自然语言处理-聊天机器人

rule-based的玩法,

以及几个角度的升级。

首先,我们看一个

最基础版本的rule-base机器人

基本就是小学生级别的 问什么 答什么

In [11]:
import random

# 打招呼
greetings = ['hola', 'hello', 'hi', 'Hi', 'hey!','hey']
# 回复打招呼
random_greeting = random.choice(greetings)

# 对于“你怎么样?”这个问题的回复
question = ['How are you?','How are you doing?']
# “我很好”
responses = ['Okay',"I'm fine"]
# 随机选一个回
random_response = random.choice(responses)

# 机器人跑起来
while True:
    userInput = input(">>> ")
    if userInput in greetings:
        print(random_greeting)
    elif userInput in question:
        print(random_response)
    # 除非你说“拜拜”
    elif userInput == 'bye':
        break
    else:
        print("I did not understand what you said")
>>> hi
hey
>>> how are u
I did not understand what you said
>>> how are you
I did not understand what you said
>>> how are you?
I did not understand what you said
>>> How are you?
I'm fine
>>> bye

升级I:

显然 这样的rule太弱智了,我们需要更好一点的“精准对答”

比如

透过关键词来判断这句话的意图是什么(intents)

In [10]:
from nltk import word_tokenize
import random

# 打招呼
greetings = ['hola', 'hello', 'hi', 'Hi', 'hey!','hey']
# 回复打招呼
random_greeting = random.choice(greetings)

# 对于“假期”的话题关键词
question = ['break','holiday','vacation','weekend']
# 回复假期话题
responses = ['It was nice! I went to Paris',"Sadly, I just stayed at home"]
# 随机选一个回
random_response = random.choice(responses)



# 机器人跑起来
while True:
    userInput = input(">>> ")
    # 清理一下输入,看看都有哪些词
    cleaned_input = word_tokenize(userInput)
    # 这里,我们比较一下关键词,确定他属于哪个问题
    if  not set(cleaned_input).isdisjoint(greetings):
        print(random_greeting)
    elif not set(cleaned_input).isdisjoint(question):
        print(random_response)
    # 除非你说“拜拜”
    elif userInput == 'bye':
        break
    else:
        print("I did not understand what you said")
>>> hi
hey
>>> how was your holiday?
It was nice! I went to Paris
>>> wow, amazing!
I did not understand what you said
>>> bye

大家大概能发现,这依旧是文字层面的“精准对应”。

现在主流的研究方向,是做到语义层面的对应。

比如,“肚子好饿哦”, “饭点到了”

都应该表示的是要吃饭了的意思。

在这个层面,就需要用到word vector之类的embedding方法,

这部分内容 日后的课上会涉及到。

升级II:

光是会BB还是不行,得有知识体系!才能解决用户的问题。

我们可以用各种数据库,建立起一套体系,然后通过搜索的方式,来查找答案。

比如,最简单的就是Python自己的graph数据结构来搭建一个“地图”。

依据这个地图,我们可以清楚的找寻从一个地方到另一个地方的路径,

然后作为回答,反馈给用户。

In [17]:
# 建立一个基于目标行业的database
# 比如 这里我们用python自带的graph
graph = {'上海': ['苏州', '常州'],
         '苏州': ['常州', '镇江'],
         '常州': ['镇江'],
         '镇江': ['常州'],
         '盐城': ['南通'],
         '南通': ['常州']}

# 明确如何找到从A到B的路径
def find_path(start, end, path=[]):
    path = path + [start]
    if start == end:
        return path
    if start not in graph:
        return None
    for node in graph[start]:
        if node not in path:
            newpath = find_path(node, end, path)
            if newpath: return newpath
    return None
In [20]:
print(find_path('上海', "镇江"))
['上海', '苏州', '常州', '镇江']

同样的构建知识图谱的玩法,

也可以使用一些Logic Programming,比如上个世纪学AI的同学都会学的Prolog。

或者比如,python版本的prolog:PyKE。

他们可以构建一种复杂的逻辑网络,让你方便提取信息,

而不至于需要你亲手code所有的信息:

son_of(bruce, thomas, norma)
son_of(fred_a, thomas, norma)
son_of(tim, thomas, norma)
daughter_of(vicki, thomas, norma)
daughter_of(jill, thomas, norma)



升级III:

任何行业,都分个前端后端。

AI也不例外。

我们这里讲的算法,都是后端跑的。

那么, 为了做一个靠谱的前端,很多项目往往也需要一个简单易用,靠谱的前端。

比如,这里,利用Google的API,写一个类似钢铁侠Tony的语音小秘书Jarvis:

我们先来看一个最简单的说话版本。

利用gTTs(Google Text-to-Speech API), 把文本转化为音频。

In [4]:
from gtts import gTTS
import os
tts = gTTS(text='您好,我是您的私人助手,我叫小辣椒', lang='zh-tw')
tts.save("hello.mp3")
os.system("mpg321 hello.mp3")
Out[4]:
0

同理,

有了文本到语音的功能,

我们还可以运用Google API读出Jarvis的回复:

(注意:这里需要你的机器安装几个库 SpeechRecognition, PyAudio 和 PySpeech)

In [2]:
import speech_recognition as sr
from time import ctime
import time
import os
from gtts import gTTS
import sys
 
# 讲出来AI的话
def speak(audioString):
    print(audioString)
    tts = gTTS(text=audioString, lang='en')
    tts.save("audio.mp3")
    os.system("mpg321 audio.mp3")

# 录下来你讲的话
def recordAudio():
    # 用麦克风记录下你的话
    r = sr.Recognizer()
    with sr.Microphone() as source:
        audio = r.listen(source)
 
    # 用Google API转化音频
    data = ""
    try:
        data = r.recognize_google(audio)
        print("You said: " + data)
    except sr.UnknownValueError:
        print("Google Speech Recognition could not understand audio")
    except sr.RequestError as e:
        print("Could not request results from Google Speech Recognition service; {0}".format(e))
 
    return data

# 自带的对话技能(rules)
def jarvis():
    
    while True:
        
        data = recordAudio()

        if "how are you" in data:
            speak("I am fine")

        if "what time is it" in data:
            speak(ctime())

        if "where is" in data:
            data = data.split(" ")
            location = data[2]
            speak("Hold on Tony, I will show you where " + location + " is.")
            os.system("open -a Safari https://www.google.com/maps/place/" + location + "/&")

        if "bye" in data:
            speak("bye bye")
            break

# 初始化
time.sleep(2)
speak("Hi Tony, what can I do for you?")

# 跑起
jarvis()
Hi Tony, what can I do for you?
You said: how are you
I am fine
You said: what time is it now
Fri Apr  7 18:16:54 2017
You said: where is London
Hold on Tony, I will show you where London is.
You said: ok bye bye
bye bye

不仅仅是语音前端。

包括应用场景:微信,slack,Facebook Messager,等等 都可以把我们的ChatBot给integrate进去。

这部分内容也会在我们课程的后面阶段带给大家。

In [ ]:
 

没有更多推荐了,返回首页