ab764bbc6c
- notes-extractor 和 category-inference 都改用 MiniMax API - endpoint: https://api.minimaxi.com/v1/chat/completions - model: MiniMax-M2.7 (env 可覆盖 MINIMAX_MODEL) - 提示词明确禁止 <think> 标签和解释文字 - 新增 scripts/backfill_category.js (单条请求 + 严格清洗) - 新增 scripts/clean_category.js (清理 <think>/**加粗/解释行/破折号 等脏值) - 生产 .env 已写入 MINIMAX_API_KEY - 实际回填: 693/761 (91%) 已分配品类, 68 条空品类待后续处理
80 lines
2.9 KiB
JavaScript
80 lines
2.9 KiB
JavaScript
const { PrismaClient } = require('@prisma/client')
|
||
const prisma = new PrismaClient()
|
||
|
||
const KNOWN_CATEGORIES = new Set([
|
||
'防火门', '配电箱', '电线电缆', '阀门', '钢材', '涂料', '混凝土',
|
||
'变压器', '水泵', '风机', '管材', '开关', '灯具', '仪表', '电机',
|
||
])
|
||
|
||
const EXPLANATION_PREFIX = /^(让我|用户|我需要|好的|现在|首先|分析|根据|对于|这条|这个|考虑|我们|这里|注意|提示|重要|关键|总结|综上|该|其|它|他们|这些|那些|由于|因为|所以|因此|需要|可能|应该|可以|建议|希望|要求|必须)/
|
||
|
||
function cleanCategory(raw) {
|
||
if (!raw) return ''
|
||
let s = String(raw).trim()
|
||
s = s.replace(/<think>[\s\S]*?<\/think>/g, '').trim()
|
||
s = s.replace(/\*\*/g, '').trim()
|
||
s = s.replace(/^["「『]+|["」』]+$/g, '').trim()
|
||
|
||
const lines = s.split('\n').map((l) => l.trim()).filter((l) => l)
|
||
for (const line of lines) {
|
||
if (EXPLANATION_PREFIX.test(line)) continue
|
||
if (line.length > 20) continue
|
||
if (line.includes('，') || line.includes('。') || line.includes('：') || line.includes(':')) continue
|
||
if (line.includes(' - ') || line.includes(' – ') || line.includes('--')) {
|
||
const parts = line.split(/\s*[-–]\s*/).map((p) => p.trim()).filter((p) => p)
|
||
for (const p of parts) {
|
||
if (KNOWN_CATEGORIES.has(p)) return p
|
||
const m = p.match(/^([\u4e00-\u9fa5]{2,6})$/)
|
||
if (m && !EXPLANATION_PREFIX.test(p)) return m[1]
|
||
}
|
||
continue
|
||
}
|
||
const cleaned = line.replace(/^[\d]+[\.、:：]\s*/, '').trim()
|
||
if (!cleaned || cleaned.length > 10) continue
|
||
if (KNOWN_CATEGORIES.has(cleaned)) return cleaned
|
||
const m = cleaned.match(/^([\u4e00-\u9fa5]{2,6})$/)
|
||
if (m && !EXPLANATION_PREFIX.test(m[1])) return m[1]
|
||
}
|
||
return ''
|
||
}
|
||
|
||
async function main() {
|
||
const leads = await prisma.lead.findMany({
|
||
where: { NOT: { category: null } },
|
||
select: { id: true, category: true },
|
||
})
|
||
console.log(`共 ${leads.length} 条有品类的线索`)
|
||
|
||
let fixed = 0
|
||
let cleared = 0
|
||
for (const lead of leads) {
|
||
const cleaned = cleanCategory(lead.category)
|
||
if (cleaned !== lead.category) {
|
||
await prisma.lead.update({ where: { id: lead.id }, data: { category: cleaned } })
|
||
if (cleaned === '') cleared++
|
||
else fixed++
|
||
}
|
||
}
|
||
console.log(`修正: ${fixed}, 清空: ${cleared}`)
|
||
|
||
const remaining = await prisma.lead.count({ where: { OR: [{ category: null }, { category: '' }] } })
|
||
console.log(`剩余空品类: ${remaining}`)
|
||
|
||
const dist = await prisma.lead.groupBy({
|
||
by: ['category'],
|
||
where: { NOT: { category: '' } },
|
||
_count: true,
|
||
orderBy: { _count: { category: 'desc' } },
|
||
take: 30,
|
||
})
|
||
console.log('品类分布:')
|
||
dist.forEach((d) => console.log(` ${d.category}: ${d._count}`))
|
||
}
|
||
|
||
main()
|
||
.catch((e) => {
|
||
console.error(e)
|
||
process.exit(1)
|
||
})
|
||
.finally(() => prisma.$disconnect())
|