Optimized layout method and system for integrated defibrillation device

Abstract

The invention provides an optimized layout method and system for integrated defibrillation equipment. First-aid site space parameters and patient position information are collected, key elements are comprehensively analyzed, and a key element list is generated; based on the key element list, applying a multi-objective evolutionary algorithm, simulating a natural selection process and a genetic variation mechanism, performing global optimization processing on a shortest reaction path, creating a virtual first-aid environment by adopting a digital twin technology, verifying safety and accessibility, and generating a preliminary layout scheme; based on the preliminary layout scheme, carrying out unlabeled data driven learning by using a self-supervised learning graph network algorithm, and generating an optimized layout scheme by adopting a mixed reality aided design method and visualizing a scoring processing result; and on the basis of the optimized layout scheme, continuously monitoring the use efficiency and the first-aid effect, and generating an integrated defibrillation equipment optimized layout strategy. According to the technical scheme provided by the invention, the layout efficiency and safety of the integrated defibrillation equipment are remarkably improved.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of medical emergency technology, and in particular to a method and system for optimizing the layout of an integrated defibrillator device. Background Art

[0002] With the development of emergency medical technology and the increasing public demand for emergency response speed, the application of integrated defibrillator equipment at the emergency scene has become increasingly important. The spatial parameters and patient location information at the emergency scene are complex and changeable, and it is necessary to conduct a comprehensive analysis of the key factors that affect the layout of integrated defibrillator equipment, including but not limited to space size, channel width, equipment placement, and the relative distance between the patient and the equipment. In order to ensure that each defibrillator can reach the patient in the shortest time, the optimal placement point and response path must be found.

[0003] At present, most emergency agencies use manual layout methods based on experience or simple algorithm optimization. Manual layout relies on the experience and intuition of emergency personnel and lacks systematicity and scientificity. Although existing algorithm optimization methods can provide certain guidance, they often only consider a single goal (such as the shortest path) and ignore other important factors such as safety and accessibility. In addition, existing solutions are usually unable to synchronize changes at the emergency scene in real time and are difficult to adapt to emergencies in dynamic environments.

[0004] The main drawbacks of existing solutions are that manual layout methods can easily lead to unreasonable equipment placement, increase emergency response time, and inefficient layout of integrated defibrillator equipment; simple algorithm optimization may ignore complex real-world factors, making the generated path unsafe or unreachable. More importantly, the existing solution lacks a real-time monitoring and adjustment mechanism for changes in the emergency scene. Once the on-site conditions change (such as new obstacles or patient movement), the original layout plan may become invalid. Therefore, a smarter and more flexible method is needed to optimize the layout of integrated defibrillator equipment to meet the needs of modern emergency environments. Summary of the invention

[0005] The embodiments of the present application provide a method and system for optimizing the layout of an integrated defibrillator device, so as to solve the problem of insufficient layout efficiency of the integrated defibrillator device in the prior art.

[0006] In a first aspect, an embodiment of the present application provides a method for optimizing the layout of an integrated defibrillator device, comprising:

[0007] Collecting the spatial parameters and patient location information of the emergency scene, comprehensively analyzing the key factors affecting the layout of the integrated defibrillator equipment, and generating a list of key factors; the key factors refer to a set of factors that have an impact on the layout of the integrated defibrillator equipment in a specific emergency environment;

[0008] Based on the list of key elements, a multi-objective evolutionary algorithm is used to simulate the natural selection process and genetic variation mechanism to accelerate the search process, and the shortest reaction path between each defibrillator and the patient in the integrated defibrillator is globally optimized. A virtual emergency environment is created using digital twin technology, and the virtual emergency environment is synchronized with the emergency site in real time. The safety and accessibility of the shortest reaction path are verified to generate a preliminary layout plan;

[0009] Based on the preliminary layout plan, a self-supervised learning graph network algorithm is used to perform unlabeled data-driven learning on the placement points of each defibrillator in the preliminary layout plan and their associations, and all possible placement points are scored. A mixed reality-assisted design method is used to visualize the scoring results to generate an optimized layout plan;

[0010] Based on the optimized layout scheme and in combination with changes in actual emergency situations, the use efficiency and emergency effects of the integrated defibrillator equipment in the actual emergency situations are continuously monitored to generate an optimized layout strategy for the integrated defibrillator equipment.

[0011] Optionally, based on the list of key elements, a multi-objective evolutionary algorithm is used to accelerate the search process by simulating the natural selection process and the genetic variation mechanism, and a global optimization process is performed on the shortest reaction path between each defibrillator in the integrated defibrillator and the patient. A virtual first aid environment is created using digital twin technology, and the virtual first aid environment is synchronized with the first aid site in real time. The safety and accessibility of the shortest reaction path are verified, and a preliminary layout plan is generated, including:

[0012] Based on the list of key factors, through mathematical modeling and statistical analysis, the multi-dimensional key factors are converted into quantitative indicators for comprehensive analysis and processing to generate a comprehensive evaluation model;

[0013] Based on the comprehensive evaluation model, a multi-objective evolutionary algorithm is used to simulate the natural selection process and genetic variation mechanism to accelerate the search process, and the shortest reaction path between each defibrillator and the patient in the integrated defibrillator is globally optimized to generate a shortest reaction path set; the shortest reaction path set summarizes all the shortest reaction paths;

[0014] Based on the shortest reaction path set, a virtual first aid environment is created using digital twin technology, the virtual first aid environment is synchronized with the first aid site in real time, the safety and accessibility of the shortest reaction path are verified, and a shortest reaction path verification result is generated;

[0015] Based on the shortest reaction path verification result, the placement point and use process of the integrated defibrillator are fully simulated, and the response speed and operational convenience are evaluated during the comprehensive simulation process to generate a preliminary layout plan.

[0016] Optionally, based on the comprehensive evaluation model, a multi-objective evolutionary algorithm is used to simulate the natural selection process and the genetic variation mechanism to accelerate the search process, and the shortest reaction path between each defibrillator in the integrated defibrillator and the patient is globally optimized to generate a shortest reaction path set; the shortest reaction path set summarizes all possible shortest reaction paths, including:

[0017] Based on the comprehensive evaluation model, dynamic weight calculation is performed on the dynamic change factors in the key elements that affect the layout of the integrated defibrillator equipment to generate a dynamic weight matrix; the dynamic change factors include the flow pattern of emergency personnel and the frequency of occurrence of temporary obstacles;

[0018] Based on the dynamic weight matrix, a multi-objective evolutionary algorithm is used to accelerate the search process by simulating the natural selection process and the genetic variation mechanism, and the shortest reaction path between each defibrillator and the patient in the integrated defibrillator is globally optimized to screen out the optimal solution and generate a set of candidate shortest reaction paths;

[0019] Based on the candidate shortest reaction path set, a multi-factor risk assessment framework including physical obstacles and operation complexity is established, the safety risks of the candidate shortest reaction paths in the candidate shortest reaction path set are evaluated and analyzed, and a path safety score table is generated; the path safety score table is a quantitative assessment result of the safety of each candidate shortest reaction path;

[0020] Based on the path safety score table, an intelligent decision support system is introduced to screen and analyze the various safety risk indicators in the path safety score table to generate a set of shortest reaction paths; the intelligent decision support system is an advanced tool for optimizing path selection and resource allocation in complex environments.

[0021] Optionally, based on the shortest reaction path set, a virtual first aid environment is created using digital twin technology, the virtual first aid environment is synchronized with the first aid site in real time, the safety and accessibility of the shortest reaction path are verified, and a shortest reaction path verification result is generated, including:

[0022] Based on the shortest reaction path set, using scenario simulation technology, accurate modeling is performed according to key factors affecting the layout of the integrated defibrillator device to generate a multi-scenario virtual emergency environment; the multi-scenario virtual emergency environment is a series of virtual models built for different emergency situations;

[0023] Based on the multi-scenario virtual emergency environment, digital twin technology is used to create a virtual emergency environment, so that emergency personnel can experience the actual operation process of each shortest reaction path and intuitively evaluate it through the virtual emergency environment, and feedback the shortest reaction path evaluation result;

[0024] Based on the shortest reaction path evaluation result, a comprehensive evaluation is performed on the degree of human-computer interaction in each shortest reaction path in the shortest reaction path set through a human-computer collaborative evaluation method to generate a comprehensive evaluation report; the human-computer collaborative evaluation method integrates artificial intelligence and expert systems, and provides reliable evaluation results through the combination of machine learning and human expertise;

[0025] Based on the comprehensive evaluation report, important factors affecting the emergency rescue efficiency of each shortest reaction path in the shortest reaction path set are identified, the safety and accessibility of each shortest reaction path are verified, and a shortest reaction path verification result is generated.

[0026] Optionally, based on the preliminary layout plan, a self-supervised learning graph network algorithm is used to perform unlabeled data-driven learning on each placement point and its association in the preliminary layout plan, and all possible placement points are scored, and a mixed reality-assisted design method is used to visualize the scoring results to generate an optimized layout plan, including:

[0027] Based on the preliminary layout plan, collecting spatial parameters of each placement point in the preliminary layout plan and relative position information between the device and the patient, extracting key features in the spatial parameters of each placement point, and generating a placement point feature matrix;

[0028] Based on the placement point feature matrix, a self-supervised learning graph network algorithm is used to perform unlabeled data-driven learning on each placement point and its association in the preliminary layout plan, and all possible placement points are scored to generate a scoring result table;

[0029] Based on the scoring result table, an interactive virtual environment is created using a mixed reality-assisted design method, the scoring results in the scoring result table are visualized, and the results are superimposed on the interactive virtual environment to generate a visual evaluation report;

[0030] Based on the scoring results provided in the visual assessment report and the feedback from the emergency team, key placement points are identified and optimized for each placement point in the preliminary layout plan to generate an optimized layout plan.

[0031] Optionally, based on the placement point feature matrix, a self-supervised learning graph network algorithm is used to perform unlabeled data-driven learning on each placement point and its association in the preliminary layout plan, and all possible placement points are scored to generate a scoring result table, including:

[0032] Based on the placement point feature matrix, perform in-depth feature extraction on each element in the placement point feature matrix, select the most representative features for vectorization, and generate a representative feature vector;

[0033] Based on the representative feature vector, a self-supervised learning graph network algorithm is used to perform unlabeled data-driven learning on each placement point and its association in the preliminary layout plan, and all possible placement points are scored to generate a self-supervised learning result;

[0034] Based on the self-supervised learning results, for the placement points with potential problems in the unlabeled data-driven learning, the specific contents of the potential problems are recorded and optimization measures are formulated, and a summary of the placement point evaluation opinions is generated;

[0035] Based on the resettlement point evaluation opinion summary, the resettlement point information in the resettlement point evaluation opinion summary is input into the intelligent simulation system, multiple simulation tests and key evaluations are carried out, and a scoring result table is generated; the intelligent simulation system integrates multiple simulation technologies to simulate the human-computer interaction process in a complex environment.

