diff --git a/platform/backend/app/initial_data.py b/platform/backend/app/initial_data.py index 1fdc2a8..a5dcb48 100644 --- a/platform/backend/app/initial_data.py +++ b/platform/backend/app/initial_data.py @@ -105,7 +105,7 @@ def import_initial_data(): "default_format": "深度分析 3000-8000字，数据驱动", "compliance_rules": { "max_title_len": 100, - "allowed_tags": ["科技", "生活", "职场", "教育", "可持续", "AI", "远程工作", "个人成长"], + "allowed_tags": ["科技", "AI", "效率", "职场", "教育", "远程工作", "未来工作", "工具"], "forbidden_patterns": ["加微信", "私聊", "付费咨询", "点击领取"] }, "is_active": True, @@ -124,7 +124,7 @@ def import_initial_data(): "default_format": "个人叙事 2000-4000字，对话感", "compliance_rules": { "max_title_len": 32, - "allowed_tags": ["科技", "生活", "职场", "教育", "可持续", "AI", "远程工作", "个人成长"], + "allowed_tags": ["科技", "AI", "效率", "职场", "教育", "远程工作", "未来工作", "工具"], "forbidden_patterns": ["诱导分享", "朋友圈", "转发群"] }, "is_active": True, @@ -143,7 +143,7 @@ def import_initial_data(): "default_format": "精炼干货 400-1000字，实用优先", "compliance_rules": { "max_title_len": 50, - "allowed_tags": ["生活方式", "可持续", "AI", "个人成长", "极简", "环保"], + "allowed_tags": ["AI", "效率", "科技", "工具", "职场", "生活", "学习方法"], "forbidden_patterns": ["私信", "加群", "导流"] }, "is_active": True, @@ -163,9 +163,9 @@ def import_initial_data(): else: # 更新已有平台配置的字数要求（迁移：2026-06 内容质量升级） platform_updates = { - "zhihu": {"min_words": 3000, "max_words": 8000, "default_format": "深度分析 3000-8000字，数据驱动"}, - "wechat": {"min_words": 2000, "max_words": 4000, "default_format": "个人叙事 2000-4000字，对话感"}, - "xiaohongshu": {"min_words": 400, "max_words": 1000, "default_format": "精炼干货 400-1000字，实用优先"}, + "zhihu": {"min_words": 3000, "max_words": 8000, "default_format": "深度分析 3000-8000字，数据驱动+观点交锋，用一手数据和独特视角切入"}, + "wechat": {"min_words": 2000, "max_words": 4000, "default_format": "科技人文叙事 2000-4000字，个人反思+情感共鸣，记录人与技术之间的故事"}, + "xiaohongshu": {"min_words": 400, "max_words": 1000, "default_format": "精炼干货 400-1000字，亲测数据+实操结果，每个结论配真实对比"}, } for p in db.query(PlatformConfig).all(): if p.platform in platform_updates: @@ -178,41 +178,36 @@ def import_initial_data(): if db.query(TopicField).count() == 0: fields = [ - {"name": "未来工作方式", "icon": "💼", "color": "#667eea", "description": "远程工作、零工经济、职业转型", "sort_order": 1}, - {"name": "AI与效率", "icon": "🤖", "color": "#764ba2", "description": "AI工具、数字助手、效率方法", "sort_order": 2}, - {"name": "可持续生活", "icon": "🌿", "color": "#67c23a", "description": "环保、低碳、自然生活方式", "sort_order": 3}, - {"name": "数字游民", "icon": "🌍", "color": "#409eff", "description": "旅行、地理自由、海外生活", "sort_order": 4}, - {"name": "个人成长", "icon": "📚", "color": "#e6a23c", "description": "学习、技能、认知升级", "sort_order": 5}, - {"name": "科技人文", "icon": "🔬", "color": "#f56c6c", "description": "科技伦理、数字生活反思", "sort_order": 