使用Python实现深度学习模型：智能客户服务与支持

import nltk
from nltk.stem import WordNetLemmatizer
import json
import numpy as np
from sklearn.preprocessing import LabelEncoder

# 下载必要的NLTK数据包
nltk.download('punkt')
nltk.download('wordnet')

# 初始化词形还原器
lemmatizer = WordNetLemmatizer()

# 加载数据
with open('data/intents.json') as file:
    data = json.load(file)

# 提取词汇和类别
words = []
classes = []
documents = []
ignore_words = ['?', '!', '.', ',']

for intent in data['intents']:
    for pattern in intent['patterns']:
        # 分词
        word_list = nltk.word_tokenize(pattern)
        words.extend(word_list)
        documents.append((word_list, intent['tag']))
        if intent['tag'] not in classes:
            classes.append(intent['tag'])

# 词形还原并去重
words = [lemmatizer.lemmatize(w.lower()) for w in words if w not in ignore_words]
words = sorted(list(set(words)))

classes = sorted(list(set(classes)))

print(f"Classes: {classes}")
print(f"Words: {words}")

from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Dropout
from tensorflow.keras.optimizers import SGD

# 准备训练数据
training = []
output_empty = [0] * len(classes)

for doc in documents:
    bag = []
    word_patterns = doc[0]
    word_patterns = [lemmatizer.lemmatize(word.lower()) for word in word_patterns]
    for word in words:
        bag.append(1) if word in word_patterns else bag.append(0)
    
    output_row = list(output_empty)
    output_row[classes.index(doc[1])] = 1
    
    training.append([bag, output_row])

# 打乱数据并转换为数组
import random
random.shuffle(training)
training = np.array(training)

train_x = list(training[:, 0])
train_y = list(training[:, 1])

# 构建模型
model = Sequential()
model.add(Dense(128, input_shape=(len(train_x[0]),), activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(64, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(len(train_y[0]), activation='softmax'))

# 编译模型
sgd = SGD(learning_rate=0.01, decay=1e-6, momentum=0.9, nesterov=True)
model.compile(loss='categorical_crossentropy', optimizer=sgd, metrics=['accuracy'])

# 训练模型
hist = model.fit(np.array(train_x), np.array(train_y), epochs=200, batch_size=5, verbose=1)
model.save('chatbot_model.h5', hist)
print("模型训练完成并保存为 chatbot_model.h5")

import tkinter as tk
from tkinter import Text, Button

def chatbot_response(msg):
    # 预处理输入
    bag = [0]*len(words)
    s_words = nltk.word_tokenize(msg)
    s_words = [lemmatizer.lemmatize(word.lower()) for word in s_words]
    for s_word in s_words:
        for i, word in enumerate(words):
            if word == s_word:
                bag[i] = 1
    res = model.predict(np.array([bag]))[0]
    ERROR_THRESHOLD = 0.25
    results = [[i, r] for i, r in enumerate(res) if r > ERROR_THRESHOLD]
    results.sort(key=lambda x: x[1], reverse=True)
    return classes[results[0][0]]

# 创建简单的GUI
def send():
    msg = entry_box.get("1.0", 'end-1c').strip()
    entry_box.delete("0.0", tk.END)
    if msg != '':
        chat_log.config(state=tk.NORMAL)
        chat_log.insert(tk.END, "You: " + msg + '\n\n')
        chat_log.config(foreground="#442265", font=("Verdana", 12))
        
        res = chatbot_response(msg)
        chat_log.insert(tk.END, "Bot: " + res + '\n\n')
        chat_log.config(state=tk.DISABLED)
        chat_log.yview(tk.END)

base = tk.Tk()
base.title("Chatbot")
base.geometry("400x500")
base.resizable(width=tk.FALSE, height=tk.FALSE)

chat_log = Text(base, bd=0, bg="white", height="8", width="50", font="Arial",)
chat_log.config(state=tk.DISABLED)

scrollbar = tk.Scrollbar(base, command=chat_log.yview, cursor="heart")
chat_log['yscrollcommand'] = scrollbar.set

send_button = Button(base, font=("Verdana", 12, 'bold'), text="Send", width="12", height=5,
                    bd=0, bg="#32de97", activebackground="#3c9d9b", fg='#ffffff',
                    command=send)

entry_box = Text(base, bd=0, bg="white",width="29", height="5", font="Arial")

scrollbar.place(x=376,y=6, height=386)
chat_log.place(x=6,y=6, height=386, width=370)
entry_box.place(x=6, y=401, height=90, width=265)
send_button.place(x=275, y=401, height=90)

base.mainloop()