sxbh_admin/cma-management
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: 因果链三层验证机制(P2) — 数据验证+人工确认+状态机

Browse Source 
- kpi_causality 加列: source_type/verify_status/verified_at/verified_by/entity_id(回填)
- 核心服务: app/services/causality_verification.py (Pearson+滞后对齐+状态机)
- 数据验证脚本: scripts/correlation-check.py (月度cron, 输出JSON报告)
- API: create/update支持source_type, GET /verify-status, PUT /{id}/verify(人工确认)
- 全部端点按entity_id账套隔离, kpi/{id}/network/simulate补跨企业校验
- 前端: KPIDetail因果链页显示验证状态徽标(数据证实/存疑/待检)
- 测试: test_causality_verification.py 37用例 + 原因果链测试全过(59个)
- 50条因果链首轮验证: 1数据证实(#37渠补率到净利润lag1 r=-0.89), 4存疑, 45待检(数据不足)
This commit is contained in:
Hermes CI Fix
2026-08-27 15:51:19 +08:00
parent 6b479bfe7d
commit fdc42d443d
10 changed files with 1063 additions and 22 deletions
Download Patch File Download Diff File Expand all files Collapse all files
backend/app/api/kpi_causality.py
+137 -18
View File
@@ -1,6 +1,7 @@
"""KPI因果链建模 — 任务2
KPI间因果关系网络 + 模拟推演
KPI间因果关系网络 + 模拟推演 + 三层验证机制(数据/AI/人工) (2026-08-27 P2)
"""
from datetime import datetime
from fastapi import APIRouter, Depends, HTTPException, Query
from sqlalchemy.orm import Session
from sqlalchemy import text
@@ -11,6 +12,11 @@ from app.database import get_db
from app.deps import get_entity_id
from app.auth_middleware import require_auth, require_role
from app.models import KPIDefinition, KPICausality, KPIValue, OperationLog
from app.services.causality_verification import (
ALL_STATUSES,
ALL_SOURCE_TYPES,
STATUS_PENDING,
)
logger = logging.getLogger("kpi-causality")
@@ -30,8 +36,8 @@ def _to_dict(obj):
@router.get("/full-network")
def get_full_network(db: Session = Depends(get_db), entity_id: int = Depends(get_entity_id)):
"""获取全局因果网络数据（用于力导向图）— 账套隔离: 仅当前企业KPI的因果链 (2026-08-23 P1b)"""
edges = db.query(KPICausality).join(KPIDefinition, KPIDefinition.id == KPICausality.source_kpi_id).filter(KPIDefinition.entity_id == entity_id).all()
"""获取全局因果网络数据（用于力导向图）— 账套隔离: 仅当前企业KPI的因果链 (2026-08-23 P1b, 2026-08-27 用entity_id列)"""
edges = db.query(KPICausality).filter(KPICausality.entity_id == entity_id).all()
node_ids = set()
edge_list = []
for e in edges:
@@ -61,14 +67,19 @@ def get_full_network(db: Session = Depends(get_db), entity_id: int = Depends(get
@router.get("/kpi/{kpi_id}/network")
def get_kpi_network(kpi_id: int, db: Session = Depends(get_db)):
"""获取KPI的因果网络（上游驱动 + 下游影响）"""
def get_kpi_network(kpi_id: int, db: Session = Depends(get_db), entity_id: int = Depends(get_entity_id)):
"""获取KPI的因果网络（上游驱动 + 下游影响）— 账套隔离: 校验KPI属于当前企业"""
kpi = db.query(KPIDefinition).filter(KPIDefinition.id == kpi_id).first()
if not kpi:
raise HTTPException(404, "KPI不存在")
if kpi.entity_id != entity_id:
raise HTTPException(404, "KPI不存在") # 跨企业不暴露存在性
# 上游（指向当前KPI的因果）
upstream = db.query(KPICausality).filter(KPICausality.target_kpi_id == kpi_id).all()
upstream = db.query(KPICausality).filter(
KPICausality.target_kpi_id == kpi_id,
KPICausality.entity_id == entity_id,
).all()
upstream_list = []
for c in upstream:
src = db.query(KPIDefinition).filter(KPIDefinition.id == c.source_kpi_id).first()
@@ -78,10 +89,16 @@ def get_kpi_network(kpi_id: int, db: Session = Depends(get_db)):
