Big data-based position hospital decision processing method and system

Abstract

The invention provides an array hospital decision processing method and system based on big data. The method comprises the following steps: collecting and comprehensively analyzing dynamic data streams from a plurality of battlefield medical sites in real time, and generating a virtual medical resource thermodynamic diagram; based on the virtual medical resource thermodynamic diagram, a particle swarm optimization algorithm is adopted to perform intelligent planning processing on a sick and wounded evacuation path and a medical material allocation scheme, and a sick and wounded evacuation and resource allocation plan is generated; the sick and wounded evacuation and resource configuration plan is utilized, the effectiveness of a current treatment strategy is evaluated by applying a support vector machine algorithm, and a risk early warning and response scheme is generated; and according to the prospective decision support report and the risk early warning and countermeasure scheme, establishing a cloud cooperative working platform, and generating an efficient communication channel and an information security guarantee mechanism. According to the technical scheme provided by the invention, the ability and flexibility of a position hospital to deal with emergencies are remarkably improved.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of big data processing technology, and in particular to a big data-based position hospital decision-making processing method and system. Background Art

[0002] In modern military operations and disaster relief, battlefield hospitals face complex challenges in medical resource management and treatment of the wounded and sick. In order to effectively meet these challenges, a method is needed to collect and comprehensively analyze dynamic data streams from multiple battlefield medical sites in real time, covering the status of the wounded and sick, the use of medical resources, and geographical environmental factors. By generating a virtual medical resource heat map, the demand distribution and urgency of medical resources can be intuitively presented, providing decision support for the efficient allocation of medical resources.

[0003] Currently, most field hospitals rely on traditional static resource allocation and experience-based evacuation route planning methods. These methods usually involve manual recording and reporting of casualty information, which is then centrally dispatched by the command center. Although some advanced systems have begun to introduce data analysis tools, they mainly focus on post-event statistical analysis and limited prediction functions, and do not make full use of real-time data for dynamic adjustments.

[0004] The existing solutions have several significant defects: first, the lack of comprehensive integration and rapid response capabilities for real-time data leads to delayed decision-making; second, static resource allocation cannot adapt to the ever-changing situation on the battlefield, which easily leads to waste or shortage of resources; finally, the existing evacuation route planning is mostly based on fixed rules and fails to fully consider dynamic factors such as changes in traffic flow, affecting the efficiency and safety of the transfer of the wounded and sick. Summary of the invention

[0005] The embodiments of the present application provide a field hospital decision-making processing method and system based on big data, so as to solve the problem in the prior art of lacking comprehensive integration and rapid response capabilities to real-time data, resulting in delayed decision-making.

[0006] In a first aspect, an embodiment of the present application provides a method for decision-making and processing of a position hospital based on big data, comprising:

[0007] Real-time collection and comprehensive analysis of dynamic data streams from multiple battlefield medical sites, covering the status of the wounded and sick, the use of medical resources, and geographical environmental factors, to generate a virtual medical resource heat map;

[0008] Based on the virtual medical resource heat map, combined with the priority rules for the transfer of the wounded and sick and the transportation logistics optimization theory, the particle swarm optimization algorithm is used to intelligently plan the evacuation routes of the wounded and sick and the allocation plan of medical supplies, and the transportation routes are dynamically adjusted through traffic flow prediction technology to generate the evacuation of the wounded and sick and resource allocation plan;

[0009] By using the evacuation and resource allocation plan for the injured and sick, combined with the real-time updated treatment progress and resource consumption data and the historical similar case library, the support vector machine algorithm is applied to evaluate the effectiveness of the current treatment strategy, and a forward-looking decision support report is obtained. The risk points that may appear in the treatment process are monitored through time series anomaly detection technology, and risk warnings and response measures are generated;

[0010] Based on the forward-looking decision support report and risk warning and response measures plan, a cross-regional, multi-departmental cloud-based collaborative work platform will be established to generate efficient communication channels and information security assurance mechanisms to enhance the overall ability and flexibility of the position hospital to respond to emergencies.

[0011] Optionally, based on the virtual medical resource heat map, combined with the priority rules for the transfer of the sick and wounded and the transportation logistics optimization theory, a particle swarm optimization algorithm is used to perform intelligent planning and processing on the evacuation path of the sick and wounded and the allocation plan of medical supplies, and the transportation route is dynamically adjusted through traffic flow prediction technology to generate an evacuation plan of the sick and wounded and a resource allocation plan, including:

[0012] Based on the virtual medical resource heat map, the distribution and urgency of the injured and sick are evaluated and processed to obtain an urgency evaluation result of the injured and sick;

[0013] Using the emergency assessment results of the injured and sick, combined with the priority rules for the transfer of the injured and sick, the order of evacuation of the injured and sick is determined to obtain a priority sequence for the evacuation of the injured and sick;

[0014] According to the priority sequence of evacuation of the wounded and sick, the particle swarm optimization algorithm is applied to intelligently plan the evacuation path of the wounded and sick and the allocation plan of medical supplies to obtain a preliminary evacuation path and resource allocation plan;

[0015] Based on the preliminary evacuation route and resource allocation plan, combined with the transportation logistics optimization theory, the factors that may affect the transportation efficiency are analyzed and processed through the traffic flow prediction technology to obtain the analysis report of the factors affecting the transportation efficiency;

[0016] Utilizing the analysis report on factors influencing transport efficiency, the initial evacuation route is dynamically adjusted to ensure that the wounded and sick are safely transferred to the most suitable treatment location in the shortest time possible, and medical resources are efficiently allocated to generate a plan for the evacuation of the wounded and sick and resource allocation.

[0017] Optionally, based on the preliminary evacuation route and resource allocation plan, combined with the transportation logistics optimization theory, the factors that may affect the transportation efficiency are analyzed and processed by traffic flow prediction technology to obtain a transportation efficiency influencing factor analysis report, including:

[0018] Based on the preliminary evacuation route and resource allocation plan, the initial plan for evacuation of the wounded and sick and the distribution of medical supplies is evaluated and processed, key nodes that affect transportation efficiency are identified, and key node identification results are obtained;

[0019] Using the key node identification results and combining with the transportation logistics optimization theory, the traffic characteristics of these nodes in different time periods are modeled and processed to obtain a traffic characteristic model;

[0020] According to the traffic characteristic model, traffic flow prediction technology is applied to predict the traffic flow change trend of each key node in the future period of time to obtain traffic flow prediction data;

[0021] Based on the traffic flow forecast data, quantitatively analyzing the factors that hinder and promote transportation efficiency to obtain a list of factors affecting transportation efficiency;

[0022] Using the list of factors affecting transportation efficiency, combined with actual traffic rules and historical data, the importance of each factor is scored to obtain an importance score table;

[0023] According to the importance scoring table, the specific impact of various factors on transportation efficiency is comprehensively considered to generate an analysis report on factors affecting transportation efficiency.

[0024] Optionally, the analysis report of factors affecting transport efficiency is used to dynamically adjust the initial evacuation route to ensure that the wounded and sick are safely transferred to the most suitable treatment location in the shortest time, and medical resources are efficiently allocated to generate a plan for evacuating the wounded and sick and resource allocation, including:

[0025] Using the analysis report of factors affecting transport efficiency, re-evaluate key nodes and sections in the preliminary evacuation route, identify potential bottlenecks and optimization opportunities, and obtain route bottleneck and optimization point analysis results;

[0026] Based on the analysis results of the bottleneck and optimization points of the path, combined with real-time traffic data and prediction models, the preliminary evacuation path is adjusted and processed, and the path is optimized to avoid sections with high traffic or possible delays, so as to obtain an optimized evacuation path plan;

[0027] According to the optimized evacuation path plan, the evacuation sequence and time window of the injured and sick are replanned to obtain the evacuation sequence and time window plan of the injured and sick;

[0028] By using the above-mentioned evacuation sequence and time window planning for the wounded and sick, combined with the existing distribution of medical resources, the allocation of medical supplies and the arrangement of medical staff are adjusted synchronously to obtain a medical resource allocation and personnel arrangement plan;

[0029] Based on the medical resource allocation and personnel arrangement plan, a full-process monitoring and feedback mechanism is implemented, and the entire evacuation and resource allocation process is tracked and processed through the intelligent scheduling system to continuously optimize and ensure the effective implementation of the plan, and generate an evacuation and resource allocation plan for the injured and sick.

[0030] Optionally, the evacuation and resource allocation plan for the wounded and sick is combined with the real-time updated treatment progress and resource consumption data and the historical similar case library, and the support vector machine algorithm is used to evaluate the effectiveness of the current treatment strategy to obtain a forward-looking decision support report, and the risk points that may appear in the treatment process are monitored through time series anomaly detection technology to generate risk warnings and response measures, including:

[0031] Using the evacuation and resource allocation plan for the wounded and sick, combined with the real-time updated treatment progress and resource consumption data, the status of the current treatment activities is dynamically monitored and processed to obtain the treatment status monitoring results;

[0032] Based on the monitoring results of the treatment status, relevant information in the historical similar case library is integrated, and the current treatment situation is compared and analyzed with the historical cases to identify the key factors affecting the treatment effect, and obtain a key factor identification list;

[0033] Based on the key factor identification list, a support vector machine algorithm is applied to evaluate the effectiveness of the current treatment strategy. The support vector machine algorithm distinguishes data points with different treatment effects by constructing an optimal classification surface, predicts the resource demand trend and the success rate of the treatment strategy in the short term, and obtains a forward-looking decision support report;

[0034] Using the forward-looking decision support report and combining it with time series anomaly detection technology, the risk points that may appear during the treatment process are monitored and processed, abnormal situations that deviate from the normal treatment process are identified, and abnormal situation identification results are obtained;

[0035] Based on the abnormal situation identification results, specific response measures for various risks are formulated to obtain risk warning and response measures plans.

