Emergency Response Coordination System Based on IoT

Abstract

The present invention relates to the field of coordinated response technology, specifically to an emergency response coordination system based on the Internet of Things, the system includes an abnormal event identification module, an event impact analysis module, a resource dynamic matching module, an emergency plan formulation module, a scene simulation rehearsal module, a priority adjustment module, a real-time monitoring module, and an intelligent dispatching and commanding module. The present invention, by adopting discrete event simulation in the resource dynamic matching module, can dynamically collect and allocate emergency resources according to the regional impact rating in the event impact analysis record, significantly improve the accuracy of resource allocation and optimize resource utilization, ensure that key resources and personnel can be quickly dispatched to the most needed places, and the scene simulation rehearsal module adopts an individual-based model, by simulating different response strategies, improves the practicality and reliability of the emergency plan, ensures the speed and accuracy of the emergency response, and effectively reduces casualties and property losses.

Description

Technical Field

[0001] The present invention relates to the technical field of coordinated response, and in particular to an emergency response coordination system based on the Internet of Things. Background Art

[0002] The field of coordinated response technology focuses on the use of information technology and communication means to achieve effective emergency incident handling and resource allocation. This technical field covers a variety of technologies and methods, including data transmission, real-time monitoring, resource management and decision support. Its core goal is to improve the efficiency and effectiveness of the emergency response process and ensure a fast and accurate response to minimize risks and losses.

[0003] Among them, the IoT-based emergency response coordination system is an integrated solution designed to automatically detect, evaluate and respond to various emergencies, such as natural disasters, public health events or security threats, through IoT technology. The purpose is to speed up the decision-making process and optimize resource allocation through real-time data collection and analysis, thereby improving the speed and accuracy of emergency response, aiming to improve response time efficiency, reduce casualties and property losses, and enhance public safety and well-being.

[0004] Traditional systems are deficient in dynamic resource allocation and real-time data processing. They rely on experience and judgment and lack real-time response capabilities, resulting in low response efficiency and inability to optimize resource allocation in a timely manner. The lack of effective scenario simulation and rehearsal capabilities makes it impossible to fully test and adjust emergency plans based on actual conditions, increasing the uncertainty and risk of emergency handling. Summary of the invention

[0005] The purpose of the present invention is to solve the shortcomings in the prior art and to propose an emergency response coordination system based on the Internet of Things.

[0006] In order to achieve the above object, the present invention adopts the following technical solution: an emergency response coordination system based on the Internet of Things, the system comprising:

[0007] The abnormal event identification module removes noise and normalizes the data based on the multi-dimensional time series data collected by IoT devices, detects abnormal points, and identifies potential abnormal events in the data to generate abnormal event identification data;

[0008] The event impact analysis module constructs an event impact diagram based on the abnormal event identification data, demarcates the boundaries of the impact area, calculates the potential impact of the abnormal event on the area, including the impact range and severity, and obtains an event impact analysis record;

[0009] The resource dynamic matching module collects resource information, including type, quantity and location, based on the event impact analysis record and discrete event simulation, and allocates resources according to the matching degree between resources and demand, and obtains resource dynamic matching measures;

[0010] The emergency plan formulation module analyzes the dispatch timeliness and effectiveness of various emergency resources based on the dynamic resource matching measures, formulates emergency response and action plans based on the characteristics and urgency of the event, and establishes an emergency action plan;

[0011] The scenario simulation rehearsal module uses an individual-oriented model based on the emergency action plan to build a simulation environment for strategy testing, simulate differentiated response strategies and action paths, and evaluate potential problems in operations to generate scenario simulation rehearsal data;

[0012] The priority adjustment module analyzes the effects and criticality of emergency measures based on the scenario simulation rehearsal data, dynamically adjusts the task and resource priorities according to the effect evaluation results, and obtains the priority adjustment index;

[0013] The real-time monitoring module collects the development data of the emergency event and the progress information of the rescue operation in real time based on the priority adjustment index, adjusts the monitoring focus in combination with the priority adjustment result, and obtains the real-time monitoring data;

[0014] Based on the real-time monitoring data, the intelligent dispatching and commanding module analyzes the current event status and the execution effect of the response action, and intelligently dispatches rescue resources, including adjusting the deployment of resources and personnel, continuously optimizing the response plan, and generating intelligent dispatching instructions.

