A BIM-based IoT-enabled intelligent operation and maintenance command and management system for the entire hospital process.

Abstract

This invention discloses a hospital end-to-end intelligent operation and maintenance command and management system based on BIM and IoT collaboration, belonging to the field of hospital management technology. It includes: a 3D visualization management module configured to create a 3D model of the hospital building for display and management; a real-time monitoring and acquisition module configured to collect multi-source data from the hospital; a preprocessing and analysis module configured to perform pre-diagnosis and preventative maintenance of hospital equipment faults; an intelligent operation and maintenance command and management module configured to automate operation and maintenance activities; and a visualization and interactive module configured to provide an interactive interface for monitoring the hospital's operation and maintenance status anytime, anywhere. This invention solves the problem that existing systems cannot achieve intelligent operation and maintenance command and management of the entire hospital process based on BIM and IoT collaboration. This invention enables intelligent operation and maintenance command and management of the entire hospital process, achieving comprehensive digital management of hospital buildings and equipment, and providing strong support for the efficient operation and high-quality development of hospitals.

Description

Technical Field

[0001] This invention relates to the field of hospital management technology, specifically to a hospital end-to-end intelligent operation and maintenance command and management system based on BIM and IoT collaboration. Background Technology

[0002] Internet of Things (IoT) devices refer to various physical devices, sensors, software, and network structures that can connect to a network and exchange information. Hospitals, as complex organizational systems, require effective operation and maintenance management to ensure the normal operation of medical facilities and patient safety. IoT devices play a crucial role in hospital operation and maintenance management, improving operational efficiency and service quality while reducing energy consumption and costs.

[0003] Chinese patent CN114792205B discloses a method for monitoring and alarming road subsidence and collapse based on a smart hospital operation and maintenance platform. The method includes: preparing basic smart hospital data and the smart hospital operation and maintenance platform; creating a three-dimensional operation and maintenance management model for the smart hospital; comprehensively analyzing real-time monitored terrain deformation data through the smart hospital operation and maintenance platform to identify abnormal data; analyzing the abnormal data and classifying the analysis results into charts to generate high-risk areas for road subsidence; linking the smart hospital operation and maintenance platform with the three-dimensional operation and maintenance management model for timely early warning; sharing the damage information with the operation and maintenance management department; and the operation and maintenance management department taking corresponding emergency measures upon receiving the geological alarm information. This method can accurately indicate unknown risks ahead, thereby effectively preventing accidents. However, this patent has the following drawbacks:

[0004] Existing technologies cannot enable intelligent operation and maintenance command and management of the entire hospital process based on BIM and IoT collaboration, cannot effectively achieve comprehensive digital management of hospital buildings and equipment, and cannot provide strong support for the efficient operation and high-quality development of hospitals. Summary of the Invention

[0005] The purpose of this invention is to provide a hospital full-process intelligent operation and maintenance command and management system based on BIM IoT collaboration. It can carry out intelligent operation and maintenance command and management of the entire hospital process based on BIM IoT collaboration, effectively realize the comprehensive digital management of hospital buildings and equipment, and provide strong support for the efficient operation and high-quality development of hospitals, thus solving the problems mentioned in the background art.

[0006] To achieve the above objectives, the present invention provides the following technical solution:

[0007] The hospital's end-to-end intelligent operation and maintenance command and management system based on BIM and IoT collaboration includes:

[0008] The 3D visualization management module is configured to create 3D models of hospital buildings and to visualize and manage them.

[0009] The real-time monitoring and acquisition module is configured to monitor the hospital's environmental parameters, equipment operating status, and energy consumption in real time, and collect multi-source data from the hospital.

[0010] We assign corresponding weight values ​​to the hospital's environmental parameters, equipment operating status, and energy consumption for subsequent weighted fusion of multi-source data.

[0011] The preprocessing and analysis module is configured to preprocess and analyze multi-source data from the hospital, and to perform pre-diagnosis and preventive maintenance of hospital equipment failures.

[0012] The intelligent operation and maintenance command and management module is configured to automatically dispatch orders and track progress, automate the management of operation and maintenance activities, and quickly activate emergency plans and dispatch emergency resources in the event of emergencies.

[0013] The visualization and interactive module is configured to provide a user-friendly interface for monitoring the hospital's operational status anytime, anywhere.

[0014] Preferably, a 3D model of the hospital building is established for visualization and management, including:

[0015] Information on the hospital's building structure, spatial layout, and equipment installation is collected using IoT devices.

[0016] Based on BIM technology, a three-dimensional model of the hospital building is created according to the hospital's building structure, spatial layout and equipment installation information, and facility and equipment information is integrated.

[0017] Based on the 3D model of the hospital building, the system can visualize and manage the hospital's building structure, spatial layout, and equipment installation information, and view the type, area, and status of each room in the hospital in real time, so as to allocate hospital resources and optimize space.

