A disinfection process visualization and simulation optimization method and system based on digital twinning, equipment and medium

Abstract

This invention relates to the field of intelligent control technology, specifically to a method, system, device, and medium for visualizing and simulating disinfection processes based on digital twins. The method provided by this invention mainly includes acquiring three-dimensional or two-dimensional drawing data of the target building and real-time data generated within the target building; preprocessing the real-time data; constructing a digital twin model based on the drawing data and real-time data; inputting the required target parameters; simulating the process using the digital twin model based on the target parameters; and determining whether to issue an alarm. By constructing a digital twin model of a hospital disinfection scenario using digital twin technology, the effects and efficiency of different disinfection processes can be simulated, enabling "pre-implementation optimization" of disinfection plans, solving problems in traditional processes, and thereby improving hospital operational efficiency and service quality.

Description

Technical Field

[0001] This invention relates to the field of intelligent control technology, and more specifically, to a method, system, device, and medium for visualizing and simulating the disinfection process based on digital twins. Background Technology

[0002] With the development of medical informatization and intelligentization, hospital operation management systems primarily provide services through the establishment of health portals and connections to hospital networks. These services include patient health care, medical consultation guidance, and disease inquiries. Simultaneously, they access patient medical records through various hospital business systems, allowing doctors and patients to access relevant information via computers or mobile phones. However, existing hospital operation management systems lack pre-emptive control over the allocation of medical resources, resulting in untimely data feedback and insufficient utilization of digital twin technology, leading to uneven resource allocation and low operational efficiency.

[0003] Traditional methods for developing hospital disinfection procedures often rely on manual experience and lack scientific simulation and optimization mechanisms. This "blindly developed and passively adjusted" approach is ill-suited to the complex and ever-changing medical environment, especially in complex scenarios such as newly built hospital areas and temporary isolation zones. Traditional static scheduling methods are no longer sufficient to address the dynamic changes in production.

[0004] Therefore, there is an urgent need for a technical solution that can visualize and simulate the disinfection process to improve its scientific validity and feasibility. Summary of the Invention

[0005] The purpose of this invention is to provide a method, system, device, and medium for visualizing and simulating the optimization of disinfection processes based on digital twins, in order to solve the problems of blindly formulating disinfection processes, passively adjusting them, and lacking effective visualization and simulation optimization mechanisms in the existing technology.

[0006] This invention is achieved through the following technical solution:

[0007] In a first aspect, the present invention provides a method for visualizing and simulating the optimization of a disinfection process based on digital twins, comprising: Acquire 3D or 2D drawing data of the target building and real-time data generated within the target building, preprocess the real-time data, and construct a digital twin model based on the drawing data and real-time data; Input the target parameters required at present, and simulate based on the target parameters through a digital twin model to obtain the result of whether to issue an alarm; If an alarm is triggered, the target parameters are readjusted until no more warnings are issued. If no alarm result is generated, a disinfection process is generated, sent to the disinfection execution agency, and real-time disinfection data is obtained. Determine whether the error between the current real-time data and the standard data is within a safe threshold; if so, output a prompt signal. If not, the final comparison data after disinfection will be obtained. If the error between the comparison data and the standard data is within the safe threshold, a disinfection report for this disinfection will be generated and saved. If not, a prompt signal will be issued.

[0008] Preferably, the preprocessing of real-time data includes: A dynamic weighted fusion model is established by fusing various heterogeneous data from multiple sources within the real-time data set.

[0009] In the formula, The reliability of the fused data at time t. The baseline confidence level of the i-th type of sensor at time t. As a weighting factor for business scenarios, This is the data stability factor.

[0010] Preferably, the simulation based on target parameters using a digital twin model includes: Establish a multi-objective disinfection efficiency evaluation model:

[0011] In the formula, It is a comprehensive efficiency index. , , These are the weighting coefficients. This represents the current area to be disinfected. This is the largest disinfection area in the hospital. For the minimum feasible disinfection time, This refers to the actual disinfection time. Due to uncontrollable waiting time, This refers to the number of areas where the microbial concentration meets the standard after disinfection. This represents the total number of disinfected areas. The cost of this disinfection work, This is the standard cost.

