岗位覆盖扩充至 26 个 + 图谱岗位子图模式

- 新增 8 岗位族（大数据/机器学习/机器人/数据治理/边缘计算/物联网安全/智能系统架构/隐私计算），词表 161→179 - 图谱详情面板新增'岗位子图'模式（只看该岗位及一跳邻居，徽标可退出） - 测试集扩至 176 条、匹配标注 52 对；real_jd_500 F1 99.82%；合成三项 100% 保持
2026-08-12 15:58:22 +08:00
parent 1722c00249
commit 33aee6b8ae
8 changed files with 296 additions and 20 deletions
@@ -57,10 +57,10 @@ SKILLS = [
    ("Struts", "后端框架", [], "L1", ["Java"]), ("Servlet", "后端框架", [], "L1", ["Java"]),
    ("JSP", "后端框架", [], "L1", ["Java"]), ("SSM", "后端框架", [], "L2", ["Spring", "MyBatis"]),
    # 前端
-    ("Vue", "前端", ["Vue.js"], "L2", ["JavaScript"]), ("React", "前端", ["React.js"], "L2", ["JavaScript"]),
+    ("Vue", "前端", ["Vue.js"], "L2", ["JavaScript"]), ("React", "前端", ["React.js", "ReactJS"], "L2", ["JavaScript"]),
    ("Angular", "前端", ["AngularJS"], "L2", ["TypeScript"]), ("jQuery", "前端", [], "L1", ["JavaScript"]),
    ("Webpack", "前端", [], "L2", ["JavaScript"]), ("Vite", "前端", [], "L2", ["JavaScript"]),
-    ("Node.js", "前端", ["Node"], "L2", ["JavaScript"]), ("小程序开发", "前端", ["微信小程序"], "L2", ["JavaScript"]),
+    ("Node.js", "前端", ["Node", "NodeJS"], "L2", ["JavaScript"]), ("小程序开发", "前端", ["微信小程序"], "L2", ["JavaScript"]),
    ("Element UI", "前端", [], "L1", ["Vue"]), ("Ant Design", "前端", [], "L1", ["React"]),
    ("HTML", "前端", ["HTML5"], "L1", []), ("CSS", "前端", ["CSS3"], "L1", []),
    ("Tailwind CSS", "前端", [], "L2", ["CSS"]), ("低代码平台", "前端", [], "L2", []),
@@ -141,6 +141,28 @@ SKILLS = [
    ("Tableau", "数据分析", [], "L2", ["数据可视化"]), ("Power BI", "数据分析", ["PowerBI"], "L2", ["数据可视化"]),
    ("SPSS", "数据分析", [], "L2", []), ("数据可视化", "数据分析", [], "L2", ["数据分析"]),
    ("A/B测试", "数据分析", ["AB测试"], "L2", ["数据分析"]),
+    # 机器人与智能系统（岗位覆盖扩展）
+    ("ROS", "AI算法", ["机器人操作系统"], "L2", ["C++", "Linux"]),
+    ("SLAM", "AI算法", ["同步定位与建图"], "L3", ["计算机视觉"]),
+    ("路径规划", "AI算法", [], "L3", ["机器学习"]),
+    # 数据治理
+    ("数据治理", "大数据", [], "L2", ["SQL"]),
+    ("数据脱敏", "大数据", ["数据遮蔽"], "L2", ["SQL"]),
+    ("元数据管理", "大数据", ["元数据"], "L2", ["数据治理"]),
+    ("数据血缘", "大数据", [], "L3", ["元数据管理"]),
+    ("湖仓一体", "大数据", ["实时湖仓"], "L3", ["Hive"]),
+    # 边缘计算
+    ("边缘推理", "物联网", ["边缘推理框架"], "L3", ["边缘计算", "深度学习"]),
+    ("TensorRT", "AI算法", [], "L3", ["深度学习"]),
+    ("KubeEdge", "云原生", [], "L3", ["Kubernetes", "边缘计算"]),
+    # 安全与隐私计算
+    ("零信任", "安全", ["零信任架构"], "L3", []),
+    ("入侵检测", "安全", [], "L2", ["Linux"]),
+    ("等保合规", "安全", [], "L2", []),
+    ("联邦学习", "AI算法", [], "L3", ["机器学习"]),
+    ("多方安全计算", "安全", ["MPC"], "L3", []),
+    ("同态加密", "安全", [], "L3", []),
+    ("差分隐私", "安全", [], "L3", ["机器学习"]),
 ]

 SCENARIOS = ["电商", "金融", "物流", "社交", "教育", "医疗", "政务", "游戏",
@@ -152,11 +174,11 @@ INDUSTRIES = ["互联网/软件", "人工智能", "金融科技", "智能制造"