[0036] Optionally, the forward-looking decision support report is used in combination with time series anomaly detection technology to monitor and process risk points that may occur during the treatment process, identify abnormal situations that deviate from the normal treatment process, and obtain abnormal situation identification results, including:

[0037] Utilizing the forward-looking decision support report, analyzing and processing the success rate and resource demand trend of the current treatment strategy, determining key treatment links that require special attention, and obtaining a list of key treatment links;

[0038] Based on the list of key treatment links, combined with time series anomaly detection technology, the historical data and real-time data of these links are compared and analyzed, and an anomaly detection model is constructed to obtain an anomaly detection model;

[0039] According to the abnormality detection model, various indicators in the treatment process are continuously monitored and processed to identify data patterns that are inconsistent with the normal treatment process and obtain preliminary abnormal situation prompts;

[0040] Using the preliminary abnormality prompts, combined with clinical expertise and a historical similar case library, an in-depth assessment and processing of possible risk points is performed to confirm the true abnormality and its severity, and obtain abnormality confirmation results;

[0041] Based on the abnormal situation confirmation result, the identified abnormal situation is classified and processed to distinguish different types of abnormal situations, and the specific manifestation and occurrence frequency of each abnormal situation are recorded to obtain the abnormal situation identification result.

[0042] Optionally, based on the forward-looking decision support report and risk warning and response plan, a cross-regional, multi-departmental cloud-based collaborative work platform is established to generate efficient communication channels and information security mechanisms to enhance the overall ability and flexibility of the field hospital to respond to emergencies, including:

[0043] Using the forward-looking decision support report, comprehensively evaluate the success rate of the treatment strategy and the resource demand trend, determine the key links and participating departments that need to be coordinated, and obtain a list of key coordination points;

[0044] Based on the list of key coordination points, combined with risk warning and response measures, design the functional requirements and architecture blueprint of the cloud-based collaborative work platform to ensure that the platform can meet the needs of multi-party collaboration and obtain the platform design plan;

[0045] According to the platform design plan, develop and integrate efficient communication tools and information sharing modules, so that frontline doctors, rear expert teams and logistics support departments can communicate and share treatment information in real time, and obtain efficient communication channels;

[0046] By utilizing the above-mentioned efficient communication channels and combining information security technologies and management measures, we can build security functions for data encryption transmission, access permission control, and audit tracking to ensure the security of sensitive medical information during transmission and storage, and obtain an information security assurance mechanism.

[0047] In a second aspect, the embodiment of the present application provides a big data-based hospital decision-making processing system, including:

[0048] The collection module is used to collect and comprehensively analyze dynamic data streams from multiple battlefield medical sites in real time, covering the status of the wounded and sick, the use of medical resources, and geographical environmental factors, and generate a virtual medical resource heat map;

[0049] A planning module is used to intelligently plan and process the evacuation routes of the sick and wounded and the allocation of medical supplies based on the virtual medical resource heat map, combined with the priority rules for the transfer of the sick and wounded and the transportation logistics optimization theory, using a particle swarm optimization algorithm, dynamically adjust the transportation routes through traffic flow prediction technology, and generate a plan for the evacuation of the sick and wounded and resource allocation;

[0050] An evaluation module is used to utilize the evacuation and resource allocation plan for the injured and sick, combined with the real-time updated treatment progress and resource consumption data and the historical similar case library, to apply the support vector machine algorithm to evaluate the effectiveness of the current treatment strategy, obtain a forward-looking decision support report, monitor the risk points that may appear in the treatment process through time series anomaly detection technology, and generate risk warnings and response measures;

[0051] A generation module is used to establish a cross-regional, multi-departmental cloud-based collaborative work platform based on the forward-looking decision support report and risk warning and response measures plan, and to generate efficient communication channels and information security assurance mechanisms.

[0052] In a third aspect, an embodiment of the present application provides a computing device, comprising 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 a position hospital decision processing method based on big data as described in the first aspect.

[0053] In a fourth aspect, an embodiment of the present application provides a computer storage medium storing a computer program. When the computer program is executed by a computer, it implements a position hospital decision-making processing method based on big data as described in the first aspect.

[0054] In the embodiment of the present application, dynamic data streams from multiple battlefield medical sites are collected and comprehensively analyzed in real time, covering the status of the wounded, the use of medical resources and geographical environmental factors, and a virtual medical resource heat map is generated; based on the virtual medical resource heat map, combined with the priority rules for the transfer of the wounded and the transportation logistics optimization theory, the particle swarm optimization algorithm is used to intelligently plan and process the evacuation path of the wounded and the allocation plan of medical supplies, and the transportation route is dynamically adjusted through the traffic flow prediction technology to generate the evacuation and resource allocation plan of the wounded; using the evacuation and resource allocation plan of the wounded, combined with the real-time updated treatment progress and resource consumption data and the historical similar case library, the support vector machine algorithm is applied to evaluate the effectiveness of the current treatment strategy, and a forward-looking decision support report is obtained. The risk points that may appear in the treatment process are monitored through time series anomaly detection technology, and risk warning and response measures are generated; according to the forward-looking decision support report and the risk warning and response measures, a cross-regional, multi-departmental cloud-based collaborative work platform is established to generate efficient communication channels and information security assurance mechanisms.

[0055] The technical solution of this application has the following beneficial effects:

[0056] The big data-based decision-making and processing method for position hospitals provided in this application solves the problems of delayed decision-making, inflexible resource allocation, and suboptimal evacuation route planning in existing solutions through real-time data-driven intelligent planning and dynamic adjustment mechanisms, thereby significantly improving the ability and flexibility of position hospitals to respond to emergencies.

[0057] Furthermore, through the intelligent planning and dynamic adjustment mechanism based on the virtual medical resource heat map, combined with the emergency assessment of the wounded and sick, the transfer priority rules and the particle swarm optimization algorithm, the refined and intelligent management of the evacuation routes of the wounded and sick and the allocation plan of medical supplies is realized. This method can not only accurately determine the evacuation priority of the wounded and sick, ensuring that the most urgent cases are handled in a timely manner, but also dynamically adjust the transportation routes through traffic flow prediction technology, effectively avoiding traffic delays, ensuring that the wounded and sick can be safely transferred to the most suitable treatment location in the shortest time, and efficiently allocating medical resources. This method significantly improves the response speed and resource utilization efficiency of the position hospital in responding to emergencies, enhances the treatment effect and overall operational flexibility, thereby greatly improving the problems of inflexible resource allocation and insufficient optimization of evacuation route planning in the existing scheme.

[0058] Furthermore, by using the evacuation and resource allocation plan for the wounded and sick, combined with the real-time updated treatment progress and resource consumption data and the historical similar case library, this method uses the support vector machine algorithm to evaluate the effectiveness of the current treatment strategy and generate a forward-looking decision support report. At the same time, with the help of time series anomaly detection technology, potential risk points in the treatment process are monitored, and risk warning and response measures are formulated. This method not only realizes the dynamic monitoring of the state of treatment activities and the accurate identification of key influencing factors, but also provides data-driven forward-looking decision support through scientific evaluation of the effectiveness of treatment strategies, ensuring the optimal allocation and efficient use of medical resources. In addition, through real-time risk monitoring and early warning mechanisms, abnormal situations that deviate from the normal treatment process can be discovered and handled in advance, thereby improving the safety and success rate of the treatment process, enhancing the ability of medical institutions to respond to public health emergencies, and ultimately providing strong support for improving patient treatment effects and medical service quality.

[0059] 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

[0060] 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.

[0061] Figure 1 A flowchart of a big data-based decision-making method for a position hospital provided in an embodiment of the present application;

[0062] Figure 2 A schematic diagram of the structure of a big data-based decision-making processing system for a frontline hospital provided in an embodiment of the present application;

[0063] Figure 3 A schematic diagram of the structure of a computing device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0064] 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.

[0065] 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.

[0066] 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.

[0067] Figure 1 A flowchart of a big data-based hospital decision-making processing method is provided for an embodiment of the present application, such as Figure 1 As shown, the method includes:

[0068] 101. Real-time collection and comprehensive analysis of dynamic data streams from multiple battlefield medical sites, covering the status of the wounded and sick, the use of medical resources and geographical factors, to generate a virtual medical resource heat map;

[0069] This step involves real-time collection of dynamic data streams from multiple battlefield medical sites, including but not limited to the status of the wounded and sick (such as vital signs, injury descriptions), medical resource usage (such as drug inventory, equipment availability), and geographical environmental factors (such as geographic location, weather conditions). By integrating and analyzing these multi-source data, the system can generate a virtual medical resource heat map to intuitively present the demand distribution and urgency of medical resources.

[0070] In the embodiment of the present application, the system first obtains dynamic data from each medical site in real time and performs preliminary cleaning and standardization. Then, the data is comprehensively evaluated using big data analysis technology to identify key information points. Finally, the analysis results are converted into a virtual medical resource heat map through visualization tools to help decision makers quickly understand the current resource demand status and its urgency.

[0071] Suppose during a military exercise, the system receives real-time information on the number, type, severity and local weather changes of the wounded and sick from various field hospitals participating in the exercise. By analyzing this data, the system generates a detailed virtual medical resource heat map to guide the command center to quickly deploy emergency supplies and personnel to where they are most needed, ensuring that all the wounded and sick can receive appropriate treatment in a timely manner.