[0012] Preferably, it also includes establishing a dynamic decay disinfectant concentration prediction model to obtain the disinfectant concentration at future times, which is used to evaluate the comprehensive efficiency index at future times:

[0013] In the formula, for Time coordinates The concentration of disinfectant at the location, This is the initial release concentration of the disinfection machine. , , , These are dimensionless weighting coefficients. coordinates The straight-line distance to the sterilizer. As a distance reference benchmark, As a temperature reference, This is the difference between the actual temperature and the standard temperature. As a humidity reference standard, This represents the difference between the actual humidity and the standard humidity. This refers to the time elapsed since disinfection. It serves as a time reference benchmark.

[0014] Preferably, the result of whether or not an alarm is issued includes: Set a judgment threshold, obtain the current comprehensive efficiency index, and determine whether the current comprehensive efficiency index is greater than the judgment threshold. If it is greater than the threshold, no alarm will be issued; if it is less than or equal to the threshold, an alarm will be issued. An adaptive deviation threshold correction model is constructed, and the current judgment threshold is corrected through the adaptive deviation threshold correction model.

[0015] Preferably, the adaptive deviation threshold correction model includes:

[0016] In the formula, This is the corrected judgment threshold. This is the initial judgment threshold. Risk level, It is classified as a risk area.

[0017] Preferably, it also includes: Determine whether an emergency use signal for the current site has been received during the current disinfection process. If so, obtain the usage time period within the current emergency use signal. If the end point of the disinfection time is later than the end point of the usage time period, send a signal to start the disinfection equipment after the end point of the usage time period. Otherwise, stop the current disinfection process.

[0018] Secondly, the present invention also provides a disinfection process visualization and simulation optimization system based on digital twins, including a method for performing the above-mentioned disinfection process visualization and simulation optimization method based on digital twins, comprising: The model building module is configured to acquire 3D or 2D drawing data of the target building and real-time data generated within the target building, preprocess the real-time data, and construct a digital twin model based on the drawing data and real-time data; input the target parameters required at present, simulate the target parameters through the digital twin model, and obtain the result of whether to issue an alarm; if an alarm occurs, readjust the target parameters until no more alarms are issued; if no alarm occurs, generate a disinfection process, send it to the disinfection execution agency, and acquire the current real-time disinfection data in real time; The feedback module is configured to determine whether the error between the current real-time data and the standard data is within a safe threshold. If yes, it outputs a prompt signal; otherwise, it obtains the final comparison data after disinfection. If the error between the comparison data and the standard data is within a safe threshold, it generates and saves a disinfection report for this disinfection; otherwise, it issues a prompt signal.

[0019] Thirdly, the present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to perform the aforementioned method for visualizing and simulating a disinfection process based on digital twins.

[0020] Fourthly, the present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, performs the aforementioned method for visualizing and simulating a disinfection process based on digital twins.

[0021] The technical solution of the present invention has at least the following advantages and beneficial effects: The method provided by this invention mainly includes acquiring three-dimensional or two-dimensional drawing data of the target building and real-time data generated within the target building; preprocessing the real-time data; constructing a digital twin model based on the drawing data and real-time data; inputting the currently required target parameters; simulating the process using the digital twin model based on the target parameters; and obtaining a result indicating whether to issue an alarm. By constructing a digital twin model of a hospital disinfection scenario using digital twin technology, the effects and efficiency of different disinfection processes can be simulated, enabling "pre-implementation optimization" of disinfection plans, solving problems in traditional processes, and thereby improving hospital operational efficiency and service quality.