[0036] Optionally, based on the optimized layout scheme and in combination with changes in actual emergency situations, the use efficiency and emergency effects of the integrated defibrillator equipment in the actual emergency situations are continuously monitored to generate an optimized layout strategy for the integrated defibrillator equipment, including:

[0037] Based on the optimized layout scheme, real-time sensors and monitoring devices are deployed in the integrated defibrillator device to track the use of the integrated defibrillator device in real time and generate a device dynamic data set;

[0038] Based on the dynamic data set of the device, using anomaly detection technology, automatically identifying abnormal conditions and trend changes during the use of the integrated defibrillator device, and generating device anomaly detection results;

[0039] Based on the abnormality detection result of the device, a problem-oriented analysis method is used to perform a problem-oriented adjustment on the operation process of the integrated defibrillator device to generate an optimized adjustment plan;

[0040] Based on the optimization and adjustment plan, combined with the long-term monitoring data generated by the real-time sensors deployed in the integrated defibrillator device, a plan for dealing with emergencies is formulated to generate an optimized layout strategy for the integrated defibrillator device.

[0041] In a second aspect, an embodiment of the present application provides an optimized layout system for an integrated defibrillator device, including:

[0042] A collection module is used to collect the spatial parameters and patient location information of the emergency scene, conduct a comprehensive analysis of the key factors affecting the layout of the integrated defibrillator equipment, and generate a list of key factors; the key factors refer to a set of factors that have a significant impact on the layout of the integrated defibrillator equipment in a specific emergency environment;

[0043] A simulation module is used to use a multi-objective evolutionary algorithm based on the key element list to accelerate the search process by simulating the natural selection process and the genetic variation mechanism, perform global optimization processing on the shortest reaction path between each defibrillator in the integrated defibrillator and the patient, use digital twin technology to create a virtual emergency environment, synchronize the virtual emergency environment with the emergency site in real time, verify the safety and accessibility of the shortest reaction path, and generate a preliminary layout plan;

[0044] A learning module is used to perform unlabeled data-driven learning on each placement point and its relationship in the preliminary layout plan based on the preliminary layout plan by using a self-supervised learning graph network algorithm, and to score all possible placement points, and to visualize the scoring results by using a mixed reality-assisted design method to generate an optimized layout plan;

[0045] The monitoring module is used to continuously monitor the use efficiency and first aid effect of the integrated defibrillator in the actual first aid situation based on the optimized layout plan and in combination with changes in the actual first aid situation, and generate an optimized layout strategy for the integrated defibrillator.

[0046] In a third aspect, an embodiment of the present application provides a computing device, characterized in that it includes a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement an optimized layout method for an integrated defibrillator device as described in the first aspect.

[0047] In a fourth aspect, an embodiment of the present application provides a computer storage medium, characterized in that a computer program is stored therein, and when the computer program is executed by a computer, an optimized layout method of an integrated defibrillator device as described in the first aspect is implemented.

[0048] In the embodiment of the present application, the spatial parameters of the emergency scene and the patient location information are collected, the key factors affecting the layout of the integrated defibrillator equipment are comprehensively analyzed, and a list of key factors is generated; the key factors refer to a set of factors that have an impact on the layout of the integrated defibrillator equipment in a specific emergency environment; based on the list of key factors, a multi-objective evolutionary algorithm is used to simulate the natural selection process and the genetic variation mechanism to accelerate the search process, and the shortest reaction path between each defibrillator in the integrated defibrillator and the patient is globally optimized, and a virtual emergency environment is created using digital twin technology, and the virtual emergency environment is synchronized with the emergency scene in real time. The safety and accessibility of the shortest reaction path are verified to generate a preliminary layout plan; based on the preliminary layout plan, the self-supervised learning graph network algorithm is used to perform unlabeled data-driven learning on the placement points and their associations of each defibrillator in the preliminary layout plan, and all possible placement points are scored, and the mixed reality-assisted design method is used to visualize the scoring results to generate an optimized layout plan; based on the optimized layout plan, combined with the changes in the actual emergency situation, the efficiency of the use of the integrated defibrillator in the actual emergency situation and the emergency effect are continuously monitored to generate an optimized layout strategy for the integrated defibrillator. Through a comprehensive analysis of the spatial parameters of the emergency scene and the patient's location information, it is ensured that all influencing factors are fully considered, thereby improving the emergency response speed; a multi-objective evolutionary algorithm is used for global optimization processing, and a virtual emergency environment is created in combination with digital twin technology to verify the safety and accessibility of the shortest reaction path and reduce operational risks; through virtual simulation, the demand for actual sites and equipment is reduced, and the cost and time of training and drills are greatly reduced; the response speed and operational convenience are evaluated during the comprehensive simulation process to ensure that emergency personnel can use the equipment quickly and accurately in an emergency.

[0049] Furthermore, by introducing a multi-objective evolutionary algorithm, multiple optimization objectives can be considered at the same time, such as response time, operational convenience and safety, to ensure that the Pareto optimal solution set is found and the shortest and optimal reaction path is generated; digital twin technology is used to create a virtual first aid environment and synchronize it with the actual first aid site in real time to ensure that the generated shortest reaction path is also applicable in real scenarios, thereby enhancing the reliability and feasibility of the solution; through comprehensive simulation in the virtual environment, potential problems can be discovered in advance and optimized adjustments can be made, avoiding risks and errors that may occur in actual first aid; comprehensive simulation is carried out based on the shortest reaction path verification results to evaluate response speed and operational convenience, providing high-quality decision support for the first aid team.

[0050] Furthermore, a self-supervised learning graph network algorithm is used to perform unlabeled data-driven learning on each resettlement point and its association in the preliminary layout plan, generating an accurate scoring result table, thereby improving the accuracy and reliability of the scoring process; a mixed reality-assisted design method is used to create an interactive virtual environment, and the scoring results are superimposed on the virtual environment, thereby enhancing the transparency and interactivity of the decision-making process and making the optimized layout plan more in line with actual needs; based on the scoring results provided by the visual evaluation report and the feedback from the emergency team, key resettlement points are identified and optimized to ensure that each resettlement point can play its maximum role in actual emergency treatment; through the mixed reality-assisted design method, the emergency team can repeatedly test and adjust the layout plan in a virtual environment to achieve continuous optimization and improvement, and ultimately generate the optimal layout strategy.

[0051] These and other aspects of the present application will become more clearly understood in the description of the following embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0053] Figure 1 A flow chart of a method for optimizing the layout of an integrated defibrillator device provided in an embodiment of the present application;

[0054] Figure 2 A schematic diagram of the structure of an optimized layout system for an integrated defibrillator device provided in an embodiment of the present application;

[0055] Figure 3 A schematic diagram of the structure of a computing device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0056] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application.

[0057] In some of the processes described in the specification and claims of this application and the above-mentioned figures, multiple operations that appear in a specific order are included, but it should be clearly understood that these operations may not be executed in the order in which they appear in this article or executed in parallel. The serial numbers of the operations, such as 101, 102, etc., are only used to distinguish between different operations, and the serial numbers themselves do not represent any execution order. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions of "first", "second", etc. in this article are used to distinguish different messages, devices, modules, etc., do not represent the order of precedence, and do not limit the "first" and "second" to be different types.

[0058] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0059] Figure 1 A flowchart of a method for optimizing the layout of an integrated defibrillator device is provided for an embodiment of the present application. Figure 1 As shown, the method includes:

[0060] 101. Collect the spatial parameters and patient location information of the emergency scene, conduct a comprehensive analysis of the key factors affecting the layout of the integrated defibrillator equipment, and generate a list of key factors; the key factors refer to a set of factors that have an impact on the layout of the integrated defibrillator equipment in a specific emergency environment;

[0061] In this step, the emergency scene space parameters refer to the specific data of the physical environment in the emergency environment, including room size, door location and size, passage width, obstacle distribution, etc. These parameters are used to ensure that each defibrillator can reach the patient in the shortest time and have enough space for operation.

[0062] Patient location information refers to the patient's specific location at the emergency scene and its possible changes, including the patient's initial location, movement path, and possible final location. This information is used to plan the shortest effective path from the defibrillator to the patient.

[0063] Key elements refer to a set of factors that affect the layout of integrated defibrillator equipment in a specific emergency environment. These factors include space parameters, patient location information, equipment placement, and operational convenience for emergency personnel.

[0064] The critical elements checklist is a detailed list of all important factors that affect the layout of the integrated defibrillator device and is used to guide subsequent optimization steps.

[0065] In the embodiment of the present application, first, the spatial parameters and patient location information of the emergency scene are collected to ensure that all relevant data are completely recorded; second, these data are preprocessed to eliminate noise and outliers to improve the accuracy of subsequent analysis; third, feature extraction technology is used to extract key information from the original data to provide a solid foundation for subsequent steps; finally, a list of key elements is generated to clearly list all important factors that affect the layout of the integrated defibrillator equipment.

[0066] Suppose a large shopping mall needs to quickly deploy emergency resources to respond to a sudden heart attack. First, the emergency team uses a laser rangefinder and a GPS positioning system to collect the mall's spatial parameters (such as room size, aisle width) and patient location information (such as the patient's initial location and possible movement path). Second, the data is uploaded to the cloud server through a mobile application for preliminary processing. Third, the server uses a machine learning algorithm to analyze the data, extract key features, and generate a list of key elements. Finally, the list is displayed to the emergency team in real time through a tablet computer, guiding the emergency team to quickly determine the best equipment placement location.

[0067] 102. Based on the list of key elements, a multi-objective evolutionary algorithm is used to simulate the natural selection process and genetic variation mechanism to accelerate the search process, and the shortest reaction path between each defibrillator and the patient in the integrated defibrillator is globally optimized. The digital twin technology is used to create a virtual emergency environment, and the virtual emergency environment is synchronized with the emergency site in real time. The safety and accessibility of the shortest reaction path are verified to generate a preliminary layout plan;

[0068] In this step, the multi-objective evolutionary algorithm is an intelligent algorithm that can simultaneously consider multiple optimization objectives (such as response time, operational convenience and safety). It accelerates the process of searching for the optimal solution by simulating the natural selection process and genetic variation mechanism, aiming to find the Pareto optimal solution set, that is, the best solution that achieves a balance between multiple objectives.

[0069] The natural selection process refers to a computational model that mimics the law of survival of the fittest in nature. In this process, the performance of each candidate solution is evaluated according to a pre-defined fitness function, and the best performing individuals are selected as the basis for the next generation. The fitness function is used to quantify the quality of each candidate solution. The higher the fitness, the closer the solution is to the optimal solution.

