CN-122025048-A - Ultra wideband positioning based hospital induction real-time tracing and intelligent early warning method and related equipment

CN122025048ACN 122025048 ACN122025048 ACN 122025048ACN-122025048-A

Abstract

The invention discloses a hospital induction real-time tracing and intelligent early warning method and related equipment based on UWB ultra-wideband positioning, wherein the method comprises the steps of acquiring multi-source heterogeneous data through an ultra-wideband, a hospital information system, a laboratory information system, a disinfection supply center management system and a surgical anesthesia management system; the method comprises the steps of carrying out time sequence alignment, feature fusion and redundancy filtration on multi-source heterogeneous data to construct a hospital-sensing prevention and control data set, constructing a target quantization model, carrying out multi-dimensional risk identification and quantization analysis according to the hospital-sensing prevention and control data set and the target quantization model, outputting a risk quantization value of target risk, obtaining a risk assessment index according to preset personnel weight, a preset regional risk coefficient of a target region, a preset risk weight of the target risk and the risk quantization value, and outputting a target early warning result and a target early warning treatment task according to the risk quantization value and the risk assessment index. The invention can trace back the risk event of the hospital and intelligent early warning in the whole course, and can be widely applied to the technical field of wireless positioning.

Inventors

ZHANG TINGTING
TAN WENCHONG

Assignees

南方医科大学南方医院

Dates

Publication Date: 20260512
Application Date: 20260123

Claims (10)

