基于Python编写一个简易聊天机器人详解

import re
from nltk.tokenize import word_tokenize
from nltk.stem import WordNetLemmatizer
 
class TextPreprocessor:
    def __init__(self):
        self.lemmatizer = WordNetLemmatizer()
        self.stopwords = set(
            ["the", "a", "an", "is", "are", "in", "on", "at"]
        )
 
    def clean(self, text):
        # 1. 特殊字符处理
        text = re.sub(r'[^\w\s]', '', text)
        # 2. 统一小写
        text = text.lower()
        # 3. 词形还原
        tokens = word_tokenize(text)
        tokens = [self.lemmatizer.lemmatize(t) for t in tokens]
        # 4. 停用词过滤
        return [t for t in tokens if t not in self.stopwords]

class IntentRecognizer:
    def __init__(self):
        self.patterns = {
            "greet": ["hello", "hi", "hey"],
            "weather": ["weather", "temperature", "rain"],
            "farewell": ["bye", "goodbye", "see you"]
        }
 
    def classify(self, tokens):
        for intent, keywords in self.patterns.items():
            if any(kw in tokens for kw in keywords):
                return intent
        return "unknown"

class ResponseGenerator:
    def __init__(self):
        self.templates = {
            "greet": ["Hello!", "Hi there!"],
            "weather": [
                "Today's weather in {city} is {condition} with {temp}°C",
                "The forecast shows {condition} in {city}"
            ]
        }
 
    def generate(self, intent, entities=None):
        if intent in self.templates:
            template = random.choice(self.templates[intent])
            return template.format(**entities) if entities else random.choice(self.templates[intent])
        return "I didn't understand that."

from flask import Flask, request, jsonify
 
app = Flask(__name__)
preprocessor = TextPreprocessor()
recognizer = IntentRecognizer()
generator = ResponseGenerator()
 
@app.route('/chat', methods=['POST'])
def chat():
    data = request.json
    user_input = data.get('message', '')
    
    # 完整处理流程
    tokens = preprocessor.clean(user_input)
    intent = recognizer.classify(tokens)
    response = generator.generate(intent)
    
    return jsonify({'response': response})
 
if __name__ == '__main__':
    app.run(debug=True)

class DialogueManager:
    def __init__(self):
        self.context = []
    
    def update_context(self, message):
        if len(self.context) > 5:  # 限制对话历史长度
            self.context.pop(0)
        self.context.append(message)