[0070] The genetic variation mechanism includes two main operations: crossover and mutation. Crossover refers to randomly selecting part of the genome from two or more parent individuals to synthesize new offspring individuals; mutation refers to randomly changing the value of certain genes to introduce new diversity.

[0071] The shortest response path refers to the shortest effective path from the defibrillator to the patient. Its safety and accessibility are important indicators for evaluating the quality of the path.

[0072] Digital twin technology refers to the construction of virtual models to reflect the status and behavior of physical objects in real time, ensuring that the virtual environment is completely consistent with the real world. This technology makes it possible to simulate actual emergency scenarios in a virtual environment and conduct various tests and optimizations without repeated trials in the real environment, thus saving time and costs.

[0073] Global optimization processing refers to the process of finding the optimal path in the entire emergency environment to ensure that the path between each defibrillator and the patient is optimal. This process not only takes into account the distance factor, but also comprehensively considers the safety and accessibility of the path to ensure that the patient can be reached quickly and safely in an emergency.

[0074] The preliminary layout plan is a preliminary defibrillator equipment layout plan generated based on the results of global optimization processing. The plan describes in detail the specific location of each defibrillator and the shortest response path between it and the patient, ensuring that the equipment can reach the patient quickly and safely during the emergency treatment process.

[0075] In the embodiments of the present application, firstly, based on the list of key factors, multiple optimization objectives are defined, such as response time, operational convenience and safety; secondly, a multi-objective evolutionary algorithm is applied to accelerate the process of searching for the optimal solution by simulating the natural selection process and the genetic variation mechanism; thirdly, the shortest reaction path between each defibrillator and the patient is globally optimized; finally, a virtual emergency environment is created by using digital twin technology, and it is synchronized with the emergency scene in real time to verify the safety and accessibility of the shortest reaction path and generate a preliminary layout plan.

[0076] For example, continuing with the previous example, assuming that the emergency team has generated a list of key elements, the next step is to optimize the layout of the defibrillator equipment. First, based on the list of key elements, define multiple optimization goals, such as response time, ease of operation, and safety; second, apply a multi-objective evolutionary algorithm to accelerate the search for the optimal solution by simulating the natural selection process and genetic variation mechanism; third, globally optimize the shortest reaction path between each defibrillator and the patient; finally, use digital twin technology to create a virtual emergency environment, and synchronize it with the emergency site in real time to verify the safety and accessibility of the shortest reaction path and generate a preliminary layout plan.

[0077] 103. Based on the preliminary layout plan, a self-supervised learning graph network algorithm is used to perform unlabeled data-driven learning on the placement points of each defibrillator device in the preliminary layout plan and their associations, and all possible placement points are scored, and a mixed reality-assisted design method is used to visualize the scoring results to generate an optimized layout plan;

[0078] In this step, the self-supervised learning graph network algorithm is a learning method driven by unlabeled data. It automatically discovers patterns and structures in the data by learning nodes and their relationships. The algorithm does not require pre-labeled data, but instead mines the inherent laws in the data through self-learning, which is suitable for scenarios where there is a lack of labeled data.

[0079] The placement points and their associations refer to the specific location of each defibrillator device and its relationship with other devices or environmental elements. The selection of placement points should not only consider the characteristics of the device itself, but also the influence of the surrounding environment, such as channel width, obstacle distribution, etc. The association relationship describes the interaction between devices, such as signal transmission path, collaborative operation process, etc.

[0080] Mixed reality-assisted design method is a method that combines virtual reality and augmented reality technologies to create an interactive virtual environment to help users better understand and make decisions. This method can simulate actual scenes in a virtual environment and superimpose the scoring results into the virtual environment, allowing users to intuitively see the effects of different placement points.

[0081] The optimized layout plan is the final optimized plan generated through scoring and visualization processing based on the preliminary layout plan. This plan not only takes into account the advantages of the preliminary layout plan, but also further optimizes the positions of each placement point and their correlation through the self-supervised learning graph network algorithm, ensuring that each placement point can play the maximum role in actual first aid.

[0082] In the embodiment of the present application, first, based on the preliminary layout plan, the spatial parameters of each placement point and the relative position information between the equipment and the patient are collected; secondly, the self-supervised learning graph network algorithm is used to perform unlabeled data-driven learning on each placement point and their associations in the preliminary layout plan; thirdly, all possible placement points are scored and a scoring result table is generated; finally, a mixed reality-assisted design method is used to visualize the scoring results and generate an optimized layout plan.

[0083] For example, continuing with the previous example, assuming that the preliminary layout plan has been generated, the next step is to optimize each placement point. First, based on the preliminary layout plan, collect the spatial parameters of each placement point and the relative position information between the equipment and the patient; second, use the self-supervised learning graph network algorithm to perform unlabeled data-driven learning on each placement point and its association in the preliminary layout plan; third, score all possible placement points and generate a scoring result table; finally, use the mixed reality-assisted design method to visualize the scoring results and generate an optimized layout plan to ensure that each placement point can play the maximum role in actual emergency treatment.

[0084] 104. Based on the optimized layout plan and in combination with changes in actual emergency situations, the use efficiency and emergency effects of the integrated defibrillator equipment in the actual emergency situations are continuously monitored to generate an optimized layout strategy for the integrated defibrillator equipment.

[0085] In this step, usage efficiency refers to the speed and effectiveness of the defibrillator in actual emergency situations.

[0086] The first aid effect refers to the degree to which the defibrillator improves the patient's health during the first aid process.

[0087] Continuous monitoring refers to the real-time tracking and evaluation of the efficiency of the use of defibrillator equipment and the effectiveness of first aid during the actual first aid process.

[0088] The integrated defibrillator equipment optimization layout strategy is a complete set of optimization recommendations and implementation steps generated based on continuous monitoring results. This strategy not only includes specific adjustment measures, such as equipment location adjustment, quantity increase or decrease, etc., but also includes predictions and response plans for new situations that may arise in the future, to ensure the long-term and efficient operation of the emergency system.

[0089] In the embodiments of the present application, firstly, based on the optimized layout plan, combined with the changes in the actual emergency rescue situation; secondly, the use efficiency and emergency rescue effect of the integrated defibrillator equipment in the actual emergency rescue situation are continuously monitored; thirdly, the monitoring data is analyzed to identify the factors affecting the emergency rescue effect; finally, the optimized layout strategy of the integrated defibrillator equipment is generated according to the monitoring results to ensure that the best emergency rescue effect can be achieved in various situations.

[0090] For example, continuing with the above example, assume that the optimized layout plan has been generated and applied to the actual first aid scenario. First, based on the optimized layout plan, combined with the changes in the actual first aid situation, the efficiency of the use of the integrated defibrillator equipment and the first aid effect are continuously monitored; secondly, the monitoring data is analyzed to identify factors that affect the first aid effect, such as equipment response time, first aid personnel's operating proficiency, etc.; thirdly, the layout plan is adjusted according to the monitoring results to ensure that each defibrillator can play the maximum efficiency in actual first aid; finally, the integrated defibrillator equipment optimization layout strategy is generated to provide a reference for similar scenarios in the future to ensure the maximization of the first aid effect.

[0091] In order to solve the problems of inaccurate path planning and insufficient safety verification that may occur during the optimization of the layout of the integrated defibrillator, in some embodiments, the global optimization process in step 102 includes: based on the key element list, through mathematical modeling and statistical analysis, the multi-dimensional key elements are converted into quantitative indicators for comprehensive analysis and processing to generate a comprehensive evaluation model; based on the comprehensive evaluation model, a multi-objective evolutionary algorithm is used to simulate the natural selection process and the genetic variation mechanism to accelerate the search process, and the shortest reaction path between each defibrillator in the integrated defibrillator and the patient is globally optimized to generate a shortest reaction path set; the shortest reaction path set summarizes all the shortest reaction paths; based on the shortest reaction path set, a virtual emergency environment is created using digital twin technology, the virtual emergency environment is synchronized with the emergency site in real time, the safety and accessibility of the shortest reaction path are verified, and a shortest reaction path verification result is generated; based on the shortest reaction path verification result, the installation point and use process of the integrated defibrillator are fully simulated, and the response speed and operation convenience are evaluated during the comprehensive simulation process to generate a preliminary layout plan.

[0092] In this embodiment, the comprehensive evaluation model is a data set that stores quantitative indicators obtained after mathematical modeling and statistical analysis, which is used for subsequent optimization algorithm processing. These quantitative indicators can accurately reflect the influence of each factor on the layout of the defibrillator equipment, thereby providing reliable input data for the subsequent optimization algorithm.

[0093] Mathematical modeling is the process of abstracting real-world problems into mathematical expressions, aiming to describe actual phenomena by establishing mathematical relationships. In this process, the model can capture the complex relationships between various factors and provide a basis for subsequent calculations and optimization.

[0094] Statistical analysis is a data analysis method used to explore potential patterns and trends in data. It can help identify key features that affect the layout of defibrillator equipment and quantify the importance of these features.

[0095] Quantitative indicators are specific values ​​or scores obtained by processing and converting raw data. They are used to measure the impact of different factors on layout optimization. These indicators make complex data more intuitive and easier to compare.

[0096] The shortest response path set summarizes all possible shortest response paths, which are the optimal paths from each defibrillator to the patient. The set not only takes into account the distance factor, but also comprehensively considers the safety and accessibility of the path to ensure that the patient can be reached quickly and safely in an emergency.

[0097] The virtual emergency environment is a virtual model created through digital twin technology, which can reflect the status and changes of the emergency scene in real time.

[0098] The shortest reaction path verification result is obtained after the safety and reachability of each path in the shortest reaction path set are verified. The verification result not only provides quantitative evaluation data, but also provides an intuitive reference for subsequent decision-making.

[0099] Comprehensive simulation is a detailed simulation of the placement and use of integrated defibrillator equipment in a virtual emergency environment. This process not only takes into account the location of the equipment, but also includes the operating procedures of emergency personnel, the collaboration between equipment and other aspects.

[0100] In the embodiments of the present application, firstly, according to the list of key elements, through mathematical modeling and statistical analysis, the multi-dimensional key elements are converted into quantitative indicators for comprehensive analysis and processing, and a comprehensive evaluation model is generated; secondly, based on the comprehensive evaluation model, a multi-objective evolutionary algorithm is used to simulate the natural selection process and the genetic variation mechanism to accelerate the search process, and the shortest reaction path between each defibrillator device and the patient in the integrated defibrillator device is globally optimized to generate a set of shortest reaction paths; thirdly, based on the set of shortest reaction paths, a virtual first aid environment is created using digital twin technology, the virtual first aid environment is synchronized with the first aid site in real time, the safety and accessibility of the shortest reaction path are verified, and a shortest reaction path verification result is generated; finally, based on the shortest reaction path verification result, the installation point and use process of the integrated defibrillator device are fully simulated, and the response speed and operational convenience are evaluated during the comprehensive simulation process to generate a preliminary layout plan.

