selfrelease
74e35fed96
- 新增场景基类、配置加载、注册表与原语模块 - 添加 r10_refund_split 规则及场景 JSON Schema - 扩展 scan 引擎与 scenarios API - 新增场景注册表/配置/集成测试 - 更新前端 App、api、labels 支持新场景
137 lines
4.9 KiB
Python
137 lines
4.9 KiB
Python
"""场景一 · 政企收入全链路穿透：拆单规避检测（R8）。
|
|
|
|
检测点：
|
|
1. 合同金额集中分布在审批阈值边缘（如阈值 80% 以上但不超阈值）。
|
|
2. 结合知识图谱穿透识别隐性实控人（多个客户经法人关联到同一实控人）。
|
|
满足上述模式则生成线索，附证据链与人话理由。
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
from dataclasses import dataclass, field
|
|
|
|
from app.scenarios.base import BaseScenario, ClueDraft, ScanOutcome
|
|
from app.scenarios.registry import register_scenario
|
|
|
|
|
|
@dataclass
|
|
class ContractRecord:
|
|
"""穿透分析输入：一份合同的关键信息。"""
|
|
|
|
contract_id: str
|
|
customer_key: str
|
|
amount: float
|
|
|
|
|
|
@dataclass
|
|
class SplitFinding:
|
|
"""拆单检测结果。"""
|
|
|
|
near_threshold: list[ContractRecord] = field(default_factory=list)
|
|
ratio: float = 0.0
|
|
total_amount: float = 0.0
|
|
|
|
@property
|
|
def hit(self) -> bool:
|
|
return len(self.near_threshold) >= 3
|
|
|
|
|
|
def detect_threshold_edge(
|
|
contracts: list[ContractRecord],
|
|
approval_threshold: float,
|
|
edge_ratio: float = 0.8,
|
|
) -> SplitFinding:
|
|
"""识别金额集中在审批阈值边缘 [edge_ratio*阈值, 阈值) 的合同。
|
|
|
|
这类"刚好低于阈值"的批量合同是典型的拆单规避特征。
|
|
"""
|
|
if approval_threshold <= 0:
|
|
raise ValueError("审批阈值必须为正数")
|
|
lower = edge_ratio * approval_threshold
|
|
near = [c for c in contracts if lower <= c.amount < approval_threshold]
|
|
finding = SplitFinding(
|
|
near_threshold=near,
|
|
ratio=(len(near) / len(contracts)) if contracts else 0.0,
|
|
total_amount=sum(c.amount for c in near),
|
|
)
|
|
return finding
|
|
|
|
|
|
def split_risk_score(finding: SplitFinding, shared_controller: bool) -> float:
|
|
"""综合评分：阈值边缘集中度 + 是否穿透到同一实控人。"""
|
|
if not finding.hit:
|
|
return 0.0
|
|
base = min(0.6, 0.1 * len(finding.near_threshold)) # 数量越多越可疑
|
|
base += 0.2 * finding.ratio
|
|
if shared_controller:
|
|
base += 0.3 # 同一实控人是强证据
|
|
return round(min(base, 1.0), 3)
|
|
|
|
|
|
def build_rationale(finding: SplitFinding, threshold: float, shared_controller: bool) -> str:
|
|
parts = [
|
|
f"检测到 {len(finding.near_threshold)} 份合同金额集中在审批阈值 "
|
|
f"{threshold:.0f} 的边缘区间（占比 {finding.ratio:.0%}），",
|
|
f"边缘合同金额合计约 {finding.total_amount:.0f}。",
|
|
]
|
|
if shared_controller:
|
|
parts.append("且经工商关联穿透，相关客户疑似同属一个隐性实控人，高度符合拆单规避特征。")
|
|
else:
|
|
parts.append("建议进一步穿透客户关联关系以确认是否同一实控人。")
|
|
return "".join(parts)
|
|
|
|
|
|
@register_scenario
|
|
class SplitContractScenario(BaseScenario):
|
|
"""场景一拆单检测的插件封装：检测→评分→产出线索草稿。
|
|
|
|
数据通过构造注入（兼容现有 seed/测试的数据流）；后续可改为从 session 自取数，
|
|
接口保持不变。
|
|
"""
|
|
|
|
code = "R8"
|
|
title = "疑似政企拆单规避审批"
|
|
risk_domain = "收入"
|
|
label = "政企拆单"
|
|
score_threshold = 0.0 # 命中即出线索（与原 run_split_contract_scan 的 score>0 一致）
|
|
|
|
def __init__(
|
|
self,
|
|
contracts: list[ContractRecord],
|
|
approval_threshold: float,
|
|
shared_controller: bool = False,
|
|
) -> None:
|
|
self.contracts = contracts
|
|
self.approval_threshold = approval_threshold
|
|
self.shared_controller = shared_controller
|
|
|
|
def scan(self, session, *, data_version_id=None) -> ScanOutcome:
|
|
finding = detect_threshold_edge(self.contracts, self.approval_threshold)
|
|
score = split_risk_score(finding, self.shared_controller)
|
|
drafts: list[ClueDraft] = []
|
|
if score > 0:
|
|
drafts.append(
|
|
ClueDraft(
|
|
score=score,
|
|
rationale=build_rationale(
|
|
finding, self.approval_threshold, self.shared_controller
|
|
),
|
|
evidence={
|
|
"near_threshold_contracts": [
|
|
c.contract_id for c in finding.near_threshold
|
|
],
|
|
"edge_ratio": finding.ratio,
|
|
"near_threshold_amount": finding.total_amount,
|
|
"approval_threshold": self.approval_threshold,
|
|
"shared_controller": self.shared_controller,
|
|
},
|
|
subjects={
|
|
"customers": sorted(
|
|
{c.customer_key for c in finding.near_threshold}
|
|
)
|
|
},
|
|
amount_involved=finding.total_amount,
|
|
)
|
|
)
|
|
return ScanOutcome(scanned_count=len(self.contracts), drafts=drafts)
|