[0018] Preferably, the hospital's environmental parameters, equipment operating status, and energy consumption are monitored in real time, and multi-source data from the hospital is collected, including:

[0019] Based on IoT devices, the temperature, humidity, air quality, pressure and flow rate in the hospital are monitored and collected in real time to determine the hospital's environmental parameters;

[0020] Based on IoT devices, the on / off status, operating parameters, equipment location, operating sound and vibration of equipment in the hospital are monitored and collected in real time to determine the operating status of the hospital's equipment;

[0021] Based on IoT devices, the hospital's electricity consumption, water consumption, gas consumption and heat consumption are monitored and collected in real time to determine the hospital's energy consumption data.

[0022] Based on the hospital's environmental parameters, equipment operating status, and energy consumption data, multi-source data for the hospital based on IoT devices is determined.

[0023] Preferably, corresponding weight values ​​are assigned to the hospital's environmental parameters, equipment operating status, and energy consumption. These weight values ​​are used for subsequent weighted fusion of multi-source data from the hospital, including:

[0024] The environmental parameters, equipment operating status parameters, and energy consumption parameters are used as data item types.

[0025] Extract the number and types of data types contained in each data item category;

[0026] Detect the correlation coefficients between the various data types contained in each data item category;

[0027] The average correlation coefficient for each data type in each data item category is obtained based on the correlation coefficient between each data type and other data types in that data item category.

[0028] Extract the median value of the average correlation coefficient for each data type contained in the environmental parameters, and process the median value of the average correlation coefficient using the Sigmoid function to generate the weight value corresponding to the environmental parameters.

[0029] Temperature, humidity, and air quality from the environmental parameters are used as the target data type;

[0030] Extract the data change rate of each data type in other data item categories corresponding to a change of one preset unit data volume in the target data type of the environmental parameters; wherein, the preset unit data volume corresponding to each data type is as follows:

[0031] The preset unit of data for temperature is 3℃.

[0032] The preset unit data size for humidity is 5%;

[0033] The preset unit data volume for air quality is 0.1% of the standard concentration of the substances included in the air quality monitoring.

[0034] The weight values ​​for other data item categories are obtained by combining the data change rate of each data type in other data item categories with the average correlation coefficient of each data type in other data item categories when the target data type in the environmental parameters changes by a preset unit of data.

[0035] Preferably, the weight values ​​for other data item categories are obtained by combining the data change rate of each data type in other data item categories when the target data type in the environmental parameters changes by a preset unit of data volume with the average correlation coefficient of each data type in other data item categories, including:

[0036] Extract the rate of change of each data type in other data items when the target data type in the environmental parameters changes by a preset unit of data volume;

[0037] Compare the rate of change of each data type included in other data item categories with the preset rate of change reference value;

[0038] Select the data types whose data change rate is not lower than the preset change rate reference value from other data item categories as reference data types;

[0039] Extract the average correlation coefficient corresponding to the reference data type in the other data item categories, and use the average correlation coefficient corresponding to the reference data type in the other data item categories to obtain the total average correlation coefficient;

[0040] The weight values ​​corresponding to other data item categories are obtained by combining the data change rate of each data type contained in other data item categories when the target data type in the environmental parameters changes by a preset unit of data volume with the total average value of the correlation coefficient.

[0041] Preferably, preprocessing of multi-source hospital data includes:

[0042] Clean the multi-source data of the hospital to remove noisy and duplicate data that are not useful for the intelligent operation and maintenance command and management of the entire hospital process;

[0043] Clean the multi-source data of the hospital, identify missing values ​​and outliers in the multi-source data, and check the identified missing values ​​and outliers to determine whether the identified missing values ​​and outliers are useful for the hospital's full-process intelligent operation and maintenance command and management.

[0044] If the identified missing values ​​and outliers are useful for the hospital's full-process intelligent operation and maintenance command and management, then the missing values ​​are filled and the outliers are corrected. If the identified missing values ​​and outliers are not useful for the hospital's full-process intelligent operation and maintenance command and management, then the missing values ​​and outliers are deleted.

[0045] Preferably, preprocessing of multi-source hospital data also includes:

[0046] Normalize the multi-source data of the hospital to convert it into a unified data format, remove the differences in dimensions in the multi-source data of the hospital, and determine the standardized multi-source data of the hospital.

[0047] Feature extraction is performed on multi-source data from hospitals. Feature vectors useful for intelligent operation and maintenance command and management of the entire hospital process are extracted from the multi-source data of hospitals. The feature vectors are then weighted and fused to determine the characteristic data of the hospital.

[0048] Preferably, pre-diagnosis and preventative maintenance of hospital equipment malfunctions include:

[0049] Based on the needs of intelligent operation and maintenance command and management of the entire hospital process based on BIM IoT collaboration, historical hospital data is collected, and the collected historical hospital data is divided to determine the training set and test set.

[0050] The deep learning model is trained based on the training set, enabling the deep learning model to autonomously learn the pre-diagnosis behavior of hospital equipment faults and determine the pre-diagnosis model of hospital equipment faults.

