Hospital medical consumable abnormal consumption identification and automatic early warning method based on rule engine

By using a rule-based engine approach, combined with dynamic benchmark prediction and causal reasoning attribution, the problems of false alarms and low decision-making efficiency in hospital medical consumables management systems have been solved. This approach enables accurate early warning and intelligent management of consumable usage, adapting to the development and changes in medical technology.

CN122392847APending Publication Date: 2026-07-14ANHUI ZHONGJI NAT MEDICAL MEDICAL TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
ANHUI ZHONGJI NAT MEDICAL MEDICAL TECH CO LTD
Filing Date
2026-04-20
Publication Date
2026-07-14

AI Technical Summary

Technical Problem

Existing hospital medical consumables management systems are unable to adapt to the complexity and dynamism of clinical practice, resulting in numerous false alarms and inefficient decision-making. Furthermore, rule base updates rely on manual maintenance, making it difficult to adapt to the development of medical technology and changes in clinical pathways.

Method used

By employing a rule-based engine approach that integrates dynamic benchmark prediction, causal inference attribution, and closed-loop feedback learning, and through multi-source data fusion, an interpretable dynamic benchmark model, and a causal knowledge graph, the system identifies real abnormal consumption and provides interpretable decision support, thereby achieving continuous self-optimization.

Benefits of technology

It improves the accuracy and interpretability of consumable usage warnings, reduces false alarms, provides clear decision-making basis, and can autonomously adapt to changes in clinical practice and treatment models, achieving an intelligent leap from static monitoring to dynamic learning.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122392847A_ABST
    Figure CN122392847A_ABST
Patent Text Reader

Abstract

The application discloses a hospital medical consumable abnormal consumption identification and automatic early warning method based on a rule engine, and belongs to the technical field of medical information management and data processing. The method comprises the following steps: acquiring and fusing multiple source heterogeneous data to generate a feature set; constructing an interpretable dynamic benchmark model based on historical data, inputting a clinical context to calculate an expected consumption amount, and comparing the actual consumption amount to generate a deviation signal; calling a real-time causal reasoning model based on a causal knowledge graph to deduce the deviation signal, dynamically adjusting the parameters of the rule engine according to the deviation signal, and generating a corrected judgment result; generating an early warning decision package containing suspicious root causes and suggestions based on comprehensive information, and outputting the early warning decision package; and collecting feedback data to update the model in a closed loop. The application adopts a double driving mode of a dynamic benchmark and causal reasoning, can realize accurate identification, root cause analysis and adaptive early warning, and improves the intelligent level of management and the cost control ability.
Need to check novelty before this filing date? Find Prior Art