初始提交：餐智库 CIBank 餐饮行业知识库

2026-07-20 19:49:27 +08:00
commit a40b0f14ae
99 changed files with 22553 additions and 0 deletions
@@ -0,0 +1,154 @@
+PRAGMA journal_mode = WAL;
+PRAGMA foreign_keys = ON;
+
+-- 文章表：公众号文章 + 视频号ASR转写文本
+CREATE TABLE IF NOT EXISTS articles (
+    id INTEGER PRIMARY KEY AUTOINCREMENT,
+    canonical_url TEXT NOT NULL UNIQUE,
+    source TEXT NOT NULL DEFAULT 'hongcan',         -- 来源平台
+    source_name TEXT,                                 -- 公众号名称 / 视频号名称
+    source_type TEXT NOT NULL DEFAULT '公众号',       -- 公众号 | 视频号
+    title TEXT,
+    author TEXT,
+    published_at TEXT,
+    summary TEXT,
+    content TEXT,
+    content_hash TEXT,
+    category TEXT,                                    -- 赛道：茶饮咖啡/快餐/火锅/正餐/烘焙/供应链/综合
+    crawl_status TEXT NOT NULL DEFAULT 'pending',     -- pending | success | failed
+    retry_count INTEGER NOT NULL DEFAULT 0,
+    last_error TEXT,
+    media_url TEXT,                                    -- 原始视频文件路径（视频号专用）
+    discovered_at TEXT NOT NULL,
+    crawled_at TEXT,
+    updated_at TEXT NOT NULL
+);
+
+CREATE INDEX IF NOT EXISTS idx_articles_published_at ON articles(published_at);
+CREATE INDEX IF NOT EXISTS idx_articles_crawl_status ON articles(crawl_status, retry_count);
+CREATE INDEX IF NOT EXISTS idx_articles_source_type ON articles(source_type);
+CREATE INDEX IF NOT EXISTS idx_articles_category ON articles(category);
+
+-- 采集运行记录
+CREATE TABLE IF NOT EXISTS crawl_runs (
+    id INTEGER PRIMARY KEY AUTOINCREMENT,
+    started_at TEXT NOT NULL,
+    finished_at TEXT,
+    status TEXT NOT NULL DEFAULT 'running',
+    source_type TEXT NOT NULL DEFAULT '公众号',
+    discovered_count INTEGER NOT NULL DEFAULT 0,
+    inserted_count INTEGER NOT NULL DEFAULT 0,
+    updated_count INTEGER NOT NULL DEFAULT 0,
+    failed_count INTEGER NOT NULL DEFAULT 0,
+    message TEXT
+);
+
+-- AI 结构化分析结果
+CREATE TABLE IF NOT EXISTS ai_analyses (
+    id INTEGER PRIMARY KEY AUTOINCREMENT,
+    article_id INTEGER NOT NULL,
+    model TEXT NOT NULL,
+    analysis_type TEXT NOT NULL DEFAULT 'editorial',
+    result_json TEXT NOT NULL,                        -- 完整结构化JSON
+    content_hash TEXT,
+    created_at TEXT NOT NULL,
+    updated_at TEXT NOT NULL,
+    UNIQUE(article_id, model, analysis_type),
+    FOREIGN KEY(article_id) REFERENCES articles(id) ON DELETE CASCADE
+);
+
+CREATE INDEX IF NOT EXISTS idx_ai_analyses_article ON ai_analyses(article_id, updated_at);
+
+-- 向量嵌入表（用于RAG检索）
+CREATE TABLE IF NOT EXISTS embeddings (
+    id INTEGER PRIMARY KEY AUTOINCREMENT,
+    article_id INTEGER NOT NULL,
+    chunk_index INTEGER NOT NULL DEFAULT 0,
+    chunk_text TEXT NOT NULL,
+    embedding BLOB,                                   -- JSON序列化的float数组
+    model TEXT NOT NULL,
+    content_hash TEXT,
+    created_at TEXT NOT NULL,
+    FOREIGN KEY(article_id) REFERENCES articles(id) ON DELETE CASCADE,