[0101] Here is a specific example:

[0102] Suppose a large shopping mall needs to quickly deploy emergency resources to respond to sudden heart attacks. First, the emergency team uses laser rangefinders and GPS positioning systems to collect the mall's spatial parameters (such as room size, aisle width) and patient location information (such as the patient's initial location and possible movement path), and generates a list of key elements based on these data; second, based on the list of key elements, through mathematical modeling and statistical analysis, the multi-dimensional key elements are converted into quantitative indicators for comprehensive analysis and processing to generate a comprehensive evaluation model; third, based on the comprehensive evaluation model, a multi-objective evolutionary algorithm is applied to accelerate the search for the optimal solution by simulating the natural selection process and genetic variation mechanism. The shortest reaction path between each defibrillator and the patient is globally optimized to generate a set of shortest reaction paths. Then, based on the set of shortest reaction paths, a virtual first aid environment is created using digital twin technology. The virtual first aid environment is synchronized with the first aid site in real time to verify the safety and accessibility of the shortest reaction path and generate a verification result of the shortest reaction path. Finally, based on the verification result of the shortest reaction path, a comprehensive simulation is performed on the placement point and use process of the integrated defibrillator. The response speed and ease of operation are evaluated during the comprehensive simulation process to generate a preliminary layout plan to ensure that each placement point can achieve maximum effectiveness in actual first aid.

[0103] In order to solve the problems of inaccurate path planning and insufficient safety verification that may occur during the optimization of the layout of the integrated defibrillator equipment, and to further improve the safety and accessibility of the shortest reaction path, in some embodiments, the global optimization process in step 102 includes: based on the comprehensive evaluation model, dynamically calculating the weights of the dynamic change factors in the key elements that affect the layout of the integrated defibrillator equipment to generate a dynamic weight matrix; the dynamic change factors include the flow pattern of emergency personnel and the frequency of occurrence of temporary obstacles; based on the dynamic weight matrix, using a multi-objective evolutionary algorithm, by simulating the natural selection process and the genetic variation mechanism to accelerate the search process, the shortest reaction path between each defibrillator in the integrated defibrillator equipment and the patient is calculated. A global optimization process is performed to screen out the optimal solution and generate a set of candidate shortest reaction paths; based on the set of candidate shortest reaction paths, a multi-factor risk assessment framework including physical obstacles and operational complexity is established, the safety risks of the candidate shortest reaction paths in the set of candidate shortest reaction paths are evaluated and analyzed, and a path safety score table is generated; the path safety score table is a quantitative assessment result of the safety of each candidate shortest reaction path; based on the path safety score table, an intelligent decision support system is introduced to screen and analyze the various safety risk indicators in the path safety score table to generate a set of shortest reaction paths; the intelligent decision support system is an advanced tool for optimizing path selection and resource allocation in complex environments.

[0104] The dynamic weight matrix is ​​a data structure that stores the weight values ​​of dynamically changing factors in the key elements that affect the layout of integrated defibrillator equipment. These weight values ​​reflect the importance of different factors at different time points, such as changes in the flow patterns of emergency personnel and the frequency of temporary obstacles.

[0105] Dynamic factors are those that change over time and with environmental changes, such as the mobility patterns of first responders (i.e., how first responders move around the emergency scene) and the frequency of temporary obstacles (i.e., obstacles that suddenly appear at the emergency scene).

[0106] The candidate shortest reaction path set is a set of shortest reaction paths that have been screened. These paths are considered to be potential optimal solutions. By applying a multi-objective evolutionary algorithm, the path that best meets the optimization goal can be selected from a large number of possible paths.

[0107] The multi-factor risk assessment framework is a systematic assessment tool that is used to comprehensively evaluate the safety risks of candidate shortest reaction paths by taking into account factors such as physical obstacles and operational complexity. The framework can help identify potential risk points and provide quantitative assessment results.

[0108] The path safety score table is a quantitative assessment result of the safety of each candidate shortest reaction path. Through the multi-factor risk assessment framework, a safety score can be assigned to each path, thereby helping decision makers choose the safest path.

[0109] The intelligent decision support system is an advanced tool used to optimize path selection and resource allocation in complex environments. It can automatically analyze various safety risk indicators based on the information provided by the path safety score sheet, recommend the optimal path, and assist decision makers in making the final decision.

[0110] In an embodiment of the present application, first, based on a comprehensive evaluation model, dynamic weight calculations are performed on the dynamic changing factors in the key elements that affect the layout of the integrated defibrillator device to generate a dynamic weight matrix; secondly, based on the dynamic weight matrix, a multi-objective evolutionary algorithm is used to accelerate the search process by simulating the natural selection process and the genetic variation mechanism, and a global optimization process is performed on the shortest reaction path between each defibrillator device and the patient in the integrated defibrillator device to screen out the optimal solution and generate a set of candidate shortest reaction paths; thirdly, based on the set of candidate shortest reaction paths, a multi-factor risk assessment framework including physical obstacles and operational complexity is established, and the safety risks of the candidate shortest reaction paths in the set of candidate shortest reaction paths are evaluated and analyzed to generate a path safety score table; finally, based on the path safety score table, an intelligent decision support system is introduced to screen and analyze the various safety risk indicators in the path safety score table to generate a set of shortest reaction paths.

[0111] Here is a specific example:

[0112] Assuming that emergency resources are deployed in a busy city square to respond to sudden heart attacks, first, the emergency team calculates the dynamic weights of the key factors affecting the layout of the integrated defibrillator equipment (such as the flow pattern of emergency personnel and the frequency of temporary obstacles) based on the comprehensive evaluation model, and generates a dynamic weight matrix. Secondly, based on the dynamic weight matrix, a multi-objective evolutionary algorithm is used to simulate the natural selection process and genetic variation mechanism to accelerate the search process, and the shortest reaction path between each defibrillator and the patient in the integrated defibrillator equipment is globally optimized to screen out the optimal solution and generate a set of candidate shortest reaction paths. Thirdly, based on the set of candidate shortest reaction paths, a multi-factor risk assessment framework including physical obstacles and operation complexity is established, and the safety risks of the candidate shortest reaction paths in the set of candidate shortest reaction paths are evaluated and analyzed to generate a path safety score table. Finally, based on the path safety score table, an intelligent decision support system is introduced to screen and analyze the various safety risk indicators in the path safety score table to generate a set of shortest reaction paths, ensuring that each placement point can play the maximum role in actual emergency treatment, while maximizing the safety and accessibility of the path.

[0113] In order to solve the problem of insufficient verification of the safety and accessibility of the shortest reaction path during the optimization of the layout of the integrated defibrillator equipment and further improve the authenticity and reliability of the path planning, in some embodiments, the global optimization processing in step 102 includes: based on the shortest reaction path set, using scenario simulation technology, accurately modeling according to the key factors affecting the layout of the integrated defibrillator equipment, and generating a multi-scenario virtual emergency environment; the multi-scenario virtual emergency environment is a series of virtual models constructed for different emergency situations; based on the multi-scenario virtual emergency environment, using digital twin technology to create a virtual emergency environment so that emergency personnel can experience each shortest reaction path through the virtual emergency environment. The actual operation process of the reaction path is intuitively evaluated, and the shortest reaction path evaluation result is fed back; based on the shortest reaction path evaluation result, the degree of human-computer interaction in each shortest reaction path in the shortest reaction path set is comprehensively evaluated through a human-computer collaborative evaluation method, and a comprehensive evaluation report is generated; the human-computer collaborative evaluation method integrates artificial intelligence and expert systems, and provides reliable evaluation results through machine learning combined with human professional knowledge; based on the comprehensive evaluation report, the important factors affecting the emergency rescue efficiency of each shortest reaction path in the shortest reaction path set are identified, the safety and accessibility of each shortest reaction path are verified, and the shortest reaction path verification result is generated.

[0114] The multi-scenario virtual emergency environment is a series of virtual models built for different emergency situations. These virtual models accurately simulate various possible emergency scenarios, including but not limited to different types of buildings, different patient distributions, and obstacle locations.

[0115] Scenario simulation technology is a method for creating and running simulations that can accurately model key factors that affect the layout of integrated defibrillator equipment (such as spatial parameters, patient location information, temporary obstacles, etc.). This technology can help identify potential risk points and provide quantitative assessment results.

[0116] The shortest response path evaluation results are an intuitive evaluation and feedback of the actual operation process of each shortest response path. First responders can experience and evaluate the operational convenience and safety of each path through a virtual first aid environment, providing valuable practical experience feedback.

[0117] The human-machine collaborative evaluation method is a comprehensive evaluation method that combines artificial intelligence and expert systems. It analyzes data through machine learning algorithms and combines human expertise to provide reliable evaluation results. This method not only improves the accuracy of the evaluation, but also enhances the credibility of the evaluation results.

[0118] The comprehensive evaluation report is a document generated after a comprehensive evaluation of the degree of human-computer interaction in each shortest reaction path in the shortest reaction path set. The report content includes but is not limited to the safety, accessibility, response speed and ease of operation of the path, providing an important reference for subsequent optimization.

[0119] In an embodiment of the present application, first, based on the shortest reaction path set, scenario simulation technology is used to accurately model the key factors affecting the layout of the integrated defibrillator equipment, and a multi-scenario virtual first aid environment is generated; secondly, based on the multi-scenario virtual first aid environment, digital twin technology is used to create a virtual first aid environment, so that first aid personnel can experience the actual operation process of each shortest reaction path through the virtual first aid environment and intuitively evaluate it, and feedback the shortest reaction path evaluation results; thirdly, based on the shortest reaction path evaluation results, a human-computer collaborative evaluation method is used to comprehensively evaluate the degree of human-computer interaction in each shortest reaction path in the shortest reaction path set, and a comprehensive evaluation report is generated; finally, based on the comprehensive evaluation report, the important factors affecting the first aid efficiency of each shortest reaction path in the shortest reaction path set are identified, the safety and accessibility of each shortest reaction path are verified, and the shortest reaction path verification results are generated.

[0120] Here is a specific example:

[0121] Assuming that the layout of integrated defibrillator equipment needs to be optimized in a large hospital to deal with sudden cardiac events, firstly, based on the shortest reaction path set, scenario simulation technology is used to accurately model the key factors affecting the layout of integrated defibrillator equipment (such as ward layout, corridor width, patient position, etc.) to generate a multi-scenario virtual emergency environment; secondly, based on the multi-scenario virtual emergency environment, digital twin technology is used to create a virtual emergency environment, so that emergency personnel can experience the actual operation process of each shortest reaction path through the virtual emergency environment and intuitively evaluate it, and feedback the shortest reaction path evaluation results; thirdly, based on the shortest reaction path evaluation results, the human-computer interaction degree in each shortest reaction path in the shortest reaction path set is comprehensively evaluated through the human-computer collaborative evaluation method, and a comprehensive evaluation report is generated; finally, based on the comprehensive evaluation report, the important factors affecting the emergency efficiency of each shortest reaction path in the shortest reaction path set are identified, the safety and accessibility of each shortest reaction path are verified, and the shortest reaction path verification results are generated to ensure that each placement point can play the maximum role in actual emergency treatment, while maximizing the safety and accessibility of the path.

