feat: 初始提交 - 科创企业特有风险的识别与管理 (数智风控系统)

risk_engine/__init__.py

@@ -0,0 +1,2 @@
+# -*- coding: utf-8 -*-
+"""风险评估引擎模块"""

risk_engine/dynamic_pricing.py

@@ -0,0 +1,184 @@
+# -*- coding: utf-8 -*-
+"""
+动态保险定价模型
+基于精算原理，结合六维风险评分实现"千企千面"费率计算
+"""
+import logging
+import sys
+import os
+
+# 将项目根目录添加到 Python 路径
+sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+
+from config import INSURANCE_PRODUCTS
+
+logger = logging.getLogger(__name__)
+
+
+# 行业风险系数
+INDUSTRY_RISK_FACTORS = {
+    "芯片": 1.35,      # 地缘风险+技术迭代双高
+    "AI": 1.30,         # 合规风险+技术竞争
+    "软件": 1.05,       # 相对成熟
+    "医疗器械": 0.95,   # 技术壁垒高但风险较稳
+    "新能源": 1.15,     # 技术路线之争+贸易摩擦
+    "消费电子": 1.10,   # 供应链风险
+}
+
+# 企业规模折扣（大企业风险分散能力更强）
+SCALE_DISCOUNT = {
+    "超大型": 0.85,   # 营收 > 500亿
+    "大型": 0.90,     # 100-500亿
+    "中型": 1.00,     # 10-100亿
+    "小型": 1.15,     # 1-10亿
+    "微型": 1.30,     # < 1亿
+}
+
+
+def get_enterprise_scale(revenue: float) -> str:
+    """根据营收判断企业规模"""
+    if revenue >= 50_000_000_000:
+        return "超大型"
+    elif revenue >= 10_000_000_000:
+        return "大型"
+    elif revenue >= 1_000_000_000:
+        return "中型"
+    elif revenue >= 100_000_000:
+        return "小型"
+    return "微型"
+
+
+def calculate_premium(
+    product_key: str,
+    comprehensive_risk_score: int,
+    six_dimension_scores: dict,
+    sector: str = "",
+    revenue: float = 0,
+) -> dict:
+    """
+    动态费率计算器
+
+    定价公式：
+    实际保费 = 基础保费 × 风险系数 × 行业调整 × 规模折扣
+
+    风险系数由综合评分决定（分段线性）：
+    - [0, 30)  → 0.7 ~ 0.9（优质折扣）
+    - [30, 50) → 0.9 ~ 1.2（标准浮动）
+    - [50, 70) → 1.2 ~ 1.8（风险上浮）
+    - [70, 90) → 1.8 ~ 2.5（惩罚性费率）
+    - [90,100] → 拒保或附加极高免赔额
+    """
+    product = INSURANCE_PRODUCTS.get(product_key)
+    if not product:
+        return {"error": f"未知保险产品: {product_key}"}
+
+    base_premium = product["base_premium"]
+    base_coverage = product["base_coverage"]
+
+    # 1. 计算风险系数
+    risk_multiplier = _calculate_risk_multiplier(comprehensive_risk_score)
+
+    # 2. 行业调整系数
+    industry_factor = INDUSTRY_RISK_FACTORS.get(sector, 1.0)
+
+    # 3. 规模折扣
+    scale = get_enterprise_scale(revenue)
+    scale_factor = SCALE_DISCOUNT[scale]
+
+    # 4. 特定险种的维度调整
+    dimension_adjustment = _get_dimension_adjustment(product_key, six_dimension_scores)
+
+    # 5. 最终保费
+    final_premium = base_premium * risk_multiplier * industry_factor * scale_factor * dimension_adjustment
+
+    # 6. 核保条件
+    deductible_rate = _calculate_deductible(comprehensive_risk_score)
+    adjusted_coverage = base_coverage * (1.0 if comprehensive_risk_score < 70 else 0.7)
+
+    return {
+        "product_name": product["name"],
+        "product_key": product_key,
+        "base_premium": base_premium,
+        "base_coverage": base_coverage,
