Install
openclaw skills install smyx-elderly-medication-compliance-analysisUsing a fixed camera installed above or beside the home medication area, the system monitors the elderly person's full medication process in real time. With pose estimation and object detection, it recognizes three key steps: (1) picking up — hand takes a tablet/capsule out of the pill box; (2) to-mouth — hand brings the medication to the lips; (3) swallowing — throat/jaw movement indicating a swallow. When a step is missing (e.g., picked up but not brought to mouth, or brought to mouth but no swallow), the case is recorded as 'medication not completed' and an alert is pushed to family members or caregivers. This skill helps ensure chronic-disease elders take medication on time and in the right dose, preventing missed or wrong doses. Application scenarios: chronic-disease elder households, nursing homes, community rehab centers. The system auto-runs at scheduled medication times and generates compliance reports after each session. Skill features: missed/wrong doses are a major cause of poor chronic-disease control and ER visits among elders. AI verification of pick-up / to-mouth / swallow greatly improves medication safety and reduces medical cost. Can be integrated into smart-home cameras or elderly-care management systems as a key tool for chronic-disease management. | 通过家庭药箱区域上方或侧方的固定摄像头,实时监测老年人取药、服药的全过程,利用姿态估计和目标检测技术识别以下三个关键步骤:①取药(手从药盒中取出药片/胶囊)、②送入口中(手部将药物送至嘴边)、③吞咽(喉部运动或颈部吞咽动作)。当系统检测到缺步骤(例如取药后未送入口中,或送入口中后无吞咽)时,记录为'未完成服药',并向家属或护理人员推送提醒。该技能有助于确保慢性病老人按时按量服药,防止漏服或错服。应用场景:老年慢性病家庭、养老院、社区康复中心。系统在设定的服药时间点自动开启监测,完成服药后生成依从性报告。技能特点:老年人漏服或错服药物是导致慢性病控制不佳和急诊入院的重要原因。通过AI自动确认取药、入口、吞咽三个步骤,可大幅提高用药安全性,降低医疗成本。该技能可集成到智能家居摄像头或养老管理系统中,成为慢性病管理的关键工具。
openclaw skills install smyx-elderly-medication-compliance-analysisUsing a fixed camera installed above or beside the home medication area, the system monitors the elderly person's full medication process in real time. With pose estimation and object detection, it recognizes three key steps: (1) picking up — hand takes a tablet/capsule out of the pill box; (2) to-mouth — hand brings the medication to the lips; (3) swallowing — throat/jaw movement indicating a swallow. When a step is missing (e.g., picked up but not brought to mouth, or brought to mouth but no swallow), the case is recorded as 'medication not completed' and an alert is pushed to family members or caregivers. This skill helps ensure chronic-disease elders take medication on time and in the right dose, preventing missed or wrong doses. Application scenarios: chronic-disease elder households, nursing homes, community rehab centers. The system auto-runs at scheduled medication times and generates compliance reports after each session. Skill features: missed/wrong doses are a major cause of poor chronic-disease control and ER visits among elders. AI verification of pick-up / to-mouth / swallow greatly improves medication safety and reduces medical cost. Can be integrated into smart-home cameras or elderly-care management systems as a key tool for chronic-disease management.
通过家庭药箱区域上方或侧方的固定摄像头,实时监测老年人取药、服药的全过程,利用姿态估计和目标检测技术识别以下三个关键步骤:①取药(手从药盒中取出药片/胶囊)、②送入口中(手部将药物送至嘴边)、③吞咽(喉部运动或颈部吞咽动作)。当系统检测到缺步骤(例如取药后未送入口中,或送入口中后无吞咽)时,记录为'未完成服药',并向家属或护理人员推送提醒。该技能有助于确保慢性病老人按时按量服药,防止漏服或错服。应用场景:老年慢性病家庭、养老院、社区康复中心。系统在设定的服药时间点自动开启监测,完成服药后生成依从性报告。技能特点:老年人漏服或错服药物是导致慢性病控制不佳和急诊入院的重要原因。通过AI自动确认取药、入口、吞咽三个步骤,可大幅提高用药安全性,降低医疗成本。该技能可集成到智能家居摄像头或养老管理系统中,成为慢性病管理的关键工具。
假设你是一个专业的老年人用药安全 AI。你的任务是分析药箱区域固定摄像头的实时视频,检测老年人服药的完整动作流程。需识别三个关键步骤:取药(手从药盒中取出药物)、送入口中(药物接触口唇区域)、吞咽(颈部喉结运动或下颌运动)。若任一动作缺失,则判定为"未完成"。不要提供医疗建议或具体用药方案,仅输出步骤检测结果与依从性判断。
python -m scripts.smyx_elderly_medication_compliance_analysis --list --open-id 参数调用 API
查询云端的历史报告数据requests>=2.28.0
在执行老年人服药动作确认前,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_elderly_medication_compliance_analysis 处理输入(必须在技能根目录下运行脚本)--input: 本地药箱区域服药全过程监控视频文件路径--url: 网络药箱区域服药全过程监控视频 URL 地址(API 服务自动下载)--pet-type: 类别标识,老人用药安全场景默认 other--open-id: 当前用户的 open-id(必填,按上述流程获取)--list: 显示老年人服药动作依从性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)服药依从性确认报告-{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 | 依从性状态 | 分析时间 | 点击查看 |
|---|---|---|---|
| 服药依从性确认报告-20260312172200001 | partial_no_swallow(缺吞咽) | 2026-03-12 17:22:00 | 🔗 查看报告 |
# 分析本地服药全过程视频(以下只是示例,禁止直接使用openclaw-control-ui 作为 open-id)
python -m scripts.smyx_elderly_medication_compliance_analysis --input /path/to/medication.mp4 --open-id your-open-id
# 分析网络服药全过程视频(以下只是示例,禁止直接使用openclaw-control-ui 作为 open-id)
python -m scripts.smyx_elderly_medication_compliance_analysis --url https://example.com/medication.mp4 --open-id your-open-id
# 显示历史服药依从性报告(自动触发关键词:查看服药依从性历史报告、用药依从性报告清单等)
python -m scripts.smyx_elderly_medication_compliance_analysis --list --open-id your-open-id
# 输出精简报告
python -m scripts.smyx_elderly_medication_compliance_analysis --input med.mp4 --open-id your-open-id --detail basic
# 保存结果到文件
python -m scripts.smyx_elderly_medication_compliance_analysis --input med.mp4 --open-id your-open-id --output result.json