fmode-voc-projects/scripts/tools/_audit-lactic-voc.js

#!/usr/bin/env node
// ==============================================================================
// 乳酸菌素片儿童版 VOC 质量审计脚本
// ==============================================================================
// 检查：重复 / 跳题 / 内容过短 / 纯表情 / 与章节主题不相关等问题
// ==============================================================================

const LA = require('./lactic-analyze.js');
const data = LA.loadMerged();
const items = data.items;

function dump(title, arr, maxShow = 5) {
    console.log('\n' + '─'.repeat(60));
    console.log(`【${title}】`);
    console.log('─'.repeat(60));
    arr.slice(0, maxShow).forEach((it, i) => {
        console.log(`  [${i + 1}] ${it.platform.toUpperCase()} · ${it.keyword} · ${it.nickname} · ♥${it.likes}`);
        console.log(`      「${(it.content || '').slice(0, 160)}」`);
    });
}

console.log('=========================================');
console.log('江中乳酸菌素片儿童版 · VOC 质量审计');
console.log(`总条数：${items.length} / 平台：${Object.keys(data.meta?.platforms || {}).join('+')}`);
console.log('=========================================');

// === 1. 检查 Ch1.1 引用的爆款 VOC 是否相关 ===
console.log('\n▶ Ch1.1 · 成人版爆款 VOC（应该都提到乳酸菌素片/肠胃）');
const adultHit = LA.getEvidence(items, {
    keyword: '乳酸菌素片',
    contentMatch: /肠鸣|胃胀|神药|便秘|好了|有用|治好|咕噜/,
    minChars: 20, top: 4, seed: 7,
});
dump('Ch1.1 成人版爆款', adultHit);

// === 2. 检查 Ch2.1 妈咪爱 VOC ===
console.log('\n▶ Ch2.1 · 妈咪爱家长场景（应该是宝宝/孩子相关）');
const maomi = LA.getEvidence(items, {
    keyword: '妈咪爱',
    contentMatch: /宝宝|孩子|月|胀气|胀肚|便秘|腹泻|医生|儿科|医院/,
    minChars: 30, top: 4, seed: 7,
});
dump('Ch2.1 妈咪爱场景', maomi);

// === 3. 检查 Ch2.2 亿活/金双岐 ===
console.log('\n▶ Ch2.2 · 亿活/金双岐（应该是腹泻/抗生素/菌群相关）');
const yihuo = LA.getEvidence(items, {
    keyword: '亿活 儿童',
    contentMatch: /腹泻|抗生素|酵母菌|布拉氏|发烧|宝宝|孩子|儿童|药店/,
    minChars: 30, top: 3, seed: 5,
});
dump('Ch2.2 亿活', yihuo);
const jinshuangqi = LA.getEvidence(items, {
    keyword: '金双岐',
    contentMatch: /拉肚|便秘|菌群|三联|嚼|腹泻|宝宝|孩子/,
    minChars: 25, top: 3, seed: 9,
});
dump('Ch2.2 金双岐', jinshuangqi);

// === 4. 检查 Ch3.1 合生元 ===
console.log('\n▶ Ch3.1 · 合生元（应该是儿童/宝宝场景）');
const hsy = LA.getEvidence(items, {
    keyword: '合生元益生菌',
    contentMatch: /宝宝|孩子|奶味|便秘|拉肚|幼儿园|月龄|岁/,
    minChars: 30, top: 4, seed: 7,
});
dump('Ch3.1 合生元', hsy);

// === 5. 检查 Ch3.2 万益蓝（不应该出现成人减肥）===
console.log('\n▶ Ch3.2 · 万益蓝（此产品主打成人减肥，儿童 VOC 稀薄 - 是我们要揭示的定位错位）');
const wyl = LA.getEvidence(items, { keyword: '万益蓝益生菌', minChars: 30, top: 3, seed: 13 });
dump('Ch3.2 万益蓝 top', wyl);