+        "risk_multiplier": round(risk_multiplier, 3),
+        "industry_factor": round(industry_factor, 3),
+        "scale_factor": round(scale_factor, 3),
+        "scale_label": scale,
+        "dimension_adjustment": round(dimension_adjustment, 3),
+        "final_premium": round(final_premium, 2),
+        "adjusted_coverage": round(adjusted_coverage, 2),
+        "deductible_rate": round(deductible_rate, 3),
+        "deductible_amount": round(adjusted_coverage * deductible_rate, 2),
+        "comprehensive_risk_score": comprehensive_risk_score,
+        "is_insurable": comprehensive_risk_score < 90,
+        "pricing_breakdown": (
+            f"¥{base_premium:,.0f} × {risk_multiplier:.2f}(风险) "
+            f"× {industry_factor:.2f}(行业) × {scale_factor:.2f}(规模) "
+            f"× {dimension_adjustment:.2f}(维度) = ¥{final_premium:,.0f}"
+        ),
+    }
+
+
+def _calculate_risk_multiplier(score: int) -> float:
+    """分段线性风险系数计算"""
+    if score < 30:
+        return 0.7 + (score / 30) * 0.2       # 0.7 ~ 0.9
+    elif score < 50:
+        return 0.9 + ((score - 30) / 20) * 0.3  # 0.9 ~ 1.2
+    elif score < 70:
+        return 1.2 + ((score - 50) / 20) * 0.6  # 1.2 ~ 1.8
+    elif score < 90:
+        return 1.8 + ((score - 70) / 20) * 0.7  # 1.8 ~ 2.5
+    else:
+        return 3.0  # 拒保级别
+
+
+def _get_dimension_adjustment(product_key: str, scores: dict) -> float:
+    """针对特定险种，根据相关维度得分进行微调"""
+    if product_key == "ip_lawsuit":
+        # 知识产权被诉险：重点看技术路线和专利
+        tech_score = scores.get("tech_disruption", 50)
+        return 0.8 + (tech_score / 100) * 0.4  # 0.8 ~ 1.2
+
+    elif product_key == "exec_departure":
+        # 高管离职险：重点看人员流失风险
+        talent_score = scores.get("talent_loss", 50)
+        return 0.7 + (talent_score / 100) * 0.6  # 0.7 ~ 1.3
+
+    elif product_key == "data_compliance":
+        # 数据合规险：重点看合规风险
+        compliance_score = scores.get("algo_compliance", 50)
+        return 0.8 + (compliance_score / 100) * 0.4  # 0.8 ~ 1.2
+
+    return 1.0
+
+
+def _calculate_deductible(score: int) -> float:
+    """计算免赔率"""
+    if score < 30:
+        return 0.05   # 5%
+    elif score < 50:
+        return 0.10   # 10%
+    elif score < 70:
+        return 0.15   # 15%
+    elif score < 90:
+        return 0.25   # 25%
+    else:
+        return 0.50   # 50%（惩罚性高免赔）
+
+
+def calculate_all_products(
+    comprehensive_risk_score: int,
+    six_dimension_scores: dict,
+    sector: str = "",
+    revenue: float = 0,
+) -> list:
+    """计算所有险种的保费"""
+    results = []
+    for product_key in INSURANCE_PRODUCTS:
+        result = calculate_premium(
+            product_key, comprehensive_risk_score,
+            six_dimension_scores, sector, revenue,
+        )
+        results.append(result)
+    return results