[0051] The hospital equipment fault pre-diagnosis model was tested based on the test set, and its performance was evaluated to determine whether the hospital equipment fault pre-diagnosis model could achieve the effect of pre-diagnosing hospital equipment faults.

[0052] Based on the test and evaluation results, the parameters of the hospital equipment failure pre-diagnosis model are adjusted and optimized to determine the optimal hospital equipment failure pre-diagnosis model.

[0053] Deploy the best hospital equipment failure pre-diagnosis model and place it in a real hospital equipment failure pre-diagnosis environment.

[0054] Hospital characteristic data is input into the hospital equipment failure pre-diagnosis model. The hospital characteristic data is analyzed based on the hospital equipment failure pre-diagnosis model, and the hospital equipment failure is pre-diagnosed. The pre-diagnosis results of the hospital equipment failure are determined, and preventive maintenance of the hospital equipment failure is carried out based on the pre-diagnosis results.

[0055] Preferably, it features automatic task dispatching and progress tracking for automated management of operations and maintenance activities. In the event of emergencies, it rapidly activates contingency plans and quickly dispatches emergency resources, including:

[0056] The system determines the maintenance personnel responsible for the equipment failure based on the cause of the failure, automatically dispatches orders to the maintenance personnel, and provides intelligent navigation to guide them to the location of the equipment failure for maintenance.

[0057] It also tracks the progress of preventive maintenance of hospital equipment failures in real time, streamlines and standardizes daily operation and maintenance processes, and automates the management of operation and maintenance activities such as reporting, inspection and maintenance of hospital equipment failures.

[0058] In the event of a hospital emergency, timely warnings should be issued, and emergency plans should be activated quickly to guide on-site personnel in a rapid response and to quickly allocate emergency resources.

[0059] Preferably, it provides a user-friendly interface for monitoring the hospital's operational status anytime, anywhere, including:

[0060] Based on the pre-diagnosis results of hospital equipment failures and combined with the hospital's preventive maintenance plan for equipment failures, a hospital-wide intelligent operation and maintenance command and management report is generated and displayed in a visual format on mobile devices to hospital managers, operation and maintenance personnel, and medical staff, so as to keep track of the hospital's operation and maintenance status anytime and anywhere.

[0061] Compared with the prior art, the beneficial effects of the present invention are:

[0062] This invention utilizes BIM technology to create a 3D model of the hospital building, integrating facility and equipment information to achieve visualized management of building structure, spatial layout, equipment installation, and other information. By installing sensors, surveillance cameras, and other IoT devices, it monitors the hospital's environmental parameters, equipment operating status, and energy consumption in real time. It collects multi-source data from the hospital and uses big data analytics to preprocess and analyze this data, providing decision support for operation and maintenance management. This enables pre-diagnosis and preventative maintenance of hospital equipment failures, and automatically dispatches and tracks progress based on equipment failure status. It streamlines and standardizes daily operation and maintenance workflows, automating the management of repair requests, inspections, and maintenance activities. In response to emergencies, it rapidly activates emergency plans, guiding on-site personnel to respond quickly and enabling rapid dispatch of emergency resources, thus improving emergency response capabilities. It provides a user-friendly interface for hospital management, operation and maintenance personnel, and medical staff, supporting mobile access for convenient monitoring of hospital operation and maintenance status anytime, anywhere. Based on BIM and IoT collaboration, it enables intelligent operation and maintenance command and management of the entire hospital process, effectively achieving comprehensive digital management of hospital buildings and equipment, and providing strong support for efficient hospital operation and high-quality development. Attached Figure Description

[0063] Figure 1 This is a module diagram of the hospital end-to-end intelligent operation and maintenance command and management system based on BIM IoT collaboration of the present invention;

[0064] Figure 2 This is a flowchart of the hospital end-to-end intelligent operation and maintenance command and management system based on BIM IoT collaboration of the present invention. Detailed Implementation

[0065] 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. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0066] To address the current limitations of existing technologies that fail to enable intelligent operation and maintenance management across the entire hospital process based on BIM and IoT collaboration, effectively achieve comprehensive digital management of hospital buildings and equipment, and provide strong support for efficient hospital operation and high-quality development, please refer to [link to relevant documentation]. Figures 1-2 This embodiment provides the following technical solution:

[0067] The hospital's end-to-end intelligent operation and maintenance command and management system based on BIM and IoT collaboration includes: a 3D visualization management module, a real-time monitoring and acquisition module, a preprocessing and analysis module, an intelligent operation and maintenance command and management module, and a visualization display and interaction module.

[0068] Specifically, through the interaction between the 3D visualization management module, real-time monitoring and acquisition module, preprocessing and analysis module, intelligent operation and maintenance command and management module, and visualization display and interaction module, intelligent operation and maintenance command and management of the entire hospital process can be carried out based on BIM IoT collaboration. This can effectively realize comprehensive digital management of hospital buildings and equipment, and provide strong support for the hospital's efficient operation and high-quality development.