[0072] 102. Based on the virtual medical resource heat map, combined with the priority rules for the transfer of the wounded and sick and the transportation logistics optimization theory, the particle swarm optimization algorithm is used to intelligently plan the evacuation routes of the wounded and sick and the allocation plan of medical supplies, and the transportation routes are dynamically adjusted through traffic flow prediction technology to generate the evacuation of the wounded and sick and resource allocation plan;

[0073] In this step, based on the generated virtual medical resource heat map, combined with the transfer priority rules of the wounded and sick and the transportation logistics optimization theory, the particle swarm optimization algorithm is used to determine the optimal evacuation path for the wounded and sick and the allocation plan for medical supplies. At the same time, the transportation route is dynamically adjusted through traffic flow prediction technology to ensure efficient transfer of the wounded and sick and allocation of resources.

[0074] In the embodiment of the present application, the system evaluates the urgency of the injured and sick according to the heat map and determines the evacuation priority sequence. Then, the particle swarm optimization algorithm simulates multiple possible evacuation paths and resource allocation schemes to select the optimal solution. At the same time, traffic flow prediction technology is used to monitor and adjust transportation routes in real time to avoid delays.

[0075] Assuming that in the same military exercise, the system calculated the best evacuation route based on the high density of casualties in a specific area shown by the heat map, using the particle swarm optimization algorithm. Taking into account the local traffic flow forecast, the system recommended roads that bypass peak hours to ensure that the ambulance can reach the destination in the shortest time, improving rescue efficiency.

[0076] Optionally, in step 102, based on the virtual medical resource heat map, combined with the priority rules for the transfer of the sick and wounded and the transportation logistics optimization theory, a particle swarm optimization algorithm is used to perform intelligent planning and processing on the evacuation path of the sick and wounded and the allocation plan of medical supplies, and the transportation route is dynamically adjusted through traffic flow prediction technology to generate an evacuation plan of the sick and wounded and a resource allocation plan, including:

[0077] Based on the virtual medical resource heat map, the distribution and urgency of the wounded and sick are evaluated and processed to obtain the urgency assessment results of the wounded and sick; using the urgency assessment results of the wounded and sick, combined with the priority rules for the transfer of the wounded and sick, the evacuation order of the wounded and sick is determined and processed to obtain the evacuation priority sequence of the wounded and sick; according to the evacuation priority sequence of the wounded and sick, the particle swarm optimization algorithm is applied to intelligently plan the evacuation path of the wounded and sick and the allocation plan of medical supplies to obtain a preliminary evacuation path and resource allocation plan; based on the preliminary evacuation path and resource allocation plan, combined with the transportation logistics optimization theory, the factors that may affect the transportation efficiency are analyzed and processed through traffic flow prediction technology to obtain an analysis report on factors affecting transportation efficiency; using the analysis report on factors affecting transportation efficiency, the preliminary evacuation path is dynamically adjusted to ensure that the wounded and sick are safely transferred to the most suitable treatment location in the shortest time, and medical resources are efficiently allocated to generate an evacuation and resource allocation plan for the wounded and sick.

[0078] In this step, based on the virtual medical resource heat map, the map summarizes the information of the distribution of the wounded and the urgency of the wounded. By evaluating this information, the urgency assessment results of the wounded can be obtained. Using this result, combined with the pre-set priority rules for the transfer of the wounded, the order of evacuation of the wounded is determined to form a priority sequence for the evacuation of the wounded. Subsequently, the particle swarm optimization algorithm is used to plan the evacuation route of the wounded and the allocation plan of medical supplies. Traffic flow prediction technology is used to analyze the factors that may affect the transportation efficiency, and dynamically adjust the evacuation route according to these factors to ensure that the wounded can safely reach the treatment location in the shortest time, while efficiently allocating medical resources.

[0079] In the embodiment of the present application, first, the system evaluates the distribution and urgency of the wounded and sick in the virtual medical resource heat map; secondly, the evacuation order of the wounded and sick is determined based on the evaluation results and the transfer priority rules; thirdly, the particle swarm optimization algorithm is used to formulate a preliminary plan for the evacuation route of the wounded and sick and the allocation of medical resources; finally, combined with the transportation logistics optimization theory, the traffic flow prediction technology is used to analyze the factors that may affect the transportation efficiency, and the preliminary evacuation route is optimized and adjusted accordingly to generate the final evacuation and resource allocation plan for the wounded and sick.

[0080] Assume that in a large-scale urban disaster response exercise, the system first generates a detailed virtual medical resource heat map from the data collected from various temporary medical sites; this enables the command center to identify which areas need urgent attention; then, the system formulates an evacuation priority sequence based on the severity of the injuries and geographical location of the injured; thirdly, the system uses the particle swarm optimization algorithm to calculate multiple feasible evacuation paths and proposes a preliminary medical resource allocation plan; finally, through traffic flow prediction technology, the system finds some road congestion points during peak hours and adjusts the evacuation paths accordingly to ensure that all the injured can be transferred to the nearest and most suitable treatment facilities in the shortest time, while ensuring the effective allocation of medical resources; through the above steps, the entire rescue operation can be carried out efficiently and orderly, maximizing the rescue efficiency and reducing unnecessary delays.

[0081] Optionally, based on the preliminary evacuation route and resource allocation plan, combined with the transportation logistics optimization theory, the factors that may affect the transportation efficiency are analyzed and processed by traffic flow prediction technology to obtain a transportation efficiency influencing factor analysis report, including:

[0082] Based on the preliminary evacuation route and resource allocation plan, the initial plan for the evacuation of the wounded and the distribution of medical supplies is evaluated and processed, and the key nodes that affect the transportation efficiency are identified to obtain the key node identification results; using the key node identification results, combined with the transportation logistics optimization theory, the traffic characteristics of these nodes in different time periods are modeled and processed to obtain a traffic characteristic model; based on the traffic characteristic model, the traffic flow prediction technology is applied to predict the traffic flow change trend of each key node in the future period of time to obtain traffic flow prediction data; based on the traffic flow prediction data, the factors that hinder and promote transportation efficiency are quantitatively analyzed and processed to obtain a list of factors affecting transportation efficiency; using the list of factors affecting transportation efficiency, combined with actual traffic rules and historical data, the importance of each influencing factor is scored and processed to obtain an importance scoring table; based on the importance scoring table, the specific impact of each factor on transportation efficiency is comprehensively considered to generate a transportation efficiency influencing factor analysis report.

[0083] Optionally, the analysis report of factors affecting transport efficiency is used to dynamically adjust the initial evacuation route to ensure that the wounded and sick are safely transferred to the most suitable treatment location in the shortest time, and medical resources are efficiently allocated to generate a plan for evacuating the wounded and sick and resource allocation, including:

[0084] By using the analysis report of factors affecting transport efficiency, the key nodes and sections in the preliminary evacuation route are re-evaluated, potential bottlenecks and optimization opportunities are identified, and the analysis results of the route bottlenecks and optimization points are obtained; based on the analysis results of the route bottlenecks and optimization points, in combination with real-time traffic data and prediction models, the preliminary evacuation route is adjusted, and the route is optimized to avoid sections with high traffic or possible delays, so as to obtain an optimized evacuation route plan; according to the optimized evacuation route plan, the evacuation sequence and time window of the wounded are re-planned, and the evacuation sequence and time window plan of the wounded are obtained; by using the evacuation sequence and time window plan of the wounded, in combination with the distribution of existing medical resources, the allocation of medical supplies and the arrangement of medical staff are synchronously adjusted, and a medical resource allocation and personnel arrangement plan is obtained; based on the medical resource allocation and personnel arrangement plan, a full-process monitoring and feedback mechanism is implemented, and the entire evacuation and resource allocation process is tracked and processed through the intelligent scheduling system, and the effective implementation of the plan is continuously optimized and ensured, so as to generate an evacuation and resource allocation plan for the wounded.

[0085] In this step, based on the preliminary evacuation route and resource allocation plan, combined with the theory of traffic logistics optimization, the factors that may affect the transportation efficiency are analyzed and processed through traffic flow forecasting technology. This process includes identifying the key nodes that affect the transportation efficiency, establishing the traffic characteristic model of these nodes, predicting the trend of traffic flow changes in the future, and quantitatively analyzing the factors that hinder and promote transportation efficiency. Finally, a transportation efficiency influencing factor analysis report is generated to dynamically adjust the preliminary evacuation route, ensure the safe and rapid transfer of the wounded and sick to the most suitable treatment location, and efficiently allocate medical resources.

[0086] In the embodiment of the present application, first, the system evaluates the initial planning of the evacuation of the wounded and the distribution of medical supplies, and identifies the key nodes that affect the transportation efficiency; secondly, the key node identification results are used, combined with the transportation logistics optimization theory, to model the traffic characteristics of these nodes in different time periods; thirdly, according to the traffic characteristic model, the traffic flow prediction technology is applied to predict the future traffic flow change trend of each key node; finally, based on the traffic flow prediction data, the factors affecting the transportation efficiency are quantitatively analyzed, and combined with the actual traffic rules and historical data scores, a transportation efficiency influencing factor analysis report is generated. Subsequently, this report is used to re-evaluate the key nodes and sections in the path, identify bottlenecks and optimization opportunities; based on these analysis results, combined with real-time traffic data and prediction models, the evacuation path is adjusted to avoid high traffic or possible delay sections; according to the optimized evacuation path, the evacuation order and time window of the wounded are re-planned; combined with the existing distribution of medical resources, the allocation of medical supplies and the arrangement of medical staff are adjusted synchronously; finally, a full-process monitoring and feedback mechanism is implemented, and the entire evacuation and resource allocation process is tracked through the intelligent scheduling system, and continuous optimization and effective implementation of the plan are ensured.

