实现自学习系统，输入excel文件，能学习后进行相应回答

import pandas as pd
from sklearn.metrics.pairwise import cosine_similarity
from sentence_transformers import SentenceTransformer

'''
效果理想
'''

class SelfLearningQASystem:
    def __init__(self, excel_path):
        # 读取Excel文件
        self.df = pd.read_excel(excel_path)
        # 假定有 'question' 和 'answer' 两列
        self.questions = self.df['question'].astype(str).tolist()
        self.answers = self.df['answer'].astype(str).tolist()

        # 使用预训练的多语言句子嵌入模型
        self.model = SentenceTransformer(r'D:\modelproject\paraphrase-multilingual-MiniLM-L12-v2')
        # 将所有问题向量化
        self.question_vectors = self.model.encode(self.questions)

    def ask(self, user_question):
        # 将用户问题向量化
        user_vector = self.model.encode(user_question)

        # 确保向量是二维的
        if len(user_vector.shape) == 1:
            user_vector = user_vector.reshape(1, -1)

        # 如果question_vectors是一维的，转换为二维
        question_vectors = self.question_vectors
        if len(question_vectors.shape) == 1:
            question_vectors = question_vectors.reshape(1, -1)

        # 计算用户问题与所有已有问题的相似度
        similarities = cosine_similarity(user_vector, question_vectors)
        # print(similarities)
        # 找出最相似的问题的索引
        most_similar_idx = similarities.argmax()
        # print(most_similar_idx)
        max_similarity = similarities[0, most_similar_idx]
        print("问题相似度",max_similarity)
        # 可选择设置一个阈值，低于则认为没有匹配到
        threshold = 0.5  # 可调，根据实际情况调整
        if max_similarity < threshold:
            return "抱歉，我暂时无法回答这个问题。您可以更新我的知识库。"

        # 返回最相似问题对应的答案
        return self.answers[most_similar_idx]


    def add_qa_pair(self, new_question, new_answer, excel_path=None):
        # 自学习追加
        # 追加到内存
        self.questions.append(new_question)
        self.answers.append(new_answer)
        # 重新训练向量化
        self.question_vectors = self.model.encode(self.questions)
        # 可选：将新数据写入 Excel
        if excel_path:
            new_data = pd.DataFrame({
                'question': [new_question],
                'answer': [new_answer]
            })
            try:
                existing = pd.read_excel(excel_path)
                updated = pd.concat([existing, new_data], ignore_index=True)
                updated.to_excel(excel_path, index=False)
            except FileNotFoundError:
                new_data.to_excel(excel_path, index=False)


if __name__ == "__main__":
    # 初始化问答系统，传入你的Excel路径
    inputfile = "input.xlsx"
    qa_system = SelfLearningQASystem(inputfile)
    qa_system.add_qa_pair("今天周几","星期三",inputfile)
    print("=== 欢迎使用自学习问答系统，输入 '退出' 结束对话 ===")
    while True:
        user_input = input("\n你：")
        if user_input.strip() in ['退出', 'exit', 'quit']:
            print("系统：再见！")
            break
        answer = qa_system.ask(user_input)
        print(f"系统：{answer}")