"kpi_id": src.id, "kpi_code": src.kpi_code, "kpi_name": src.kpi_name,
"strength": c.strength, "lag_months": c.lag_months,
"direction": c.direction, "formula": c.formula,
"source_type": c.source_type, "verify_status": c.verify_status,
"verified_at": c.verified_at.isoformat() if c.verified_at else None,
"verified_by": c.verified_by,
})
# 下游（当前KPI指向的因果）
downstream = db.query(KPICausality).filter(KPICausality.source_kpi_id == kpi_id).all()
downstream = db.query(KPICausality).filter(
KPICausality.source_kpi_id == kpi_id,
KPICausality.entity_id == entity_id,
).all()
downstream_list = []
for c in downstream:
tgt = db.query(KPIDefinition).filter(KPIDefinition.id == c.target_kpi_id).first()
@@ -91,6 +108,9 @@ def get_kpi_network(kpi_id: int, db: Session = Depends(get_db)):
"kpi_id": tgt.id, "kpi_code": tgt.kpi_code, "kpi_name": tgt.kpi_name,
"strength": c.strength, "lag_months": c.lag_months,
"direction": c.direction, "formula": c.formula,
"source_type": c.source_type, "verify_status": c.verify_status,
"verified_at": c.verified_at.isoformat() if c.verified_at else None,
"verified_by": c.verified_by,
})
return {
@@ -101,7 +121,7 @@ def get_kpi_network(kpi_id: int, db: Session = Depends(get_db)):
@router.post("/simulate")
def simulate_causality(data: dict, db: Session = Depends(get_db)):
def simulate_causality(data: dict, db: Session = Depends(get_db), entity_id: int = Depends(get_entity_id)):
"""模拟推演: 修改一个KPI的值，预测对其他KPI的影响
Body: { kpi_id: int, new_value: float, period: str }
"""
@@ -115,6 +135,8 @@ def simulate_causality(data: dict, db: Session = Depends(get_db)):
source_kpi = db.query(KPIDefinition).filter(KPIDefinition.id == kpi_id).first()
if not source_kpi:
raise HTTPException(404, "KPI不存在")
if source_kpi.entity_id != entity_id:
raise HTTPException(404, "KPI不存在")
# 获取当前值
current_value = None
@@ -142,9 +164,10 @@ def simulate_causality(data: dict, db: Session = Depends(get_db)):
continue
visited.add(current_kpi_id)
# 查找从current_kpi_id出发的下游因果链
# 查找从current_kpi_id出发的下游因果链（账套隔离: 仅本企业链）
downstream = db.query(KPICausality).filter(
KPICausality.source_kpi_id == current_kpi_id
KPICausality.source_kpi_id == current_kpi_id,
KPICausality.entity_id == entity_id,
).all()
for edge in downstream:
@@ -212,15 +235,18 @@ def simulate_causality(data: dict, db: Session = Depends(get_db)):
def list_causalities(
source_kpi_id: Optional[int] = None,
target_kpi_id: Optional[int] = None,
verify_status: Optional[str] = None,
db: Session = Depends(get_db),
entity_id: int = Depends(get_entity_id),
):
"""获取因果链列表（账套隔离: 仅当前企业KPI, 2026-08-23 P1b）"""
query = db.query(KPICausality).join(KPIDefinition, KPIDefinition.id == KPICausality.source_kpi_id).filter(KPIDefinition.entity_id == entity_id)
"""获取因果链列表（账套隔离: 仅当前企业KPI, 2026-08-23 P1b, 2026-08-27 支持verify_status筛选）"""
query = db.query(KPICausality).filter(KPICausality.entity_id == entity_id)
if source_kpi_id:
query = query.filter(KPICausality.source_kpi_id == source_kpi_id)
if target_kpi_id:
query = query.filter(KPICausality.target_kpi_id == target_kpi_id)
if verify_status:
query = query.filter(KPICausality.verify_status == verify_status)
items = query.order_by(KPICausality.id).all()