+    UNIQUE(article_id, chunk_index, model)
+);
+
+CREATE INDEX IF NOT EXISTS idx_embeddings_article ON embeddings(article_id);
+
+-- 品牌实体库
+CREATE TABLE IF NOT EXISTS brands (
+    id INTEGER PRIMARY KEY AUTOINCREMENT,
+    name TEXT NOT NULL UNIQUE,
+    category TEXT,
+    stores INTEGER DEFAULT 0,
+    avg_price INTEGER DEFAULT 0,
+    model TEXT,                                       -- 直营 | 加盟 | 直营+加盟
+    city_tier_json TEXT DEFAULT '[]',                 -- [{tier, pct}]
+    trend_json TEXT DEFAULT '[]',                     -- 近12个月门店数
+    latest_news TEXT,
+    news_date TEXT,
+    growth REAL DEFAULT 0,
+    created_at TEXT NOT NULL,
+    updated_at TEXT NOT NULL
+);
+
+-- 行业信号（跨文章聚合）
+CREATE TABLE IF NOT EXISTS industry_signals (
+    id INTEGER PRIMARY KEY AUTOINCREMENT,
+    signal_date TEXT NOT NULL,
+    title TEXT NOT NULL,
+    summary TEXT NOT NULL,
+    trend TEXT NOT NULL DEFAULT 'emerging',
+    confidence REAL NOT NULL DEFAULT 0.5,
+    implications_json TEXT NOT NULL DEFAULT '[]',
+    article_ids_json TEXT NOT NULL DEFAULT '[]',
+    tags_json TEXT NOT NULL DEFAULT '[]',
+    model TEXT NOT NULL,
+    created_at TEXT NOT NULL,
+    updated_at TEXT NOT NULL,
+    UNIQUE(signal_date, title)
+);
+
+CREATE INDEX IF NOT EXISTS idx_industry_signals_date ON industry_signals(signal_date DESC, confidence DESC);
+
+-- 报告表
+CREATE TABLE IF NOT EXISTS reports (
+    id INTEGER PRIMARY KEY AUTOINCREMENT,
+    title TEXT NOT NULL,
+    report_date TEXT NOT NULL,
+    period TEXT,
+    highlights_json TEXT NOT NULL DEFAULT '[]',
+    sections_json TEXT NOT NULL DEFAULT '[]',
+    created_at TEXT NOT NULL
+);
+
+CREATE INDEX IF NOT EXISTS idx_reports_date ON reports(report_date DESC);
+
+CREATE TABLE IF NOT EXISTS pipeline_runs (
+    id INTEGER PRIMARY KEY AUTOINCREMENT,
+    run_type TEXT NOT NULL,
+    started_at TEXT NOT NULL,
+    finished_at TEXT,
+    status TEXT NOT NULL DEFAULT 'running',
+    current_step TEXT,
+    steps_json TEXT NOT NULL DEFAULT '{}',
+    error_message TEXT,
+    created_at TEXT NOT NULL
+);
+
+CREATE INDEX IF NOT EXISTS idx_pipeline_runs_started ON pipeline_runs(started_at DESC);
+
+-- 信源配置表（公众号 + 视频号）
+CREATE TABLE IF NOT EXISTS sources (
+    id INTEGER PRIMARY KEY AUTOINCREMENT,
+    source_type TEXT NOT NULL DEFAULT '公众号',     -- 公众号 | 视频号
+    name TEXT NOT NULL,                              -- 信源名称（公众号名称/视频号账号名）
+    finder TEXT,                                     -- 视频号 finder ID（视频号专用）
+    list_url TEXT,                                   -- 列表页URL（公众号专用）
+    download_dir TEXT,                               -- 下载目录（视频号专用）
+    enabled INTEGER NOT NULL DEFAULT 1,              -- 是否启用 1/0
+    last_crawled_at TEXT,                            -- 最近采集时间
+    created_at TEXT NOT NULL,
+    updated_at TEXT NOT NULL,
+    UNIQUE(source_type, name)
+);