[0087] Assuming that after a natural disaster occurs in a large city, the rescue command center first evaluates the initial evacuation routes and resource allocation plans, and identifies key nodes that affect transportation efficiency, such as major bridges and intersections; secondly, using the information of these key nodes and combining it with the theory of transportation logistics optimization, a traffic characteristic model of these nodes in different time periods is established; thirdly, based on the established traffic characteristic model, traffic flow prediction technology is applied to predict the traffic flow change trend of each key node in the next few days; finally, based on the predicted data, the factors that hinder and promote transportation efficiency are quantitatively analyzed, and the importance of each influencing factor is scored in combination with actual traffic rules and historical data to generate A detailed analysis report on factors affecting transport efficiency was prepared. Subsequently, the command center used this report to re-evaluate key nodes and sections in the evacuation route, identifying potential bottlenecks and optimization opportunities. Based on these analysis results, combined with real-time traffic data and prediction models, the initial evacuation route was adjusted to optimize the route to avoid sections with high traffic or possible delays. Based on the optimized evacuation route, the evacuation sequence and time window for the injured and sick were replanned. Combined with the distribution of existing medical resources, the allocation of medical supplies and the arrangement of medical staff were adjusted synchronously. Finally, a full-process monitoring and feedback mechanism was implemented, and the entire evacuation and resource allocation process was tracked through the intelligent dispatching system to continuously optimize and ensure the effective implementation of the plan.

[0088] Through the above steps, the rescue operation was carried out efficiently and orderly, maximizing rescue efficiency and reducing unnecessary delays, ensuring that all injured and sick people could be transferred to the most suitable treatment facilities in the shortest time, while ensuring the effective allocation of medical resources.

[0089] This application takes into account that in the prior art, since the planning of evacuation routes for the wounded and the allocation of medical supplies usually relies on static data and fixed rules, it is not possible to flexibly respond to the dynamically changing battlefield environment. In addition, the traditional method lacks comprehensive consideration of factors such as the priority of the wounded, resource demand, and traffic flow, resulting in problems such as uneven resource allocation and low transportation efficiency. Therefore, the embodiment of the present invention proposes this optional solution, which aims to achieve intelligent planning and processing through a particle swarm optimization algorithm combined with the evacuation priority of the wounded and the path distance to adjust the inertia weight, solve the above-mentioned technical problems, and ensure that resources efficiently meet the needs of treatment.

[0090] Optionally, the particle swarm optimization algorithm is applied according to the priority sequence of evacuation of the wounded and sick to perform intelligent planning processing on the evacuation path of the wounded and sick and the allocation plan of medical supplies to obtain a preliminary evacuation path and resource allocation plan, including:

[0091] Calculating the new velocity of the particle Before that, it is necessary to evaluate the current fitness of each particle and record its historical best position pbest i,d and the optimal position of the group g -1 bestt d , and adjust the inertia weight w(t) according to the evacuation priority of the injured and sick and the path distance to provide an information basis for speed update;

[0092]

[0093] represents the new velocity of the i-th particle in the d-th dimension; w(t) represents the time-dependent inertia weight, which is adjusted with the number of iterations; represents the current velocity of the ith particle in the dth dimension; c 1 ,c 2 represents the acceleration factor; r 1 ,r 2 represents a random number in the interval [0,1]; pbestt i,d represents the historical optimal position of the i-th particle; represents the current position of the ith particle in the dth dimension; gbest d represents the value of the optimal position of the group in the dth dimension; α represents the weighting factor considering the priority and distance of the wounded and sick; priority j represents the evacuation priority of the jth injured person; ij represents the distance from the evacuation path represented by the i-th particle to the j-th injured person's location; N represents the total number of injured people;

[0094] Complete new speed After the calculation, the updated speed is applied to the particle position adjustment, and the position update is weighted by considering factors such as the evacuation priority of the wounded and sick, the demand for medical supplies, and the traffic flow, to ensure that the new position selection is close to the actual situation and improve the effectiveness and feasibility of the plan;

[0095]

[0096] represents the new position of the i-th particle in the d-th dimension; represents the current position of the i-th particle in the d-th dimension; represents the new velocity of the ith particle in the dth dimension; β represents the weighting factor considering the impact of resource demand; resourceDemand j,d represents the value of the demand for medical supplies by the jth injured and sick person in the dth dimension; γ represents the weighting factor considering the influence of traffic flow and route distance; trafficFlow k represents the traffic flow of the kth evacuation route;ik represents the distance from the evacuation path represented by the i-th particle to the k-th evacuation path; M represents the total number of evacuation paths;

[0097] Calculate the new particle position After that, it is necessary to verify the accessibility and safety of the path, and re-evaluate the resource allocation situation to ensure that resources efficiently meet the rescue needs; finally, by comparing the results of different iterations, the optimal evacuation path combination and resource allocation strategy are selected to form a preliminary evacuation path and resource allocation plan, providing a scientific basis and technical support for implementation.

[0098] This formula aims to improve the effectiveness and feasibility of the evacuation path and resource allocation plan for the wounded and sick. By introducing the particle swarm optimization algorithm and taking into full account factors such as the priority of the wounded and sick, resource demand, and traffic flow in the process of speed update and position update, the final plan is closer to the actual situation, thereby improving the rescue efficiency and the rationality of resource utilization.

[0099] The following is a brief introduction to the design reasons of each sub-item of the formula:

[0100]

[0101] Calculating the new velocity of the particle Before that, it is necessary to evaluate the current fitness of each particle and record its historical best position pbest i,d and the group optimal position gbestt d , and adjust the inertia weight w(t) according to the evacuation priority and path distance of the injured and sick, providing information basis for speed update; time-dependent inertia weight w(t): adjusted with the number of iterations to balance exploration and development; current speed Reflects the historical movement trend of particles and is used to inherit the velocity information of the previous moment; acceleration term Guide the particle to move closer to its historical optimal position, where c 1 is the acceleration factor, r 1 is a random number in the interval [0,1]; the acceleration term Guide the particles to move closer to the global optimal position, where c 2 is the acceleration factor, r 2 is a random number in the interval [0,1]; a weighting factor that takes into account the priority of the injured and the path distance Adjust the route selection according to the evacuation priority of the injured and sick to ensure that high-priority injured and sick people receive resources and support first;

[0102] The following is a brief introduction to how to obtain the parameters of the formula:

[0103] Time-dependent inertia weight w(t): adjusted with the number of iterations; current speed Obtained from the previous iteration result; acceleration coefficient c 1 ,c 2 : Set according to experience; random number r 1 ,r 2 : Randomly generated in the interval [0,1]; historical optimal position Record the historical optimal solution of each particle; current position The particle position in the current iteration; the optimal position of the group g -1 estd d : records the global optimal solution of all particles; weighting factor α: set according to the actual application scenario; priority of evacuation of the wounded and sick j : Determined according to the emergency level of the injured and sick; path distance ij : Calculated by Geographic Information System (GIS); Total number of injured and sick people N: Count the number of injured and sick people who need to be evacuated at present;

[0104] The following is a brief introduction to the design reasons of each sub-item of the formula:

[0105]

[0106] Factors such as medical supplies demand and traffic flow are weighted to update the location to ensure that the new location is close to the actual situation and improve the effectiveness and feasibility of the plan; Current location The current particle's position information is used to inherit the position state of the previous moment; the new speed The newly calculated velocity is used to update the particle position; a weighting factor to account for the impact of resource requirements Adjust the location according to the resource demand of the injured and sick to ensure reasonable resource allocation; consider the weighting factors of traffic flow and route distance Optimize routing based on traffic flow and route distance to avoid congestion and delays.

[0107] The following is a brief introduction to how to obtain the parameters of the formula:

[0108] Current location The particle's position in the current iteration; the new velocity Calculated by the first formula; weighting factor β: set according to the actual application scenario; resource demand resourceDemandd j,d : Determined based on the injuries and treatment needs of the wounded and sick; priority of evacuation of the wounded and sick j : Determined according to the emergency level of the injured and sick; Total number of injured and sick N: Count the number of injured and sick people who need to be evacuated; Weighting factor γ: Set according to the actual application scenario; Traffic flow trafficFlow k: Obtained through real-time traffic monitoring system; route distance routeDistance ik : Calculated by Geographic Information System (GIS); Total number of evacuation routes M: Count the number of available evacuation routes;

[0109] The inertia weight w(t) is adjusted according to the evacuation priority and path distance of the injured and sick, providing an information basis for velocity update; for example, for a specific particle i, the new velocity in the dth dimension is The calculation of is as follows:

[0110] Complete new speed After calculating , the updated speed is applied to the particle position adjustment, and the position update is weighted by considering factors such as the evacuation priority of the wounded and sick, the demand for medical supplies, and the traffic flow, to ensure that the new position selection is close to the actual situation and improve the effectiveness and feasibility of the scheme; for example, for the same particle i, the new position in the dth dimension The calculation of is as follows:

[0111] Calculate the new particle position After that, it is necessary to verify the accessibility and safety of the path, and re-evaluate the resource allocation situation to ensure that resources efficiently meet the rescue needs; finally, by comparing the results of different iterations, the optimal evacuation path combination and resource allocation strategy are selected to form a preliminary evacuation path and resource allocation plan, providing a scientific basis and technical support for implementation.

[0112] Assuming the threshold is set to 3.0, since the result 3.52 is greater than the threshold, it shows that the selected path and resource allocation strategy can effectively improve the rescue efficiency and ensure that resources can efficiently meet the treatment needs. This not only solves the problems of uneven resource allocation and low transportation efficiency in the existing technology, but also significantly improves the ability and flexibility of the field hospital to respond to emergencies.