[0022] Based on hospital CAD drawings and real-time data, a digital twin model containing "area layout, personnel trajectory, and disinfection machine parameters" was constructed, realizing real-time synchronous updates of environmental data, personnel data, and disinfection machine status, thus improving the accuracy and timeliness of the data. Before developing a disinfection plan, nurses can input a preliminary plan through the panel. AI simulates the plan in a digital twin model and outputs information such as efficiency analysis, effect prediction, and safety warnings, which effectively avoids potential risks in the disinfection process and improves disinfection safety. AI generates the final disinfection process based on the optimized simulation plan and pushes it to the disinfection machine for execution, realizing the automated execution of the disinfection process, improving disinfection efficiency, and reducing the risk of disinfection delays caused by human factors. The digital twin model synchronizes actual disinfection data in real time, simulates and adjusts the plan, and prompts nurses, enabling dynamic adjustment of the disinfection process. This improves the flexibility and adaptability of the disinfection process, making it particularly suitable for complex scenarios such as newly built hospital areas and temporary isolation areas. Attached Figure Description

[0023] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0024] Figure 1 This is a schematic diagram of the process of the present invention. Figure 2 This is a schematic diagram of the system structure of the present invention. Detailed Implementation

[0025] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. The components of the embodiments of the present invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations.

[0026] The terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. The naming or numbering of steps in this application does not imply that the steps in the method flow must be executed in the chronological / logical order indicated by the naming or numbering. The execution order of named or numbered process steps can be changed according to the desired technical objective, as long as the same or similar technical effect is achieved.

[0027] The independently described modules or sub-modules may or may not be physically separated; they may be implemented in software or hardware, and some modules or sub-modules may be implemented in software, with the processor calling the software to implement the function of these modules or sub-modules, while other modules or sub-modules may be implemented in hardware, such as through hardware circuits. Furthermore, some or all of the modules can be selected to achieve the purpose of this application's solution according to actual needs.

[0028] Please refer to Figures 1-2 This invention provides a method for visualizing and simulating the optimization of a disinfection process based on digital twins, comprising: S101: Acquire the three-dimensional or two-dimensional drawing data of the target building and the real-time data generated within the target building, preprocess the real-time data, and construct a digital twin model based on the drawing data and real-time data; This module synchronously updates environmental data (temperature and humidity), personnel data (real-time location), and disinfection machine status (working mode). Unlike existing patents that use single-dimensional modeling (only space / personnel / equipment) and fixed-weight data fusion, this module constructs a three-layer architecture of "physical perception layer - heterogeneous fusion layer - twin interaction layer" to achieve precise linkage of multi-source data.

[0029] Physical sensing layer: Breaking through the traditional single sensor acquisition mode, it deploys a "dynamic sensing cluster" which includes a dual-mode personnel positioning sensor with ultra-wideband (UWB) + inertial navigation, a multi-modal environmental sensor with lidar + temperature and humidity + microorganisms, and equipment sensors with the operating status of the disinfection machine and the remaining amount of medicine. At the same time, it connects to the hospital's HIS system for business data such as surgical scheduling and patient transfer, forming a four-dimensional raw data pool of "space-personnel-equipment-business".

[0030] Heterogeneous Fusion Layer: Abandoning the fixed weighted fusion algorithm of existing patents, a hierarchical dynamic weighted fusion mechanism is designed: for structured data such as equipment / environment, Kalman filtering + sliding window noise reduction is used to eliminate hardware acquisition noise; For semi-structured / unstructured data such as personnel trajectories and business scheduling, introduce business scenario weight factors (e.g., increase the weight of personnel trajectories during surgery by 30%), and achieve data association through heterogeneous data association graphs; A data credibility assessment submodule is established to automatically reduce the weight of data sources with sensor malfunctions or data anomalies, thereby addressing the problem of insufficient accuracy in data fusion using existing technologies.

