CareerNexus 职联：岗位能力图谱构建与动态演化分析平台（挑战杯 XH-202621）

- 全链路：多源JD接入/清洗交叉验证/结构化抽取(星火+离线双通道)/时序知识图谱/新岗位发现/演化分析/人岗匹配/学习路径 - WebUI 五视图：驾驶舱/图谱工作台/岗位演化/匹配(单人+批量)/学习路径 - 设置中心(config.json)/Token鉴权/SQLite状态库/语义向量通道(BGE-M3本地或联网API) - 71 个 pytest 用例；数据目录仅保留结构(.gitkeep)，数据由 scripts/generate_dataset.py 复现
2026-08-03 13:15:35 +08:00
commit a10442d78c
78 changed files with 12860 additions and 0 deletions
@@ -0,0 +1,139 @@
+"""CareerNexus 全链路数据模型（pydantic v2）。
+
+覆盖：JD 原始记录、结构化抽取结果、岗位定义、图谱观察、
+变更事件、人岗匹配结果、简历画像与人机协同审核记录。
+"""
+from __future__ import annotations
+
+from datetime import date
+from typing import Literal, Optional
+
+from pydantic import BaseModel, Field
+
+
+class JDRecord(BaseModel):
+    """一条招聘 JD 原始记录。source_id 由接入层分配（文件名#行号），不可变。"""
+
+    jid: str
+    job_title: str
+    company: str
+    city: str = ""
+    salary: str = ""
+    industry: str = ""            # 招聘平台标注的所属行业
+    publish_date: date
+    source: str = ""
+    url: str = ""
+    text: str
+    source_id: str = ""           # 形如 batch_2023.jsonl#17
+    weight: float = 1.0           # 清洗阶段赋予的时间衰减权重
+    is_duplicate: bool = False    # 近重复（抄袭）降权标记
+    dup_of: Optional[str] = None  # 指向被保留的最早来源 jid
+    is_noise: bool = False        # 噪声（广告/无关条款）标记
+
+
+class ExtractionResult(BaseModel):
+    """从单条 JD 文本抽取出的结构化岗位定义。"""
+
+    jid: str = ""
+    job_title: str = ""
+    responsibilities: list[str] = Field(default_factory=list)
+    required_skills: list[str] = Field(default_factory=list)
+    preferred_skills: list[str] = Field(default_factory=list)
+    scenarios: list[str] = Field(default_factory=list)
+    evidence: dict[str, str] = Field(default_factory=dict)  # 字段 -> 证据片段
+    confidence: float = 0.0
+    extractor: str = "offline"
+    prompt_version: str = "offline-v1"
+
+
+class JobDefinition(BaseModel):
+    """聚合后的岗位定义（图谱中的 Job 节点属性）。"""
+
+    job_id: str
+    title: str
+    category: str = ""
+    industries: list[str] = Field(default_factory=list)  # 归属行业（1-2 个）
+    required_skills: list[str] = Field(default_factory=list)
+    preferred_skills: list[str] = Field(default_factory=list)
+    responsibilities: list[str] = Field(default_factory=list)
+    scenarios: list[str] = Field(default_factory=list)
+    expected_years: int = 3
+    status: Literal["active", "pending", "rejected"] = "active"
+    source_count: int = 0    # 支撑 JD 数
+    company_count: int = 0   # 独立企业数
+    # 候选新岗位的支撑证据（新岗位发现时填写）：支撑 JD 的 source_id 与出现季度窗口，
+    # 审核入库时用于生成真实的 REQUIRES 区间、来源列表与演化事件。
+    support_source_ids: list[str] = Field(default_factory=list)
+    support_windows: list[str] = Field(default_factory=list)
+
+
+class GraphObservation(BaseModel):
+    """一次岗位-技能关系观察（带时间窗，追加而不覆盖）。"""
+
+    job_id: str
+    skill: str
+    importance: Literal["required", "preferred"]
+    weight: float = 1.0
+    window: str = ""                 # 季度窗口，如 2022Q1
+    source_ids: list[str] = Field(default_factory=list)
+
+
+class ChangeEvent(BaseModel):
+    """岗位能力演化事件：新增 / 增强 / 减弱 / 退出。"""
+
+    event_id: str
+    job_id: str
+    skill: str
+    change_type: Literal["新增", "增强", "减弱", "退出"]
+    window: str
+    prev_weight: float = 0.0
+    curr_weight: float = 0.0
+    source_ids: list[str] = Field(default_factory=list)
+    description: str = ""
+    created_at: str = ""
+
+
+class ResumeProfile(BaseModel):
+    """脱敏后的简历画像。"""
+
+    name: str = ""
+    phone: str = ""
+    email: str = ""
+    years: float = 0.0
+    skills: list[str] = Field(default_factory=list)
+    scenarios: list[str] = Field(default_factory=list)
+    raw_masked_text: str = ""
+    # 结构化信息（规范简历模板用）
+    gender: str = ""                     # 性别（不脱敏，人口统计学字段）
+    education: str = ""                  # 最高学历（本科/硕士/博士…）
+    address: str = ""                    # 家庭住址/现居地（脱敏到城市）
+    photo_b64: str = ""                  # 证件照 base64（data URI，无照片为空）
+    sections: list[dict] = Field(default_factory=list)  # [{title, text}] 分节正文
+
+
+class MatchResult(BaseModel):
+    """人岗匹配结果：总分、四维分、命中/缺失/可迁移技能与学习路径。"""
+
+    job_id: str
+    job_title: str = ""
+    total_score: float = 0.0
+    dimension_scores: dict[str, float] = Field(default_factory=dict)
+    matched_required: list[str] = Field(default_factory=list)
+    missing_required: list[str] = Field(default_factory=list)
+    matched_preferred: list[str] = Field(default_factory=list)
+    missing_preferred: list[str] = Field(default_factory=list)
+    transferable_skills: list[str] = Field(default_factory=list)
+    learning_path: list[dict] = Field(default_factory=list)
+    is_match: bool = False
+
+
+class ReviewRecord(BaseModel):
+    """人机协同审核留痕。"""
+
+    candidate_id: str
+    action: Literal["accept", "modify", "reject"]
+    operator: str
+    reason: str = ""
+    before: dict = Field(default_factory=dict)
+    after: dict = Field(default_factory=dict)
+    time: str = ""