1. The hospital feel real-time tracing and intelligent early warning method based on UWB ultra-wideband positioning is characterized by comprising the following steps: Acquiring multi-source heterogeneous data through an ultra-wideband, a hospital information system, a laboratory information system, a disinfection supply center management system and a surgical anesthesia management system; performing time sequence alignment, feature fusion and redundancy filtration on the multi-source heterogeneous data to construct a hospital-sensing prevention and control data set; constructing a target quantization model according to the target risk of each dimension; According to the hospital infection prevention and control data set and the target quantization model, performing multidimensional risk identification and quantization analysis, and outputting a risk quantization value of the target risk; Acquiring a risk assessment index according to preset personnel weights, preset regional risk coefficients of a target region, preset risk weights of the target risks and the risk quantification values; and outputting a target early warning result and a target early warning treatment task according to the risk quantification value and the risk assessment index.
2. The method according to claim 1, characterized in that the method further comprises the steps of: generating an early warning prompt according to the target early warning result; distributing the target early warning treatment task according to the early warning prompt and the role authority; tracking the progress state of the target early warning treatment task, if the progress state is overtime unprocessed, generating an overtime prompt, and if the progress state is finished, checking early warning treatment data and generating an analysis improvement suggestion.
3. The method of claim 1, wherein the acquiring multi-source heterogeneous data via an ultra-wideband, hospital information system, laboratory information system, disinfection supply center management system, and surgical anesthesia management system, comprises the steps of: The method comprises the steps of obtaining positioning data of a target tag through ultra-wideband, wherein the target tag comprises a personnel tag and a device tag, and the positioning data comprises position coordinates, a moving track and residence time; Acquiring basic information of a patient, a course record and a diagnosis and treatment operation record through the hospital information system; acquiring the infection state of a patient and a microorganism detection result through the laboratory information system; acquiring an instrument cleaning and disinfecting flow record and an instrument multiplexing record through the disinfecting and supplying center management system; And acquiring a surgical record, a participator and an instrument use list through the surgical anesthesia management system.
4. The method of claim 1, wherein the performing the time alignment, feature fusion and redundancy filtering on the multi-source heterogeneous data constructs a hospital-susceptibility prevention dataset, the formula comprising: ; In the formula, Representation of Fused data at the moment; Represent the first Credibility weights of the class data sources; Representation of Time of day (time) Raw data of the class data source; representing the number of types of data sources participating in the fusion.
5. The method according to claim 1, wherein the constructing the target quantization model according to the target risk of each dimension comprises the steps of: Constructing a personnel contact risk quantification model according to preset infection state weights, disease transmission coefficients, safety contact distance thresholds and risk contact duration thresholds; acquiring personnel access rights of the target area, and constructing an area rights management and control quantitative model according to the personnel access rights and positioning data in the multi-source heterogeneous data; Constructing a protection article compliance quantification model according to the number of types of protection articles required by the operation of the target area, the number of types of worn protection articles, the wearing standardization coefficient and the total number of people in the target area; constructing an equipment cleaning state quantification model according to a preset cleaning and disinfection period of medical equipment, the number of diagnosis and treatment areas visited by the medical equipment, the accumulated use time length of the medical equipment and a disinfection record effectiveness coefficient; And constructing an instrument multiplexing risk quantification model according to the microorganism hazard grade coefficient, the microorganism detection result of the patient, the microorganism safety concentration threshold, the instrument accumulated multiplexing times and the instrument maximum allowable multiplexing times.
6. The method of claim 5, wherein the performing a multidimensional risk identification and quantization analysis based on the hospital-susceptibility control dataset and the target quantization model, outputting a risk quantization value for the target risk, comprises the steps of: Dynamically acquiring the inter-personnel space distance and the accumulated contact time according to the positioning data in the hospital sensing prevention and control data set; according to the inter-personnel space distance, the accumulated contact time length and the personnel contact risk quantification model, personnel contact risk identification and quantification analysis are executed, and a personnel contact risk value is output; Executing regional authority identification and quantitative analysis according to the personnel access authority, the positioning data in the hospital-sensing prevention and control data set and the regional authority management and control quantitative model, and outputting authority matching degree and residence time compliance rate; acquiring video monitoring data, and performing behavior recognition on the video monitoring data through artificial intelligent vision to obtain the number of types of the worn protective articles of a single person, the wearing standardization coefficient of the single person and the total number of the persons in the target area; according to the number of types of the worn protective articles, the wearing standardization coefficient, the total number of people and the protective article compliance quantization model, carrying out protective article identification and quantization analysis, and outputting single-person protective compliance rate and regional overall protective compliance rate; Acquiring the number of diagnosis and treatment areas visited by the medical equipment in a current cleaning and disinfection period according to positioning data in the hospital sensing prevention and control data set, acquiring the finishing moment of the previous cleaning and disinfection period, the starting moment of the current cleaning and disinfection period, the preset cleaning and disinfection period of the medical equipment, the disinfection record of the medical equipment and the equipment cleaning state quantification model according to the instrument cleaning and disinfection flow record in the hospital sensing prevention and control data set, executing equipment cleaning state identification and quantification analysis, and outputting an equipment cleaning risk value; and according to the microorganism detection result, the instrument multiplexing record and the multiplexing risk quantification model in the hospital infection prevention and control data set, performing instrument multiplexing identification and quantification analysis, and outputting an instrument multiplexing risk value.
7. The method according to claim 1, wherein the acquiring the risk assessment index according to the preset personnel weight, the preset regional risk coefficient of the target region, the preset risk weight of the target risk, and the risk quantification value, the formula used includes: ; In the formula, Representing a risk assessment index; Representing personnel weights; representing a preset region risk coefficient of the target region; Representing a summation symbol; Represent the first Preset risk weights of the individual dimension risks; Represent the first Risk quantification value for each dimension.
8. The method according to claim 1, wherein the outputting the target early warning result and the target early warning treatment task according to the risk quantification value and the risk assessment index comprises the steps of: judging whether the risk quantification value meets the standard according to a preset risk threshold value, and generating a single-dimensional early warning result and a single-dimensional early warning treatment task of corresponding dimensions; and starting a grading early warning mechanism according to the risk assessment index and the risk quantification value, and outputting grading early warning results and grading early warning treatment tasks.
9. The utility model provides a sense of hospital real-time traceability and intelligent early warning device based on UWB ultra wide band location which characterized in that includes: The data acquisition module is used for acquiring multi-source heterogeneous data through an ultra-wideband, a hospital information system, a laboratory information system, a disinfection supply center management system and a surgical anesthesia management system; The data preprocessing module is used for carrying out time sequence alignment, feature fusion and redundancy filtration on the multi-source heterogeneous data to construct a hospital-sensing prevention and control data set; the quantization model construction module is used for constructing a target quantization model according to the target risk of each dimension; The risk quantization module is used for executing multidimensional risk identification and quantization analysis according to the hospital induction prevention and control data set and the target quantization model and outputting a risk quantization value of the target risk; The risk assessment module is used for acquiring a risk assessment index according to preset personnel weight, a preset regional risk coefficient of a target region, a preset risk weight of the target risk and the risk quantification value; And the early warning judging module is used for outputting a target early warning result and a target early warning treatment task according to the risk quantification value and the risk assessment index.
10. A computer program product comprising a computer program which, when executed by a processor, implements the method of any one of claims 1 to 8.