[0069] Among them, the 3D visualization management module is used to create a 3D model of the hospital building, and to visualize and manage the hospital building;

[0070] In this embodiment, a three-dimensional model of the hospital building is established for visualization and management, including:

[0071] Information on the hospital's building structure, spatial layout, and equipment installation is collected using IoT devices.

[0072] Based on BIM technology, a three-dimensional model of the hospital building is created according to the hospital's building structure, spatial layout and equipment installation information, and facility and equipment information is integrated.

[0073] Based on the 3D model of the hospital building, the system can visualize and manage the hospital's building structure, spatial layout, and equipment installation information, and view the type, area, and status of each room in the hospital in real time, so as to allocate hospital resources and optimize space.

[0074] Among them, the real-time monitoring and acquisition module is used to monitor the hospital's environmental parameters, equipment operating status and energy consumption in real time, and collect multi-source data from the hospital;

[0075] In this embodiment, the hospital's environmental parameters, equipment operating status, and energy consumption are monitored in real time, and multi-source data from the hospital is collected, including:

[0076] Based on IoT devices, the temperature, humidity, air quality, pressure and flow rate in the hospital are monitored and collected in real time to determine the hospital's environmental parameters;

[0077] Specifically, temperature is monitored by temperature sensors to ensure the medical environment meets patient comfort and the operational requirements of medical equipment; humidity is monitored by humidity sensors to prevent excessive humidity from causing mold growth or excessively low humidity from affecting patient comfort; air quality is monitored by air quality sensors to assess whether air quality meets the needs of the medical environment; pressure is monitored by pressure sensors to monitor pressure changes in the ventilation system to ensure reasonable airflow distribution; and flow rate is monitored by flow rate sensors to monitor fresh air volume and drainage volume to optimize the operation of the ventilation and drainage systems.

[0078] Based on IoT devices, the on / off status, operating parameters, equipment location, operating sound and vibration of equipment in the hospital are monitored and collected in real time to determine the operating status of the hospital's equipment;

[0079] Specifically, power on / off status refers to recording the time when the equipment is turned on and off, which is convenient for statistical analysis of equipment usage frequency; operating parameters refer to current, voltage, power, etc., which are used to evaluate equipment operating efficiency and energy consumption; equipment location refers to using the positioning function of IoT devices to monitor the equipment location in real time, which is convenient for rapid scheduling and maintenance; operating sound and vibration refers to monitoring whether the equipment is operating abnormally through sound sensors or vibration sensors, and providing early warning of potential faults.

[0080] Based on IoT devices, the hospital's electricity consumption, water consumption, gas consumption and heat consumption are monitored and collected in real time to determine the hospital's energy consumption data.

[0081] Specifically, electricity consumption refers to monitoring the electricity usage of various departments and equipment, analyzing energy consumption trends, and formulating energy-saving measures; water consumption refers to recording water usage, optimizing water resource allocation, and reducing waste; gas consumption refers to monitoring the amount of gas used by the hospital and evaluating energy consumption efficiency; and heat consumption refers to the heat energy usage of the heating system, used to analyze energy distribution and optimize it.

[0082] Based on the hospital's environmental parameters, equipment operating status, and energy consumption data, multi-source data for the hospital based on IoT devices is determined.

[0083] Specifically, weight values ​​are assigned to the hospital's environmental parameters, equipment operating status, and energy consumption. These weight values ​​are used for subsequent weighted fusion of multi-source data from the hospital, including:

[0084] The environmental parameters, equipment operating status parameters, and energy consumption parameters are used as data item types.

[0085] Extract the number and types of data types contained in each data item category;

[0086] Detect the correlation coefficients between the various data types contained in each data item category;

[0087] The average correlation coefficient for each data type in each data item category is obtained based on the correlation coefficient between each data type and other data types in that data item category.

[0088] Extract the median value of the average correlation coefficient for each data type contained in the environmental parameters, and process the median value of the average correlation coefficient using the Sigmoid function to generate the weight value corresponding to the environmental parameters.

[0089] Temperature, humidity, and air quality from the environmental parameters are used as the target data type;

[0090] Extract the data change rate of each data type in other data item categories corresponding to a change of one preset unit data volume in the target data type of the environmental parameters; wherein, the preset unit data volume corresponding to each data type is as follows:

[0091] The preset unit of data for temperature is 3℃.

[0092] The preset unit data size for humidity is 5%;

[0093] The preset unit data volume for air quality is 0.1% of the standard concentration of the substances included in the air quality monitoring.

[0094] The weight values ​​for other data item categories are obtained by combining the data change rate of each data type in other data item categories with the average correlation coefficient of each data type in other data item categories when the target data type in the environmental parameters changes by a preset unit of data.

