Install
openclaw skills install smyx-trauma-stress-behavior-detection-analysisUsing fixed cameras in emergency shelters, the system analyzes video of disaster-affected crowds to detect typical acute stress reactions: stupor (prolonged motionless state with no response to external stimulation), tremor (involuntary shaking of body or limbs), unresponsiveness (no orientation or avoidance reaction to calls or sounds), and hypervigilance (frequent scanning of surroundings, startle reactions). When these behaviors are detected, the system outputs a psychological crisis alert to notify on-site psychological-rescue teams to intervene in time, provide emergency psychological support, and help prevent acute stress disorder or post-traumatic stress disorder. Application scenarios: emergency shelters for earthquakes, floods and other natural disasters; wartime air-defense facilities; temporary accident-site resettlement points. The system monitors in real time, displays alerts on command-center screens with location markers, and guides psychological-rescue staff to the site. Skill features: after earthquakes, floods and similar disasters, affected people may develop acute stress disorder; without timely intervention this can progress to PTSD. AI auto-identification of stupor / tremor and other behavioral signals helps rescue teams quickly locate those needing psychological support, improving rescue efficiency and reducing long-term trauma. Can be integrated into emergency command systems or mobile-shelter security devices as an important aid for disaster psychological rescue. | 通过应急避难所内的固定摄像头,分析受灾人群的行为视频,检测急性应激反应下的典型行为:木僵(长时间静止不动,对外界刺激无反应)、颤抖(身体或四肢不自主抖动)、无反应(对呼唤、声响等刺激没有定向或回避反应)以及过度警觉(频繁环顾四周、惊跳反应)。当检测到上述行为时,输出心理危机预警,提示现场心理救援团队及时介入,提供紧急心理支持,预防急性应激障碍或创伤后应激障碍。应用场景:地震、洪水等自然灾害应急避难所、战时防空设施、事故现场临时安置点。系统实时监测,当发现心理创伤行为时,通过指挥中心屏幕预警,并标注位置,引导心理救援人员前往。技能特点:地震、洪水等灾害发生后,受灾人群可能出现急性应激障碍,若不及时干预可能发展为创伤后应激障碍。通过AI自动识别木僵、颤抖等行为信号,可帮助救援团队快速定位需要心理支持的人员,提高救援效率,减少长期心理创伤。该技能可集成到应急指挥系统或移动避难所安防设备中,成为灾害心理救援的重要辅助工具。
openclaw skills install smyx-trauma-stress-behavior-detection-analysisUsing fixed cameras in emergency shelters, the system analyzes video of disaster-affected crowds to detect typical acute stress reactions: stupor (prolonged motionless state with no response to external stimulation), tremor (involuntary shaking of body or limbs), unresponsiveness (no orientation or avoidance reaction to calls or sounds), and hypervigilance (frequent scanning of surroundings, startle reactions). When these behaviors are detected, the system outputs a psychological crisis alert to notify on-site psychological-rescue teams to intervene in time, provide emergency psychological support, and help prevent acute stress disorder or post-traumatic stress disorder. Application scenarios: emergency shelters for earthquakes, floods and other natural disasters; wartime air-defense facilities; temporary accident-site resettlement points. The system monitors in real time, displays alerts on command-center screens with location markers, and guides psychological-rescue staff to the site. Skill features: after earthquakes, floods and similar disasters, affected people may develop acute stress disorder; without timely intervention this can progress to PTSD. AI auto-identification of stupor / tremor and other behavioral signals helps rescue teams quickly locate those needing psychological support, improving rescue efficiency and reducing long-term trauma. Can be integrated into emergency command systems or mobile-shelter security devices as an important aid for disaster psychological rescue.
通过应急避难所内的固定摄像头,分析受灾人群的行为视频,检测急性应激反应下的典型行为:木僵(长时间静止不动,对外界刺激无反应)、颤抖(身体或四肢不自主抖动)、无反应(对呼唤、声响等刺激没有定向或回避反应)以及过度警觉(频繁环顾四周、惊跳反应)。当检测到上述行为时,输出心理危机预警,提示现场心理救援团队及时介入,提供紧急心理支持,预防急性应激障碍或创伤后应激障碍。应用场景:地震、洪水等自然灾害应急避难所、战时防空设施、事故现场临时安置点。系统实时监测,当发现心理创伤行为时,通过指挥中心屏幕预警,并标注位置,引导心理救援人员前往。技能特点:地震、洪水等灾害发生后,受灾人群可能出现急性应激障碍,若不及时干预可能发展为创伤后应激障碍。通过AI自动识别木僵、颤抖等行为信号,可帮助救援团队快速定位需要心理支持的人员,提高救援效率,减少长期心理创伤。该技能可集成到应急指挥系统或移动避难所安防设备中,成为灾害心理救援的重要辅助工具。
假设你是一个专业的灾后心理危机识别 AI(必须由应急指挥中心 / 卫健委授权部署 + 现场配合持证心理救援人员)。你的任务是分析应急避难所固定摄像头的视频,检测受灾人群的急性应激行为:木僵(连续静止 ≥ 5 分钟且对外界刺激无定向反应)、颤抖(肉眼可见四肢/躯干持续抖动 ≥ 5 秒)、无反应(对声音或移动物体无定向转头/无回避)、过度警觉(频繁转头张望、惊跳反应)。当检测到这些行为时,输出心理危机预警,标注分区位置,引导救援人员前往。不提供任何临床诊断,仅输出基于视觉的行为观察结果;高危预警必须人工复核后再升级到救援调度,并按 PFA(心理急救)原则实施干预。
python -m scripts.smyx_trauma_stress_behavior_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
在执行受灾人群心理创伤行为识别前,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.smyx_trauma_stress_behavior_detection_analysis 处理输入(必须在技能根目录下运行脚本)--input: 本地应急避难所/临时安置点固定摄像头视频文件路径--url: 网络应急避难所/临时安置点固定摄像头视频 URL 地址(API 服务自动下载)--pet-type: 类别标识,灾后心理危机识别场景默认 other--open-id: 当前用户的 open-id(必填,应急指挥中心 / 心理救援团队授权)--list: 显示受灾人群心理创伤行为识别历史预警清单(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)心理危机预警-{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 | 危机等级/分区位置/主要行为 | 分析时间 | 点击查看 |
|---|---|---|---|
| 心理危机预警-20260312172200001 | psych_crisis_alert / Zone-B 中部 / 木僵 6min + 颤抖 | 2026-03-12 17:22:00 | 🔗 查看报告 |
# 分析本地避难所视频(以下只是示例,禁止直接使用openclaw-control-ui 作为 open-id)
python -m scripts.smyx_trauma_stress_behavior_detection_analysis --input /path/to/shelter.mp4 --open-id your-open-id
# 分析网络避难所视频/实时流(以下只是示例,禁止直接使用openclaw-control-ui 作为 open-id)
python -m scripts.smyx_trauma_stress_behavior_detection_analysis --url https://example.com/shelter.mp4 --open-id your-open-id
# 显示历史心理危机预警清单(自动触发关键词:查看心理危机预警历史报告、灾后心理救援清单等)
python -m scripts.smyx_trauma_stress_behavior_detection_analysis --list --open-id your-open-id
# 输出精简报告
python -m scripts.smyx_trauma_stress_behavior_detection_analysis --input sh.mp4 --open-id your-open-id --detail basic
# 保存结果到文件
python -m scripts.smyx_trauma_stress_behavior_detection_analysis --input sh.mp4 --open-id your-open-id --output result.json