锦中人工智能助手

def simple_chatbot():

print("欢迎使用咸阳职业技术学院智能客服！")

while True:

user_input = input("请输入您的问题（输入'退出'结束）: ")

if user_input.lower() == '退出':

print("感谢使用，再见！")

break

elif "课程" in user_input:

print("您可以访问教务处网站查询课程安排。")

elif "成绩" in user_input:

print("请登录教务系统查看成绩。")

elif "图书馆" in user_input:

print("图书馆开放时间为每天8:00-22:00。")

elif "食堂" in user_input:

print("学校有三个食堂，分别是东区、西区和南区。")

else:

print("抱歉，我暂时无法回答这个问题，请联系人工客服。")

simple_chatbot()

from transformers import AutoTokenizer, AutoModelForSequenceClassification

import torch

# 加载预训练模型和分词器

model_name = "bert-base-uncased"

tokenizer = AutoTokenizer.from_pretrained(model_name)

model = AutoModelForSequenceClassification.from_pretrained(model_name)

# 示例数据

texts = [

"我的成绩什么时候出来？",

"怎么选课？",

"图书馆开放时间？",

"食堂几点开门？",

"我要请假怎么办？"

]

labels = [1, 0, 2, 3, 4] # 假设这些是不同的意图类别

# 编码输入

inputs = tokenizer(texts, padding=True, truncation=True, return_tensors="pt")

# 模型预测

with torch.no_grad():

outputs = model(**inputs)

predictions = torch.softmax(outputs.logits, dim=1)

# 输出预测结果

for i, text in enumerate(texts):

predicted_label = predictions[i].argmax().item()

print(f"问题: {text} -> 预测意图: {predicted_label}")

# 根据意图返回相应的回答

if predicted_label == 0:

print("回答: 课程安排请查看教务系统。")

elif predicted_label == 1:

print("回答: 选课流程请参考教务处通知。")

elif predicted_label == 2:

print("回答: 图书馆开放时间是每天8:00-22:00。")

elif predicted_label == 3:

print("回答: 食堂营业时间根据区域有所不同。")

elif predicted_label == 4:

print("回答: 请假需向辅导员提交申请。")

print("-" * 50)

from flask import Flask, request, jsonify

from transformers import AutoTokenizer, AutoModelForSequenceClassification

import torch

app = Flask(__name__)

# 加载模型和分词器

model_name = "bert-base-uncased"

tokenizer = AutoTokenizer.from_pretrained(model_name)

model = AutoModelForSequenceClassification.from_pretrained(model_name)

@app.route('/chat', methods=['POST'])

def chat():

data = request.json

user_input = data.get('input', '')

# 对用户输入进行编码

inputs = tokenizer(user_input, return_tensors="pt")

# 进行预测

with torch.no_grad():

outputs = model(**inputs)

predictions = torch.softmax(outputs.logits, dim=1)

predicted_label = predictions.argmax().item()

# 返回对应的回答

if predicted_label == 0:

response = "课程安排请查看教务系统。"

elif predicted_label == 1:

response = "选课流程请参考教务处通知。"

elif predicted_label == 2:

response = "图书馆开放时间是每天8:00-22:00。"

elif predicted_label == 3:

response = "食堂营业时间根据区域有所不同。"

elif predicted_label == 4:

response = "请假需向辅导员提交申请。"

else:

response = "抱歉，我暂时无法回答这个问题，请联系人工客服。"

return jsonify({"response": response})

if __name__ == '__main__':

app.run(host='0.0.0.0', port=5000)

from transformers import pipeline

# 创建情感分析管道

sentiment_pipeline = pipeline("sentiment-analysis", model="distilbert-base-uncased-finetuned-sst-2-english")

# 测试情感分析

text = "我对学校的食堂非常满意。"

result = sentiment_pipeline(text)[0]

print(f"文本: {text}")

print(f"情感: {result['label']}，置信度: {result['score']:.2f}")