 # ---------------------------------------------------------------- 岗位原型
 def arc(title, category, years, salary, scenarios, industries,
-        duty_tmpls, duty_objs, timeline, volumes):
+        duty_tmpls, duty_objs, timeline, volumes, test_n=8):
    return dict(title=title, category=category, years=years, salary=salary,
                scenarios=scenarios, industries=industries,
                duty_tmpls=duty_tmpls, duty_objs=duty_objs,
-                timeline=timeline, volumes=volumes)
+                timeline=timeline, volumes=volumes, test_n=test_n)

 BACKEND_DUTIES = ["负责{o}的设计与开发", "参与{o}的性能优化与重构", "配合产品团队完成{o}的需求评审",
                  "编写{o}的技术文档与接口文档", "承担{o}的线上问题排查与修复", "推动{o}的代码评审与质量改进"]
@@ -325,6 +347,69 @@ ARCHETYPES = [
        ["营销文案生成", "智能客服话术", "内容创作", "教学辅导", "商品描述", "对话流程"],
        [(2024, 2026, ["提示词工程", "大模型应用开发", "Python", "数据分析"], ["LangChain", "RAG", "AI产品"])],
        {2024: 2, 2025: 6, 2026: 10}),
+    # —— 岗位覆盖扩展（8 个既有岗位族，2019 年前已存在，支撑赛题领域覆盖） ——
+    # 大数据开发：2019-2021 Hadoop 离线系 → 2022+ Flink 实时/湖仓一体（演化信号）
+    arc("大数据开发工程师", "大数据", 3, "16K-32K", ["电商", "金融", "短视频"],
+        ["互联网/软件", "金融科技"],
+        ["负责{o}的离线计算任务开发", "搭建{o}的实时计算链路", "参与{o}的数据模型设计",
+         "优化{o}的任务性能与资源消耗", "维护{o}的调度依赖与数据质量"],
+        ["离线数仓", "实时数仓", "用户行为日志", "流量数据", "交易数据", "数据集市"],
+        [(2019, 2021, ["SQL", "Hadoop", "Hive", "Spark", "HDFS"], ["Sqoop", "HBase", "Scala"]),
+         (2022, 2026, ["SQL", "Spark", "Flink", "Kafka", "Hive"], ["ClickHouse", "Doris", "湖仓一体"])],
+        {2019: 4, 2020: 4, 2021: 4, 2022: 5, 2023: 5, 2024: 6, 2025: 6, 2026: 6}, test_n=4),
+    # 机器学习工程师：2023+ 加分项出现"模型微调/大模型应用开发"（演化信号）
+    arc("机器学习工程师", "AI算法", 3, "18K-35K", ["金融", "电商", "广告"],
+        ["人工智能"],
+        ["负责{o}的特征工程与模型训练", "参与{o}的离线评估与线上实验", "优化{o}的推理性能与资源占用",
+         "建设{o}的样本与特征流水线", "跟进{o}的算法迭代与复盘"],
+        ["风控模型", "搜索排序", "召回策略", "销量预测", "异常检测", "用户分层"],
+        [(2019, 2022, ["Python", "机器学习", "Scikit-learn", "SQL", "XGBoost"], ["LightGBM", "TensorFlow", "Spark"]),
+         (2023, 2026, ["Python", "机器学习", "深度学习", "PyTorch", "XGBoost"], ["模型微调", "大模型应用开发", "LightGBM"])],
+        {2019: 4, 2020: 4, 2021: 4, 2022: 5, 2023: 5, 2024: 6, 2025: 6, 2026: 6}, test_n=4),
+    arc("智能机器人算法工程师", "AI算法", 3, "20K-40K", ["智能制造", "物流", "出行"],
+        ["人工智能", "智能制造"],
+        ["负责{o}的算法研发与调优", "参与{o}的仿真验证与实机部署", "优化{o}的实时性与鲁棒性",
+         "建设{o}的数据闭环与评测体系", "跟进{o}的前沿方案并落地"],
+        ["SLAM 建图", "定位导航", "运动规划", "多传感器融合", "机械臂控制", "避障策略"],
+        [(2019, 2026, ["C++", "Python", "ROS", "SLAM", "路径规划"], ["深度学习", "强化学习", "OpenCV"])],
+        {2019: 4, 2020: 4, 2021: 4, 2022: 5, 2023: 5, 2024: 6, 2025: 6, 2026: 6}, test_n=4),
+    arc("数据治理工程师", "大数据", 3, "15K-30K", ["金融", "政务", "医疗"],
+        ["金融科技", "互联网/软件"],