[0031] Twin Interaction Layer: Based on the 3D foundation of hospital CAD drawings and BIM models, a dynamic interconnected twin of "area-equipment-personnel" is constructed. Each twin unit has built-in three-element attributes of "operating condition threshold-safety constraint-business rule", supporting multi-dimensional linkage queries on the visual interface (e.g., clicking on an area can simultaneously retrieve the status of the disinfection machine in that area, the duration of personnel stay, and the historical disinfection effect). Moreover, the data update frequency of the twin can be adaptively adjusted according to the business scenario (1 second / time for the operating area, 10 seconds / time for the general ward). S102: Input the target parameters required at present, simulate based on the target parameters through the digital twin model, and obtain the result of whether to issue an alarm; AI Process Simulation and Optimization: Before developing a disinfection plan, nurses input a preliminary plan through a panel. The AI ​​then simulates the plan in a digital twin model, executing the following sub-steps: Efficiency analysis: Simulates the execution time of the disinfection process, outputs suggested time adjustments, and optimizes the area order if it is found that the time needs to be shortened. Effect prediction: Simulate the dosage distribution during the disinfection process to predict whether the disinfectant concentration will exceed the standard in the area; Safety alert: Determines if any surgery or special examination is in progress, and if so, prompts a delay in disinfection.

[0032] S103: If an alarm result is obtained, the target parameters will be readjusted until no more alarms are issued; S104: If no alarm result is generated, a disinfection process is generated, sent to the disinfection execution agency, and real-time disinfection data is obtained. S105: Determine whether the error between the current real-time data and the standard data is within the safety threshold; if so, output a prompt signal. Determine if any deviation has occurred; if so, immediately simulate and adjust the plan and notify the nurse.

[0033] S106: If not, the final comparison data after disinfection will be obtained. If the error between the comparison data and the standard data is within the safe threshold, a disinfection report for this disinfection will be generated and saved. If not, a prompt signal will be issued.

[0034] This invention primarily involves acquiring 3D or 2D drawing data of a target building and real-time data generated within the building, preprocessing the real-time data, and constructing a digital twin model based on the drawing data and real-time data. It then inputs the required target parameters, simulates the process using the digital twin model based on these parameters, and determines whether to issue an alarm. By constructing a digital twin model of a hospital disinfection scenario using digital twin technology, the effects and efficiency of different disinfection processes can be simulated, enabling "pre-implementation optimization" of disinfection plans, solving problems in traditional processes, and thereby improving hospital operational efficiency and service quality.

[0035] Based on hospital CAD drawings and real-time data, a digital twin model was constructed that includes "area layout, personnel trajectory, and disinfection machine parameters." This enabled real-time synchronous updates of environmental data, personnel data, and disinfection machine status, improving data accuracy and timeliness. Before formulating a disinfection plan, nurses can input a preliminary plan through the panel. The AI ​​simulates the plan in the digital twin model and outputs information such as efficiency analysis, effect prediction, and safety warnings, effectively avoiding potential risks in the disinfection process and improving disinfection safety.

[0036] An exemplary embodiment of the present invention includes preprocessing real-time data by: designing a dynamic weighted fusion formula to achieve accurate weighting of data sources based on the fusion reliability of multi-source heterogeneous data.

[0037] A dynamic weighted fusion model is established by fusing various heterogeneous data from multiple sources within the real-time data set.

[0038] In the formula, The confidence value of the fused data at time t (values ​​range from 0 to 1, with higher confidence values ​​closer to 1). The baseline reliability of the i-th type of sensor at time t (based on the factory calibration accuracy of the device, such as lidar). ), For business scenario weighting factors (if time t is the surgical period, personnel positioning sensor The remaining sensors Non-surgical period ), For data stability factors, , Let be the standard deviation of the data from the i-th type of sensor at time t. The mean of the data at time t is used to quantify the degree of data fluctuation; the greater the fluctuation, the lower the mean. The smaller.

[0039] One exemplary implementation of this invention, AI process simulation and optimization, differs from the single-objective optimization of existing patents (efficiency only / space priority only). This module achieves coupled optimization of four-dimensional objectives: efficiency, effectiveness, safety, and cost. The core process is as follows: Preliminary plan input: Nurses input basic parameters such as disinfection area, initial time, and drug type through a visual panel. The system automatically matches the three attributes of the twin to generate an initial protocol baseline.

