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)

collectors/__init__.py

@@ -0,0 +1,2 @@
+# -*- coding: utf-8 -*-
+"""数据采集模块"""

collectors/annual_report_parser.py

@@ -0,0 +1,188 @@
+# -*- coding: utf-8 -*-
+"""
+年报 PDF 文本解析模块
+从年报中提取关键风险信息：核心技术人员、技术路线、诉讼、风险提示等
+"""
+import re
+import logging
+from pathlib import Path
+from typing import Optional
+
+logger = logging.getLogger(__name__)
+
+
+def parse_annual_report(pdf_path: str) -> dict:
+    """
+    解析年报 PDF，提取关键风险相关信息
+    返回结构化的风险要素字典
+    """
+    text = _extract_text_from_pdf(pdf_path)
+    if not text:
+        return {"error": "PDF 解析失败", "raw_text": ""}
+
+    return {
+        "core_personnel_info": _extract_core_personnel(text),
+        "tech_route_info": _extract_tech_route(text),
+        "litigation_info": _extract_litigation(text),
+        "risk_factors": _extract_risk_factors(text),
+        "rd_capitalization_info": _extract_rd_capitalization(text),
+        "customer_concentration": _extract_customer_concentration(text),
+        "raw_text_length": len(text),
+    }
+
+
+def _extract_text_from_pdf(pdf_path: str) -> Optional[str]:
+    """使用 pdfplumber 提取 PDF 全文"""
+    try:
+        import pdfplumber
+        text_parts = []
+        with pdfplumber.open(pdf_path) as pdf:
+            for page in pdf.pages:
+                page_text = page.extract_text()
+                if page_text:
+                    text_parts.append(page_text)
+        return "\n".join(text_parts)
+    except ImportError:
+        logger.warning("pdfplumber 未安装，尝试 PyPDF2")
+        try:
+            from PyPDF2 import PdfReader
+            reader = PdfReader(pdf_path)
+            return "\n".join(
+                page.extract_text() or "" for page in reader.pages
+            )
+        except Exception as e:
+            logger.error(f"PyPDF2 解析失败: {e}")
+    except Exception as e:
+        logger.error(f"PDF 解析失败: {e}")
+    return None
+
+
+def _extract_core_personnel(text: str) -> dict:
+    """提取核心技术人员相关信息"""
+    result = {
+        "has_departure": False,
+        "departure_details": [],
+        "personnel_count": 0,
+        "key_mentions": [],
+    }
+
+    # 匹配离职/辞职相关表述
+    departure_patterns = [
+        r"(核心技术人员|核心人员|关键技术人员).{0,30}(离职|辞职|离任|不再担任)",
+        r"(CTO|首席技术官|技术总监|研发总监).{0,30}(离职|辞职|离任)",
+        r"(离职|辞职).{0,30}(核心技术人员|核心人员)",
+    ]
+    for pattern in departure_patterns:
+        matches = re.findall(pattern, text)
+        if matches:
+            result["has_departure"] = True
+            result["departure_details"].extend([str(m) for m in matches])
+
+    # 统计核心技术人员数量
+    count_match = re.search(r"核心技术人员\s*(\d+)\s*[名人]", text)
+    if count_match:
