单人数字人直播系统的选品与商业模式设计：基于公开数据的市场分析实践

import requests
import json
import time

def collect_topic_data(keywords: list, platform: str) -> dict:
    """
    模拟采集指定关键词在目标平台的话题数据
    实际部署时需根据各平台公开API或合规的采集方式实现
    """
    results = {}
    for keyword in keywords:
        # 模拟搜索热度采集
        # 实际场景中应使用各平台合规的公开数据获取方式
        data = {
            "keyword": keyword,
            "related_topics": [f"{keyword}相关话题{i}" for i in range(1, 6)],
            "discussion_volume": len(f"{keyword}相关话题") * 100  # 模拟值
        }
        results[keyword] = data
        time.sleep(0.5)  # 控制请求频率
    return results

# 示例关键词
keywords = ["劳动纠纷", "合同审核", "知识产权", "婚姻法律", "公司注册"]
platform = "抖音"
topic_data = collect_topic_data(keywords, platform)

def collect_competitor_info(accounts: list) -> list:
    """采集竞品账号的公开信息"""
    results = []
    for account in accounts:
        info = {
            "name": account,
            "category": "",  # 内容分类
            "post_frequency": 0,  # 发布频率
            "avg_likes": 0,  # 平均点赞
            "avg_comments": 0,  # 平均评论
            "monetization": [],  # 变现方式
            "products": []  # 主要产品方向
        }
        # 实际场景中需通过平台合规方式获取数据
        results.append(info)
    return results

import re
from collections import Counter

class UserQuestionAnalyzer:
    def __init__(self, category_keywords: dict):
        """
        category_keywords: 各分类的关键词映射
        示例: {'劳动纠纷': ['裁员', '降薪', '加班', '赔偿']}
        """
        self.category_keywords = category_keywords

    def classify_question(self, question: str) -> str:
        """将用户问题归类到对应品类"""
        for category, keywords in self.category_keywords.items():
            for kw in keywords:
                if kw in question:
                    return category
        return "未分类"

    def get_priority_list(self, questions: list) -> list:
        """生成需求优先级列表"""
        classified = [self.classify_question(q) for q in questions]
        counter = Counter(classified)
        # 按出现频次排序
        priority_list = sorted(
            [(k, v / len(questions) * 100) for k, v in counter.items()],
            key=lambda x: x[1],
            reverse=True
        )
        return priority_list

# 示例数据
category_keywords = {
    "劳动纠纷": ["裁员", "降薪", "加班", "劳动合同", "赔偿"],
    "合同纠纷": ["违约", "定金", "欠款", "合同解除"],
    "知识产权": ["商标", "专利", "著作权", "侵权"]
}

analyzer = UserQuestionAnalyzer(category_keywords)
sample_questions = ["被裁员怎么赔偿", "公司单方面降薪合法吗", "商标被抢注怎么办"]
priority = analyzer.get_priority_list(sample_questions)

def evaluate_product_direction(direction: dict) -> float:
    """计算产品方向的综合评分"""
    dimensions = {
        "需求规模": 0.25,
        "竞争强度": 0.20,
        "内容可生产性": 0.20,
        "资源匹配度": 0.20,
        "盈利潜力": 0.15
    }

    score = 0
    for dim, weight in dimensions.items():
        score += direction.get(dim, 3) * weight

    return score

# 示例
direction = {
    "名称": "劳动纠纷法律科普",
    "需求规模": 4,
    "竞争强度": 3,
    "内容可生产性": 5,
    "资源匹配度": 3,
    "盈利潜力": 3
}
print(f"综合评分：{evaluate_product_direction(direction):.1f}/5.0")