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

scripts/run_demo.py

@@ -0,0 +1,68 @@
+"""端到端冒烟：生成数据（若缺失）→ 跑 pipeline → 打印图谱规模、演化事件数、一个匹配示例。
+
+不需要启动服务，用于快速验证全链路可用。
+"""
+from __future__ import annotations
+
+import json
+import sys
+from pathlib import Path
+
+ROOT = Path(__file__).resolve().parents[1]
+sys.path.insert(0, str(ROOT))
+
+from app.config import load_config, resolve  # noqa: E402
+from app.graph.tkg import TemporalKG  # noqa: E402
+from app.match.engine import MatchEngine  # noqa: E402
+from app.match.resume import parse_resume  # noqa: E402
+from app.models import ResumeProfile  # noqa: E402
+from app.services.pipeline import run_pipeline  # noqa: E402
+from app.extract.base import load_lexicon  # noqa: E402
+
+
+def main() -> None:
+    if not (ROOT / "data" / "jd_raw").exists():
+        print("数据不存在，先生成数据集……")
+        import subprocess
+        subprocess.run([sys.executable, str(ROOT / "scripts" / "generate_dataset.py")],
+                       check=True)
+
+    print("=" * 56)
+    print("步骤 1/3：端到端 pipeline（导入→清洗→抽取→图谱→演化→发现）")
+    print("=" * 56)
+    stats = run_pipeline(load_config())
+    print(json.dumps(stats["stages"], ensure_ascii=False, indent=2))
+
+    print("\n步骤 2/3：图谱规模与演化事件")
+    kg = TemporalKG.load(resolve(load_config(), "graph_path"))
+    print("图谱统计：", kg.stats())
+    java_id = "job_Java开发工程师"
+    java_events = kg.events_of(java_id)
+    print(f"Java开发工程师 演化事件 {len(java_events)} 条，示例：")
+    for ev in java_events[:4]:
+        print("  -", ev.description)
+    snap_2020 = kg.snapshot(java_id, "2020-06-01")
+    snap_2025 = kg.snapshot(java_id, "2025-06-01")
+    print("2020 时点技能：", sorted(s["skill"] for s in snap_2020["skills"])[:8])
+    print("2025 时点技能：", sorted(s["skill"] for s in snap_2025["skills"])[:8])
+
+    print("\n步骤 3/3：人岗匹配示例（resume_full.txt vs Java开发工程师）")
+    text = (ROOT / "data" / "resumes" / "resume_full.txt").read_text(encoding="utf-8")
+    profile = parse_resume(text)
+    job = kg.jobs[java_id]
+    result = MatchEngine(load_lexicon()).match(profile, job)
+    print(f"脱敏后姓名: {profile.name}  手机: {profile.phone}  邮箱: {profile.email}")
+    print(f"总分 {result.total_score}，维度 {result.dimension_scores}，是否匹配 {result.is_match}")
+    print("缺失必备技能：", result.missing_required)
+    for stage in result.learning_path:
+        print(" ", stage["goal"])
+
+    # 断言冒烟通过的关键指标
+    assert kg.stats()["jobs"] >= 15, "岗位节点数量异常"
+    assert kg.stats()["events"] > 0, "未产生演化事件"
+    assert result.total_score >= 60, "完整简历应匹配 Java 岗位"
+    print("\n冒烟测试通过 [OK]")
+
+
+if __name__ == "__main__":
+    main()