[0122] In order to solve the problems of unreasonable selection of placement points and unclear associations that may occur during the layout optimization of the integrated defibrillator equipment, and to further improve the scientificity and rationality of the layout plan, in some embodiments, the global optimization process in step 103 includes: based on the preliminary layout plan, collecting the spatial parameters of each placement point in the preliminary layout plan and the relative position information between the equipment and the patient, extracting the key features in the spatial parameters of each placement point, and generating a placement point feature matrix; based on the placement point feature matrix, using a self-supervised learning graph network algorithm, performing unlabeled data-driven learning on each placement point and its association in the preliminary layout plan, and scoring all possible placement points to generate a scoring result table; based on the scoring result table, using a mixed reality-assisted design method to create an interactive virtual environment, visualizing the scoring results in the scoring result table, superimposing them on the interactive virtual environment, and generating a visual evaluation report; based on the scoring results provided in the visual evaluation report and the feedback from the emergency team, identifying and optimizing key placement points for each placement point in the preliminary layout plan to generate an optimized layout plan.

[0123] In this embodiment, the placement point feature matrix is ​​a data structure that stores the spatial parameters of each placement point in the preliminary layout plan and the relative position information between the device and the patient. These parameters are formed into a matrix after extracting key features for subsequent self-supervised learning graph network algorithm analysis.

[0124] The scoring result table is a collection of results generated after scoring all possible placement points. The scoring criteria can be formulated based on multiple dimensions, such as response time, operational convenience, safety, etc. The scoring result table not only provides quantitative evaluation data, but also provides an intuitive reference for subsequent decision-making, helping to determine the optimal placement point configuration.

[0125] The visual evaluation report is created through mixed reality-assisted design methods. It is a report that visualizes the scoring results in the scoring result table. This report not only shows the scoring of each resettlement point, but also provides a visual representation of the relationship between the resettlement points, making the evaluation process more transparent and easy to understand.

[0126] Identification and optimization of key placement points refers to analyzing each placement point in the preliminary layout plan based on the scoring results provided by the visual assessment report and the feedback from the emergency team, identifying the key placement points that have the greatest impact on the overall layout, and optimizing and adjusting them to ensure that the final optimized layout plan can achieve the best results in actual applications.

[0127] In an embodiment of the present application, first, based on a preliminary layout plan, spatial parameters of each placement point in the preliminary layout plan and relative position information between the equipment and the patient are collected, key features in the spatial parameters of each placement point are extracted, and a placement point feature matrix is ​​generated; secondly, based on the placement point feature matrix, a self-supervised learning graph network algorithm is used to perform unlabeled data-driven learning on each placement point and its association in the preliminary layout plan, and all possible placement points are scored to generate a scoring result table; thirdly, based on the scoring result table, a mixed reality-assisted design method is used to create an interactive virtual environment, the scoring results in the scoring result table are visualized, superimposed on the interactive virtual environment, and a visualization evaluation report is generated; finally, based on the scoring results provided in the visualization evaluation report and the feedback from the emergency team, key placement points are identified and optimized for each placement point in the preliminary layout plan to generate an optimized layout plan.

[0128] Here is a specific example:

[0129] Assuming that in a cardiology department of a large hospital, in order to optimize the layout of defibrillator equipment to deal with sudden cardiac arrest events, firstly, based on the preliminary layout plan, the spatial parameters of each placement point in the preliminary layout plan (such as ward layout, corridor width, emergency room location) and the relative position information between the defibrillator equipment and the patient (such as the nearest bed or first aid station) are collected, and the key features in the spatial parameters of each placement point are extracted to generate a placement point feature matrix; secondly, based on the placement point feature matrix, the self-supervised learning graph network algorithm is used to perform unlabeled data-driven learning on each placement point and its association in the preliminary layout plan, and all possible placement points are scored to generate a scoring result table; thirdly, based on the scoring result table, a mixed reality-assisted design method is used to create an interactive virtual environment, and the scoring results in the scoring result table are visualized and superimposed on the interactive virtual environment to generate a visual evaluation report; finally, based on the scoring results provided in the visual evaluation report and the feedback from the first aid team, the key placement points in the preliminary layout plan are identified and optimized to generate an optimized layout plan to ensure that each placement point can play the maximum role in actual first aid and maximize the safety and accessibility of the path.

[0130] In order to solve the problems of unreasonable selection of placement points and unclear associations that may occur during the layout optimization of the integrated defibrillator equipment, and to further improve the accuracy and scientificity of the scoring process, in some embodiments, the global optimization process described in step 103 includes: based on the placement point feature matrix, performing in-depth feature extraction on each element in the placement point feature matrix, screening the most representative features for vectorization, and generating a representative feature vector; based on the representative feature vector, using a self-supervised learning graph network algorithm, performing unlabeled data-driven learning on each placement point and its association in the preliminary layout plan, and scoring all possible placement points to generate a self-supervised learning result; based on the self-supervised learning result, for placement points with potential problems in the unlabeled data-driven learning, recording the specific content of the potential problems and formulating optimization measures, and generating a summary of placement point evaluation opinions; based on the summary of placement point evaluation opinions, inputting the placement point information in the summary of placement point evaluation opinions into an intelligent simulation system, performing multiple simulation tests and key evaluations, and generating a scoring result table; the intelligent simulation system integrates multiple simulation technologies to simulate the human-computer interaction process in a complex environment.

[0131] In this embodiment, the representative feature vector refers to the result of in-depth feature extraction of each element in the placement point feature matrix, screening out the most representative features and vectorizing them. These features can capture the key attributes of each placement point, such as spatial position, channel width, obstacle distribution, etc.

[0132] The self-supervised learning results are obtained by performing unlabeled data-driven learning on the various placement points and their associations in the preliminary layout plan through a self-supervised learning graph network algorithm. These results not only include the evaluation score of each placement point, but also reveal the potential associations and influencing factors between the placement points.

[0133] The summary of resettlement point evaluation opinions is a collection of specific contents and optimization measures recorded for resettlement points with potential problems in unlabeled data-driven learning. This summary document describes the specific circumstances of each potential problem in detail and provides targeted improvement suggestions to ensure the rationality and effectiveness of the final layout plan.

[0134] The intelligent simulation system is an advanced tool that integrates multiple simulation technologies and is used to simulate first aid processes and human-computer interactions in complex environments. It can conduct multiple simulation tests and key evaluations to help verify the feasibility and safety of different placement points, thereby generating a more accurate scoring result table.

[0135] In the embodiment of the present application, first, based on the resettlement point feature matrix, in-depth feature extraction is performed on each element in the resettlement point feature matrix, the most representative features are screened for vectorization, and a representative feature vector is generated; secondly, based on the representative feature vector, a self-supervised learning graph network algorithm is used to perform unlabeled data-driven learning on each resettlement point and its association in the preliminary layout plan, and all possible resettlement points are scored to generate a self-supervised learning result; thirdly, based on the self-supervised learning result, for resettlement points with potential problems in the unlabeled data-driven learning, the specific contents of the potential problems are recorded and optimization measures are formulated to generate a resettlement point evaluation opinion summary; finally, based on the resettlement point evaluation opinion summary, the resettlement point information in the resettlement point evaluation opinion summary is input into the intelligent simulation system, multiple simulation tests and key evaluations are performed, and a scoring result table is generated.

[0136] Here is a specific example:

[0137] Assuming that in a large cardiology hospital, in order to optimize the layout of defibrillator equipment to deal with sudden cardiac arrest events, firstly, based on the placement point feature matrix, the elements in the placement point feature matrix (such as ward layout, corridor width, emergency room location) are deeply extracted, the most representative features are selected for vectorization, and a representative feature vector is generated; secondly, based on the representative feature vector, the self-supervised learning graph network algorithm is used to perform unlabeled data-driven learning on each placement point and its association in the preliminary layout plan, and all possible placement points are scored to generate self-supervised learning results; thirdly, based on the self-supervised learning results, the self-supervised learning results are used to optimize the layout of defibrillator equipment to deal with sudden cardiac arrest events. Based on the results, for resettlement points with potential problems in unlabeled data-driven learning (such as passages in some areas that are too narrow or there are many obstacles), the specific contents of the potential problems (such as insufficient passage width, obstacles blocking the rescue route) are recorded and optimization measures (such as adjusting the passage layout, removing unnecessary obstacles) are formulated to generate a summary of resettlement point evaluation opinions; finally, based on the summary of resettlement point evaluation opinions, the resettlement point information in the summary of resettlement point evaluation opinions is input into the intelligent simulation system, and multiple simulation tests and key evaluations are carried out to generate a scoring result table to ensure that each resettlement point can play the maximum role in actual first aid while maximizing the safety and accessibility of the path.

[0138] In order to solve the problems of low utilization efficiency and poor first aid effect that may occur during the optimization of the layout of the integrated defibrillator equipment, and further improve the ability to respond to changes in actual first aid situations, in some embodiments, the global optimization processing described in step 104 includes: based on the optimized layout plan, deploying real-time sensors and monitoring equipment in the integrated defibrillator equipment, tracking the use of the integrated defibrillator equipment in real time, and generating a dynamic data set of equipment; based on the dynamic data set of equipment, using anomaly detection technology to automatically identify abnormal conditions and trend changes during the use of the integrated defibrillator equipment, and generating equipment anomaly detection results; based on the equipment anomaly detection results, using a problem-oriented analysis method, problem-oriented adjustments are made to the operating procedures of the integrated defibrillator equipment to generate an optimized adjustment plan; based on the optimized adjustment plan, combined with the long-term monitoring data generated by the real-time sensors deployed in the integrated defibrillator equipment, a plan for dealing with emergencies is formulated to generate an optimized layout strategy for the integrated defibrillator equipment.

[0139] In this embodiment, the real-time sensors and monitoring equipment refer to hardware devices installed on the integrated defibrillator device, which are used to track the use of the device in real time. These devices can collect various data, such as the number of device startups, usage time, operator information, etc., and transmit the data to the central system for analysis.

[0140] The device dynamic data set is a data set containing the usage of the integrated defibrillator device in different time periods. This data not only records the basic operation information of the device, but also may include additional information such as environmental conditions (such as temperature and humidity) and patient status. The device dynamic data set provides rich data support for anomaly detection and trend analysis.

[0141] Anomaly detection technology is a data analysis method that aims to automatically identify abnormal patterns or trend changes in data. It can help discover potential problems in the use of integrated defibrillator equipment, such as equipment failure, operational errors, etc.