result = []
@@ -236,11 +262,51 @@ def list_causalities(
return {"data": result, "total": len(result)}
@router.get("/verify-status")
def get_verify_status(
verify_status: Optional[str] = None,
db: Session = Depends(get_db),
entity_id: int = Depends(get_entity_id),
):
"""验证状态总览 — 按状态统计 + 链列表（2026-08-27 三层验证机制）
可选 ?verify_status=pending/data_verified/human_verified/disputed 筛选
"""
if verify_status and verify_status not in ALL_STATUSES:
raise HTTPException(400, f"verify_status 必须为 {'/'.join(ALL_STATUSES)}")
query = db.query(KPICausality).filter(KPICausality.entity_id == entity_id)
if verify_status:
query = query.filter(KPICausality.verify_status == verify_status)
items = query.order_by(KPICausality.id).all()
by_status = {s: 0 for s in ALL_STATUSES}
data = []
for c in items:
by_status[c.verify_status] = by_status.get(c.verify_status, 0) + 1
d = _to_dict(c)
src = db.query(KPIDefinition).filter(KPIDefinition.id == c.source_kpi_id).first()
tgt = db.query(KPIDefinition).filter(KPIDefinition.id == c.target_kpi_id).first()
d["source_kpi_code"] = src.kpi_code if src else None
d["source_kpi_name"] = src.kpi_name if src else None
d["target_kpi_code"] = tgt.kpi_code if tgt else None
d["target_kpi_name"] = tgt.kpi_name if tgt else None
d["verified_at"] = c.verified_at.isoformat() if c.verified_at else None
data.append(d)
return {
"summary": {"total": len(items), "by_status": by_status},
"data": data,
}
@router.get("/{causality_id}")
def get_causality(causality_id: int, db: Session = Depends(get_db)):
def get_causality(causality_id: int, db: Session = Depends(get_db), entity_id: int = Depends(get_entity_id)):
c = db.query(KPICausality).filter(KPICausality.id == causality_id).first()
if not c:
raise HTTPException(404, "因果链不存在")
if c.entity_id != entity_id:
raise HTTPException(404, "因果链不存在") # 账套隔离
d = _to_dict(c)
src = db.query(KPIDefinition).filter(KPIDefinition.id == c.source_kpi_id).first()
tgt = db.query(KPIDefinition).filter(KPIDefinition.id == c.target_kpi_id).first()
@@ -251,7 +317,7 @@ def get_causality(causality_id: int, db: Session = Depends(get_db)):
@router.post("")
def create_causality(data: dict, db: Session = Depends(get_db), user=WRITE_ROLES):
"""创建因果链"""
"""创建因果链（source_type标记来源, 2026-08-27）"""
source_id = data.get("source_kpi_id")
target_id = data.get("target_kpi_id")
if not source_id or not target_id:
@@ -262,6 +328,8 @@ def create_causality(data: dict, db: Session = Depends(get_db), user=WRITE_ROLES
tgt = db.query(KPIDefinition).filter(KPIDefinition.id == target_id).first()
if not src or not tgt:
raise HTTPException(404, "KPI不存在")
if src.entity_id != tgt.entity_id:
raise HTTPException(400, "源KPI和目标KPI必须属于同一企业")
existing = db.query(KPICausality).filter(
KPICausality.source_kpi_id == source_id,
@@ -270,40 +338,91 @@ def create_causality(data: dict, db: Session = Depends(get_db), user=WRITE_ROLES
if existing:
raise HTTPException(400, f"因果链已存在: {src.kpi_code}→{tgt.kpi_code}")
source_type = data.get("source_type", "manual")
if source_type not in ALL_SOURCE_TYPES:
raise HTTPException(400, f"source_type 必须为 {'/'.join(ALL_SOURCE_TYPES)}")
c = KPICausality(
entity_id=src.entity_id,