+        result["personnel_count"] = int(count_match.group(1))
+
+    return result
+
+
+def _extract_tech_route(text: str) -> dict:
+    """提取技术路线相关信息"""
+    result = {
+        "competing_tech_mentioned": False,
+        "tech_keywords": [],
+        "risk_mentions": [],
+    }
+
+    # 技术竞争关键词
+    tech_keywords = [
+        "技术路线", "技术迭代", "技术替代", "技术颠覆",
+        "竞争技术", "替代方案", "新一代技术",
+    ]
+    for kw in tech_keywords:
+        if kw in text:
+            result["tech_keywords"].append(kw)
+            result["competing_tech_mentioned"] = True
+
+    return result
+
+
+def _extract_litigation(text: str) -> dict:
+    """提取诉讼/仲裁相关信息"""
+    result = {
+        "has_litigation": False,
+        "litigation_count": 0,
+        "ip_related": False,
+    }
+
+    # 诉讼关键词
+    litigation_patterns = [
+        r"(诉讼|仲裁|起诉|被告).{0,50}(知识产权|专利|商标|著作权)",
+        r"(专利侵权|商标侵权|著作权纠纷)",
+    ]
+    for pattern in litigation_patterns:
+        if re.search(pattern, text):
+            result["has_litigation"] = True
+            result["ip_related"] = True
+
+    return result
+
+
+def _extract_risk_factors(text: str) -> list:
+    """提取风险因素章节的关键信息"""
+    risk_keywords = [
+        "地缘政治", "实体清单", "出口管制", "贸易摩擦",
+        "数据安全", "数据合规", "算法备案", "数据出境",
+        "客户集中", "供应商集中", "单一客户", "单一供应商",
+        "研发资本化", "开发支出", "无形资产",
+        "人才流失", "核心人员", "竞业限制",
+    ]
+    found_risks = []
+    for kw in risk_keywords:
+        if kw in text:
+            found_risks.append(kw)
+    return found_risks
+
+
+def _extract_rd_capitalization(text: str) -> dict:
+    """提取研发资本化相关信息"""
+    result = {
+        "has_capitalization": False,
+        "capitalization_mentioned": False,
+        "amount_keywords": [],
+    }
+
+    cap_keywords = ["开发支出", "研发资本化", "资本化研发", "开发阶段支出"]
+    for kw in cap_keywords:
+        if kw in text:
+            result["capitalization_mentioned"] = True
+            result["amount_keywords"].append(kw)
+
+    # 检查是否有具体的资本化金额
+    cap_amount = re.search(r"开发支出.{0,30}([\d,\.]+)\s*(万元|百万|亿)", text)
+    if cap_amount:
+        result["has_capitalization"] = True
+
+    return result
+
+
+def _extract_customer_concentration(text: str) -> dict:
+    """提取客户/供应商集中度信息"""
+    result = {
+        "top5_customer_ratio": None,
+        "top5_supplier_ratio": None,
+        "single_customer_dependency": False,
+    }
+
+    # 前五大客户占比
+    customer_match = re.search(
+        r"前五[名大]客户.{0,30}([\d\.]+)\s*%", text
+    )
+    if customer_match:
+        result["top5_customer_ratio"] = float(customer_match.group(1)) / 100
+
+    # 单一客户依赖
+    if re.search(r"(第一大客户|最大客户).{0,30}([\d\.]+)\s*%", text):
+        result["single_customer_dependency"] = True
+
+    return result

