Install
openclaw skills install smyx-depression-behavioral-markers-analysisUsing fixed home cameras (bedroom and dining area), the system analyzes the multi-day behavior pattern of elderly people or solo-living individuals, detecting daily lying-in-bed duration (continuous lying > 20 hours per day) and a sharp drop in eating frequency / duration (e.g., daily eating-action count below 50% of personal baseline). When these behavioral changes persist beyond a configured threshold (e.g., 3 days), the system outputs a behavioral-change report to remind family members or community doctors about possible depressive tendency or other health issues. This skill is ONLY a behavioral-observation aid and is NOT a medical diagnostic tool. Application scenarios: solo-living elderly homes, remote mental-health monitoring, community elderly care. The system generates a daily behavior summary and pushes alerts when an abnormal pattern is detected. Skill features: depression in the elderly often presents as decreased activity, reduced appetite, and increased bed time. AI auto-monitoring of these behavior changes can issue early signals before family or doctors notice, supporting timely intervention, reducing suicide risk, and improving quality of life. Can be integrated into home-care cameras or health-management platforms as a practical mental-health monitoring tool. | 通过家庭固定摄像头(卧室和餐厅区域),分析老年人或独居者连续多日的行为模式,检测卧床时长(连续卧床超过20小时/天)以及进食频次/时长骤减(如每日进食动作次数低于历史基线的50%)。当这些行为变化持续超过设定天数(如3天)时,输出行为变化报告,提醒家属或社区医生关注可能存在的抑郁倾向或其他健康问题。该技能仅为行为观察辅助工具,不作为医学诊断依据。应用场景:独居老人家庭、精神健康远程监测、社区养老。系统每日生成行为摘要,当检测到异常行为模式时推送提醒。技能特点:老年人抑郁症常表现为活动减少、食欲下降、卧床时间增多。通过AI自动监测这些行为变化,可在家属或医生尚未察觉时发出早期信号,有助于及时干预,降低自杀风险,改善生活质量。该技能可集成到居家养老摄像头或健康管理平台中,成为精神健康监测的实用工具。
openclaw skills install smyx-depression-behavioral-markers-analysisUsing fixed home cameras (bedroom and dining area), the system analyzes the multi-day behavior pattern of elderly people or solo-living individuals, detecting daily lying-in-bed duration (continuous lying > 20 hours per day) and a sharp drop in eating frequency / duration (e.g., daily eating-action count below 50% of personal baseline). When these behavioral changes persist beyond a configured threshold (e.g., 3 days), the system outputs a behavioral-change report to remind family members or community doctors about possible depressive tendency or other health issues. This skill is ONLY a behavioral-observation aid and is NOT a medical diagnostic tool. Application scenarios: solo-living elderly homes, remote mental-health monitoring, community elderly care. The system generates a daily behavior summary and pushes alerts when an abnormal pattern is detected. Skill features: depression in the elderly often presents as decreased activity, reduced appetite, and increased bed time. AI auto-monitoring of these behavior changes can issue early signals before family or doctors notice, supporting timely intervention, reducing suicide risk, and improving quality of life. Can be integrated into home-care cameras or health-management platforms as a practical mental-health monitoring tool.
通过家庭固定摄像头(卧室和餐厅区域),分析老年人或独居者连续多日的行为模式,检测卧床时长(连续卧床超过20小时/天)以及进食频次/时长骤减(如每日进食动作次数低于历史基线的50%)。当这些行为变化持续超过设定天数(如3天)时,输出行为变化报告,提醒家属或社区医生关注可能存在的抑郁倾向或其他健康问题。该技能仅为行为观察辅助工具,不作为医学诊断依据。应用场景:独居老人家庭、精神健康远程监测、社区养老。系统每日生成行为摘要,当检测到异常行为模式时推送提醒。技能特点:老年人抑郁症常表现为活动减少、食欲下降、卧床时间增多。通过AI自动监测这些行为变化,可在家属或医生尚未察觉时发出早期信号,有助于及时干预,降低自杀风险,改善生活质量。该技能可集成到居家养老摄像头或健康管理平台中,成为精神健康监测的实用工具。
假设你是一个专业的老年人行为健康监测 AI。你的任务是分析家庭固定摄像头(卧室和餐厅区域)的连续视频(至少 24 小时),检测卧床时长(统计一天内卧床总时长)以及进食行为(识别手部抓握餐具送入口中的动作次数和时长)。对比历史基线(过去 7-14 天的个人平均数据),当卧床时长超过 20 小时/天或进食动作次数/时长低于基线的 50% 时,输出行为变化报告。不要提供医疗诊断,仅输出基于视觉的行为统计和变化提示。
python -m scripts.smyx_depression_behavioral_markers_analysis --list --open-id 参数调用 API
查询云端的历史报告数据requests>=2.28.0
在执行抑郁症辅助行为标记分析前,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_depression_behavioral_markers_analysis 处理输入(必须在技能根目录下运行脚本)--input: 本地家庭固定摄像头(卧室+餐厅区域,≥24h)视频文件路径--url: 网络家庭固定摄像头(卧室+餐厅区域,≥24h)视频 URL 地址(API 服务自动下载)--pet-type: 类别标识,老年人行为健康监测场景默认 other--open-id: 当前用户的 open-id(必填,按上述流程获取)--list: 显示抑郁症辅助行为标记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)strong_signal 或老人有任何自伤/自杀言语或行为时,必须在提醒中附心理援助热线 010-82951332 / 400-161-9995并强烈建议家属立即介入抑郁辅助行为标记报告-{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 | 风险信号/异常模式 | 分析时间 | 点击查看 |
|---|---|---|---|
| 抑郁辅助行为标记报告-20260312172200001 | notable_signal / both(卧床 21h + 进食 -60%,连续 3 天) | 2026-03-12 17:22:00 | 🔗 查看报告 |
# 分析本地连续 24h+ 卧室+餐厅视频(以下只是示例,禁止直接使用openclaw-control-ui 作为 open-id)
python -m scripts.smyx_depression_behavioral_markers_analysis --input /path/to/24h_home.mp4 --open-id your-open-id
# 分析网络连续 24h+ 卧室+餐厅视频(以下只是示例,禁止直接使用openclaw-control-ui 作为 open-id)
python -m scripts.smyx_depression_behavioral_markers_analysis --url https://example.com/24h_home.mp4 --open-id your-open-id
# 显示历史抑郁症辅助行为标记报告(自动触发关键词:查看抑郁行为标记历史报告、行为变化报告清单等)
python -m scripts.smyx_depression_behavioral_markers_analysis --list --open-id your-open-id
# 输出精简报告
python -m scripts.smyx_depression_behavioral_markers_analysis --input 24h.mp4 --open-id your-open-id --detail basic
# 保存结果到文件
python -m scripts.smyx_depression_behavioral_markers_analysis --input 24h.mp4 --open-id your-open-id --output result.json