[0113] 103. Using the evacuation and resource allocation plan for the injured and sick, combined with the real-time updated treatment progress and resource consumption data and the historical similar case library, the support vector machine algorithm is used to evaluate the effectiveness of the current treatment strategy, obtain a forward-looking decision support report, monitor the risk points that may appear in the treatment process through time series anomaly detection technology, and generate risk warnings and response measures;

[0114] In this step, the support vector machine algorithm is used to evaluate the effectiveness of the current treatment strategy by using the evacuation and resource allocation plan for the injured and sick, combined with the real-time updated treatment progress and resource consumption data, as well as the historical similar case library. In addition, the risk points in the treatment process are monitored through time series anomaly detection technology to generate forward-looking decision support reports and risk warning and response measures.

[0115] In the embodiment of the present application, the status of rescue activities is first dynamically monitored, and the progress of rescue and resource consumption are recorded. Then, the support vector machine algorithm is used to evaluate the success rate of the existing strategy in combination with the historical case library. Subsequently, potential risk points are identified through time series anomaly detection technology, and countermeasures are formulated to form a comprehensive decision support and risk warning plan.

[0116] Assume that during the exercise, the system continuously monitors the progress of treatment in a certain area and finds that the recovery rate of certain types of patients is slower than expected. By comparing with the historical similar case library, the system identifies these cases as having infection risks and issues early warnings. Subsequently, the medical team takes additional disinfection and isolation measures to prevent the spread of infection and protect the safety of other patients.

[0117] Optionally, in step 103, the evacuation and resource allocation plan for the wounded and sick is used in combination with the real-time updated treatment progress and resource consumption data and the historical similar case library, and a support vector machine algorithm is applied to evaluate the effectiveness of the current treatment strategy to obtain a forward-looking decision support report, and the risk points that may appear in the treatment process are monitored by time series anomaly detection technology to generate risk warnings and response measures, including:

[0118] The evacuation and resource allocation plan for the wounded and sick is used in combination with the real-time updated treatment progress and resource consumption data to dynamically monitor the status of the current treatment activities and obtain the treatment status monitoring results; based on the treatment status monitoring results, the relevant information in the historical similar case library is integrated, the current treatment situation is compared and analyzed with the historical cases, the key factors affecting the treatment effect are identified, and a key factor identification list is obtained; based on the key factor identification list, the support vector machine algorithm is applied to evaluate the effectiveness of the current treatment strategy. The support vector machine algorithm distinguishes data points with different treatment effects by constructing an optimal classification surface, predicts the resource demand trend and the success rate of the treatment strategy in the short term, and obtains a forward-looking decision support report; using the forward-looking decision support report, combined with the time series anomaly detection technology, the risk points that may appear in the treatment process are monitored and processed, and the abnormal situations that deviate from the normal treatment process are identified to obtain the abnormal situation identification results; based on the abnormal situation identification results, specific response measures for various risks are formulated to obtain risk warning and response measures plans.

[0119] In this step, the evacuation and resource allocation plan for the wounded and sick is used, combined with the real-time updated treatment progress and resource consumption data and the historical similar case library, and the support vector machine algorithm is used to evaluate the effectiveness of the current treatment strategy and generate a forward-looking decision support report. At the same time, the time series anomaly detection technology is used to monitor the risk points that may appear during the treatment process, and to formulate risk warning and response measures. Specifically, the system first dynamically monitors the current status of the treatment activities to obtain the treatment status monitoring results; secondly, it integrates the information of the historical similar case library to identify the key factors affecting the treatment effect; thirdly, it uses the support vector machine to construct the optimal classification surface to predict the resource demand trend and the success rate of the treatment strategy in the short term; finally, combined with the time series anomaly detection technology, it identifies abnormal situations that deviate from the normal treatment process and formulates corresponding response measures.

[0120] In the embodiment of the present application, first, the system dynamically monitors the evacuation and resource allocation plan of the wounded and sick, as well as the real-time updated treatment progress and resource consumption data, to obtain the treatment status monitoring results; secondly, based on these monitoring results, the relevant information in the historical similar case library is integrated, the current treatment situation and historical cases are compared and analyzed, the key factors affecting the treatment effect are identified, and a key factor identification list is formed; thirdly, according to the key factor identification list, the support vector machine algorithm is applied to evaluate the effectiveness of the current treatment strategy, predict the short-term resource demand trend and the success rate of the treatment strategy, and generate a forward-looking decision support report; finally, combined with the time series anomaly detection technology, the risk points that may appear in the treatment process are monitored, the abnormal situations that deviate from the normal treatment process are identified, and specific response measures are formulated for various risks to form a risk warning and response plan.

[0121] Assume that in a large-scale natural disaster rescue operation, the system first dynamically monitors the evacuation and resource allocation plan of the wounded and sick, as well as the real-time updated treatment progress and resource consumption data, and obtains detailed treatment status monitoring results; secondly, based on these monitoring results, the system integrates the information of the historical similar case library, compares and analyzes the current treatment situation with historical cases, identifies the key factors that affect the treatment effect, such as the recovery speed of specific types of wounded and sick, the consumption rate of medical supplies, etc., and forms a key factor identification list; thirdly, based on the key factor identification list, the system uses the support vector machine algorithm to evaluate the effectiveness of the current treatment strategy, predict the resource demand trend and the success rate of the treatment strategy in the short term, and generates a forward-looking decision support report, pointing out that some areas may face the problem of shortage of medical supplies; finally, combined with time series anomaly detection technology, the system monitors the risk points that may occur during the treatment process, identifies some abnormal situations that deviate from the normal treatment process, such as the abnormal increase in the occupancy rate of intensive care beds in a hospital, and formulates specific response measures accordingly, such as deploying more medical staff and equipment to the hospital to ensure timely handling of emergencies;

[0122] Through the above steps, the rescue command center can detect potential problems in advance and take effective measures based on scientific data analysis and model prediction to ensure that the entire rescue operation is carried out efficiently and orderly, maximize the success rate of treatment, and reduce unnecessary delays and waste of resources.

[0123] Optionally, the forward-looking decision support report is used in combination with time series anomaly detection technology to monitor and process risk points that may occur during the treatment process, identify abnormal situations that deviate from the normal treatment process, and obtain abnormal situation identification results, including:

[0124] Utilize the forward-looking decision support report to analyze and process the success rate and resource demand trends of the current treatment strategy, determine the key treatment links that require special attention, and obtain a list of key treatment links; based on the list of key treatment links, combine time series anomaly detection technology to compare and analyze the historical data and real-time data of these links, build an anomaly detection model, and obtain an anomaly detection model; according to the anomaly detection model, continuously monitor and process various indicators in the treatment process, identify data patterns that are inconsistent with the normal treatment process, and obtain preliminary abnormal situation prompts; utilize the preliminary abnormal situation prompts, combine clinical expertise and a historical similar case library, conduct in-depth evaluation and processing of possible risk points, confirm the true abnormal situation and its severity, and obtain abnormal situation confirmation results; based on the abnormal situation confirmation results, classify the identified abnormal situations, distinguish different types of abnormal situations, and record the specific manifestations and occurrence frequencies of each abnormality to obtain abnormal situation identification results.

[0125] In this step, forward-looking decision support reports are used in combination with time series anomaly detection technology to monitor and process possible risk points during the treatment process. This process includes analyzing the success rate and resource demand trends of the current treatment strategy, determining key treatment links; building an anomaly detection model to continuously monitor various indicators during the treatment process and identify data patterns that deviate from the normal treatment process; combining clinical expertise and historical similar case libraries to evaluate possible risk points and confirm the true abnormalities and their severity; finally, classifying and processing the abnormalities, and recording the specific manifestations and frequency of each abnormality.

[0126] First, systematically analyze the success rate and resource demand trends in the forward-looking decision support report to identify the key treatment links that require special attention; second, based on these key links, combined with time series anomaly detection technology, compare and analyze historical data and real-time data to build an anomaly detection model; third, according to the anomaly detection model, continuously monitor various indicators during the treatment process, identify data patterns that are inconsistent with the normal treatment process, and obtain preliminary abnormal situation prompts; finally, use the preliminary abnormal situation prompts, combined with clinical expertise and historical similar case libraries, to deeply evaluate possible risk points, confirm the true abnormal situation and its severity, and classify and process the abnormal situation, and record the specific manifestations and frequency of occurrence.

[0127] Assume that in a large-scale public health event, the system first analyzes the success rate and resource demand trends in the forward-looking decision support report, identifies the key treatment links that need special attention, such as intensive care, ventilator use, etc., and forms a list of key treatment links; secondly, based on these key links, the system combines time series anomaly detection technology, compares and analyzes historical data and real-time data, and builds an anomaly detection model to identify potential anomalies; thirdly, according to the anomaly detection model, the system continuously monitors various indicators in the treatment process and identifies some data patterns that are inconsistent with the normal treatment process, such as a sudden increase in the occupancy rate of intensive care beds in a hospital, which gives preliminary abnormal situation prompts; finally, using these preliminary prompts, the system combines clinical expertise and historical similar case libraries to deeply evaluate possible risk points, confirm the real abnormalities and their severity, such as the deterioration rate of some patients' conditions exceeding expectations, and then classifies and processes these abnormalities, distinguishes different types of abnormalities, and records the specific manifestations and frequency of each abnormality, such as the high frequency of deterioration of a specific type of injured and sick patients;

[0128] Through the above steps, the medical team can promptly detect and deal with deviations from the normal treatment process, take preventive measures in advance, ensure the safety and effectiveness of the treatment process, maximize the success rate of treatment, and reduce unnecessary delays and waste of resources.