+        ["负责{o}的标准制定与落地", "建设{o}的元数据与血缘体系", "推进{o}的质量监控与整改",
+         "制定{o}的分级分类与脱敏策略", "组织{o}的盘点与确权工作"],
+        ["数据资产", "主数据", "指标口径", "敏感数据", "数据目录", "质量规则"],
+        [(2019, 2026, ["SQL", "数据治理", "元数据管理", "数据脱敏", "Python"], ["数据血缘", "Hive", "Spark"])],
+        {2019: 4, 2020: 4, 2021: 4, 2022: 5, 2023: 5, 2024: 6, 2025: 6, 2026: 6}, test_n=4),
+    arc("边缘计算工程师", "物联网", 3, "16K-30K", ["智能制造", "安防", "物流"],
+        ["物联网", "智能制造"],
+        ["负责{o}的部署与调优", "参与{o}的模型压缩与推理加速", "建设{o}的云边协同链路",
+         "优化{o}的资源占用与稳定性", "编写{o}的技术文档"],
+        ["边缘网关", "边缘节点", "端侧推理", "视频分析", "设备接入", "边云协同"],
+        [(2019, 2021, ["C++", "Python", "Linux", "MQTT", "嵌入式开发"], ["Docker", "边缘计算", "OpenCV"]),
+         (2022, 2026, ["Python", "边缘计算", "Docker", "Linux", "MQTT"], ["边缘推理", "TensorRT", "KubeEdge"])],
+        {2019: 4, 2020: 4, 2021: 4, 2022: 5, 2023: 5, 2024: 6, 2025: 6, 2026: 6}, test_n=4),
+    arc("物联网安全工程师", "物联网", 3, "16K-32K", ["智能制造", "安防", "政务"],
+        ["物联网", "智慧城市"],
+        ["负责{o}的安全评估与加固", "建设{o}的入侵检测与响应体系", "参与{o}的固件安全审计",
+         "制定{o}的接入认证策略", "跟踪{o}的漏洞情报与处置"],
+        ["设备接入", "设备网络", "边缘网关", "固件", "通信协议", "密钥体系"],
+        [(2019, 2026, ["Linux", "Python", "入侵检测", "零信任", "MQTT"], ["等保合规", "嵌入式开发", "云计算"])],
+        {2019: 4, 2020: 4, 2021: 4, 2022: 5, 2023: 5, 2024: 6, 2025: 6, 2026: 6}, test_n=4),
+    arc("智能系统架构师", "云原生", 5, "30K-60K·14薪", ["金融", "政务", "智能制造"],
+        ["互联网/软件", "人工智能"],
+        ["负责{o}的整体架构设计", "主导{o}的技术选型与评审", "制定{o}的容量与容灾方案",
+         "推动{o}的架构演进与落地", "沉淀{o}的架构规范与最佳实践"],
+        ["智能平台", "业务中台", "云边端协同", "高可用体系", "多云架构", "技术路线"],
+        [(2019, 2021, ["分布式系统", "微服务", "云计算", "高并发", "Linux"], ["Docker", "Kubernetes", "Service Mesh"]),
+         (2022, 2026, ["分布式系统", "微服务", "Kubernetes", "云计算", "高并发"], ["Service Mesh", "边缘计算", "物联网平台"])],
+        {2019: 4, 2020: 4, 2021: 4, 2022: 5, 2023: 5, 2024: 6, 2025: 6, 2026: 6}, test_n=4),
+    arc("隐私计算工程师", "AI算法", 4, "25K-45K", ["金融", "政务", "医疗"],
+        ["人工智能", "金融科技"],
+        ["负责{o}的方案设计与实现", "参与{o}的性能优化与工程化", "建设{o}的协同计算链路",
+         "评估{o}的安全性与合规性", "跟进{o}的最新研究成果"],
+        ["联邦建模", "多方联合统计", "安全求交", "数据协作", "密文计算", "隐私保护"],
+        [(2019, 2026, ["Python", "机器学习", "联邦学习", "同态加密", "多方安全计算"], ["差分隐私", "模型微调", "Spark"])],
+        {2019: 4, 2020: 4, 2021: 4, 2022: 5, 2023: 5, 2024: 6, 2025: 6, 2026: 6}, test_n=4),
 ]

 COMPANY_PRE = ["星澜", "云启", "数联", "智汇", "蓝湾", "极光", "恒宇", "锐思", "博远", "辰安",
@@ -779,8 +864,8 @@ def main() -> None:
    # 5. 测试集（与 raw 不同 jid 命名空间）+ 标准答案
    testset, gold = [], {}
    tseq = 0
-    per_arc = 8  # 18 岗位 × 8 = 144 条 >= 120
    for a in ARCHETYPES:
+        per_arc = a["test_n"]  # 原 18 岗位 × 8 + 扩展 8 岗位 × 4 = 176 条 >= 120
        years = sorted(a["volumes"])
        for _ in range(per_arc):
            tseq += 1