mirror of
https://github.com/ThearchyHelios/AgentLab.git
synced 2026-11-20 13:42:00 +00:00
业务本体与标准实体:跨源键值对齐、对账共变算子、健康证据链与实体助手
- 新增标准业务实体(CanonicalEntity)模型、确定性跨源编码翻译、后台候选实体扫描与文档驱动实体智能助手 - 新增指标本体图谱(factor / reconciles_with / upstream_driver)、DAG 防环校验以及 ontology_neighbors / source_health 内置工具 - 新增跨源对账(analysis_reconcile)与滞后共变(analysis_cochange)分析算子,打通 [[h:H1]] 数据源健康证据链、报告导出与本体消融评测 - 数据目录新增「标准业务实体」视图与候选审阅工作台,口径页集成指标本体拓扑面板与端到端浏览器检查
This commit is contained in:
@@ -19,6 +19,11 @@ _PHRASES = {
|
||||
"no_evidence": "西南和华东的退款率差异可能只是样本波动(样本量 40、230)",
|
||||
"comparable": "两期可比",
|
||||
"incomparable": "两期不可比:本期只有 3 天数据",
|
||||
"aligned": "两侧报废数对账一致(主侧 120,对账侧 120,相差 0)",
|
||||
"diverged": "两侧报废数存在显著偏差(主侧 120,对账侧 95,相差 +25,+26.3%),偏差集中在 L2",
|
||||
"missing_counterpart": "两侧报废数对账发现对侧缺失记录(共 1 项缺失:L4)",
|
||||
"co_anomalous": "产线效率本期变化 -14.2% 超出常规波动,关联的非计划停机在同期同样超出其常规波动(+185.0%,同期同步异动,统计伴随关系,非因果断言)",
|
||||
"target_normal": "产线效率本期变化 -14.2% 超出常规波动,但关联的非计划停机在同期处于其常规波动范围内(+2.1%)",
|
||||
}
|
||||
|
||||
_WEEKS = ["2026-07-20", "2026-07-27", "2026-08-03", "2026-08-10", "2026-08-17", "2026-08-24", "2026-08-31",
|
||||
@@ -102,13 +107,57 @@ def _comparable() -> tuple[dict[str, Any], dict[str, Any], dict[str, Any], list[
|
||||
return table, values, params, ["gmv"]
|
||||
|
||||
|
||||
def _reconcile() -> tuple[dict[str, Any], dict[str, Any], dict[str, Any], list[str]]:
|
||||
columns = ["line_code", "base", "target", "scaled_target", "diff", "rel_diff", "status"]
|
||||
table = {
|
||||
"columns": columns,
|
||||
"labels": {"line_code": "产线", "base": "主侧", "target": "对账侧原值", "scaled_target": "换算后对账侧",
|
||||
"diff": "差值", "rel_diff": "相对偏差", "status": "结果"},
|
||||
"rows": [["L2", "60", "35", "35", "25", "0.714285714286", "超差"],
|
||||
["L1", "60", "60", "60", "0", "0", "一致"]],
|
||||
"column_types": {"line_code": "text", "base": "number", "target": "number", "scaled_target": "number",
|
||||
"diff": "number", "rel_diff": "number", "status": "text"},
|
||||
}
|
||||
values = {"base_total": "120", "target_total": "95", "diff_total": "25", "rel_diff_total": "0.263157894737",
|
||||
"unit_factor": "1", "matched_count": "2", "diverged_count": "1", "missing_base_count": "0",
|
||||
"missing_target_count": "0", "max_abs_diff": "25"}
|
||||
params = {"base_query": "Q1", "target_query": "Q2", "by": ["line_code"], "measure": "scrap_qty",
|
||||
"target_measure": "scrap_units", "unit_factor": "1", "label": "报废数"}
|
||||
return table, values, params, ["line_code", "scrap_qty"]
|
||||
|
||||
|
||||
def _cochange() -> tuple[dict[str, Any], dict[str, Any], dict[str, Any], list[str]]:
|
||||
columns = ["day", "primary_value", "primary_change", "driver_value", "driver_change", "role"]
|
||||
rows = [[w, "92", "0.01", "12", "0.02", "历史"] for w in _WEEKS[:-1]] + [
|
||||
[_WEEKS[-1], "79", "-0.141304347826", "34", "1.833333333333", "本期"]
|
||||
]
|
||||
table = {
|
||||
"columns": columns,
|
||||
"labels": {"day": "日期", "primary_value": "产线效率", "primary_change": "主指标变化率",
|
||||
"driver_value": "非计划停机", "driver_change": "关联指标变化率", "role": "说明"},
|
||||
"rows": rows,
|
||||
"column_types": {"day": "text", "primary_value": "number", "primary_change": "number",
|
||||
"driver_value": "number", "driver_change": "number", "role": "text"},
|
||||
}
|
||||
values = {"primary_x": "-0.141304347826", "primary_z": "-4.2", "primary_band_lo": "-0.04",
|
||||
"primary_band_hi": "0.04", "driver_x": "1.833333333333", "driver_z": "5.8",
|
||||
"driver_band_lo": "-0.15", "driver_band_hi": "0.15", "lag": "0", "n_history": "12",
|
||||
"co_direction": "opposite"}
|
||||
params = {"base_query": "Q1", "target_query": "Q2", "period": "day", "measure": "efficiency",
|
||||
"driver_measure": "unplanned_min", "lag": 0, "basis": "change", "target": _WEEKS[-1],
|
||||
"label": "产线效率"}
|
||||
return table, values, params, ["day", "efficiency"]
|
||||
|
||||
|
||||
_SHAPES = {"decompose": _decompose, "baseline": _baseline, "trend": _trend, "differ": _differ,
|
||||
"comparable": _comparable}
|
||||
"comparable": _comparable, "reconcile": _reconcile, "cochange": _cochange}
|
||||
_CRITERIA = {"decompose": "一段占总变化一半以上算主要来源",
|
||||
"baseline": "本期和过去 12 周的中位数比,差不到 2 倍稳健标准差算常规波动",
|
||||
"trend": "Mann–Kendall 检验的双侧 p 值小于 0.05 时按 Theil–Sen 斜率的正负判上升或下降",
|
||||
"differ": "双侧 p 值小于 0.05 算差异站得住",
|
||||
"comparable": "只差日期、窗口一样长、是整期、星期构成相同才算可比"}
|
||||
"comparable": "只差日期、窗口一样长、是整期、星期构成相同才算可比",
|
||||
"reconcile": "两侧总量及各对齐切片相对偏差均不超过 1.0% 且无缺失项算对账一致",
|
||||
"cochange": "主指标与关联指标在对齐期次上同按各自历史中位数 ± 2.0 倍稳健标准差检验是否同步超出常规波动"}
|
||||
|
||||
|
||||
def fake_result(op: str = "decompose", mode: str | None = "additive", verdict: str | None = "driver", *,
|
||||
@@ -121,7 +170,7 @@ def fake_result(op: str = "decompose", mode: str | None = "additive", verdict: s
|
||||
elif op == "differ" and mode not in ("rate", "mean", "rows"):
|
||||
mode = "rate"
|
||||
table, values, params, columns = _SHAPES.get(op, _decompose)()
|
||||
if op == "comparable":
|
||||
if op in ("comparable", "reconcile", "cochange"):
|
||||
default_inputs = [{"ref": ref, "artifact": "0" * 64, "role": role, "columns": columns, "rows": "all"}
|
||||
for ref, role in (("Q4", "base"), ("Q5", "target"))]
|
||||
else:
|
||||
|
||||
Reference in New Issue
Block a user