[0129] This application takes into account that in the prior art, due to the lack of methods for dynamically evaluating the effectiveness of treatment strategies, they often rely on static historical data and empirical rules and cannot adapt to changing medical needs in a timely manner. In addition, when predicting resource demand trends and treatment success rates, traditional methods fail to fully consider complex factors such as seasonal fluctuations, priorities of the injured and sick, and resource requirements, resulting in inaccurate prediction results, affecting decision-making efficiency and quality. Therefore, the embodiment of the present invention proposes this optional solution, which aims to use a support vector machine algorithm combined with multiple weighting factors to construct an optimal classification surface to distinguish data points with different treatment effects, predict short-term resource demand trends and the success rate of treatment strategies, solve the above-mentioned technical problems, and provide more scientific and reasonable forward-looking decision support.

[0130] Optionally, the effectiveness of the current treatment strategy is evaluated and processed by applying a support vector machine algorithm based on the key factor identification list. The support vector machine algorithm distinguishes data points with different treatment effects by constructing an optimal classification surface, predicts the resource demand trend and the success rate of the treatment strategy in the short term, and obtains a forward-looking decision support report, including:

[0131] Before constructing the weight vector w of the optimal classification surface, it is necessary to standardize the sample characteristics, identify key factors and calculate the correction vector, evaluate the impact of seasonal fluctuations, and calculate the weighting factor based on the priority of the injured and sick and resource requirements to provide a basis for subsequent calculations;

[0132]

[0133] w represents the weight vector of the optimal classification surface; α i represents the Lagrange multiplier, corresponding to the support vector coefficient of the i-th sample; y i represents the label of the i-th sample, representing the data point of the treatment effect; x i represents the key factor feature vector of the i-th sample; N represents the total number of samples; λ represents the regularization parameter, which is used to control the complexity of the model to prevent overfitting; c represents the correction vector calculated based on the historical similar case library, which helps adjust the classification surface to adapt to specific rescue scenarios; γ represents the seasonal effect adjustment factor, which is used to adjust the impact of seasonal fluctuations on the classification surface; seasonalEffect k represents the kth seasonal impact factor, reflecting the changing trend in different time periods; s k represents the eigenvector corresponding to the kth seasonal influencing factor; K represents the number of seasonal influencing factors; δ represents the priority and resource demand weighting factor, which is used to adjust the priority of the sick and wounded and the degree of influence of resource demand; priority j represents the evacuation priority of the jth injured person; r j M represents the resource demand feature vector corresponding to the jth injured or sick person;s Indicates the total number of sick and wounded;

[0134] After the weight vector w is calculated, the kernel function is used to measure the sample similarity, and the prediction function f(x) is optimized by combining the classification bias term and various weighting factors to ensure that it can accurately distinguish different treatment effects and predict resource demand trends and treatment success rates;

[0135]

[0136] f(x) represents the prediction result of the new input sample x, which is used to judge the resource demand trend and the success rate of the treatment strategy in the short term; α i represents the Lagrange multiplier, corresponding to the support vector coefficient of the i-th sample; y i represents the label of the i-th sample, representing the data point of the treatment effect; K(x i ,x) represents the kernel function, which measures the sample x i and the similarity between the new input sample x; b represents the classification bias term, which is obtained by solving the optimization problem; η represents the weighting factor, which is used to adjust the degree of influence of resource demand; priority j Indicates the evacuation priority of the jth injured person; resourceDemand j represents the demand for medical supplies by the jth injured patient; M s Indicates the total number of sick and wounded;

[0137] After calculating the prediction function f(x), the prediction results are interpreted and visualized, the rationality of the adjusted prediction is verified, and resource allocation and treatment strategy adjustment plans are formulated, ultimately forming a forward-looking decision support report to provide a scientific basis for actual decision-making.

[0138] This formula aims to improve the accuracy and foresight of treatment strategy evaluation. By introducing the support vector machine algorithm and fully considering the influence of factors such as seasonal fluctuations, priority of the injured and sick, and resource requirements in the calculation process of the weight vector w and the prediction function f(x), the final forward-looking decision support report is closer to the actual situation, thereby improving the rationality of resource allocation and the effectiveness of treatment strategies.

[0139] The following is a brief introduction to the design reasons of each sub-item of the formula:

[0140]

[0141] Before constructing the weight vector w of the optimal classification surface, the sample features need to be standardized, key factors need to be identified and correction vectors need to be calculated, the impact of seasonal fluctuations need to be evaluated, and weighting factors need to be calculated based on the priority of the injured and sick and resource requirements to provide a basis for subsequent calculations; Sample feature standardization: ensure that each feature has the same scale to improve model performance; Lagrange multiplier multiplication with label and feature vector Reflects the impact of the support vector on the classification surface, ensuring that the model can accurately distinguish data points with different treatment effects; the product of the regularization parameter and the correction vector λ·c: controls the complexity of the model to prevent overfitting, and adjusts the impact of seasonal fluctuations on the classification surface to ensure that the model can adapt to the changing trends in different time periods; the product of the priority and resource demand weighting factor and the priority and resource demand feature vector of the injured and sick Adjust triage according to patient priorities and resource requirements to ensure that high-priority patients and resource requirements are given priority;

[0142] The following is a brief introduction to how to obtain the parameters of the formula:

[0143] Sample feature standardization: ensure that each feature has the same scale; identify key factors and calculate the correction vector c: extract from the historical similar case library; Lagrange multiplier α i : obtained by solving the optimization problem; label y i : Labeled according to treatment effect; feature vector x i : The key factor extracted from the sample; Regularization parameter λ: Controls the complexity of the model to prevent overfitting; Seasonal effect adjustment factor γ: Adjusts the impact of seasonal fluctuations on the classification surface; Seasonal effect factor seasonalEffectt k : Analyze the changing trends in different time periods; characteristic vector s k : corresponds to each seasonal influencing factor; priority and resource demand weighting factor δ: adjusts the impact of the priority and resource demand of the wounded and sick; priority of evacuation of the wounded and sick j :Determined according to the emergency level of the injured and sick; resource demand characteristic vector r j :Determined based on the injuries and treatment needs of the wounded and sick; Total number of wounded and sick M s : Count the number of injured and sick people who need to be evacuated; Number of seasonal influencing factors K: Result from statistical analysis; Total number of samples N: Count the number of all available samples

[0144] The following is a brief introduction to the design reasons of each sub-item of the formula:

[0145]

[0146] After completing the calculation of the weight vector w, the kernel function is used to measure the sample similarity, and the prediction function f(x) is optimized by combining the classification bias term and various weighting factors to ensure that it can accurately distinguish different treatment effects and predict resource demand trends and treatment success rates; the kernel function measures sample similarity Measures the similarity between existing samples and support vectors to ensure the prediction accuracy of new input samples; classification bias term b: provides a baseline offset to help the model better fit the data; adjusts the prediction results based on priorities and resource requirements to ensure more reasonable resource allocation and improve the success rate of treatment strategies.

[0147] The following is a brief introduction to how to obtain the parameters of the formula:

[0148] Kernel function K(x i ,x): measure sample x i The similarity between the new input sample x and the Lagrange multiplier α i : obtained by solving the optimization problem; label y i : Labeled according to the treatment effect; Classification bias term b: obtained by solving the optimization problem; Weighting factor η: adjusts the degree of influence of resource demand; Priority of evacuation of the wounded and sick j :Determined according to the urgency of the injured and sick; the demand for medical supplies resourceDemand j :Determined based on the injuries and treatment needs of the wounded and sick; Total number of wounded and sick M s : Count the number of injured and sick people who need to be evacuated; Total number of samples N: Count the number of all available samples;

[0149] Assume that in a large-scale disaster relief operation, the system first standardizes the sample features, identifies key factors and calculates the correction vector c, evaluates the impact of seasonal fluctuations, and calculates weighting factors based on the priority of the injured and sick and resource requirements to provide a basis for subsequent calculations; for example, for a specific scenario, the weight vector w is calculated as follows:

[0150]

[0151] After the weight vector w is calculated, the kernel function is used to measure the sample similarity, and the prediction function f(x) is optimized by combining the classification bias term and various weighting factors to ensure that it can accurately distinguish different treatment effects and predict resource demand trends and treatment success rates. For example, for the same scenario, the prediction function f(x) is calculated as follows:

[0152]

[0153] After calculating the prediction function f(x), the prediction results are interpreted and visualized, the rationality of the adjusted prediction is verified, and resource allocation and treatment strategy adjustment plans are formulated, ultimately forming a forward-looking decision support report to provide a scientific basis for actual decision-making.

[0154] Assuming the threshold is set to 0, since the result 1.82 is greater than the set threshold, it shows that the selected treatment strategy can effectively improve the rationality of resource allocation and the success rate of the treatment strategy. This not only solves the problems of uneven resource allocation and inaccurate prediction results in the existing technology, but also significantly improves the ability and flexibility of the frontline hospital to respond to emergencies, and provides more scientific and reasonable forward-looking decision support.

[0155] 104. Based on the forward-looking decision support report and risk warning and response plan, a cross-regional, multi-departmental cloud-based collaborative work platform will be established to generate efficient communication channels and information security assurance mechanisms to enhance the overall ability and flexibility of the field hospital to respond to emergencies.

[0156] In this step, a cross-regional, multi-departmental cloud-based collaborative work platform was established based on forward-looking decision support reports and risk warning and response measures. The platform provides efficient communication channels and strict information security mechanisms to ensure that all parties can simultaneously access and share the latest treatment information, thereby improving the overall ability and flexibility of field hospitals to respond to emergencies.

[0157] In the embodiment of this application, first, a cloud-based collaborative work platform is designed and deployed, integrating efficient communication tools and information sharing modules. Secondly, strict security measures are implemented, such as data encryption transmission, access permission control, etc., to ensure the security of sensitive information. Finally, training and technical support services are provided to improve the convenience and reliability of platform use and promote seamless collaboration among multiple departments.