[0095] The technical effects of the above solution are as follows: By extracting the number and types of data types from the data items, detecting the correlation coefficients between data types, and calculating the average correlation coefficient, the inherent relationships between different data types can be considered more comprehensively and accurately. The weight values ​​generated on this basis allow for a more reasonable allocation of the weight of each data point during the weighted fusion of multi-source hospital data, thereby improving the accuracy of data fusion and providing a more reliable foundation for subsequent analysis and decision-making based on the fused data. The Sigmoid function is used to process the median value of the average correlation coefficients of the data types in the environmental parameters to generate the corresponding weight values ​​for the environmental parameters. The Sigmoid function has the characteristics of mapping values ​​to specific intervals and smoothing data, which makes the determination of environmental parameter weights more scientific and reasonable, avoiding extreme cases of weight values, and also considering the comprehensive correlation between data types within the environmental parameters. By using temperature, humidity, and air quality as target data types from environmental parameters, and considering the rate of change of each data type in other data categories when these parameters change by a preset unit, and combining this with the average correlation coefficient of data types in other data categories to obtain the corresponding weight values ​​for those data categories, we can more accurately reflect the mutual influence between environmental parameters and other data categories. This allows for a more accurate representation of the importance of different data categories in multi-source data fusion, facilitating in-depth exploration of potential correlations between multi-source data and improving the comprehensiveness and accuracy of the overall hospital operation analysis. Analyzing the parameters corresponding to energy consumption and determining their weight values ​​can highlight the role of energy consumption data in multi-source data fusion, helping hospitals to more clearly understand the relationship between energy consumption and other environmental parameters, equipment operating status, and other factors. This provides stronger data support for energy management and optimization, enabling hospitals to take targeted measures to reduce energy consumption and improve energy efficiency.

[0096] Specifically, based on the rate of change of each data type in other data item categories when the target data type in the environmental parameters changes by a preset unit of data volume, and combined with the average correlation coefficient of each data type in the other data item categories, the weight values ​​corresponding to other data item categories are obtained, including:

[0097] Extract the rate of change of each data type in other data items when the target data type in the environmental parameters changes by a preset unit of data volume;

[0098] Compare the rate of change of each data type included in other data item categories with the preset rate of change reference value;

[0099] Select the data types whose data change rate is not lower than the preset change rate reference value from other data item categories as reference data types;

[0100] Extract the average correlation coefficient corresponding to the reference data type in the other data item categories, and use the average correlation coefficient corresponding to the reference data type in the other data item categories to obtain the total average correlation coefficient;

[0101] The weight values ​​corresponding to other data item categories are obtained by combining the data change rate of each data type contained in other data item categories when the target data type in the environmental parameters changes by a preset unit of data volume with the total average value of the correlation coefficient.

[0102] The weight values ​​corresponding to the other data item types are obtained using the following formula:

[0103] ;

[0104] Where W represents the weight value corresponding to other data item categories; m represents the number of data types included in other data item categories; G i B represents the average correlation coefficient of the i-th data type included in other data item categories; i This represents the rate of change of the i-th data type among other data item categories when the target data type changes by a preset unit of data volume; G p B represents the overall average of the correlation coefficients; p This represents the average rate of change of data across all reference data types.

[0105] The process of constructing the above mathematical model is as follows:

[0106] Step 1: Determine the rate of change and correlation coefficient of the influencing factors of the weights. The weight W must reflect the following two core factors simultaneously.

[0107] Step 2: Construct the contribution value for each data type. The contribution value for each data type needs to be combined with its data change rate and correlation coefficient, with the following structure:

[0108] ;

[0109] in, The geometric mean representing the rate of change of data, taking into account the response of a single data type (B). i), and also incorporates the average response of the overall reference data type (B) p This avoids interference from extreme values. Furthermore, Used to constrain the influence of correlation coefficients, specifically... This is used to map the data volume corresponding to the correlation coefficient to [0, 1], and to ensure that the denominator is non-negative; Choose a smaller correlation coefficient mapping value to prevent the contribution value from becoming abnormally large due to an excessively small denominator.

[0110] Step 3: Average the contribution values ​​of the m data types to reflect the overall impact, and compress the total contribution value to the [0,1][0,1] interval using the Sigmoid function to ensure the stability of the weight values. The final model for obtaining the weight values ​​is as follows:

[0111] ;

[0112] Where W represents the weight value corresponding to other data item categories; m represents the number of data types included in other data item categories; G i B represents the average correlation coefficient of the i-th data type included in other data item categories; i This represents the rate of change of the i-th data type among other data item categories when the target data type changes by a preset unit of data volume; G p B represents the overall average of the correlation coefficients; p This represents the average rate of change of data across all reference data types.

[0113] The technical effects of the above solution are as follows: By comparing the data change rates of each data type in other data item categories with preset reference values, data types with data change rates not lower than the reference values ​​are selected as reference data types. This eliminates data types less affected by changes in environmental parameters, focuses on key data types, improves the accuracy of subsequent analysis and processing, and thus enhances the reliability of performance indicator calculations based on these data. Extracting the average correlation coefficients corresponding to the reference data types and calculating the overall average correlation coefficient, combined with the data change rate to obtain weight values, comprehensively considers the degree of correlation between data types and the degree of influence from changes in environmental parameters. This makes weight determination more scientific and reasonable, helps to more accurately integrate multi-source data, and improves data fusion performance. Analyzing the impact of environmental parameter changes on other data item categories and determining weights allows the system to better adapt to fluctuations in environmental parameters within the hospital environment. It enables the reasonable allocation of weights for each data item category under different environmental conditions, improving the system's adaptability to complex and changing environments and its overall performance.