risk_engine/report_generator.py

@@ -0,0 +1,146 @@
+# -*- coding: utf-8 -*-
+"""
+核保决策报告生成器
+生成结构化的风险评估报告
+"""
+import json
+import logging
+from datetime import datetime
+from typing import Optional
+
+logger = logging.getLogger(__name__)
+
+
+def generate_report(
+    company_data: dict,
+    debate_result: dict,
+    pricing_results: list,
+) -> dict:
+    """
+    生成完整的核保决策报告
+    """
+    company_name = company_data.get("short_name", "未知企业")
+    judge = debate_result.get("judge_result", {})
+    scores = judge.get("six_dimension_scores", {})
+    comprehensive = judge.get("comprehensive_score", 50)
+    decision = judge.get("underwriting_decision", "标准承保")
+
+    report = {
+        "title": f"科创企业智能风控核保报告 —— {company_name}",
+        "report_id": f"RPT-{datetime.now().strftime('%Y%m%d%H%M%S')}",
+        "generate_time": datetime.now().strftime("%Y-%m-%d %H:%M:%S"),
+        "company_profile": {
+            "name": company_name,
+            "stock_code": company_data.get("stock_code", ""),
+            "industry": company_data.get("industry", ""),
+            "sector": company_data.get("sector", ""),
+            "description": company_data.get("description", ""),
+        },
+        "risk_assessment": {
+            "comprehensive_score": comprehensive,
+            "risk_level": judge.get("risk_level", "中"),
+            "six_dimension_scores": scores,
+            "key_risks": judge.get("key_risks", []),
+        },
+        "debate_summary": {
+            "law_findings": debate_result.get("law_result", {}).get("key_findings", []),
+            "tech_findings": debate_result.get("tech_result", {}).get("key_findings", []),
+            "fin_findings": debate_result.get("finance_result", {}).get("key_findings", []),
+            "conflicts": debate_result.get("conflicts", []),
+            "resolution": judge.get("conflict_resolution", ""),
+        },
+        "underwriting_decision": {
+            "decision": decision,
+            "conditions": judge.get("underwriting_conditions", []),
+            "summary": judge.get("summary", ""),
+        },
+        "pricing": pricing_results,
+    }
+
+    return report
+
+
+def format_report_markdown(report: dict) -> str:
+    """将报告格式化为 Markdown"""
+    lines = []
+    lines.append(f"# {report['title']}")
+    lines.append(f"\n> 报告编号: {report['report_id']} | 生成时间: {report['generate_time']}")
+
+    # 企业概况
+    profile = report["company_profile"]
+    lines.append("\n## 一、企业概况")
+    lines.append(f"- **企业名称**: {profile['name']}")
+    lines.append(f"- **股票代码**: {profile['stock_code']}")
+    lines.append(f"- **所属行业**: {profile['industry']}")
+    lines.append(f"- **企业描述**: {profile['description']}")
+
+    # 风险评估
+    risk = report["risk_assessment"]
+    lines.append("\n## 二、风险评估")
+    lines.append(f"- **综合风险评分**: {risk['comprehensive_score']} 分")
+    lines.append(f"- **风险等级**: {risk['risk_level']}")
+
+    lines.append("\n### 六维风险评分")
+    dim_names = {
+        "tech_disruption": "技术路线颠覆",
+        "talent_loss": "核心人员流失",
+        "algo_compliance": "算法/数据合规",
+        "geopolitical": "地缘政治/出口管制",
+        "rd_capitalization": "研发资本化操纵",
+        "concentration": "客户/供应商集中",
+    }
+    lines.append("| 风险维度 | 评分 | 等级 |")
+    lines.append("|---------|------|------|")
+    for dim, score in risk.get("six_dimension_scores", {}).items():
+        name = dim_names.get(dim, dim)
+        level = "高" if score >= 70 else ("中" if score >= 40 else "低")
+        lines.append(f"| {name} | {score} | {level} |")
+
+    # 辩论摘要
+    debate = report["debate_summary"]
+    lines.append("\n## 三、多智能体交叉验证摘要")
+
+    lines.append("\n### 👩‍⚖️ 法务风控节点")
+    for f in debate.get("law_findings", []):
+        lines.append(f"- {f}")
+
+    lines.append("\n### 👨‍🔬 技术风控节点")
+    for f in debate.get("tech_findings", []):
+        lines.append(f"- {f}")
+
+    lines.append("\n### 👔 财务风控节点")
+    for f in debate.get("fin_findings", []):
+        lines.append(f"- {f}")
+
+    if debate.get("conflicts"):
+        lines.append("\n### ⚠️ 冲突点")
+        for c in debate["conflicts"]:
+            lines.append(f"- {c}")
+
+    # 核保决策
+    uw = report["underwriting_decision"]
+    lines.append(f"\n## 四、核保决策")
+    lines.append(f"\n**决策**: 【{uw['decision']}】")
+    lines.append(f"\n{uw.get('summary', '')}")
+
+    if uw.get("conditions"):
+        lines.append("\n### 核保附加条件")
+        for c in uw["conditions"]:
+            lines.append(f"- {c}")
+
+    # 保费方案
+    lines.append("\n## 五、保险产品费率方案")
+    if report.get("pricing"):
+        lines.append("| 险种 | 基础保费 | 最终保费 | 保额 | 免赔率 |")
+        lines.append("|------|---------|---------|------|--------|")
+        for p in report["pricing"]:
+            if p.get("is_insurable"):
+                lines.append(
+                    f"| {p['product_name']} | ¥{p['base_premium']:,.0f} | "
+                    f"¥{p['final_premium']:,.0f} | ¥{p['adjusted_coverage']:,.0f} | "
+                    f"{p['deductible_rate']:.0%} |"
+                )
+            else:
+                lines.append(f"| {p['product_name']} | - | **拒保** | - | - |")
+
+    return "\n".join(lines)