[0158] Suppose that in a multinational joint military exercise, participating troops from various countries have established a cloud-based collaborative work platform. The platform allows real-time communication between frontline doctors, rear expert teams, and logistics support departments. For example, when a soldier is injured, frontline doctors can immediately upload diagnostic information, rear experts can provide instant remote consultation, and the logistics department can quickly allocate necessary medical supplies as needed. The entire process is achieved through secure data transmission and strict access control, which ensures information security and response speed, greatly improving rescue efficiency.

[0159] Optionally, in step 104, based on the forward-looking decision support report and the risk warning and response plan, a cross-regional, multi-departmental cloud collaborative work platform is established to generate efficient communication channels and information security mechanisms to enhance the overall ability and flexibility of the field hospital to respond to emergencies, including:

[0160] Utilize the forward-looking decision support report to comprehensively evaluate the success rate of treatment strategies and resource demand trends, identify key links and participating departments that require focused coordination, and obtain a list of key coordination points; based on the list of key coordination points, combined with risk warning and response measures, design the functional requirements and architecture blueprint of the cloud-based collaborative work platform to ensure that the platform can meet the needs of multi-party collaboration and obtain a platform design plan; according to the platform design plan, develop and integrate efficient communication tools and information sharing modules so that frontline doctors, rear expert teams, and logistics support departments can communicate and share treatment information in real time and obtain an efficient communication channel; utilize the efficient communication channel, combined with information security technology and management measures, build security functions for data encryption transmission, access permission control, and audit tracking to ensure the security of sensitive medical information during transmission and storage and obtain an information security assurance mechanism.

[0161] In this step, a cross-regional, multi-departmental cloud-based collaborative work platform is established based on forward-looking decision support reports and risk warning and response measures. The platform enhances the overall ability and flexibility of the frontline hospital to respond to emergencies by generating efficient communication channels and information security mechanisms. Specifically, the system first conducts a comprehensive assessment of the success rate of the treatment strategy and the resource demand trend to determine the key coordination points; secondly, based on these key points, the functional requirements and architecture blueprint of the cloud platform are designed; thirdly, efficient communication tools and information sharing modules are developed and integrated to ensure real-time communication and information sharing among multiple parties; finally, information security technologies and management measures are combined to build security functions for data encryption transmission, access rights control, and audit tracking to protect sensitive medical information.

[0162] In the embodiment of the present application, first, the system uses the data in the forward-looking decision support report to comprehensively evaluate the success rate of the treatment strategy and the resource demand trend, determine the key links and participating departments that need to be coordinated, and form a list of key coordination points; secondly, based on the list of key coordination points, and in combination with the risk warning and response measures plan, the functional requirements and architectural blueprint of the cloud-based collaborative work platform are designed to ensure that the platform can meet the needs of collaboration of all parties; thirdly, according to the design plan, efficient communication tools and information sharing modules are developed and integrated, so that front-line doctors, rear expert teams and logistics support departments can communicate and share treatment information in real time, and establish efficient communication channels; finally, using efficient communication channels, combined with information security technologies and management measures, construct security functions of data encryption transmission, access permission control and audit tracking, ensure the security of sensitive medical information during transmission and storage, and form an information security protection mechanism.

[0163] Assuming that in an international joint military exercise, the system first uses the data in the forward-looking decision support report to conduct a comprehensive assessment of the success rate of the treatment strategy and the resource demand trend, and determines the key links that need to be coordinated (such as intensive care, material allocation) and participating departments (such as front-line medical teams, logistics support departments), and forms a list of key coordination points; secondly, based on these key points, and combined with risk warning and response measures, the system designs the functional requirements and architecture blueprint of the cloud-based collaborative work platform to ensure that the platform can meet the needs of multi-party collaboration, especially cross-border real-time communication and information sharing; thirdly, according to the design plan, the system starts The system has developed and integrated efficient communication tools and information sharing modules, allowing frontline doctors, rear expert teams, and logistics support departments to communicate and share treatment information in real time, and has established efficient communication channels, such as seamless collaboration through video conferencing and instant messaging tools. Finally, by utilizing efficient communication channels, the system combines information security technologies and management measures to build security functions for data encryption transmission, access rights control, and audit tracking to ensure the security of sensitive medical information during transmission and storage. For example, all data transmission is end-to-end encrypted, only authorized personnel can access specific information, and each access is recorded for audit purposes.

[0164] Through the above steps, the medical rescue operations during the entire exercise were carried out efficiently and safely, the communication between the participants was smoother, and the information was transmitted more timely and accurately, which significantly enhanced the ability and flexibility of the position hospital to respond to emergencies and ensured that all the wounded and sick could receive the most timely and effective treatment.

[0165] In summary, steps 101 to 104 cover the complete process from data collection to intelligent planning, evaluation and optimization, and finally to collaborative work, aiming to provide a comprehensive, intelligent emergency response solution for field hospitals to meet the needs of efficient, flexible and safe medical resource management and treatment of the wounded and sick in complex and changing battlefield environments.

[0166] Figure 2 A schematic diagram of a big data-based decision-making system for a hospital in the field is provided for the present application embodiment. Figure 2 As shown, the device comprises:

[0167] The collection module 21 is used to collect and comprehensively analyze the dynamic data streams from multiple battlefield medical sites in real time, covering the status of the wounded and sick, the use of medical resources and geographical environmental factors, and generate a virtual medical resource heat map;

[0168] Planning module 22, for intelligently planning and processing the evacuation routes of the sick and wounded and the allocation of medical supplies based on the virtual medical resource heat map, combined with the priority rules for the transfer of the sick and wounded and the transportation logistics optimization theory, using the particle swarm optimization algorithm, dynamically adjusting the transportation routes through the traffic flow prediction technology, and generating the evacuation of the sick and wounded and resource allocation plan;

[0169] Evaluation module 23, used to use the evacuation and resource allocation plan for the injured and sick, combined with the real-time updated treatment progress and resource consumption data and the historical similar case library, apply the support vector machine algorithm to evaluate the effectiveness of the current treatment strategy, obtain a forward-looking decision support report, monitor the risk points that may appear in the treatment process through time series anomaly detection technology, and generate risk warning and response measures;

[0170] The generation module 24 is used to establish a cross-regional, multi-departmental cloud-based collaborative work platform based on the forward-looking decision support report and risk warning and response measures plan, and generate efficient communication channels and information security assurance mechanisms.

[0171] Figure 2 The big data-based hospital decision-making processing system can be implemented Figure 1 The implementation principle and technical effect of the big data-based position hospital decision processing method described in the illustrated embodiment will not be repeated. The specific way in which each module and unit performs operations in the big data-based position hospital decision processing system in the above embodiment has been described in detail in the embodiment of the method, and will not be elaborated here.

[0172] In one possible design, Figure 2 A big data-based decision processing system for a hospital in a field according to the embodiment shown can 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;

[0173] 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 .

[0174] The processing component 32 is used to: collect and comprehensively analyze dynamic data streams from multiple battlefield medical sites in real time, covering the status of the wounded, the use of medical resources and geographical environmental factors, and generate a virtual medical resource heat map; based on the virtual medical resource heat map, combined with the priority rules for the transfer of the wounded and the transportation logistics optimization theory, use the particle swarm optimization algorithm to intelligently plan and process the evacuation path of the wounded and the allocation plan of medical supplies, dynamically adjust the transportation route through traffic flow prediction technology, and generate a plan for the evacuation of the wounded and resource allocation; use the evacuation of the wounded and resource allocation plan, combine the real-time updated treatment progress and resource consumption data and the historical similar case library, apply the support vector machine algorithm to evaluate the effectiveness of the current treatment strategy, obtain a forward-looking decision support report, monitor the possible risk points in the treatment process through time series anomaly detection technology, and generate risk warning and response measures; according to the forward-looking decision support report and the risk warning and response measures, establish a cross-regional, multi-departmental cloud-based collaborative work platform to generate efficient communication channels and information security assurance mechanisms.

[0175] 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.

[0176] 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.

[0177] Of course, the computing device may also include other components, such as input / output interfaces, display components, communication components, etc.

[0178] 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.

[0179] The communication component is configured to facilitate, among other things, wired or wireless communications between the computing device and other devices.

[0180] 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.

[0181] The present application also provides a computer storage medium storing a computer program, wherein the computer program can achieve the above-mentioned Figure 1 The illustrated embodiment is a method for position hospital decision-making based on big data.

[0182] 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.

[0183] 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.

[0184] 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.

[0185] 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 decision-making processing method for a frontier hospital based on big data, characterized in that: include: Real-time collection and comprehensive analysis of dynamic data streams from multiple battlefield medical sites, covering the status of the wounded and sick, the use of medical resources, and geographical environmental factors, to generate a virtual medical resource heat map; Based on the virtual medical resource heat map, combined with the priority rules for the transfer of the wounded and sick and the transportation logistics optimization theory, the particle swarm optimization algorithm is used to intelligently plan the evacuation routes of the wounded and sick and the allocation plan of medical supplies, and the transportation routes are dynamically adjusted through traffic flow prediction technology to generate the evacuation of the wounded and sick and resource allocation plan; By using the evacuation and resource allocation plan for the injured and sick, combined with the real-time updated treatment progress and resource consumption data and the historical similar case library, the support vector machine algorithm is applied to evaluate the effectiveness of the current treatment strategy, and a forward-looking decision support report is obtained. The risk points that may appear in the treatment process are monitored through time series anomaly detection technology, and risk warnings and response measures are generated; Based on the forward-looking decision support report and risk warning and response measures plan, a cross-regional, multi-departmental cloud-based collaborative work platform will be established to generate efficient communication channels and information security assurance mechanisms to enhance the overall ability and flexibility of the position hospital to respond to emergencies.