[0040] Four-dimensional target simulation evaluation: Efficiency dimension: Optimize the non-conflict sequence of the disinfection path by combining area distance, disinfection machine movement speed, and personnel avoidance time; Effectiveness dimension: Simulate the diffusion attenuation of disinfectant under different temperatures and humidity levels to predict concentration distribution; Safety dimension: Link the surgery / examination scheduling of the HIS system to generate a safety matrix of "disinfection restricted areas - disinfectable time periods"; Cost dimension: Statistically analyze the drug consumption and equipment energy consumption of different schemes to screen for low-cost schemes.

[0041] Multi-objective decision output: The four-dimensional objectives are screened for Pareto optimal solutions using the non-dominated sorting genetic algorithm (NSGA-Ⅲ), and three candidate solutions are output with the objective priority of each solution marked (such as "efficient", "safe", "economical") for nurses to choose from.

[0042] Specifically, simulations based on target parameters using digital twin models include: Establish a multi-objective disinfection efficiency evaluation model:

[0043] In the formula, It is a comprehensive efficiency index. , , These are the weighting coefficients. This represents the current area to be disinfected. This is the largest disinfection area in the hospital. For the minimum feasible disinfection time, This refers to the actual disinfection time. Due to uncontrollable waiting time, This refers to the number of areas where the microbial concentration meets the standard after disinfection. This represents the total number of disinfected areas. The cost of this disinfection work, This is the standard cost.

[0044] An exemplary embodiment of the present invention further includes establishing a dynamically decaying disinfectant concentration prediction model to obtain the disinfectant concentration at future times, which is used to evaluate the comprehensive efficiency index at future times, thus addressing the insufficient accuracy of existing concentration prediction methods.

[0045] in, The effective half-life of the disinfectant type is the time elapsed after disinfection (tested in the laboratory to ensure coverage of the main decay stage and to match actual disinfection scenarios): Chlorine-containing disinfectant: 30 min; Ultraviolet disinfectant: 15 min. The effective half-life of the time reference is the same as t, ensuring that the dimensionless time term is in the 0-1 interval, which is 30 min.

[0046] coordinates The straight-line distance to the disinfection machine; the effective disinfection radius specified by the manufacturer for the disinfection equipment (ensuring coverage of the actual working range of the equipment and conforming to the equipment's instruction manual): Spray disinfection machine: 5m; Ultraviolet lamp: 3m; For distance reference benchmark The effective disinfection radius is 5m, ensuring that the dimensionless distance term is in the 0-1 range.

[0047] The difference between the actual temperature and the standard temperature represents the maximum allowable temperature fluctuation in a medical disinfection environment (refer to the "Technical Specifications for Hospital Disinfection"). As a temperature reference standard, the same The maximum allowable temperature fluctuation.

[0048] The difference between actual humidity and standard humidity represents the maximum allowable fluctuation in humidity for medical disinfection environments (refer to the "Technical Specifications for Hospital Disinfection"). As a humidity reference standard, the same The maximum allowable fluctuation in humidity.

[0049] , , , These are dimensionless weighting coefficients, calibrated experimentally and ranging from 0 to 1, used to adjust the contribution of each influencing factor to concentration decay. Their sum is 1. Specifically, , , , .

[0050] Hypothesis: Chlorine-containing disinfectant mg / L, disinfection t=15min, target point distance m, , After substituting into the formula: Concentration results: mg / L, which is consistent with the actual law of chlorine-containing disinfectants decaying over time and distance.

[0051] Secondly, the result of whether or not an alarm is issued includes: Set a judgment threshold, obtain the current comprehensive efficiency index, and determine whether the current comprehensive efficiency index is greater than the judgment threshold. If it is greater than the threshold, no alarm will be issued; if it is less than or equal to the threshold, an alarm will be issued. An adaptive deviation threshold correction model is constructed, and the current judgment threshold is corrected through the adaptive deviation threshold correction model.