[0114] By using sine function transformation and taking the minimum value as the denominator, the excessive influence of abnormal average values ​​of correlation coefficients of certain data types on weight calculation is avoided. This balances the role of correlation coefficients of different data types in weight calculation, making weight calculation more robust. This item will change the rate of change of a single data type, B. i Average rate of change B compared to reference data type p This approach combines the characteristics of individual data type changes with the overall reference data type change level in a smooth manner, allowing weight calculations to more comprehensively reflect data changes and enhancing the ability of weight values ​​to represent actual data changes. By mapping the calculation results to the (0,1) interval using the Sigmoid function, the final weight values ​​are kept within a reasonable range, meeting the general requirements for weights to represent importance. This provides standardized and appropriate weights for multi-source data weighting fusion, improving data fusion performance and ultimately enhancing the accuracy of various analyses and decisions based on the fused data.

[0115] Among them, the preprocessing and analysis module is used to preprocess and analyze multi-source data from the hospital, and to perform pre-diagnosis and preventive maintenance of hospital equipment failures;

[0116] In this embodiment, the preprocessing of multi-source data from the hospital includes:

[0117] Clean the multi-source data of the hospital to remove noisy and duplicate data that are not useful for the intelligent operation and maintenance command and management of the entire hospital process;

[0118] Clean the multi-source data of the hospital, identify missing values ​​and outliers in the multi-source data, and check the identified missing values ​​and outliers to determine whether the identified missing values ​​and outliers are useful for the hospital's full-process intelligent operation and maintenance command and management.

[0119] If the identified missing values ​​and outliers are useful for the hospital's full-process intelligent operation and maintenance command and management, then the missing values ​​are filled and the outliers are corrected. If the identified missing values ​​and outliers are not useful for the hospital's full-process intelligent operation and maintenance command and management, then the missing values ​​and outliers are deleted.

[0120] In this embodiment, the preprocessing of multi-source hospital data further includes:

[0121] Normalize the multi-source data of the hospital to convert it into a unified data format, remove the differences in dimensions in the multi-source data of the hospital, and determine the standardized multi-source data of the hospital.

[0122] Feature extraction is performed on multi-source data from hospitals. Feature vectors useful for intelligent operation and maintenance command and management of the entire hospital process are extracted from the multi-source data of hospitals. The feature vectors are then weighted and fused to determine the characteristic data of the hospital.

[0123] In this embodiment, pre-diagnosis and preventative maintenance of hospital equipment malfunctions include:

[0124] Based on the needs of intelligent operation and maintenance command and management of the entire hospital process based on BIM IoT collaboration, historical hospital data is collected, and the collected historical hospital data is divided to determine the training set and test set.

[0125] The deep learning model is trained based on the training set, enabling the deep learning model to autonomously learn the pre-diagnosis behavior of hospital equipment faults and determine the pre-diagnosis model of hospital equipment faults.

[0126] The hospital equipment fault pre-diagnosis model was tested based on the test set, and its performance was evaluated to determine whether the hospital equipment fault pre-diagnosis model could achieve the effect of pre-diagnosing hospital equipment faults.

[0127] Based on the test and evaluation results, the parameters of the hospital equipment failure pre-diagnosis model are adjusted and optimized to determine the optimal hospital equipment failure pre-diagnosis model.

[0128] Deploy the best hospital equipment failure pre-diagnosis model and place it in a real hospital equipment failure pre-diagnosis environment.

[0129] Hospital characteristic data is input into the hospital equipment failure pre-diagnosis model. The hospital characteristic data is analyzed based on the hospital equipment failure pre-diagnosis model, and the hospital equipment failure is pre-diagnosed. The pre-diagnosis results of the hospital equipment failure are determined, and preventive maintenance of the hospital equipment failure is carried out based on the pre-diagnosis results.

[0130] Among them, the intelligent operation and maintenance command and management module is used to automatically dispatch orders and track progress, automate the management of operation and maintenance activities, and quickly activate emergency plans and dispatch emergency resources in the event of emergencies.

[0131] In this embodiment, automatic task dispatching and progress tracking automate the management of operation and maintenance activities. For emergencies, emergency plans are quickly activated, and emergency resources are rapidly deployed, including:

[0132] The system determines the maintenance personnel responsible for the equipment failure based on the cause of the failure, automatically dispatches orders to the maintenance personnel, and provides intelligent navigation to guide them to the location of the equipment failure for maintenance.

[0133] It also tracks the progress of preventive maintenance of hospital equipment failures in real time, streamlines and standardizes daily operation and maintenance processes, and automates the management of operation and maintenance activities such as reporting, inspection and maintenance of hospital equipment failures.