Description

Ultra wideband positioning based hospital induction real-time tracing and intelligent early warning method and related equipment Technical Field The invention relates to the technical field of wireless positioning, in particular to a hospital feel real-time tracing and intelligent early warning method and related equipment based on UWB ultra-wideband positioning. Background The hospital infection prevention and control is a key link for guaranteeing medical quality and patient safety, and the current medical institution mainly relies on traditional modes of manual inspection, manual recording, periodic inspection and the like to develop hospital infection prevention and control work, and has obvious limitations that the manual inspection coverage is limited, the efficiency is low, dynamic monitoring in a whole time period is difficult to realize, data errors and omission are easy to occur in manual recording, the traceability is poor, a complete prevention and control data chain cannot be formed, the periodic inspection has time lag, infection risk hidden dangers are difficult to find in real time, and hospital infection event early warning is not timely, and even cross infection diffusion is caused. At present, a plurality of hospital feel monitoring systems exist, which mainly rely on electronic medical records, inspection indexes, inspection data and the like to monitor the hospital feel quality control in real time, do not combine environmental microorganism load, medical instrument disinfection conditions, use tracks, medical hand health execution and other key scene data, lack the intervention traceability function of actual working scenes, and lack the grading reminding of early warning information. With the development of the internet of things, in the field of hospital sensing prevention and control, an Ultra Wideband (UWB) technology has been primarily explored and practiced. However, in the existing scheme of applying the UWB technology to hospital sensing prevention and control, the defects of functional fragmentation, multi-dimensional element integration loss, intelligent early warning, insufficient traceability support and the like exist. Disclosure of Invention In view of the above, the embodiment of the invention mainly aims to provide a hospital induction real-time tracing and intelligent early warning method and related equipment based on UWB ultra-wideband positioning, so as to solve at least one of the problems in the prior art. In order to achieve the above purpose, an aspect of the embodiments of the present invention provides a method for real-time source tracing and intelligent early warning of hospital feel based on UWB ultra wideband positioning, the method comprising: Acquiring multi-source heterogeneous data through an ultra-wideband, a hospital information system, a laboratory information system, a disinfection supply center management system and a surgical anesthesia management system; performing time sequence alignment, feature fusion and redundancy filtration on the multi-source heterogeneous data to construct a hospital-sensing prevention and control data set; constructing a target quantization model according to the target risk of each dimension; According to the hospital infection prevention and control data set and the target quantization model, performing multidimensional risk identification and quantization analysis, and outputting a risk quantization value of the target risk; Acquiring a risk assessment index according to preset personnel weights, preset regional risk coefficients of a target region, preset risk weights of the target risks and the risk quantification values; and outputting a target early warning result and a target early warning treatment task according to the risk quantification value and the risk assessment index. In some embodiments, the method further comprises the steps of: generating an early warning prompt according to the target early warning result; distributing the target early warning treatment task according to the early warning prompt and the role authority; tracking the progress state of the target early warning treatment task, if the progress state is overtime unprocessed, generating an overtime prompt, and if the progress state is finished, checking early warning treatment data and generating an analysis improvement suggestion. In some embodiments, the acquiring multi-source heterogeneous data via an ultra-wideband, a hospital information system, a laboratory information system, a disinfection supply center management system, and a surgical anesthesia management system comprises the steps of: The method comprises the steps of obtaining positioning data of a target tag through ultra-wideband, wherein the target tag comprises a personnel tag and a device tag, and the positioning data comprises position coordinates, a moving track and residence time; Acquiring basic information of a patient, a course record and a diagnosis and treatment o