6}, + {"name": "AI与效率", "icon": "🤖", "color": "#764ba2", "description": "AI工具实测对比、工作流效率方法、前沿资讯解读——关注技术如何改变人的工作方式", "sort_order": 1}, + {"name": "科技人文", "icon": "🔬", "color": "#f56c6c", "description": "AI伦理困境、数字生活反思、人机关系探索——科技的温度与边界", "sort_order": 2}, + {"name": "未来工作方式", "icon": "💼", "color": "#667eea", "description": "远程协作实践、AI时代职业转型、一人企业模式——未来不是等来的", "sort_order": 3}, ] for f in fields: db.add(TopicField(**f)) db.commit() - print("✅ 插入默认领域配置") + print("✅ 插入默认领域配置（聚焦AI×人文×未来工作）") if db.query(CollectorCategory).count() == 0: default_cats = [ - {"name": "循环消费", "search_query": "以旧换新 二手交易 闲置 循环 2026", "description": "以旧换新/二手交易/租赁经济 | 2025年二手交易额1.69万亿", "sort_order": 1, "is_active": True}, - {"name": "低碳出行", "search_query": "新能源车 骑行 绿色通勤 低碳出行 2026", "description": "新能源车/骑行/绿色出行 | 年产销破1000万辆", "sort_order": 2, "is_active": True}, - {"name": "干净饮食", "search_query": "干净饮食 有机食品 植物基 本地食材 2026", "description": "有机食品/植物基/本地食材 | 有机食品1247亿", "sort_order": 3, "is_active": True}, - {"name": "零浪费生活", "search_query": "零浪费 自带杯 极简生活 可持续时尚 2026", "description": "自带杯/极简/可持续时尚 | 自带杯笔记277万篇", "sort_order": 4, "is_active": True}, - {"name": "绿色家电与节能", "search_query": "绿色家电 一级能效 以旧换新 节能 2026", "description": "一级能效/国补政策 | 一级能效占比90%+", "sort_order": 5, "is_active": True}, - {"name": "碳普惠", "search_query": "碳账户 碳普惠 个人碳减排 蚂蚁森林 2026", "description": "碳账户/碳普惠/个人减排 | 武汉200万碳账户", "sort_order": 6, "is_active": True}, - {"name": "环保科技产品", "search_query": "环保科技 绿色产品 可持续材料 2026", "description": "可持续材料/绿色产品 | 购买占比超32%", "sort_order": 7, "is_active": True}, - {"name": "AI与效率", "search_query": "AI工具 人工智能 效率提升 2026", "description": "AI工具/效率方法/数字助手 | 2026年AI深度融入消费与生活", "sort_order": 8, "is_active": True}, + {"name": "AI前沿资讯", "search_query": "AI 人工智能 大模型 2026 前沿 突破 论文解读", "description": "AI行业动态、大模型发布、技术突破 | 2026年AI全面嵌入产业", "sort_order": 1, "is_active": True}, + {"name": "AI工具实测", "search_query": "AI工具 效率提升 工作流 prompt教程 Cursor Copilot 2026", "description": "AI工具评测、效率工作流、实操指南 | 2026年AI工具爆发", "sort_order": 2, "is_active": True}, + {"name": "AI与职场", "search_query": "AI 裁员 职业转型 AI技能 远程工作 一人企业 2026", "description": "AI对就业影响、职业转型、技能升级 | 2026年AI重塑就业结构", "sort_order": 3, "is_active": True}, + {"name": "AI生活化", "search_query": "AI陪伴 AI心理咨询 生活助手 AI写作 智能体 2026", "description": "AI心理咨询/生活搭子/AI人格化 | 商业笔记互动增长263%", "sort_order": 4, "is_active": True}, + {"name": "科技人文", "search_query": "AI伦理 数字生活 科技反思 人机关系 数据隐私 2026", "description": "AI伦理/数字生活反思/科技温度 | AI从工具到共生", "sort_order": 5, "is_active": True}, ] for cd in default_cats: existing = db.query(CollectorCategory).filter(CollectorCategory.name == cd["name"]).first() if not existing: db.add(CollectorCategory(**cd)) db.commit() - print("✅ 插入默认采集类别和信息源") + print("✅ 插入默认采集类别（聚焦AI×科技人文）") db.commit() - # 补充缺失的类别和信息源（对已有数据库的迁移） + # 