sales-performance-analysis
分析门店或导购的销售业绩,支持同比(本期 vs 上期)分析,识别业绩波动原因,输出诊断结论和改进建议。
json
{
"subject_type": "store|clerk",
"subject_id": "门店ID或导购ID",
"subject_name": "门店名称或导购姓名",
"time_window": {
"from": "YYYY-MM-DD",
"to": "YYYY-MM-DD"
},
"compare_mode": "period_over_period",
"metrics": ["net_money", "effective_order_count", "customer_unit_price", "attach_qty_ratio"]
}
指标编码指标名称计算逻辑用途net_money销售总额直接取值核心收入指标effective_order_count有效订单数直接取值成交频次customer_unit_price客单价销售总额 / 订单数单笔价值effective_qty_count有效销量直接取值商品件数avg_discount平均折扣直接取值促销力度
指标编码指标名称计算逻辑用途attach_qty_ratio连带率销量 / 订单数连带销售能力piece_price件单价销售总额 / 销量商品单价水平
指标编码指标名称计算逻辑用途new_customer_count新增会员数直接取值新客获取new_member_purchase_share新会员消费占比直接取值新客贡献
text
GET /api/v1/store/dashboard/bi?storeId={store_id}&fromDate={from}&toDate={to}
API 字段指标编码说明metrics.net_money``net_money销售总额metrics.effective_order_count``effective_order_count有效订单数metrics.customer_unit_price``customer_unit_price客单价metrics.attach_qty_ratio``attach_qty_ratio连带率metrics.new_customer_count``new_customer_count新增会员数effectiveQtyCount``effective_qty_count有效销量avgDiscount``avg_discount平均折扣
本期字段上期字段反推公式metricsValue``linkRelativeValue直接使用metricsValue``linkRelativeRate + trend反推:上期 = 本期 / (1 ± 变化率)
text
销售额 = 客单价 × 订单数
= (件单价 × 连带率) × 订单数
= 件单价 × 销量
计算各指标对销售额波动的贡献度:
text
销售额变化 = 订单数变化贡献 + 客单价变化贡献
订单数变化贡献 = (本期订单数 - 上期订单数) × 上期客单价
客单价变化贡献 = (本期客单价 - 上期客单价) × 本期订单数
异常类型判断条件严重程度销售大幅下滑环比下降 > 30%🔴 高销售下滑环比下降 10%-30%🟡 中新客获取困难新客环比下降 > 40%🔴 高连带率偏低连带率 < 1.3🟡 中折扣率偏高平均折扣 < 0.8🟡 中
json
{
"status": "ok",
"subject_type": "store|clerk",
"subject_id": "...",
"subject_name": "...",
"analysis_period": {
"current": { "from": "...", "to": "..." },
"previous": { "from": "...", "to": "..." }
},
"core_metrics": {
"net_money": { "current": 0, "previous": 0, "change_pct": 0, "trend": "up|down|flat" },
"effective_order_count": { ... },
"customer_unit_price": { ... },
"attach_qty_ratio": { ... }
},
"attribution": {
"order_contribution": 0,
"atv_contribution": 0,
"primary_driver": "order|atv"
},
"findings": [
{
"title": "...",
"type": "fact|anomaly|hypothesis|recommendation",
"metric": "...",
"evidence": "...",
"confidence": "high|medium|low",
"implication": "..."
}
],
"risks": [],
"recommendations": []
}
python
from skills.sales_performance_analysis import analyze
result = analyze({
"subject_type": "store",
"subject_id": "416759_1714379448487",
"subject_name": "正义路60号店",
"time_window": { "from": "2026-03-01", "to": "2026-03-25" }
})
python
result = analyze({
"subject_type": "clerk",
"subject_id": "clerk_001",
"subject_name": "李翠",
"time_window": { "from": "2026-03-01", "to": "2026-03-25" }
})
api_client.get_copilot_data() - 数据获取~/.openclaw/workspace-front-door/ - API 客户端路径v1.0.0 - 支持门店和导购业绩同比分析