[0142] The device anomaly detection results are obtained by analyzing the device dynamic data set through anomaly detection technology. These results describe the specific circumstances of each abnormal event in detail, including the time of occurrence, scope of impact, possible causes, etc.

[0143] The problem-oriented analysis method is an analysis method that focuses on solving problems. It puts forward targeted improvement suggestions through in-depth analysis of specific problems. This method emphasizes starting from practical problems and formulating solutions based on actual conditions to achieve the best improvement effect.

[0144] The optimization and adjustment plans are the results of adjusting the operating procedures of the integrated defibrillator equipment through problem-oriented analysis methods based on the results of equipment abnormality detection. These plans are aimed at solving the problems found, optimizing the operating procedures, and improving the efficiency of equipment use and the effectiveness of first aid.

[0145] Long-term monitoring data refers to data collected over a long period of time through real-time sensors and monitoring equipment. These data reflect the changing trends in the use of equipment at different times and conditions, and provide an important reference for formulating emergency response plans.

[0146] An emergency response plan is an action plan prepared in advance to enable a quick and effective response in an emergency. The plan usually includes emergency response procedures, resource allocation plans, personnel arrangements, etc.

[0147] In the embodiments of the present application, firstly, based on the optimized layout plan, real-time sensors and monitoring devices are deployed in the integrated defibrillator device, the use of the integrated defibrillator device is tracked in real time, and a dynamic data set of the device is generated; secondly, based on the dynamic data set of the device, anomaly detection technology is used to automatically identify abnormal conditions and trend changes during the use of the integrated defibrillator device, and an abnormality detection result of the device is generated; thirdly, based on the abnormality detection result of the device, a problem-oriented analysis method is used to perform problem-oriented adjustments to the operating procedures of the integrated defibrillator device, and an optimized adjustment plan is generated; finally, based on the optimized adjustment plan, combined with the long-term monitoring data generated by the real-time sensors deployed in the integrated defibrillator device, a plan for dealing with emergencies is formulated, and an optimized layout strategy for the integrated defibrillator device is generated.

[0148] Here is a specific example:

[0149] Assuming that in a large elderly care community, in order to optimize the layout of defibrillator equipment to cope with emergency medical events such as cardiac arrest among the elderly, firstly, based on the optimized layout plan, real-time sensors and monitoring equipment are deployed in the integrated defibrillator equipment to track the use of the integrated defibrillator equipment in real time (such as the specific location of each use, the duration of use, and the identity of the operator), and generate a dynamic data set of the equipment; secondly, based on the dynamic data set of the equipment, anomaly detection technology is used to automatically identify abnormal conditions (such as the equipment not starting as expected, the operation time is too long) and trend changes during the use of the integrated defibrillator equipment, and generate equipment anomaly detection results; thirdly, based on the Based on the results of equipment anomaly detection, problem-oriented analysis methods are used to make problem-oriented adjustments to the operating procedures of the integrated defibrillator equipment (such as simplifying operating steps and strengthening training) to generate an optimized adjustment plan; finally, based on the optimized adjustment plan and combined with the long-term monitoring data generated by the real-time sensors deployed in the integrated defibrillator equipment (such as the frequency of use within one year and the types of common problems), emergency plans for dealing with emergencies are formulated (such as emergency response plans for cardiac arrest in specific areas and emergency plans for equipment failures), and an optimized layout strategy for the integrated defibrillator equipment is generated to ensure that each placement point can play its maximum effectiveness in actual first aid while maximizing the safety and accessibility of the path.

[0150] This application takes into account that in order to solve the problems of inaccurate path planning and insufficient safety verification that may occur during the optimization of the layout of the integrated defibrillator equipment, the existing technology has the problem that the path planning is too dependent on static factors, ignores dynamic changes, and fails to fully consider the combined impact of safety and accessibility, resulting in the inability to ensure the effectiveness and safety of the shortest response path in an emergency. Therefore, the embodiment of the invention proposes this optional solution to solve the above technical problems and ensure the efficient operation of the emergency system. The solution includes:

[0151] Based on the dynamic weight matrix, a multi-objective evolutionary algorithm is used to accelerate the search process by simulating the natural selection process and the genetic variation mechanism, and a global optimization process is performed on the shortest reaction path between each defibrillator and the patient in the integrated defibrillator device to screen out the optimal solution and generate a set of candidate shortest reaction paths, including:

[0152] Based on the dynamic weight matrix, perform reachability and safety analysis on each shortest reaction path, identify and quantify potential risk points, apply path analysis technology to extract key performance indicators, and normalize the key performance indicators to generate a preliminary path score;

[0153] The preliminary path score is calculated using the following formula:

[0154]

[0155] Where F(W,D) is the preliminary path score calculated based on the dynamic weight matrix; W is the dynamic weight matrix, which contains the weight information of each shortest response path; D is the distance matrix, which represents the distance between each defibrillator and the patient; w i is the weight of the i-th shortest reaction path; α is the nonlinear coefficient that adjusts the influence of distance; d i is the distance of the i-th shortest reaction path; γ is the influence coefficient of the introduction of periodic fluctuations; ω is the frequency of periodic fluctuations; λ is the influence coefficient of distance; i is the index of the shortest reaction path, from 1 to N; N is the number of shortest reaction paths;

[0156] Based on the preliminary path score, a nonlinear transformation is performed to enhance the discrimination, a coefficient for adjusting the influence of the multi-objective evolutionary algorithm is introduced to simulate the natural selection process and the genetic variation mechanism to accelerate the global search process, and the global search process is corrected by introducing the influence coefficient of the logarithmic correction term to generate a final optimization score;

[0157] The final optimization score is calculated using the following formula:

[0158]

[0159] Among them, O(W,D) is the final optimization score calculated based on the multi-objective evolutionary algorithm; F(W,D) is the preliminary path score calculated based on the dynamic weight matrix; β is the coefficient for adjusting the influence of the multi-objective evolutionary algorithm; m i is the fitness score of the i-th shortest reaction path in the multi-objective evolution process; η is the influence coefficient of the introduced logarithmic correction term; δ is the proportional coefficient of the logarithmic correction term; d i is the distance of the i-th shortest reaction path; θ is the time response influence coefficient; μ is the time response factor; t i is the time response score of the i-th shortest reaction path; ζ is the nonlinear coefficient for adjusting the degree of safety impact; s i is the safety score of the i-th shortest reaction path; i is the index of the shortest reaction path, from 1 to N; N is the number of shortest reaction paths;

[0160] Based on the global optimization score, the final optimization scores of all the shortest reaction paths are weighted averaged to highlight the shortest reaction paths with excellent performance, and cluster analysis is applied to perform group screening to generate a set of candidate shortest reaction paths.

[0161] This method aims to more accurately evaluate the safety and accessibility of each shortest reaction path, while taking into account the actual usage of the path (such as distance, time response and other factors) to calculate the preliminary path score and the final optimization score. By introducing multiple influencing factors and their interactions, it ensures that the score can accurately reflect the actual performance of the path, and then selects the optimal path set.

[0162] In the preliminary path score, the path distance decay effect term This item is used to measure the impact of distance on the path score. As the distance increases, the path score will decrease exponentially, reflecting the importance of quick arrival in emergency situations; Periodic fluctuation adjustment item This factor takes into account possible periodic obstacles or disturbances on the route (such as changes in traffic flow), making the score more realistic.

[0163] Among them, w i comes from the corresponding position in the dynamic weight matrix; α is determined by experiment and is usually set based on past emergency records; d i Obtained through field measurements or map service API; γ, ω, and λ are obtained by analyzing the temporal distribution patterns of historical emergency events;

[0164] In the final optimization score, the preliminary path score item F(W,D) is used as the basic score, which reflects the basic feasibility and safety of the path. This is the basis for subsequent optimization and ensures that each path has undergone basic safety and accessibility tests. The fitness score correction item β·m of the multi-objective evolutionary algorithm is used as the basic score. i :The fitness score generated by the iteration of the multi-objective evolutionary algorithm enhances the diversity and adaptability of the score. The evolutionary algorithm can find the Pareto optimal solution among a large number of candidate paths, that is, achieve the best balance between multiple goals, thereby improving the quality of path selection; the logarithmic correction term η·log(1+δ·d i ): Considering the additional risk that long-distance paths may bring, this correction term increases the risk penalty for long-distance paths. It helps reduce the choice of long-distance paths and encourages the system to choose shorter and more direct paths, thereby improving emergency rescue efficiency; time response factor θ·tanh(μ·t i ): Emphasizes the importance of time response speed, especially in emergency rescue scenarios. The time response factor can quantify the time benefit of the path to ensure that the selected path is not only safe but also efficient; safety impact correction term This item aims to reduce the impact of potential safety hazards on the score and ensure the safety of the route;

[0165] Among them, F(W,D) is calculated by the preliminary path scoring formula; β is determined by experiment, and m iGenerated by evolutionary algorithm iteration; η, δ are determined by experiments; θ, μ are determined by experiments, t i Obtained through simulation test; ζ determined through experiment, s i Derived through risk assessment model;

[0166] In a large international airport, in order to optimize the layout of defibrillator equipment to deal with emergency medical events such as sudden cardiac arrest of passengers; assuming that the nonlinear coefficient of the distance effect is α = 0.05; the influence coefficient of the periodic fluctuation is γ = 0.1; the frequency of the periodic fluctuation is ω = 0.5; the influence coefficient of the distance is λ = 0.01; the number of the shortest reaction paths is N = 50; the distance d of the i-th shortest reaction path is i ;

[0167]

[0168] Assume that the coefficient β for adjusting the influence of the multi-objective evolutionary algorithm is 0.03; the fitness score m of the i-th shortest reaction path in the multi-objective evolutionary process is i =0.8; the influence coefficient of the introduction of the logarithmic correction term η = 0.2; the proportional coefficient of the logarithmic correction term δ = 0.02; the time response influence coefficient θ = 0.1; the time response factor μ = 0.05; the time response score t of the i-th shortest reaction path i = 0.9; nonlinear coefficient ζ for adjusting the degree of safety impact = 0.04; safety score s for the i-th shortest reaction path i =0.85;

[0169]

[0170] Assuming that the threshold is set to 0.9, since the calculated result 0.95 is greater than the set threshold, it shows that the optimized layout scheme of the integrated defibrillator equipment has high effectiveness and safety, and can ensure a rapid and effective response in emergency situations, because the higher optimization score reflects that the path selection algorithm can effectively identify and select the best path in the current environment without affecting the efficiency and safety of emergency treatment. Through the above steps, the scientificity and rationality of the layout of the defibrillator equipment are ensured, the reliability and efficiency of emergency actions are improved, and the accuracy and response speed of the entire emergency system are enhanced.