collectors/compliance_collector.py

@@ -0,0 +1,87 @@
+# -*- coding: utf-8 -*-
+"""
+算法备案合规数据采集与查询模块
+匹配企业是否已完成网信办算法备案
+"""
+import json
+import logging
+from pathlib import Path
+from typing import Optional
+
+logger = logging.getLogger(__name__)
+
+DATA_DIR = Path(__file__).parent.parent / "data"
+
+
+def _load_algo_filings() -> list:
+    """加载算法备案数据"""
+    filepath = DATA_DIR / "algo_filings.json"
+    with open(filepath, "r", encoding="utf-8") as f:
+        return json.load(f)
+
+
+def check_algo_filing(company_name: str) -> dict:
+    """
+    查询企业的算法备案状态
+    """
+    filings = _load_algo_filings()
+    result = {
+        "has_filing": False,
+        "filings": [],
+        "needs_filing": False,  # 是否需要备案但未备案
+        "risk_level": "低",
+    }
+
+    for filing in filings:
+        if company_name in filing["company"] or filing["company"] in company_name:
+            result["has_filing"] = True
+            result["filings"].append(filing)
+
+    return result
+
+
+def assess_algo_compliance_risk(company_data: dict) -> dict:
+    """
+    综合评估企业的算法合规风险
+    考虑因素：是否涉及 AI 业务、是否已备案、数据出境风险
+    """
+    company_name = company_data.get("short_name", company_data.get("company_name", ""))
+    sector = company_data.get("sector", "")
+    compliance = company_data.get("compliance", {})
+
+    # 查询备案状态
+    filing_status = check_algo_filing(company_name)
+
+    # 判断是否需要备案
+    ai_related_sectors = ["AI", "软件", "互联网", "消费电子"]
+    needs_filing = sector in ai_related_sectors or "AI" in str(company_data.get("tech_route", {}))
+
+    # 综合评估
+    risk_level = "低"
+    risk_details = []
+
+    if needs_filing and not filing_status["has_filing"]:
+        algo_status = compliance.get("algo_filing_status", "")
+        if algo_status == "不适用":
+            risk_level = "低"
+        else:
+            risk_level = "高"
+            risk_details.append("涉及AI业务但未查到算法备案记录")
+
+    data_export_risk = compliance.get("data_export_risk", "低")
+    if data_export_risk == "高":
+        risk_level = "高"
+        risk_details.append("存在大量跨境数据传输，数据出境评估风险高")
+    elif data_export_risk == "中":
+        if risk_level != "高":
+            risk_level = "中"
+        risk_details.append("存在部分跨境数据传输，需关注数据出境合规")
+
+    return {
+        "company_name": company_name,
+        "needs_filing": needs_filing,
+        "filing_status": filing_status,
+        "data_export_risk": data_export_risk,
+        "overall_risk_level": risk_level,
+        "risk_details": risk_details,
+    }

collectors/entity_list_collector.py

@@ -0,0 +1,84 @@
+# -*- coding: utf-8 -*-
+"""
+BIS 实体清单采集与匹配模块
+支持企业名模糊匹配 + 别名映射 + 供应链上游穿透
+"""
+import json
+import logging
+from pathlib import Path
+from typing import Optional
+
+logger = logging.getLogger(__name__)
+
+DATA_DIR = Path(__file__).parent.parent / "data"
+
+
+def _load_entity_list() -> list:
+    """加载实体清单数据"""
+    filepath = DATA_DIR / "entity_list.json"
+    with open(filepath, "r", encoding="utf-8") as f:
+        return json.load(f)
+
+
+def check_entity_list(company_name: str) -> dict:
+    """
+    检查企业是否在 BIS 实体清单中
+    支持模糊匹配和别名匹配
+    """
+    entities = _load_entity_list()
+    result = {
+        "is_sanctioned": False,
+        "match_type": None,
+        "entity_detail": None,
+        "supply_chain_risk": [],  # 供应链上游被制裁的情况
+    }
+
+    for entity in entities:
+        # 精确匹配
+        if company_name in entity["entity_name"]:
+            result["is_sanctioned"] = True
+            result["match_type"] = "直接命中"
+            result["entity_detail"] = entity
+            return result
+
+        # 别名匹配
+        for alias in entity.get("aliases", []):
+            if company_name in alias or alias in company_name:
+                result["is_sanctioned"] = True
+                result["match_type"] = "别名命中"
+                result["entity_detail"] = entity
+                return result
+
+    return result
+
+
+def check_supply_chain_sanctions(company_name: str, suppliers: list) -> list:
+    """
+    检查企业供应链上游是否有被制裁的实体
+    返回受制裁的供应商列表
+    """
+    sanctioned_suppliers = []
+    entities = _load_entity_list()
+
+    for supplier in suppliers:
+        # 清洗供应商名称（去掉括号中的说明文字）
+        clean_name = supplier.split("（")[0].split("(")[0].strip()
+
+        for entity in entities:
+            all_names = [entity["entity_name"]] + entity.get("aliases", [])
+            for name in all_names:
+                if clean_name in name or name in clean_name:
+                    sanctioned_suppliers.append({
+                        "supplier": supplier,
+                        "matched_entity": entity["entity_name"],
+                        "restrictions": entity["restrictions"],
+                        "date_added": entity["date_added"],
+                    })
+                    break
+
+    return sanctioned_suppliers
+
+
+def get_all_sanctioned_entities() -> list:
+    """获取所有被制裁实体列表"""
+    return _load_entity_list()