[0052] The adaptive bias threshold correction model includes:

[0053] In the formula, This is the corrected judgment threshold. This is the initial judgment threshold. Risk level, Risk level: High-risk area General ward Office area .

[0054] Unlike existing patents that use fixed threshold deviation correction (such as a fixed 10% / 15% deviation threshold), this module constructs a closed-loop mechanism of dynamic threshold + self-iterative correction: Real-time data synchronization: During the disinfection process, the twin device synchronously collects actual disinfection data (dosage, disinfection time, and regional microbial concentration). Dynamic deviation judgment: The deviation threshold is automatically adjusted according to the risk level of the disinfection area (e.g., ICU is high risk, general ward is low risk) (5% for high risk area, 15% for low risk). Self-iterative correction: If the deviation exceeds the threshold, the system automatically calls the twin simulation to select three correction schemes (adjusting disinfection time / path / agent concentration) and feeds the effect of the corrected scheme back to the AI ​​model, realizing the self-iterative optimization of model parameters and solving the problem of passive adjustment in existing technologies.

[0055] An exemplary embodiment of the present invention further includes: Determine whether an emergency use signal for the current site has been received during the current disinfection process. If so, obtain the usage time period within the current emergency use signal. If the end point of the disinfection time is later than the end point of the usage time period, send a signal to start the disinfection equipment after the end point of the usage time period. Otherwise, stop the current disinfection process.

[0056] Specifically, the newly added disinfection-medical business linkage and collaboration function differs from the limitations of existing patents that only focus on the disinfection process itself: when the disinfection plan conflicts with business such as emergency surgery and patient transfer, the system automatically triggers collaborative scheduling (such as prioritizing the disinfection of the surgical area and adjusting the disinfection time of the general ward), and simultaneously pushes the scheduling information to the mobile terminal of medical staff, so as to achieve collaborative adaptation between the disinfection process and the overall operation of the hospital.

[0057] Secondly, the present invention also provides a disinfection process visualization and simulation optimization system based on digital twins, including a method for performing the above-mentioned disinfection process visualization and simulation optimization method based on digital twins, comprising: The model building module is configured to acquire 3D or 2D drawing data of the target building and real-time data generated within the target building, preprocess the real-time data, and construct a digital twin model based on the drawing data and real-time data; input the target parameters required at present, simulate the target parameters through the digital twin model, and obtain the result of whether to issue an alarm; if an alarm occurs, readjust the target parameters until no more alarms are issued; if no alarm occurs, generate a disinfection process, send it to the disinfection execution agency, and acquire the current real-time disinfection data in real time; The feedback module is configured to determine whether the error between the current real-time data and the standard data is within a safe threshold. If yes, it outputs a prompt signal; otherwise, it obtains the final comparison data after disinfection. If the error between the comparison data and the standard data is within a safe threshold, it generates and saves a disinfection report for this disinfection; otherwise, it issues a prompt signal.

[0058] This invention provides a specific example to further explain the above content.

[0059] Step 1: Digital Twin Modeling: Based on hospital CAD drawings and real-time data, a digital twin model including "area layout, personnel trajectory, and disinfection machine parameters" is constructed. First, BIM software is used to reconstruct the hospital's CAD drawings in 3D, constructing an area layout model of the hospital, including wards, doctors' offices, nurses' stations, restrooms, etc. Second, using a combination of ultra-wideband positioning technology and Wi-Fi fingerprint positioning technology, the movement trajectories of medical staff are tracked in real time, building a personnel trajectory database. Then, based on the disinfection machine model XJ-88, the basic parameters of the disinfection machine are set, such as a robot speed of 2 m / s, a maximum turning radius of 1.5 meters, and a maximum climbing angle of 15 degrees. Environmental data is collected in real time through temperature and humidity sensors and an air microbial sampler. A Kalman filter algorithm is used to preprocess the data, generating an environmental parameter database. A multi-source data fusion mechanism is established to perform weighted fusion and noise filtering on different types of data, forming the basic dataset for the digital twin model.