source_kpi_id=source_id,
target_kpi_id=target_id,
strength=data.get("strength", 0.5),
lag_months=data.get("lag_months", 1),
formula=data.get("formula"),
direction=data.get("direction", "positive"),
source_type=source_type,
verify_status=STATUS_PENDING,
)
db.add(c)
db.commit()
db.refresh(c)
db.add(OperationLog(action="create", target_type="kpi_causality",
detail=f"创建因果链: {src.kpi_code}→{tgt.kpi_code}"))
detail=f"创建因果链: {src.kpi_code}→{tgt.kpi_code} (source={source_type})"))
db.commit()
return _to_dict(c)
@router.put("/{causality_id}")
def update_causality(causality_id: int, data: dict, db: Session = Depends(get_db), user=WRITE_ROLES):
def update_causality(causality_id: int, data: dict, db: Session = Depends(get_db), user=WRITE_ROLES,
entity_id: int = Depends(get_entity_id)):
c = db.query(KPICausality).filter(KPICausality.id == causality_id).first()
if not c:
raise HTTPException(404, "因果链不存在")
for field in ("strength", "lag_months", "formula", "direction"):
if c.entity_id != entity_id:
raise HTTPException(404, "因果链不存在") # 账套隔离
for field in ("strength", "lag_months", "formula", "direction", "source_type"):
if field in data:
if field == "source_type" and data[field] not in ALL_SOURCE_TYPES:
raise HTTPException(400, f"source_type 必须为 {'/'.join(ALL_SOURCE_TYPES)}")
setattr(c, field, data[field])
# 修改链定义后，验证状态回到待检（定义变了旧结论失效）
if any(f in data for f in ("strength", "lag_months", "formula", "direction")):
c.verify_status = STATUS_PENDING
c.verified_at = None
c.verified_by = None
db.commit()
db.refresh(c)
return _to_dict(c)
@router.put("/{causality_id}/verify")
def verify_causality(causality_id: int, data: dict, db: Session = Depends(get_db), user=WRITE_ROLES,
entity_id: int = Depends(get_entity_id)):
"""人工确认（战略回顾会核对打标）— 2026-08-27 三层验证机制
Body: { verify_status: "human_verified"|"disputed", verified_by?: "任富海" }
默认打标 human_verified（人工最终确认）。
"""
c = db.query(KPICausality).filter(KPICausality.id == causality_id).first()
if not c:
raise HTTPException(404, "因果链不存在")
if c.entity_id != entity_id:
raise HTTPException(404, "因果链不存在") # 账套隔离
target_status = data.get("verify_status", "human_verified")
if target_status not in ("human_verified", "disputed"):
raise HTTPException(400, "verify_status 必须为 human_verified 或 disputed")
verified_by = data.get("verified_by") or user.name or user.username
c.verify_status = target_status
c.verified_at = datetime.now()
c.verified_by = str(verified_by)[:50]
db.add(OperationLog(action="verify", target_type="kpi_causality",
detail=f"因果链 #{causality_id} 人工确认: {target_status} (by {verified_by})"))
db.commit()
db.refresh(c)
d = _to_dict(c)
d["verified_at"] = c.verified_at.isoformat() if c.verified_at else None
return d
@router.delete("/{causality_id}")
def delete_causality(causality_id: int, db: Session = Depends(get_db), user=WRITE_ROLES):
def delete_causality(causality_id: int, db: Session = Depends(get_db), user=WRITE_ROLES,
entity_id: int = Depends(get_entity_id)):
c = db.query(KPICausality).filter(KPICausality.id == causality_id).first()
if c:
if c.entity_id != entity_id:
raise HTTPException(404, "因果链不存在") # 账套隔离
db.delete(c)
db.commit()
return {"message": "已删除"}