collectors/financial_collector.py

@@ -0,0 +1,105 @@
+# -*- coding: utf-8 -*-
+"""
+财务数据采集模块
+双轨策略：优先尝试 AKShare 在线采集，失败则回退到预置数据
+"""
+import json
+import logging
+from pathlib import Path
+from typing import Optional
+
+logger = logging.getLogger(__name__)
+
+DATA_DIR = Path(__file__).parent.parent / "data"
+
+
+def _load_preset_data() -> list:
+    """加载预置的科创板企业数据"""
+    filepath = DATA_DIR / "sample_companies.json"
+    with open(filepath, "r", encoding="utf-8") as f:
+        return json.load(f)
+
+
+def collect_financial_data(stock_code: str) -> Optional[dict]:
+    """
+    采集指定股票代码的财务数据
+    双轨策略：在线采集 → 离线预置
+    """
+    # 尝试在线采集
+    try:
+        return _collect_online(stock_code)
+    except Exception as e:
+        logger.warning(f"在线采集 {stock_code} 失败: {e}，回退到预置数据")
+
+    # 回退到预置数据
+    return _collect_from_preset(stock_code)
+
+
+def _collect_online(stock_code: str) -> Optional[dict]:
+    """通过 AKShare 在线采集财务数据"""
+    try:
+        import akshare as ak
+
+        # 科创板企业利润表
+        profit_df = ak.stock_profit_sheet_by_report_em(symbol=stock_code)
+        # 科创板企业资产负债表
+        balance_df = ak.stock_balance_sheet_by_report_em(symbol=stock_code)
+
+        if profit_df is not None and not profit_df.empty:
+            latest = profit_df.iloc[0]
+            return {
+                "stock_code": stock_code,
+                "revenue": float(latest.get("营业收入", 0)),
+                "net_profit": float(latest.get("净利润", 0)),
+                "rd_expense": float(latest.get("研发费用", 0)),
+                "source": "akshare_online",
+            }
+    except ImportError:
+        logger.warning("AKShare 未安装，跳过在线采集")
+    except Exception as e:
+        logger.warning(f"AKShare 采集异常: {e}")
+
+    raise RuntimeError("在线采集失败")
+
+
+def _collect_from_preset(stock_code: str) -> Optional[dict]:
+    """从预置数据中查找企业"""
+    companies = _load_preset_data()
+    for company in companies:
+        if company["stock_code"] == stock_code:
+            return {
+                "stock_code": stock_code,
+                "company_name": company["company_name"],
+                "industry": company["industry"],
+                "sector": company["sector"],
+                "financials": company["financials"],
+                "core_tech_personnel": company["core_tech_personnel"],
+                "tech_route": company["tech_route"],
+                "compliance": company["compliance"],
+                "supply_chain": company["supply_chain"],
+                "source": "preset_data",
+            }
+    return None
+
+
+def get_all_companies() -> list:
+    """获取所有预置企业列表"""
+    return _load_preset_data()
+
+
+def get_company_by_code(stock_code: str) -> Optional[dict]:
+    """通过股票代码查找企业完整数据"""
+    companies = _load_preset_data()
+    for company in companies:
+        if company["stock_code"] == stock_code:
+            return company
+    return None
+
+
+def get_company_by_name(name: str) -> Optional[dict]:
+    """通过企业名称查找（支持简称）"""
+    companies = _load_preset_data()
+    for company in companies:
+        if name in company["company_name"] or name in company["short_name"]:
+            return company
+    return None