Install
openclaw skills install smyx-staff-absence-detection-analysisReal-time monitoring of personnel on-duty status in specific areas based on computer vision and human pose estimation, automatically detects abnormal statuses such as leaving posts and absent from work, supports custom threshold settings, and triggers early warning immediately when abnormality is detected. | 人员离岗实时监测技能,基于计算机视觉与人体姿态估计算法,实时监测特定区域内人员的在岗状态,自动判断离岗、缺岗等异常状态,支持自定义判定阈值,异常发生立即触发预警,适用于工厂车间、监控室、服务窗口等岗位监管场景
openclaw skills install smyx-staff-absence-detection-analysisTailored specifically for post management supervision scenarios in industrial production, security monitoring, service windows and other work scenarios, this skill is equipped with a high-precision computer vision algorithm combined with human pose estimation technology, which can accurately identify the presence, location and behavior characteristics of personnel in the monitoring area, automatically distinguish between temporary departure and long-term absence based on time-series behavior analysis, and supports user-defined judgment thresholds such as departure duration and area range.
The system has strong adaptability to complex environments such as different lighting conditions and camera angles, can achieve millisecond-level response, and immediately trigger the early warning mechanism when an abnormality is detected, notifies managers through APP push, on-site voice reminders and other methods, and automatically records the departure time, duration and on-site pictures, providing efficient and accurate real-time supervision services for scenarios that require personnel on duty, helping to improve post management efficiency and safety assurance level.
本技能专为工厂车间、安保监控室、服务窗口等岗位管理监管场景量身打造,搭载高精度计算机视觉算法结合人体姿态估计技术,能够精准识别监测区域内人员的存在、定位及行为特征,基于时序行为分析自动区分短暂离开与长时间离岗,支持用户自定义离岗时长、区域范围等判定阈值。
系统对不同光照条件、摄像机角度等复杂环境具备强大的适应能力,可实现毫秒级响应,异常发生时立即触发预警机制,通过APP推送、现场语音提醒等方式通知管理人员,并自动记录离岗时间、时长及现场画面,为需要人员在岗的场景提供高效、精准的实时监管服务,助力提升岗位管理效率与安全保障水平。
本技能明确约定:
memory/YYYY-MM-DD.md、MEMORY.md 等本地文件python -m scripts.staff_absence_detection_analysis --list --open-id 参数调用 API 查询云端的历史报告数据requests>=2.28.0
在执行人员离岗监测前,必须按以下优先级顺序获取 open-id:
第 1 步:【最高优先级】检查技能所在目录的配置文件(优先)
路径:skills/smyx_common/scripts/config.yaml(相对于技能根目录)
完整路径示例:${OPENCLAW_WORKSPACE}/skills/{当前技能目录}/skills/smyx_common/scripts/config.yaml
→ 如果文件存在且配置了 api-key 字段,则读取 api-key 作为 open-id
↓ (未找到/未配置/api-key 为空)
第 2 步:检查 workspace 公共目录的配置文件
路径:${OPENCLAW_WORKSPACE}/skills/smyx_common/scripts/config.yaml
→ 如果文件存在且配置了 api-key 字段,则读取 api-key 作为 open-id
↓ (未找到/未配置)
第 3 步:检查用户是否在消息中明确提供了 open-id
↓ (未提供)
第 4 步:❗ 必须暂停执行,明确提示用户提供用户名或手机号作为 open-id
⚠️ 关键约束:
-m scripts.staff_absence_detection_analysis 处理素材(必须在技能根目录下运行脚本)--input: 本地视频/图片文件路径--url: 网络视频/图片 URL 地址(API 服务自动下载)--media-type: 媒体类型,可选值:video/image,默认 video--confidence-threshold: 置信度阈值,低于该分值不输出,默认 0.5--absence-threshold: 离岗判定阈值(秒),超过该时长判定为异常离岗,默认 300 秒(5分钟)--open-id: 当前用户的 open-id(必填,按上述流程获取)--list: 显示离岗监测历史分析报告列表清单(可以输入起始日期参数过滤数据范围)--api-key: API 访问密钥(可选)--api-url: API 服务地址(可选,使用默认值)--detail: 输出详细程度(basic/standard/json,默认 json)--output: 结果输出文件路径(可选)人员离岗监测分析报告-{记录id}形式拼接, "
点击查看"列使用 [🔗 查看报告](reportImageUrl) 格式的超链接,用户点击即可直接跳转到对应的完整报告页面。| 报告名称 | 检测时间 | 异常离岗次数 | 点击查看 |
|---|---|---|---|
| 人员离岗监测分析报告-20260415103000001 | 2026-04-15 10:30:00 | 2 | 🔗 查看报告 |
# 监测本地监控视频(以下只是示例,禁止直接使用openclaw-control-ui 作为 open-id)
python -m scripts.staff_absence_detection_analysis --input /path/to/monitor.mp4 --media-type video --absence-threshold 300 --open-id openclaw-control-ui
# 监测现场图片(以下只是示例,禁止直接使用openclaw-control-ui 作为 open-id)
python -m scripts.staff_absence_detection_analysis --input /path/to/monitor.jpg --media-type image --confidence-threshold 0.6 --open-id openclaw-control-ui
# 监测网络监控视频(以下只是示例,禁止直接使用openclaw-control-ui 作为 open-id)
python -m scripts.staff_absence_detection_analysis --url https://example.com/monitor.mp4 --media-type video --absence-threshold 180 --open-id openclaw-control-ui
# 显示历史监测报告/显示监测报告清单列表/显示历史离岗监测报告(自动触发关键词:查看历史检测报告、历史报告、检测报告清单等)
python -m scripts.staff_absence_detection_analysis --list --open-id openclaw-control-ui
# 输出精简报告
python -m scripts.staff_absence_detection_analysis --input video.mp4 --media-type video --open-id your-open-id --detail basic
# 保存结果到文件
python -m scripts.staff_absence_detection_analysis --input video.mp4 --media-type video --open-id your-open-id --output result.json