[0134] In the event of a hospital emergency, timely warnings should be issued, and emergency plans should be activated quickly to guide on-site personnel in a rapid response and to quickly allocate emergency resources.

[0135] The visualization and interactive module provides a user-friendly interface for monitoring the hospital's operational status anytime, anywhere.

[0136] In this embodiment, a user-friendly interface is provided to monitor the hospital's operational status anytime, anywhere, including:

[0137] Based on the pre-diagnosis results of hospital equipment failures and combined with the hospital's preventive maintenance plan for equipment failures, a hospital-wide intelligent operation and maintenance command and management report is generated and displayed in a visual format on mobile devices to hospital managers, operation and maintenance personnel, and medical staff, so as to keep track of the hospital's operation and maintenance status anytime and anywhere.

[0138] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0139] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A hospital end-to-end intelligent operation and maintenance command and management system based on BIM and IoT collaboration, characterized in that: include: The 3D visualization management module is configured to create 3D models of hospital buildings and to visualize and manage them. The real-time monitoring and acquisition module is configured to monitor the hospital's environmental parameters, equipment operating status, and energy consumption in real time, and collect multi-source data from the hospital. We assign corresponding weight values ​​to the hospital's environmental parameters, equipment operating status, and energy consumption for subsequent weighted fusion of multi-source data. The preprocessing and analysis module is configured to preprocess and analyze multi-source data from the hospital, and to perform pre-diagnosis and preventive maintenance of hospital equipment failures. The intelligent operation and maintenance command and management module is configured to automatically dispatch orders and track progress, automate the management of operation and maintenance activities, and quickly activate emergency plans and dispatch emergency resources in the event of emergencies. The visualization and interactive module is configured to provide a user-friendly interface for monitoring the hospital's operational status anytime, anywhere. This includes real-time monitoring of the hospital's environmental parameters, equipment operating status, and energy consumption, collecting multi-source data from the hospital, including: Based on IoT devices, the temperature, humidity, air quality, pressure and flow rate in the hospital are monitored and collected in real time to determine the hospital's environmental parameters; Based on IoT devices, the on / off status, operating parameters, equipment location, operating sound and vibration of equipment in the hospital are monitored and collected in real time to determine the operating status of the hospital's equipment; Based on IoT devices, the hospital's electricity consumption, water consumption, gas consumption and heat consumption are monitored and collected in real time to determine the hospital's energy consumption data. Based on the hospital's environmental parameters, equipment operating status, and energy consumption data, determine the hospital's multi-source data based on IoT devices; This includes assigning corresponding weight values ​​to the hospital's environmental parameters, equipment operating status, and energy consumption, including: The environmental parameters, equipment operating status parameters, and energy consumption parameters are used as data item types. Extract the number and types of data types contained in each data item category; Detect the correlation coefficients between the various data types contained in each data item category; The average correlation coefficient for each data type in each data item category is obtained based on the correlation coefficient between each data type and other data types in that data item category. Extract the median value of the average correlation coefficient for each data type contained in the environmental parameters, and process the median value of the average correlation coefficient using the Sigmoid function to generate the weight value corresponding to the environmental parameters. Temperature, humidity, and air quality from the environmental parameters are used as the target data type; Extract the data change rate of each data type contained in other data item categories when the target data type in the environmental parameters changes by a preset unit of data volume; The weight values ​​for other data item categories are obtained by combining the data change rate of each data type in other data item categories with the average correlation coefficient of each data type in other data item categories when the target data type in the environmental parameters changes by a preset unit of data. Specifically, the weight values ​​for other data item categories are obtained by combining the data change rate of each data type in other data item categories when the target data type in the environmental parameters changes by a preset unit of data volume, with the average correlation coefficient of each data type in the other data item categories. This includes: Extract the rate of change of each data type in other data items when the target data type in the environmental parameters changes by a preset unit of data volume; Compare the rate of change of each data type included in other data item categories with the preset rate of change reference value; Select the data types whose data change rate is not lower than the preset change rate reference value from other data item categories as reference data types; Extract the average correlation coefficient corresponding to the reference data type in the other data item categories, and use the average correlation coefficient corresponding to the reference data type in the other data item categories to obtain the total average correlation coefficient; The weight values ​​corresponding to other data item categories are obtained by combining the data change rate of each data type contained in other data item categories when the target data type in the environmental parameters changes by a preset unit of data volume with the total average value of the correlation coefficient.

2. The hospital end-to-end intelligent operation and maintenance command and management system based on BIM IoT collaboration as described in claim 1, characterized in that, Create a 3D model of the hospital building to visualize and manage it, including: Information on the hospital's building structure, spatial layout, and equipment installation is collected using IoT devices. Based on BIM technology, a three-dimensional model of the hospital building is created according to the hospital's building structure, spatial layout and equipment installation information, and facility and equipment information is integrated. Based on the 3D model of the hospital building, the system can visualize and manage the hospital's building structure, spatial layout, and equipment installation information, and view the type, area, and status of each room in the hospital in real time, so as to allocate hospital resources and optimize space.