[0060] Step 2, AI Process Simulation and Optimization: Before developing a disinfection plan, the nurse inputs a preliminary disinfection plan via a mobile terminal. The AI ​​system then simulates this plan in a digital twin model, executing the process as follows: Step 201, Efficiency Analysis: Based on the input disinfection areas and time, simulate the execution time of the disinfection process, calculate the disinfection efficiency using a deep reinforcement learning algorithm, and output suggested time adjustments. For example, for a disinfection task involving 15 areas, the suggested time is 45 minutes, while the actual execution time is 55 minutes. The suggestion is to optimize the area order and shorten the time by 10 minutes.

[0061] Step 202, Effect Prediction: Using a multimodal Transformer model, the dosage distribution during the disinfection process is simulated to predict whether the disinfectant concentration in a region will exceed the standard. For example, when the predicted concentration in a certain area reaches 1.3 times the normal value, an alarm is issued, suggesting adjustments to disinfection parameters or the order of areas.

[0062] Step 203, Safety Alert: Through the hospital information system interface, obtain real-time information on surgical and special examination schedules to determine if any surgeries or special examinations are in progress. If so, prompt the staff to postpone disinfection to avoid interfering with the surgical procedure. For example, if the surgery start time is 14:30, prompt the disinfection personnel to avoid performing disinfection operations between 14:00 and 14:30.

[0063] Step 3: Determine if the plan needs to be adjusted. If yes, return to step 2; otherwise, proceed to step 4.

[0064] Step 4: Simulation Results Implementation: The AI ​​generates the final disinfection process based on the optimized plan and pushes it to the disinfection machine for execution. The specific execution is as follows: Step 401: Through the sensor data submodule of the data acquisition module, real-time synchronization of actual disinfection data, including parameters such as the operating status of the disinfection machine, the amount of disinfectant used, and the cleanliness of the disinfection area, is achieved. A multi-source sensor fusion algorithm is used to integrate real-time data from the air microbial sampler and temperature and humidity sensor, and Kalman filtering is used to eliminate noise interference to generate pre-processed sensor data.

[0065] Step 402: Use image recognition algorithms to determine the actual execution status and whether any deviations have occurred. If a deviation is found, immediately use AI algorithms to simulate and adjust the plan and prompt the nurse via the terminal, such as "Disinfection efficiency in area D is low; it is recommended to reduce the cleaning time by 5 minutes." If there is no deviation, proceed to step 403.

[0066] Step 403: Compare the actual disinfection results with the expected results, and calculate the deviation using the mean square error. If the deviation exceeds 15%, return to step 2 to adjust the plan; if the deviation is less than 15%, proceed to step 404.

[0067] Step 404: Generate a disinfection report, including indicators such as disinfection area, disinfection time, disinfection efficiency, and disinfectant dosage, and store the report in the hospital information system.

[0068] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0069] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. This computer software product, stored in a storage medium, includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0070] The above are merely preferred embodiments of the present invention and are not intended to limit the present invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for visualizing and simulating the optimization of a disinfection process based on digital twins, characterized in that, include: Acquire 3D or 2D drawing data of the target building and real-time data generated within the target building, preprocess the real-time data, and construct a digital twin model based on the drawing data and real-time data; Input the target parameters required at present, and simulate based on the target parameters through a digital twin model to obtain the result of whether to issue an alarm; If an alarm is triggered, the target parameters are readjusted until no more warnings are issued. If no alarm result is generated, a disinfection process is generated, sent to the disinfection execution agency, and real-time disinfection data is obtained. Determine whether the error between the current real-time data and the standard data is within a safe threshold; if so, output a prompt signal. If not, the final comparison data after disinfection will be obtained. If the error between the comparison data and the standard data is within the safe threshold, a disinfection report for this disinfection will be generated and saved. If not, a prompt signal will be issued.

