am looking for online guides and courses to learn data science, can you suggest?",
        ["Pluralsight is a great option to learn data science. You can check their website",]
    ],
    [
        r"thanks for the suggestion. do they have great authors and instructors?",
        ["Yes, they have the world class best authors, that is their strength;)",]
    ],
    [
        r"(.*) thank you so much, that was helpful",
        ["Iam happy to help", "No problem, you're welcome",]
    ],
    [
        r"quit",
    ["Bye, take care. See you soon :) ","It was nice talking to you. See you soon :)"]
],
]
    

创建上述规则对后，我们使用以下代码定义聊天机器人。代码很简单，每次调用函数时都会打印一条消息。

      def chatbot():
        print("Hi, I'm the chatbot you built") 

chatbot()
    

输出：

      Hi, I'm the chatbot you built

下一步是实例化包含对和反射的Chat()函数。

      chat = Chat(set_pairs, reflections)
print(chat)
    

输出：

      <nltk.chat.util.Chat object at 0x7f49c76e3be0>

您已经创建了一个简单的基于规则的聊天机器人，最后一步是发起对话。这是使用下面的代码完成的，其中 converse ()函数触发对话。

      chat.converse()
if __name__ == "__main__":
    chatbot()
    

上面的代码将在您的笔记本中生成以下聊天框，如下图所示。

输出：

您已准备好与聊天机器人进行交互。首先在框中输入简单的问候语“hi”，然后您将收到来自机器人的响应“Hello”，如下图所示。

输出：

您可以继续与聊天机器人交谈，交谈结束后退出对话，如下图所示。

输出：

结论

在本指南中，您学习了如何使用 Python 创建一个简单的聊天机器人。您使用简单的规则和强大的nltk库来构建聊天机器人。可以添加更复杂的规则来进一步增强聊天机器人。

要了解有关文本分析和自然语言处理的更多信息，请参阅以下指南。

要了解有关使用 Python 进行数据科学的更多信息，请参阅以下指南。

_{免责声明：本内容来源于第三方作者授权、网友推荐或互联网整理，旨在为广大用户提供学习与参考之用。所有文本和图片版权归原创网站或作者本人所有，其观点并不代表本站立场。如有任何版权侵犯或转载不当之情况，请与我们取得联系，我们将尽快进行相关处理与修改。感谢您的理解与支持！}

_查看原文

python

技术指南

阅读全文

使用 Python 构建聊天机器人

杭州电子商务研究院

4年前 · 面向社会、服务行业、政产学研结合、整合资源、和谐发展

{'i am': 'you are', 'i was': 'you were', 'i': 'you', "i'm": 'you are', "i'd": 'you would', "i've": 'you have', "i'll": 'you will', 'my': 'your', 'you are': 'I am', 'you were': 'I was', "you've": 'I have', "you'll": 'I will', 'your': 'my', 'yours': 'mine', 'you': 'me', 'me': 'you'}

set_pairs = [ [ r"my name is (.*)", ["Hello %1, How are you doing today ?",] ], [ r"hi|hey|hello", ["Hello", "Hey there",] ], [ r"what is your name?", ["You can call me a chatbot ?",] ], [ r"how are you ?", ["I am fine, thank you! How can i help you?",] ], [ r"I am fine, thank you", ["great to hear that, how can i help you?",] ], [ r"how can i help you? ", ["i am looking for online guides and courses to learn data science, can you suggest?", "i am looking for data science training platforms",] ], [ r"i'm (.*) doing good", ["That's great to hear","How can i help you?:)",] ], [ r"i am looking for online guides and courses to learn data science, can you suggest?", ["Pluralsight is a great option to learn data science. You can check their website",] ], [ r"thanks for the suggestion. do they have great authors and instructors?", ["Yes, they have the world class best authors, that is their strength;)",] ], [ r"(.*) thank you so much, that was helpful", ["Iam happy to help", "No problem, you're welcome",] ], [ r"quit", ["Bye, take care. See you soon :) ","It was nice talking to you. See you soon :)"] ], ]