2. The method according to claim 1, characterized in that Based on the virtual medical resource heat map, combined with the priority rules for the transfer of the wounded and sick and the transportation logistics optimization theory, the particle swarm optimization algorithm is used to intelligently plan the evacuation path of the wounded and sick and the allocation plan of medical supplies, and the transportation route is dynamically adjusted through the traffic flow prediction technology to generate the evacuation of the wounded and sick and resource allocation plan, including: Based on the virtual medical resource heat map, the distribution and urgency of the injured and sick are evaluated and processed to obtain an urgency evaluation result of the injured and sick; Using the emergency assessment results of the injured and sick, combined with the priority rules for the transfer of the injured and sick, the order of evacuation of the injured and sick is determined to obtain the priority sequence of evacuation of the injured and sick; According to the priority sequence of evacuation of the wounded and sick, the particle swarm optimization algorithm is applied to intelligently plan the evacuation path of the wounded and sick and the allocation plan of medical supplies to obtain a preliminary evacuation path and resource allocation plan; Based on the preliminary evacuation route and resource allocation plan, combined with the transportation logistics optimization theory, the factors that may affect the transportation efficiency are analyzed and processed through the traffic flow prediction technology to obtain the analysis report of the factors affecting the transportation efficiency; Utilizing the analysis report on factors influencing transport efficiency, the initial evacuation route is dynamically adjusted to ensure that the wounded and sick are safely transferred to the most suitable treatment location in the shortest time possible, and medical resources are efficiently allocated to generate a plan for the evacuation of the wounded and sick and resource allocation.

3. The method according to claim 2, characterized in that Based on the preliminary evacuation route and resource allocation plan, combined with the transportation logistics optimization theory, the factors that may affect the transportation efficiency are analyzed and processed through the traffic flow prediction technology to obtain the analysis report of the factors affecting the transportation efficiency, including: Based on the preliminary evacuation route and resource allocation plan, the initial plan for evacuation of the wounded and sick and the distribution of medical supplies is evaluated and processed, key nodes that affect transportation efficiency are identified, and key node identification results are obtained; Using the key node identification results and combining with the transportation logistics optimization theory, the traffic characteristics of these nodes in different time periods are modeled and processed to obtain a traffic characteristic model; According to the traffic characteristic model, traffic flow prediction technology is applied to predict the traffic flow change trend of each key node in the future period of time to obtain traffic flow prediction data; Based on the traffic flow forecast data, quantitatively analyzing the factors that hinder and promote transportation efficiency to obtain a list of factors affecting transportation efficiency; Using the list of factors affecting transportation efficiency, combined with actual traffic rules and historical data, the importance of each factor is scored to obtain an importance score table; According to the importance scoring table, the specific impact of various factors on transportation efficiency is comprehensively considered to generate an analysis report on factors affecting transportation efficiency.

4. The method according to claim 2, characterized in that: The analysis report of factors affecting transport efficiency is used to dynamically adjust the initial evacuation route to ensure that the injured and sick are safely transferred to the most suitable treatment location in the shortest time, and medical resources are efficiently allocated to generate an evacuation and resource allocation plan for the injured and sick, including: Using the analysis report of factors affecting transport efficiency, re-evaluate key nodes and sections in the preliminary evacuation route, identify potential bottlenecks and optimization opportunities, and obtain route bottleneck and optimization point analysis results; Based on the analysis results of the bottleneck and optimization points of the path, combined with real-time traffic data and prediction models, the preliminary evacuation path is adjusted and processed, and the path is optimized to avoid sections with high traffic or possible delays, so as to obtain an optimized evacuation path plan; According to the optimized evacuation path plan, the evacuation sequence and time window of the injured and sick are replanned to obtain the evacuation sequence and time window plan of the injured and sick; By using the above-mentioned evacuation sequence and time window planning for the wounded and sick, combined with the existing distribution of medical resources, the allocation of medical supplies and the arrangement of medical staff are adjusted synchronously to obtain a medical resource allocation and personnel arrangement plan; Based on the medical resource allocation and personnel arrangement plan, a full-process monitoring and feedback mechanism is implemented, and the entire evacuation and resource allocation process is tracked and processed through the intelligent scheduling system to continuously optimize and ensure the effective implementation of the plan, and generate an evacuation and resource allocation plan for the injured and sick.

5. The method according to claim 1, characterized in that The evacuation and resource allocation plan for the injured and sick is used in combination with the real-time updated treatment progress and resource consumption data and the historical similar case library, and the support vector machine algorithm is used to evaluate the effectiveness of the current treatment strategy, obtain a forward-looking decision support report, monitor the risk points that may appear in the treatment process through time series anomaly detection technology, and generate risk warning and response measures, including: Using the evacuation and resource allocation plan for the wounded and sick, combined with the real-time updated treatment progress and resource consumption data, the status of the current treatment activities is dynamically monitored and processed to obtain the treatment status monitoring results; Based on the monitoring results of the treatment status, relevant information in the historical similar case library is integrated, and the current treatment situation is compared and analyzed with the historical cases to identify the key factors affecting the treatment effect, and obtain a key factor identification list; Based on the key factor identification list, a support vector machine algorithm is applied to evaluate the effectiveness of the current treatment strategy. The support vector machine algorithm distinguishes data points with different treatment effects by constructing an optimal classification surface, predicts the resource demand trend and the success rate of the treatment strategy in the short term, and obtains a forward-looking decision support report; Using the forward-looking decision support report and combining it with time series anomaly detection technology, the risk points that may appear during the treatment process are monitored and processed, abnormal situations that deviate from the normal treatment process are identified, and abnormal situation identification results are obtained; Based on the abnormal situation identification results, specific response measures for various risks are formulated to obtain risk warning and response measures plans.

6. The method according to claim 5, characterized in that The forward-looking decision support report is used in combination with time series anomaly detection technology to monitor and process risk points that may occur during the treatment process, identify abnormal situations that deviate from the normal treatment process, and obtain abnormal situation identification results, including: Utilizing the forward-looking decision support report, analyzing and processing the success rate and resource demand trend of the current treatment strategy, determining key treatment links that require special attention, and obtaining a list of key treatment links; Based on the list of key treatment links, combined with time series anomaly detection technology, the historical data and real-time data of these links are compared and analyzed, and an anomaly detection model is constructed to obtain an anomaly detection model; According to the abnormality detection model, various indicators in the treatment process are continuously monitored and processed to identify data patterns that are inconsistent with the normal treatment process and obtain preliminary abnormal situation prompts; Using the preliminary abnormality prompts, combined with clinical expertise and a historical similar case library, an in-depth assessment and processing of possible risk points is performed to confirm the true abnormality and its severity, and obtain abnormality confirmation results; Based on the abnormal situation confirmation result, the identified abnormal situation is classified and processed to distinguish different types of abnormal situations, and the specific manifestation and occurrence frequency of each abnormal situation are recorded to obtain the abnormal situation identification result.

7. The method according to claim 1, characterized in that According to the forward-looking decision support report and risk warning and response plan, a cross-regional, multi-departmental cloud-based collaborative work platform is established to generate efficient communication channels and information security mechanisms to enhance the overall ability and flexibility of the field hospital to respond to emergencies, including: Using the forward-looking decision support report, comprehensively evaluate the success rate of the treatment strategy and the resource demand trend, determine the key links and participating departments that need to be coordinated, and obtain a list of key coordination points; Based on the list of key coordination points, combined with risk warning and response measures, design the functional requirements and architecture blueprint of the cloud-based collaborative work platform to ensure that the platform can meet the needs of multi-party collaboration and obtain the platform design plan; According to the platform design plan, develop and integrate efficient communication tools and information sharing modules to enable frontline doctors, rear expert teams and logistics support departments to communicate and share treatment information in real time, thus obtaining efficient communication channels; By utilizing the above-mentioned efficient communication channels and combining information security technologies and management measures, we can build security functions for data encryption transmission, access permission control, and audit tracking to ensure the security of sensitive medical information during transmission and storage, and obtain an information security assurance mechanism.

8. A big data-based decision-making processing system for frontline hospitals, characterized in that: include: The collection module is used to collect and comprehensively analyze dynamic data streams from multiple battlefield medical sites in real time, covering the status of the wounded and sick, the use of medical resources, and geographical environmental factors, and generate a virtual medical resource heat map; A planning module is used to intelligently plan and process the evacuation routes of the sick and wounded and the allocation of medical supplies based on the virtual medical resource heat map, combined with the priority rules for the transfer of the sick and wounded and the transportation logistics optimization theory, using a particle swarm optimization algorithm, dynamically adjust the transportation routes through traffic flow prediction technology, and generate a plan for the evacuation of the sick and wounded and resource allocation; An evaluation module is used to utilize the evacuation and resource allocation plan for the injured and sick, combined with the real-time updated treatment progress and resource consumption data and the historical similar case library, to apply the support vector machine algorithm to evaluate the effectiveness of the current treatment strategy, obtain a forward-looking decision support report, monitor the risk points that may appear in the treatment process through time series anomaly detection technology, and generate risk warnings and response measures; A generation module is used to establish a cross-regional, multi-departmental cloud-based collaborative work platform based on the forward-looking decision support report and risk warning and response measures plan, and to generate efficient communication channels and information security assurance mechanisms.

9. 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 a position hospital decision processing method based on big data 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, a position hospital decision-making processing method based on big data as described in any one of claims 1 to 7 is implemented.

Images