[0015] The present invention has improvements in that the abnormal event identification data includes the timestamp, location information, and abnormal level of the abnormal event, the event impact analysis record includes the geographical scope of the affected area, the estimated impact duration, and the impact severity rating, the resource dynamic matching measures include the type, quantity, and estimated arrival time of resources allocated to multiple areas, the emergency action plan includes the emergency evacuation route and the location of the rescue material distribution point, the scenario simulation rehearsal data includes the key issues in the simulation, solution proposals, and rehearsal success rate, and the real-time monitoring data includes the real-time speed of event development, the current rescue operation efficiency, and the remaining status of on-site resources.

[0016] The present invention is improved in that the abnormal event identification module includes a data processing submodule, an abnormal point detection submodule, and an abnormal event marking submodule;

[0017] The data processing submodule filters the multidimensional time series data collected by the IoT device to remove noise and normalize the data to obtain a processed data set;

[0018] The outlier detection submodule analyzes the difference between each data point and its neighboring data points based on the processed data set, identifies potential abnormal data points that deviate from the normal state, and generates an outlier set;

[0019] The abnormal event marking submodule analyzes the concentration trend and time distribution of abnormal points based on the abnormal point set, identifies potential abnormal events in the data, performs marking processing, and generates abnormal event identification data.

[0020] The present invention is improved in that the event impact analysis module includes an impact area boundary division submodule, an impact intensity calculation submodule, and an impact analysis recording submodule;

[0021] The impact area boundary division submodule determines the geographical location where the abnormal event occurs based on the abnormal event identification data, and estimates the impact radius according to the abnormal intensity to obtain the area boundary data;

[0022] The impact intensity calculation submodule calculates the potential impact intensity of the abnormal event on the region based on the region boundary data, estimates the degree and urgency of the impact on the corresponding region based on the type and intensity of the abnormal event, and generates impact intensity information;

[0023] The impact analysis record submodule records the impact analysis of each impact area based on the impact intensity information, including the expected scope, severity and duration of the impact, to obtain an event impact analysis record.

[0024] The present invention is improved in that the resource dynamic matching module includes a resource information collection submodule, a matching degree analysis submodule, and a resource allocation plan submodule;

[0025] The resource information collection submodule is based on the event impact analysis record, and if the regional impact rating exceeds a preset threshold, it collects the resource information available in the region, including the type, quantity and current location, and generates a resource information list;

[0026] The matching degree analysis submodule is based on the resource information list and uses a long short-term memory network. If the resource type meets the emergency demand, the matching degree between the resource and the demand is calculated, and the resource matching degree information is obtained by combining the coverage, response time and efficiency of the resource;

[0027] The resource allocation plan submodule adopts discrete event simulation based on resource matching information. If the matching degree meets the standard, a resource allocation plan is formulated, and dynamic resource matching measures are obtained according to the optimal resource utilization and response requirements, including allocation location, time and quantity;

[0028] The discrete event simulation is performed according to the formula:

[0029]

[0030] Calculate resource allocation decisions and obtain dynamic resource matching measures;

[0031] in, For the The utilization score of the resource. Indicates whether to select the resource for allocation. Score resource matching. represents the cost of the resource, Indicates the resource response time, is the weight coefficient.