// === 6. 检查 Ch3.2 拜奥 ===
console.log('\n▶ Ch3.2 · 拜奥（应该是宝宝/胀气/滴剂相关）');
const baiao = LA.getEvidence(items, {
    keyword: '拜奥益生菌',
    contentMatch: /宝宝|孩子|月|胀气|绿便|滴/,
    minChars: 20, top: 3, seed: 7,
});
dump('Ch3.2 拜奥', baiao);

// === 7. 场景 Ch5 检查 ===
console.log('\n▶ Ch5.1 · 入园生病');
const entry = LA.getEvidence(items, {
    contentMatch: /入园|幼儿园|开学|交叉感染|集体|开园|托班|小班/,
    minChars: 20, top: 4, seed: 5,
});
dump('Ch5.1 入园', entry);

console.log('\n▶ Ch5.2 · 抗生素后');
const abx = LA.getEvidence(items, {
    contentMatch: /抗生素|消炎药|头孢|阿莫西林|输液|杀菌|菌群|肠道菌群/,
    minChars: 30, top: 4, seed: 7,
});
dump('Ch5.2 抗生素后', abx);

console.log('\n▶ Ch5.3 · 挑食积食');
const picky = LA.getEvidence(items, {
    contentMatch: /挑食|饭渣|不爱吃饭|厌食|专注度|饮食|食欲|脾胃|不吃菜/,
    minChars: 30, top: 4, seed: 7,
});
dump('Ch5.3 挑食', picky);

console.log('\n▶ Ch5.4 · 换季腹泻');
const season = LA.getEvidence(items, {
    contentMatch: /换季|春秋|天气转凉|季节|秋冬|春夏|拉稀|腹泻反复|反复拉/,
    minChars: 25, top: 4, seed: 7,
});
dump('Ch5.4 换季', season);

// === 8. 重复检查 ===
console.log('\n▶ 全量重复检查（前 40 字相同视为重复）');
const bucket = new Map();
for (const it of items) {
    const key = (it.content || '').slice(0, 40);
    if (!bucket.has(key)) bucket.set(key, []);
    bucket.get(key).push(it);
}
const dupGroups = [...bucket.values()].filter((g) => g.length > 1).sort((a, b) => b.length - a.length);
console.log(`共 ${dupGroups.length} 组重复`);
dupGroups.slice(0, 5).forEach((g, i) => {
    console.log(`  [重复组 ${i + 1}] ${g.length} 条`);
    console.log(`      「${g[0].content.slice(0, 80)}」`);
    console.log(`      出现在关键词: ${[...new Set(g.map((x) => x.keyword))].slice(0, 5).join(', ')}`);
});

// === 9. 潜在跳题 VOC（短/纯表情/无关内容）===
console.log('\n▶ 潜在跳题 VOC（纯表情 / 过短 / 无肠道/益生菌/儿童相关词）');
const offtopic = items.filter((it) => {
    const c = it.content || '';
    if (c.length < 15) return true;
    const stripped = c.replace(/\[[^\]]+\]/g, '').replace(/[\s\p{P}\p{Emoji_Presentation}\p{Extended_Pictographic}]/gu, '');
    if (stripped.length < 8) return true;
    const hasRelevant = /肠|胃|便|益生菌|宝宝|孩子|儿童|娃|月|岁|奶|辅食|菌|消化|乳酸/.test(c);
    return !hasRelevant && (it.likes || 0) >= 100;
});
console.log(`共 ${offtopic.length} 条潜在跳题（高赞 >100）`);
offtopic.slice(0, 10).sort((a, b) => b.likes - a.likes).forEach((it, i) => {
    console.log(`  [${i + 1}] ♥${it.likes} · ${it.keyword} · ${it.nickname}: ${(it.content || '').slice(0, 120)}`);
});

console.log('\n=========================================');
console.log('✅ 审计完成');
console.log('=========================================');