补充缺失的采集源（对已有数据库的迁移） for sd in [ - {"name": "AI工具搜索", "source_type": "web_search", "query": "AI工具 人工智能 效率提升 2026", "credibility": "medium", "focus": "AI与效率", "sort_order": 99, "is_active": True}, + {"name": "AI前沿搜索", "source_type": "web_search", "query": "AI 人工智能 大模型 前沿 2026", "credibility": "medium", "focus": "AI前沿资讯", "sort_order": 1, "is_active": True}, + {"name": "AI工具搜索", "source_type": "web_search", "query": "AI工具 效率提升 AI工作流 2026", "credibility": "medium", "focus": "AI工具实测", "sort_order": 2, "is_active": True}, ]: if not db.query(CollectorSource).filter(CollectorSource.name == sd["name"]).first(): db.add(CollectorSource(**sd)) diff --git a/scripts/collector.py b/scripts/collector.py index 9b1e651..f75aa84 100644 --- a/scripts/collector.py +++ b/scripts/collector.py @@ -1,7 +1,7 @@ #!/usr/bin/env python3 """ -内容采集：趋势抓取 → 选题生成 → 存入选题库 -收集热点趋势信息，经LLM分析后生成选题建议并存入数据库 +内容采集管道：趋势抓取 → 分析 → 选题生成 → 存入选题库 +聚焦AI与科技人文领域，从RSS搜索和Web搜索采集信息，经LLM分析后生成选题 """ import os @@ -42,14 +42,11 @@ logging.basicConfig( ) logger = logging.getLogger(__name__) DEFAULT_CHINA_PAINS = { - "循环消费": "以旧换新流程繁琐、二手商品信任缺失、租赁市场不规范", - "低碳出行": "新能源车充电设施不足、城市规划不支持骑行、通勤距离长", - "干净饮食": "有机食品价格高、真伪难辨、外卖为主的生活方式难以改变", - "零浪费生活": "环保产品溢价高、可持续选择不便、漂绿营销难以分辨", - "绿色家电与节能": "绿色家电初期投入高、节能效果难量化、老旧小区改造难", - "碳普惠": "碳账户普及率低、减排量兑换吸引力不足、公众认知有限", - "环保科技产品": "绿色产品溢价68%难以承受、缺乏统一认证标准、担心漂绿", - "AI与效率": "AI工具选择困难、数据隐私担忧、学习成本高、实际效果难验证" + "AI工具实测": "AI工具选择困难、免费版功能太受限、ChatGPT不如国产好用、学习曲线陡峭、不知道哪些AI工具真正值得付费、看了测评还是不知道怎么用", + "AI前沿资讯": "AI更新太快跟不上、论文太多看不完、不知道哪些是真突破、被营销号带偏、每天刷AI新闻但感觉什么都没学到", + "未来工作方式": "AI裁员焦虑加剧、远程协作效率打折、职业方向看不清、技能更新压力大、35岁学AI来得及吗、转行AI需要什么技能", + "科技人文反思": "AI伦理边界模糊、数据隐私被侵蚀、数字依赖越来越重、人机关系困惑、孩子该不该用AI写作业、AI生成的内容能信吗", + "AI职场应用": "AI替代担心、岗位技能要求变了、职场竞争加剧、缺乏AI实操指导、怎么用AI写周报、怎么用AI做数据分析、AI提示词怎么写才有效", } _cached_china_pains = None @@ -87,22 +84,22 @@ def _get_china_pain(category: str) -> str: @dataclass class SustainabilitySource: - """可持续性信息源""" + """内容采集源""" name: str type: str # rss, web_search, web, api, local url: Optional[str] = None # RSS URL 或通用链接 update_frequency: str = "daily" credibility: str = "medium" - focus: str = "可持续性" + focus: str = "AI与科技" keywords: Optional[List[str]] = None # 源特定关键词 query: Optional[str] = None # 搜索查询词(w eb_search类型用) @dataclass class SustainabilityCase: - """可持续性案例""" + """内容案例""" id: str country: str - category: str # 子领域:零浪费生活、循环消费等 + category: str # 类别:AI前沿资讯、AI工具实测等 title: str core_idea: str data_facts: str @@ -118,7 +115,7 @@ class SustainabilityCase: @dataclass class SustainabilityTopic: - """可持续性选题""" + """AI与科技选题""" id: str title: str cases: List[str] # 关联的案例ID列表 @@ -128,7 +125,7 @@ class SustainabilityTopic: mvp_actions: str estimated_length: int priority_score: float - field: str = "可持续生活系统" # 内容领域 + field: str = "AI与效率" # 内容领域 