销售三步法构建知识树的例子

具体代码如下：

import networkx as nx
import matplotlib.pyplot as plt
from matplotlib.font_manager import FontProperties
import requests
from py2neo import Graph, Node, Relationship
from datetime import datetime

# 设置字体路径
font_path = "/System/Library/Fonts/STHeiti Light.ttc"  # macOS系统自带的黑体字体路径
font_prop = FontProperties(fname=font_path)

# 打印带时间戳的日志
def print_with_timestamp(message):
    timestamp = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
    print(f"[{timestamp}] {message}")

# 可视化知识树
def visualize_tree(tree):
    pos = nx.spring_layout(tree, k=0.5, iterations=20)  # 节点布局
    nx.draw(tree, pos, with_labels=True, node_size=500, node_color="skyblue", font_size=8, font_weight='bold', font_family=font_prop.get_name())
    plt.title("销售三步法知识树", fontproperties=font_prop)
    plt.axis('off')  # 关闭坐标轴
    plt.show()

# 构建销售三步法知识树
def build_sales_knowledge_tree():
    print_with_timestamp("正在构建初始知识树...")
    tree = nx.DiGraph()
    
    # 树干（核心理念）
    core_idea = "销售三步法"
    tree.add_node(core_idea)
    
    # 树枝（方法论）
    methods = [
        "了解客户需求",
        "提供解决方案",
        "促成交易"
    ]
    for method in methods:
        tree.add_node(method)
        tree.add_edge(core_idea, method)
        print_with_timestamp(f"已添加方法论节点：{method}")
    
    # 树叶（具体案例、技巧）
    details = {
        "了解客户需求": [
            ("如何了解客户的需求？", "通过开放式问题引导客户表达需求。"),
            ("如何建立信任关系？", "展示专业知识和成功案例。")
        ],
        "提供解决方案": [
            ("如何根据客户需求提供解决方案？", "定制化方案，突出产品优势。"),
            ("如何处理客户异议？", "倾听并提供合理解释。")
        ],
        "促成交易": [
            ("如何促成交易？", "强调产品价值和紧迫性。"),
            ("如何跟进潜在客户？", "定期沟通，提供支持。")
        ]
    }
    
    for method, qa_pairs in details.items():
        for q, a in qa_pairs:
            tree.add_node(q)
            tree.add_node(a)
            tree.add_edge(method, q)
            tree.add_edge(q, a)
            print_with_timestamp(f"已添加问题及其回答到知识树：\nQ: {q}\nA: {a}")
    
    print_with_timestamp("初始知识树构建完成。")
    return tree, details

# 使用大模型生成补充问题并自动生成答案
def generate_supplement_questions_with_llm(details):
    print_with_timestamp("正在生成补充问题及其回答...")
    prompt = "基于以下销售三步法的知识树内容，生成一些补充问题，并提供完整的回答。\n"
    for method, qa_pairs in details.items():
        prompt += f"\n{method}：\n"
        for q, a in qa_pairs:
            prompt += f"Q: {q}\nA: {a}\n"
    prompt += """
    请按照以下格式生成补充问题及其回答：
    Q: [具体问题]
    A: [详细回答]
    """
    
    data = {
        "model": "qwen2.5:14b",
        "prompt": prompt,
        "stream": False,
        "temperature": 0.7,
        "max_tokens": 400
    }
    try:
        response = requests.post("http://127.0.0.1:11434/api/generate", json=data)
        if response.status_code == 200:
            response_text = response.json().get("response", "").strip()
            print_with_timestamp("大模型生成的内容：")
            print(response_text)
            # 解析生成的问题和答案
            qa_pairs = []
            lines = response_text.split("\n")
            i = 0
            while i < len(lines):
                if lines[i].startswith("Q: ") and i + 1 < len(lines) and lines[i + 1].startswith("A: "):
                    question = lines[i].replace("Q: ", "").strip()
                    answer = lines[i + 1].replace("A: ", "").strip()