3. The hospital end-to-end intelligent operation and maintenance command and management system based on BIM IoT collaboration as described in claim 1, characterized in that, Extract the data change rate of each data type in other data item categories corresponding to a change of one preset unit data volume in the target data type of the environmental parameters; wherein, the preset unit data volume corresponding to each data type is as follows: The preset unit of data for temperature is 3℃. The preset unit data size for humidity is 5%; The preset unit data volume for air quality is 0.1% of the standard concentration of the substances included in the air quality monitoring.

4. The hospital end-to-end intelligent operation and maintenance command and management system based on BIM IoT collaboration as described in claim 1, characterized in that, Preprocessing of multi-source hospital data, including: Clean the multi-source data of the hospital to remove noisy and duplicate data that are not useful for the intelligent operation and maintenance command and management of the entire hospital process; Clean the multi-source data of the hospital, identify missing values ​​and outliers in the multi-source data, and check the identified missing values ​​and outliers to determine whether the identified missing values ​​and outliers are useful for the hospital's full-process intelligent operation and maintenance command and management. If the identified missing values ​​and outliers are useful for the hospital's full-process intelligent operation and maintenance command and management, then the missing values ​​are filled and the outliers are corrected. If the identified missing values ​​and outliers are not useful for the hospital's full-process intelligent operation and maintenance command and management, then the missing values ​​and outliers are deleted.

5. The hospital end-to-end intelligent operation and maintenance command and management system based on BIM IoT collaboration as described in claim 1, characterized in that, Preprocessing of multi-source hospital data also includes: Normalize the multi-source data of the hospital to convert it into a unified data format, remove the differences in dimensions in the multi-source data of the hospital, and determine the standardized multi-source data of the hospital. Feature extraction is performed on multi-source data from hospitals. Feature vectors useful for intelligent operation and maintenance command and management of the entire hospital process are extracted from the multi-source data of hospitals. The feature vectors are then weighted and fused to determine the characteristic data of the hospital.

6. The hospital end-to-end intelligent operation and maintenance command and management system based on BIM IoT collaboration as described in claim 5, characterized in that, Pre-diagnosis and preventative maintenance of hospital equipment malfunctions, including: Based on the needs of intelligent operation and maintenance command and management of the entire hospital process based on BIM IoT collaboration, historical hospital data is collected, and the collected historical hospital data is divided to determine the training set and test set. The deep learning model is trained based on the training set, enabling the deep learning model to autonomously learn the pre-diagnosis behavior of hospital equipment faults and determine the pre-diagnosis model of hospital equipment faults. The hospital equipment fault pre-diagnosis model was tested based on the test set, and its performance was evaluated to determine whether the hospital equipment fault pre-diagnosis model could achieve the effect of pre-diagnosing hospital equipment faults. Based on the test and evaluation results, the parameters of the hospital equipment failure pre-diagnosis model are adjusted and optimized to determine the optimal hospital equipment failure pre-diagnosis model. Deploy the best hospital equipment failure pre-diagnosis model and place it in a real hospital equipment failure pre-diagnosis environment. Hospital characteristic data is input into the hospital equipment failure pre-diagnosis model. The hospital characteristic data is analyzed based on the hospital equipment failure pre-diagnosis model, and the hospital equipment failure is pre-diagnosed. The pre-diagnosis results of the hospital equipment failure are determined, and preventive maintenance of the hospital equipment failure is carried out based on the pre-diagnosis results.

7. The hospital end-to-end intelligent operation and maintenance command and management system based on BIM IoT collaboration as described in claim 6, characterized in that, Automated task dispatching and progress tracking enable automated management of operations and maintenance activities. In the event of emergencies, emergency plans are quickly activated, and emergency resources are rapidly deployed, including: The system determines the maintenance personnel responsible for the equipment failure based on the cause of the failure, automatically dispatches orders to the maintenance personnel, and provides intelligent navigation to guide them to the location of the equipment failure for maintenance. It also tracks the progress of preventive maintenance of hospital equipment failures in real time, streamlines and standardizes daily operation and maintenance processes, and automates the management of operation and maintenance activities such as reporting, inspection and maintenance of hospital equipment failures. In the event of a hospital emergency, timely warnings should be issued, and emergency plans should be activated quickly to guide on-site personnel in a rapid response and to quickly allocate emergency resources.

8. The hospital end-to-end intelligent operation and maintenance command and management system based on BIM IoT collaboration as described in claim 7, characterized in that, Provides a user-friendly interface for monitoring hospital operations and maintenance anytime, anywhere, including: Based on the pre-diagnosis results of hospital equipment failures and combined with the hospital's preventive maintenance plan for equipment failures, a hospital-wide intelligent operation and maintenance command and management report is generated and displayed in a visual format on mobile devices to hospital managers, operation and maintenance personnel, and medical staff, so as to keep track of the hospital's operation and maintenance status anytime and anywhere.

Images