risk_engine/risk_scorer.py

@@ -0,0 +1,148 @@
+# -*- coding: utf-8 -*-
+"""
+六维风险评分器
+整合所有数据源和分析结果，生成结构化六维风险画像
+"""
+import logging
+from typing import Optional
+
+logger = logging.getLogger(__name__)
+
+
+# 风险等级映射
+RISK_LEVELS = {
+    (0, 30): {"level": "低", "color": "#4CAF50", "emoji": "🟢"},
+    (30, 50): {"level": "中低", "color": "#8BC34A", "emoji": "🟡"},
+    (50, 70): {"level": "中高", "color": "#FF9800", "emoji": "🟠"},
+    (70, 90): {"level": "高", "color": "#F44336", "emoji": "🔴"},
+    (90, 101): {"level": "极高", "color": "#B71C1C", "emoji": "⛔"},
+}
+
+
+def get_risk_level(score: int) -> dict:
+    """根据分数获取风险等级详情"""
+    for (low, high), info in RISK_LEVELS.items():
+        if low <= score < high:
+            return info
+    return {"level": "未知", "color": "#9E9E9E", "emoji": "❓"}
+
+
+def calculate_six_dimension_scores(company_data: dict) -> dict:
+    """
+    基于企业数据直接计算六维风险评分（不依赖 LLM）
+    用于快速预览和规则引擎降级场景
+    """
+    financials = company_data.get("financials", {})
+    compliance = company_data.get("compliance", {})
+    tech_route = company_data.get("tech_route", {})
+    personnel = company_data.get("core_tech_personnel", [])
+    supply_chain = company_data.get("supply_chain", {})
+
+    scores = {}
+
+    # 1. 技术路线颠覆风险
+    competing = len(tech_route.get("competing_techs", []))
+    moat = tech_route.get("tech_moat", "")
+    tech_score = min(25 + competing * 15, 85)
+    if "差距" in moat or "受制" in moat or "威胁" in moat:
+        tech_score = min(tech_score + 15, 95)
+    if "领先" in moat or "第一" in moat:
+        tech_score = max(tech_score - 10, 10)
+    scores["tech_disruption"] = tech_score
+
+    # 2. 核心人员流失风险
+    departed = [p for p in personnel if "离职" in p.get("status", "")]
+    high_imp = [p for p in personnel if p.get("importance") == "极高"]
+    if departed:
+        scores["talent_loss"] = 80
+    elif len(high_imp) <= 1 and len(personnel) <= 2:
+        scores["talent_loss"] = 55
+    else:
+        scores["talent_loss"] = 25
+
+    # 3. 算法/数据合规风险
+    algo_status = compliance.get("algo_filing_status", "")
+    data_risk = compliance.get("data_export_risk", "低")
+    algo_score = 20
+    if "未" in algo_status:
+        algo_score = 75
+    elif data_risk == "高":
+        algo_score = 65
+    elif data_risk == "中":
+        algo_score = 40
+    elif "已备案" in algo_status:
+        algo_score = 15
+    scores["algo_compliance"] = algo_score
+
+    # 4. 地缘政治/出口管制风险
+    entity_status = compliance.get("entity_list_status", "")
+    if "被列入" in entity_status:
+        scores["geopolitical"] = 92
+    elif supply_chain.get("supplier_concentration_risk") == "极高":
+        scores["geopolitical"] = 68
+    elif supply_chain.get("supplier_concentration_risk") == "高":
+        scores["geopolitical"] = 50
+    else:
+        scores["geopolitical"] = 18
+
+    # 5. 研发资本化操纵风险
+    cap_rate = financials.get("rd_capitalization_rate", 0)
+    if cap_rate >= 0.4:
+        scores["rd_capitalization"] = 90
+    elif cap_rate >= 0.3:
+        scores["rd_capitalization"] = 72
+    elif cap_rate >= 0.15:
+        scores["rd_capitalization"] = 48
+    elif cap_rate > 0:
+        scores["rd_capitalization"] = 25
+    else:
+        scores["rd_capitalization"] = 10
+
+    # 6. 客户/供应商集中风险
+    cust_ratio = financials.get("top5_customer_ratio", 0)
+    supp_ratio = financials.get("top5_supplier_ratio", 0)
+    max_conc = max(cust_ratio, supp_ratio)
+    if max_conc >= 0.8:
+        scores["concentration"] = 88
+    elif max_conc >= 0.6:
+        scores["concentration"] = 68
+    elif max_conc >= 0.4:
+        scores["concentration"] = 42
+    else:
+        scores["concentration"] = 18
+
+    # 加权综合
+    weights = {
+        "tech_disruption": 0.20,
+        "talent_loss": 0.15,
+        "algo_compliance": 0.15,
+        "geopolitical": 0.20,
+        "rd_capitalization": 0.15,
+        "concentration": 0.15,
+    }
+    comprehensive = int(sum(scores[k] * weights[k] for k in scores))
+
+    # 维度中文名映射
+    dim_names = {
+        "tech_disruption": "技术路线颠覆",
+        "talent_loss": "核心人员流失",
+        "algo_compliance": "算法/数据合规",
+        "geopolitical": "地缘政治/出口管制",
+        "rd_capitalization": "研发资本化操纵",
+        "concentration": "客户/供应商集中",
+    }
+
+    return {
+        "scores": scores,
+        "comprehensive_score": comprehensive,
+        "risk_level": get_risk_level(comprehensive),
+        "dimension_details": {
+            k: {
+                "name": dim_names[k],
+                "score": v,
+                "level": get_risk_level(v),
+                "weight": weights[k],
+            }
+            for k, v in scores.items()
+        },
+    }