2. The method for visualizing and simulating disinfection processes based on digital twins according to claim 1, characterized in that, The preprocessing of real-time data includes: A dynamic weighted fusion model is established by fusing various heterogeneous data from multiple sources within the real-time data set. In the formula, The reliability of the fused data at time t. The baseline confidence level of the i-th type of sensor at time t. As a weighting factor for business scenarios, This is the data stability factor.

3. The method for visualizing and simulating the disinfection process based on digital twins according to claim 2, characterized in that, The simulation based on target parameters using a digital twin model includes: Establish a multi-objective disinfection efficiency evaluation model: In the formula, It is a comprehensive efficiency index. , , These are the weighting coefficients. This represents the current area to be disinfected. This is the largest disinfection area in the hospital. For the minimum feasible disinfection time, This refers to the actual disinfection time. Due to uncontrollable waiting time, This refers to the number of areas where the microbial concentration meets the standard after disinfection. This represents the total number of disinfected areas. The cost of this disinfection work, This is the standard cost.

4. The method for visualizing and simulating the disinfection process based on digital twins according to claim 3, characterized in that, This also includes establishing a dynamic decay disinfectant concentration prediction model to obtain the disinfectant concentration at future times, which is used to evaluate the overall efficiency index at future times. In the formula, for Time coordinates The concentration of disinfectant at the location, This is the initial release concentration of the disinfection machine. , , , These are dimensionless weighting coefficients. coordinates The straight-line distance to the sterilizer. As a distance reference benchmark, As a temperature reference, This is the difference between the actual temperature and the standard temperature. As a humidity reference standard, This represents the difference between the actual humidity and the standard humidity. This refers to the time elapsed since disinfection. It serves as a time reference benchmark.

5. The method for visualizing and simulating the disinfection process based on digital twins according to claim 4, characterized in that, The result of whether or not an alarm is issued includes: Set a judgment threshold, obtain the current comprehensive efficiency index, and determine whether the current comprehensive efficiency index is greater than the judgment threshold. If it is greater than the threshold, no alarm will be issued; if it is less than or equal to the threshold, an alarm will be issued. An adaptive deviation threshold correction model is constructed, and the current judgment threshold is corrected through the adaptive deviation threshold correction model.

6. The method for visualizing and simulating the disinfection process based on digital twins according to claim 5, characterized in that, The adaptive deviation threshold correction model includes: In the formula, This is the corrected judgment threshold. This is the initial judgment threshold. Risk level, It is classified as a risk area.

7. The method for visualizing and simulating the disinfection process based on digital twins according to claim 6, characterized in that, Also includes: Determine whether an emergency use signal for the current site has been received during the current disinfection process. If so, obtain the usage time period within the current emergency use signal. If the end point of the disinfection time is later than the end point of the usage time period, send a signal to start the disinfection equipment after the end point of the usage time period. Otherwise, stop the current disinfection process.

8. A disinfection process visualization and simulation optimization system based on digital twins, comprising executing the disinfection process visualization and simulation optimization method based on digital twins as described in any one of claims 1-7, characterized in that, include: The model building module is configured to acquire 3D or 2D drawing data of the target building and real-time data generated within the target building, preprocess the real-time data, and build a digital twin model based on the drawing data and real-time data; input the target parameters required at present, simulate the target parameters through the digital twin model, and obtain the result of whether to issue an alarm; If an alarm is triggered, the target parameters are readjusted until no more warnings are issued. If no alarm result is generated, a disinfection process is generated, sent to the disinfection execution agency, and real-time disinfection data is obtained. The feedback module is configured to determine whether the error between the current real-time data and the standard data is within a safe threshold. If yes, it outputs a prompt signal; otherwise, it obtains the final comparison data after disinfection. If the error between the comparison data and the standard data is within a safe threshold, it generates and saves a disinfection report for this disinfection; otherwise, it issues a prompt signal.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it performs the disinfection process visualization and simulation optimization method based on digital twins as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, which, when executed by a processor, performs the disinfection process visualization and simulation optimization method based on digital twins as described in any one of claims 1-7.

Images