[0171] This application takes into account that in order to solve the problems of unreasonable selection of placement points and unclear association relationships that may occur during the optimization of the layout of integrated defibrillator equipment, the existing technology has problems such as over-reliance on static factors, neglect of dynamic changes, and failure to fully consider the impact of complex relationships between nodes in the selection of placement points, resulting in inaccurate and inscientific scoring. Therefore, the embodiment of the invention proposes this optional solution to solve the above technical problems and ensure the accuracy and scientificity of the scoring process. The solution includes:

[0172] Based on the placement point feature matrix, a self-supervised learning graph network algorithm is used to perform unlabeled data-driven learning on each placement point and its associated relationship in the preliminary layout plan, and all possible placement points are scored to generate a scoring result table; the self-supervised learning graph network algorithm is used to learn the relationship between nodes and extract valuable information from a complex network structure, including:

[0173] Based on the resettlement point feature matrix, data cleaning technology is used to eliminate noise and outliers, and feature extraction methods are applied to extract key information from the original features of the resettlement point feature matrix, and an adjacency matrix is ​​constructed to represent the physical connection relationship between each resettlement point to generate a preliminary node relationship score;

[0174] The preliminary node relationship score is calculated using the following formula:

[0175]

[0176] Where G(A,X) is the preliminary node relationship score calculated based on the self-supervised learning graph network algorithm; A is the adjacency matrix, which represents the relationship between each placement point; X is the feature matrix, which contains the spatial parameters of each placement point and the relative position information between the device and the patient; x i is the feature vector of the ith placement point; σ is the activation function, which is used to introduce nonlinearity; W1 is the first-layer weight matrix, which is used to learn the relationship between nodes; b1 is the first-layer bias term; β' is the exponential coefficient for adjusting the degree of accessibility influence; c i Score the accessibility of the i-th resettlement point;

[0177] Based on the preliminary node relationship score, node features are transferred and updated layer by layer through a multi-layer self-supervised learning graph network, and the importance of each placement point is adjusted in combination with the relationship weights between nodes to generate a final node relationship score;

[0178] The final node relationship score is calculated using the following formula:

[0179]

[0180] Where H(A,X,Q) is the final node relationship score calculated based on the self-supervised learning graph network algorithm; G(A,X) is the preliminary node relationship score calculated based on the self-supervised learning graph network algorithm; γ' is the influence coefficient for adjusting the value information score; q i is the value information score extracted from the i-th placement point in the complex network structure; λ' is the distance attenuation coefficient; l i is the distance to the ith placement point; μ' is the safety correction factor; ν is the proportional coefficient of the safety correction term; s i' is the safety score of the ith resettlement point; θ' is the time impact coefficient; ω' is the time impact factor; t i 'Score the time response of the ith placement;

[0181] Based on the final node relationship score, normalization processing is performed to improve the comparability between different final node relationship scores, and a sensitivity analysis method is applied to evaluate the response of the final node relationship score of each placement point to changes in key parameters, identify the final node relationship score with significant response, and generate a score result table.

[0182] This method aims to accurately evaluate the relationship between each resettlement site, while taking into account the complex relationship network structure in the actual environment. By introducing multiple influencing factors and their interactions, it ensures that the score can accurately reflect the actual performance of the resettlement site, and then select the optimal resettlement site configuration.

[0183] In the preliminary node relationship scoring, the node feature vector activation term This term is used to measure the output of the feature vector of each placement point after passing through the weight matrix and activation function, reflecting the importance of the placement point in the network; σ introduces nonlinearity so that the model can capture complex nonlinear relationships; accessibility impact correction term This item takes into account the impact of the accessibility of the resettlement site on the score. i As increases, the score will gradually approach 1, emphasizing the importance of accessibility in emergency scenarios;

[0184] Among them, A is obtained by constructing an adjacency matrix, which represents the physical connection relationship between the placement points; X contains the spatial parameters of each placement point and the relative position information between the device and the patient, which is extracted from the original data; W1, b1 are obtained through model training; β' is determined by experiment; c i Derived through the accessibility assessment model;

[0185] In the final node relationship score, the preliminary node relationship score item G1(A,X): as the basic score, reflects the basic relationship of the resettlement point in the network; the value information score correction item Considering the value information score q extracted from the placement point in the network structure i , and the distance attenuation effect l i , enhancing the diversity and adaptability of scoring; security corrections The impact of safety on the score is emphasized to ensure that the safety of the selected resettlement site meets the standard; the time impact correction term (1+θ′·tanh(ω′·t′ i )):Emphasized the importance of time response speed, especially in emergency rescue scenarios, rapid response is key;

[0186] Among them, G1(A,X) is calculated by the preliminary node relationship scoring formula; γ′, λ′, μ′, v, θ′, ω′ are obtained through experiments or historical data analysis; q i Iteratively generated through self-supervised learning graph network; i Obtained through field measurement or existing map data; s′ i Derived from the risk assessment model; t′ i Obtained through simulation testing;

[0187] Suppose that in a large sports venue, in order to optimize the layout of defibrillators to deal with emergency medical events such as sudden cardiac arrest of spectators, it is necessary to construct a placement feature matrix based on the internal structure of the venue and the dynamic flow of people during the event, and use real-time monitoring data to adjust the weights;

[0188] Assume that the first-layer weight matrix W1 and the bias term b1 are obtained through model training; the activation function σ uses ReLU; the exponential coefficient β′ for adjusting the degree of accessibility influence is 0.1; the accessibility score c of the i-th placement is i =0.85; the number of shortest reaction paths N = 60;

[0189]

[0190] Assume that the influence coefficient of adjusting the value information score γ′ = 0.04; the value information score q extracted from the first placement point in the complex network structure i =0.92; distance attenuation coefficient λ′=0.015; the distance l of the ith placement point i =12; safety correction factor μ′=0.12; proportional coefficient of safety correction term v=0.03; safety score s′ of the ith placement i =0.96; time influence coefficient θ′=0.05; time influence factor ω′=0.04; time response score t' of the ith placement point i =0.88;

[0191]

[0192] Assuming that the threshold is set to 0.85, since the calculated result 0.89 is greater than the set threshold, it shows that the integrated defibrillator equipment optimization layout scheme has high effectiveness and rationality, which can ensure rapid and effective response in emergency situations. The higher final node relationship score reflects the importance and superiority of the placement point in the network structure, ensuring the scientificity and efficiency of the defibrillator equipment layout. Through the above steps, the optimization of the defibrillator equipment layout is ensured, the reliability and efficiency of emergency actions are improved, and the accuracy and response speed of the entire emergency system are enhanced.

[0193] Figure 2A schematic diagram of the structure of an optimized layout system for an integrated defibrillator device is provided for an embodiment of the present application. Figure 2 As shown, the device comprises:

[0194] The collection module 21 is used to collect the spatial parameters and patient location information of the emergency scene, conduct a comprehensive analysis of the key factors affecting the layout of the integrated defibrillator equipment, and generate a list of key factors; the key factors refer to a set of factors that have a significant impact on the layout of the integrated defibrillator equipment in a specific emergency environment;

[0195] A simulation module 22 is used to use a multi-objective evolutionary algorithm based on the key element list to accelerate the search process by simulating the natural selection process and the genetic variation mechanism, perform global optimization processing on the shortest reaction path between each defibrillator in the integrated defibrillator and the patient, use digital twin technology to create a virtual emergency environment, synchronize the virtual emergency environment with the emergency site in real time, verify the safety and accessibility of the shortest reaction path, and generate a preliminary layout plan;

[0196] The learning module 23 is used to perform unlabeled data-driven learning on each placement point and its relationship in the preliminary layout plan based on the preliminary layout plan by using a self-supervised learning graph network algorithm, and to score all possible placement points, and to visualize the scoring results by using a mixed reality-assisted design method to generate an optimized layout plan;

[0197] The monitoring module 24 is used to continuously monitor the use efficiency and emergency effect of the integrated defibrillator in the actual emergency situation based on the optimized layout plan and in combination with changes in the actual emergency situation, and generate an optimized layout strategy for the integrated defibrillator.

[0198] Figure 2 The optimized layout system of an integrated defibrillator device can be implemented Figure 1 The implementation principle and technical effect of the optimized layout method of an integrated defibrillator device described in the embodiment shown will not be described in detail. The specific manner in which each module and unit performs operations in the optimized layout system of an integrated defibrillator device in the above embodiment has been described in detail in the embodiment of the method, and will not be described in detail here.

[0199] In one possible design, Figure 2 The optimized layout system of an integrated defibrillator device of the illustrated embodiment may be implemented as a computing device, such as Figure 3 As shown, the computing device may include a storage component 31 and a processing component 32;

[0200] The storage component 31 stores one or more computer instructions, wherein the one or more computer instructions are called and executed by the processing component 32 .

[0201] The processing component 32 is used to: collect the spatial parameters of the emergency scene and the patient's location information, conduct a comprehensive analysis of the key factors that affect the layout of the integrated defibrillator equipment, and generate a list of key factors; the key factors refer to a set of factors that have an impact on the layout of the integrated defibrillator equipment in a specific emergency environment; based on the list of key factors, a multi-objective evolutionary algorithm is used to simulate the natural selection process and the genetic variation mechanism to accelerate the search process, and the shortest reaction path between each defibrillator in the integrated defibrillator and the patient is globally optimized, and a virtual emergency environment is created using digital twin technology, and the virtual emergency environment is synchronized with the emergency scene in real time. The safety and accessibility of the shortest reaction path are verified to generate a preliminary layout plan; based on the preliminary layout plan, a self-supervised learning graph network algorithm is used to perform unlabeled data-driven learning on the placement points of each defibrillator in the preliminary layout plan and their associations, and all possible placement points are scored, and a mixed reality-assisted design method is used to visualize the scoring results to generate an optimized layout plan; based on the optimized layout plan, combined with changes in actual emergency situations, the use efficiency and emergency effects of the integrated defibrillator in the actual emergency situations are continuously monitored to generate an optimized layout strategy for the integrated defibrillator.

[0202] The processing component 32 may include one or more processors to execute computer instructions to complete all or part of the steps in the above method. Of course, the processing component may also be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components to perform the above method.

[0203] The storage component 31 is configured to store various types of data to support operations at the terminal. The storage component can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0204] Of course, the computing device may also include other components, such as input / output interfaces, display components, communication components, etc.

[0205] The input / output interface provides an interface between the processing component and the peripheral interface module, which may be an output device, an input device, etc.

[0206] The communication component is configured to facilitate, among other things, wired or wireless communications between the computing device and other devices.

[0207] Among them, the computing device can be a physical device or an elastic computing host provided by a cloud computing platform, etc. In this case, the computing device can refer to a cloud server, and the above-mentioned processing components, storage components, etc. can be basic server resources rented or purchased from the cloud computing platform.

