一种基于长时间序列的急救检伤分类方法、设备及介质
By combining generative adversarial networks and causal reasoning mechanisms, the threshold for emergency triage is dynamically adjusted, which solves the problem of inaccurate fusion of multimodal long-term series data and improves the accuracy and real-time performance of emergency triage.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- FUJIAN PROVINCIAL HOSPITAL
- Filing Date
- 2026-01-07
- Publication Date
- 2026-07-17
AI Technical Summary
Existing technologies have shortcomings in the dynamic fusion and threshold optimization of multimodal long-term series data, resulting in inaccurate adjustment of emergency triage thresholds and difficulty in meeting the high real-time requirements of emergency environments.
Generative adversarial networks are used to augment and dynamically fuse multimodal long-term series data. The triage classification threshold is dynamically adjusted by combining causal inference mechanism. The threshold is optimized by causal inference through the collection of real-time resource status data. The injury level is estimated by combining Bayesian neural network.
It improves the accuracy and robustness of emergency triage, enhances sensitivity to dynamic changes in injuries, and enables more reliable output of injury severity levels.
Smart Images
Figure CN121483649B_ABST