format: str = "趋势洞察 + 实操指南" # 内容形式 core_concept: str = "" # 核心理念 audience_pain: str = "" # 受众痛点 @@ -150,7 +147,7 @@ class SustainabilityTopic: self.platform_urls = {} class SustainabilityCollector: - """可持续性内容收集器""" + """AI与科技内容采集器""" def __init__(self): self.load_config() @@ -191,7 +188,7 @@ class SustainabilityCollector: url=s.url or '', query=s.query or '', credibility=s.credibility or 'medium', - focus=s.focus or '可持续性', + focus=s.focus or 'AI与科技', )) logger.info(f"从DB加载 {len(cats)} 个类别, {len(self.sources)} 个信息源") db.close() @@ -209,7 +206,7 @@ class SustainabilityCollector: if 'base_url' in source_info and 'url' not in source_info: source_info['url'] = source_info.pop('base_url') source_info.setdefault('update_frequency', 'daily') - source_info.setdefault('focus', '可持续性') + source_info.setdefault('focus', 'AI与科技') source_info.setdefault('keywords', None) allowed_keys = {'name', 'type', 'url', 'update_frequency', 'credibility', 'focus', 'keywords', 'query'} filtered_info = {k: v for k, v in source_info.items() if k in allowed_keys} @@ -379,7 +376,7 @@ class SustainabilityCollector: 'source_name': source.name }) - logger.info(f"从 {source.name} 获取到 {len(articles)} 篇可持续性文章") + logger.info(f"从 {source.name} 获取到 {len(articles)} 篇文章") return articles except Exception as e: @@ -720,8 +717,16 @@ class SustainabilityCollector: return topic def map_category_to_field(self, category: str) -> str: - """将案例类别映射到内容领域的字段""" - return "可持续生活系统" + """将采集类别映射到内容领域""" + mapping = { + "AI前沿资讯": "AI与效率", + "AI工具实测": "AI与效率", + "AI趋势分析": "AI与效率", + "AI职场应用": "未来工作方式", + "科技人文反思": "科技人文", + "未来工作方式": "未来工作方式", + } + return mapping.get(category, "AI与效率") def save_results(self): """保存收集结果""" @@ -851,7 +856,7 @@ class SustainabilityCollector: def run(self): """主运行流程""" - logger.info("开始可持续性内容收集") + logger.info("开始AI与科技内容收集") existing_titles = self._get_existing_titles() diff --git a/scripts/topic_selector.py b/scripts/topic_selector.py index 5d8ec19..5e8fa55 100644 --- a/scripts/topic_selector.py +++ b/scripts/topic_selector.py @@ -24,18 +24,25 @@ TODAY = __import__('datetime').datetime.now().strftime("%Y-%m-%d") logger = logging.getLogger(__name__) DEFAULT_TREND_DOMAIN_MAP = { - "远程工作": "未来工作方式", "AI工具": "AI与效率", - "可持续生活": "可持续生活系统", - "知识管理": "个人知识工厂", - "数字生活": "科技人文交叉", - "科技人文": "科技人文交叉", - "个人成长": "个人成长", - "副业": "个人成长", "AI创作": "AI与效率", - "未来工作": "未来工作方式", + "AI职场": "AI与效率", "效率工具": "AI与效率", - "家庭教育": "科技人文交叉", + "Prompt": "AI与效率", + "提示词": "AI与效率", + "AI编程": "AI与效率", + "AI写作": "AI与效率", + "未来工作": "未来工作方式", + "远程工作": "未来工作方式", + "AI就业": "未来工作方式", + "一人企业": "未来工作方式", + "副业": "未来工作方式", + "科技人文": "科技人文", + "数字生活": "科技人文", + "AI伦理": "科技人文", + "AI情感": "科技人文", + "数据隐私": "科技人文", + "AI教育": "科技人文", } _cached_trend_domain_map = None