[0208] The present application also provides a computer storage medium storing a computer program, wherein the computer program can achieve the above-mentioned Figure 1 An optimized layout method for an integrated defibrillator device according to the illustrated embodiment.

[0209] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0210] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0211] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0212] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for optimizing the layout of an integrated defibrillator device, characterized in that: include: Collecting the spatial parameters and patient location information of the emergency scene, comprehensively analyzing the key factors affecting the layout of the integrated defibrillator equipment, and generating a list of key factors; the key factors refer to a set of factors that have an impact on the layout of the integrated defibrillator equipment in a specific emergency environment; Based on the list of key elements, a multi-objective evolutionary algorithm is used to simulate the natural selection process and genetic variation mechanism to accelerate the search process, and the shortest reaction path between each defibrillator and the patient in the integrated defibrillator is globally optimized. A virtual emergency environment is created using digital twin technology, and the virtual emergency environment is synchronized with the emergency site in real time. The safety and accessibility of the shortest reaction path are verified to generate a preliminary layout plan; Based on the preliminary layout plan, a self-supervised learning graph network algorithm is used to perform unlabeled data-driven learning on the placement points of each defibrillator in the preliminary layout plan and their associations, and all possible placement points are scored. A mixed reality-assisted design method is used to visualize the scoring results to generate an optimized layout plan; Based on the optimized layout scheme and in combination with changes in actual emergency situations, the use efficiency and emergency effects of the integrated defibrillator equipment in the actual emergency situations are continuously monitored to generate an optimized layout strategy for the integrated defibrillator equipment.

2. The method according to claim 1, characterized in that Based on the list of key elements, a multi-objective evolutionary algorithm is used to accelerate the search process by simulating the natural selection process and the genetic variation mechanism, and a global optimization process is performed on the shortest reaction path between each defibrillator in the integrated defibrillator and the patient. A virtual emergency environment is created using digital twin technology, and the virtual emergency environment is synchronized with the emergency site in real time. The safety and accessibility of the shortest reaction path are verified, and a preliminary layout plan is generated, including: Based on the list of key factors, through mathematical modeling and statistical analysis, the multi-dimensional key factors are converted into quantitative indicators for comprehensive analysis and processing to generate a comprehensive evaluation model; Based on the comprehensive evaluation model, a multi-objective evolutionary algorithm is used to simulate the natural selection process and genetic variation mechanism to accelerate the search process, and the shortest reaction path between each defibrillator and the patient in the integrated defibrillator is globally optimized to generate a shortest reaction path set; the shortest reaction path set summarizes all the shortest reaction paths; Based on the shortest reaction path set, a virtual first aid environment is created using digital twin technology, the virtual first aid environment is synchronized with the first aid site in real time, the safety and accessibility of the shortest reaction path are verified, and a shortest reaction path verification result is generated; Based on the shortest reaction path verification result, the placement point and use process of the integrated defibrillator are fully simulated, and the response speed and operational convenience are evaluated during the comprehensive simulation process to generate a preliminary layout plan.

3. The method according to claim 2, characterized in that Based on the comprehensive evaluation model, a multi-objective evolutionary algorithm is used to accelerate the search process by simulating the natural selection process and the genetic variation mechanism, and a global optimization process is performed on the shortest reaction path between each defibrillator and the patient in the integrated defibrillator to generate a shortest reaction path set; the shortest reaction path set summarizes all possible shortest reaction paths, including: Based on the comprehensive evaluation model, dynamic weight calculation is performed on the dynamic change factors in the key elements that affect the layout of the integrated defibrillator equipment to generate a dynamic weight matrix; the dynamic change factors include the flow pattern of emergency personnel and the frequency of occurrence of temporary obstacles; Based on the dynamic weight matrix, a multi-objective evolutionary algorithm is used to accelerate the search process by simulating the natural selection process and the genetic variation mechanism, and the shortest reaction path between each defibrillator and the patient in the integrated defibrillator is globally optimized to screen out the optimal solution and generate a set of candidate shortest reaction paths; Based on the candidate shortest reaction path set, a multi-factor risk assessment framework including physical obstacles and operation complexity is established, the safety risks of the candidate shortest reaction paths in the candidate shortest reaction path set are evaluated and analyzed, and a path safety score table is generated; the path safety score table is a quantitative assessment result of the safety of each candidate shortest reaction path; Based on the path safety score table, an intelligent decision support system is introduced to screen and analyze the various safety risk indicators in the path safety score table to generate a set of shortest reaction paths; the intelligent decision support system is an advanced tool for optimizing path selection and resource allocation in complex environments.

4. The method according to claim 2, characterized in that: Based on the shortest reaction path set, a virtual first aid environment is created by using digital twin technology, the virtual first aid environment is synchronized with the first aid site in real time, the safety and accessibility of the shortest reaction path are verified, and a shortest reaction path verification result is generated, including: Based on the shortest reaction path set, using scenario simulation technology, accurate modeling is performed according to key factors affecting the layout of the integrated defibrillator device to generate a multi-scenario virtual emergency environment; the multi-scenario virtual emergency environment is a series of virtual models built for different emergency situations; Based on the multi-scenario virtual emergency environment, digital twin technology is used to create a virtual emergency environment, so that emergency personnel can experience the actual operation process of each shortest reaction path and intuitively evaluate it through the virtual emergency environment, and feedback the shortest reaction path evaluation result; Based on the shortest reaction path evaluation result, a comprehensive evaluation is performed on the degree of human-computer interaction in each shortest reaction path in the shortest reaction path set through a human-computer collaborative evaluation method to generate a comprehensive evaluation report; the human-computer collaborative evaluation method integrates artificial intelligence and expert systems, and provides reliable evaluation results through the combination of machine learning and human expertise; Based on the comprehensive evaluation report, important factors affecting the emergency rescue efficiency of each shortest reaction path in the shortest reaction path set are identified, the safety and accessibility of each shortest reaction path are verified, and a shortest reaction path verification result is generated.

5. The method according to claim 1, characterized in that Based on the preliminary layout plan, the self-supervised learning graph network algorithm is used to perform unlabeled data-driven learning on each placement point and its association in the preliminary layout plan, and all possible placement points are scored, and the scoring results are visualized using a mixed reality-assisted design method to generate an optimized layout plan, including: Based on the preliminary layout plan, collecting spatial parameters of each placement point in the preliminary layout plan and relative position information between the device and the patient, extracting key features in the spatial parameters of each placement point, and generating a placement point feature matrix; Based on the placement point feature matrix, a self-supervised learning graph network algorithm is used to perform unlabeled data-driven learning on each placement point and its association in the preliminary layout plan, and all possible placement points are scored to generate a scoring result table; Based on the scoring result table, an interactive virtual environment is created using a mixed reality-assisted design method, the scoring results in the scoring result table are visualized, and the results are superimposed on the interactive virtual environment to generate a visual evaluation report; Based on the scoring results provided in the visual assessment report and the feedback from the emergency team, key placement points are identified and optimized for each placement point in the preliminary layout plan to generate an optimized layout plan.

6. The method according to claim 5, characterized in that Based on the placement point feature matrix, the self-supervised learning graph network algorithm is used to perform unlabeled data-driven learning on each placement point and its association in the preliminary layout plan, and all possible placement points are scored to generate a scoring result table, including: Based on the placement point feature matrix, perform in-depth feature extraction on each element in the placement point feature matrix, select the most representative features for vectorization, and generate a representative feature vector; Based on the representative feature vector, a self-supervised learning graph network algorithm is used to perform unlabeled data-driven learning on each placement point and its association in the preliminary layout plan, and all possible placement points are scored to generate a self-supervised learning result; Based on the self-supervised learning results, for the placement points with potential problems in the unlabeled data-driven learning, the specific contents of the potential problems are recorded and optimization measures are formulated, and a summary of the placement point evaluation opinions is generated; Based on the resettlement point evaluation opinion summary, the resettlement point information in the resettlement point evaluation opinion summary is input into the intelligent simulation system, multiple simulation tests and key evaluations are carried out, and a scoring result table is generated; the intelligent simulation system integrates multiple simulation technologies to simulate the human-computer interaction process in a complex environment.

7. The method according to claim 1, characterized in that Based on the optimized layout scheme, combined with changes in actual emergency situations, the use efficiency and emergency effects of the integrated defibrillator equipment in the actual emergency situations are continuously monitored to generate an optimized layout strategy for the integrated defibrillator equipment, including: Based on the optimized layout scheme, real-time sensors and monitoring devices are deployed in the integrated defibrillator device to track the use of the integrated defibrillator device in real time and generate a device dynamic data set; Based on the dynamic data set of the device, using anomaly detection technology, automatically identifying abnormal conditions and trend changes during the use of the integrated defibrillator device, and generating device anomaly detection results; Based on the abnormality detection result of the device, a problem-oriented analysis method is used to perform a problem-oriented adjustment on the operation process of the integrated defibrillator device to generate an optimized adjustment plan; Based on the optimization and adjustment plan, combined with the long-term monitoring data generated by the real-time sensors deployed in the integrated defibrillator device, a plan for dealing with emergencies is formulated to generate an optimized layout strategy for the integrated defibrillator device.

8. An optimized layout system for an integrated defibrillator device, characterized in that: include: A collection module is used to collect the spatial parameters and patient location information of the emergency scene, conduct a comprehensive analysis of the key factors affecting the layout of the integrated defibrillator equipment, and generate a list of key factors; the key factors refer to a set of factors that have a significant impact on the layout of the integrated defibrillator equipment in a specific emergency environment; A simulation module is used to use a multi-objective evolutionary algorithm based on the key element list to accelerate the search process by simulating the natural selection process and the genetic variation mechanism, perform global optimization processing on the shortest reaction path between each defibrillator in the integrated defibrillator and the patient, use digital twin technology to create a virtual emergency environment, synchronize the virtual emergency environment with the emergency site in real time, verify the safety and accessibility of the shortest reaction path, and generate a preliminary layout plan; A learning module is used to perform unlabeled data-driven learning on each placement point and its relationship in the preliminary layout plan based on the preliminary layout plan by using a self-supervised learning graph network algorithm, and to score all possible placement points, and to visualize the scoring results by using a mixed reality-assisted design method to generate an optimized layout plan; The monitoring module is used to continuously monitor the use efficiency and first aid effect of the integrated defibrillator in the actual first aid situation based on the optimized layout plan and in combination with changes in the actual first aid situation, and generate an optimized layout strategy for the integrated defibrillator.

9. A computing device, characterized in that It comprises a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement an optimized layout method for an integrated defibrillator device as described in any one of claims 1 to 7.

10. A computer storage medium, characterized in that: A computer program is stored, and when the computer program is executed by a computer, the method for optimizing the layout of an integrated defibrillator device as claimed in any one of claims 1 to 7 is implemented.

Images