[0032] The present invention is improved in that the emergency plan formulation module includes a resource scheduling analysis submodule, an emergency assessment submodule, and an action plan formulation submodule;

[0033] The resource scheduling analysis submodule analyzes the scheduling timeliness and effectiveness of resources based on dynamic resource matching measures, and generates resource scheduling analysis records in combination with resource arrival time, coverage and contribution to emergency response;

[0034] The emergency assessment submodule assesses the characteristics and current emergency level of the emergency event based on the resource scheduling analysis record, and obtains an emergency assessment result in combination with the spread speed, impact scope and potential losses caused by the event;

[0035] The action plan formulation submodule designs response measures and action plans based on the emergency assessment results, including personnel evacuation, material allocation and rescue team deployment, and establishes an emergency action plan.

[0036] The present invention is improved in that the scenario simulation rehearsal module includes an environment parameter setting submodule, a strategy testing submodule, and a problem identification submodule;

[0037] The environmental parameter setting submodule is based on the emergency action plan and adopts an individual-based model to establish an initial environmental model and set initial conditions, including the terrain characteristics of the event location, surrounding buildings and population density, determine the basic parameters of the simulated environment, and generate an environmental basic model;

[0038] The individual-based model is based on the formula:

[0039]

[0040] Calculate the distribution density of personnel safety paths and generate the basic model of the environment;

[0041] in, Represents the distribution density of personnel safety paths, is the total number of personnel, is the area of ​​the region considered, is the terrain height factor, is the building layout factor, is the risk assessment factor;

[0042] The strategy testing submodule is based on the environment basic model and uses a support vector machine to cyclically execute differentiated response strategies and action paths, record the execution results and key event points of each strategy, and generate a strategy execution result set;

[0043] The problem identification submodule makes execution strategy judgments based on the strategy execution result set, identifies problems that occur during the process, including low evacuation efficiency or improper resource allocation, summarizes potential improvement targets, and generates scenario simulation rehearsal data.

[0044] The present invention is improved in that the priority adjustment module includes an effect analysis submodule, a criticality assessment submodule, and a priority adjustment strategy submodule;

[0045] The effect analysis submodule analyzes the execution effect of emergency measures based on the scenario simulation rehearsal data, including evacuation speed and resource arrival time, and obtains effect analysis results;

[0046] The criticality assessment submodule assesses the criticality of the emergency measures based on the effect analysis results, and obtains a criticality assessment record in combination with the contribution to the success of the emergency response;

[0047] The priority adjustment strategy submodule dynamically adjusts the priorities of tasks and resources based on the criticality assessment records, continuously optimizes the response efficiency and effect, and obtains the priority adjustment index.

[0048] The present invention is improved in that the real-time monitoring module includes a data collection submodule, a monitoring focus adjustment submodule, and a real-time information update submodule;

[0049] The data collection submodule collects the development data of the emergency incident and the progress information of the rescue operation in real time based on the priority adjustment index, and integrates the information data to generate a real-time data set;

[0050] The monitoring focus adjustment submodule analyzes the current emergency situation based on the real-time data set, adjusts the monitoring focus, and generates an adjusted monitoring focus;

[0051] The real-time information updating submodule updates the real-time monitoring information based on the adjusted monitoring focus, reflects the emergency event status and the progress of the rescue operation, and obtains real-time monitoring data.

[0052] The present invention is improved in that the intelligent dispatching and commanding module includes an event status analysis submodule, a resource dispatching and optimizing submodule, and an instruction generation submodule;

[0053] The event status analysis submodule analyzes the current status and change trend of emergency events based on real-time monitoring data, evaluates the effectiveness of response actions, including rescue speed and coverage, and generates event analysis records;

[0054] The resource scheduling optimization submodule identifies the shortcomings and advantages in resource allocation based on event analysis records, and re-evaluates and optimizes the deployment strategy of resources and personnel by comparing expected results and situations to obtain a resource optimization plan;

[0055] The instruction generation submodule formulates scheduling measures based on the resource optimization plan, including resource reallocation, personnel transfer and task priority adjustment, and generates intelligent scheduling instructions.

[0056] Compared with the prior art, the advantages and positive effects of the present invention are:

[0057] In the present invention, by using discrete event simulation in the dynamic resource matching module, emergency resources can be dynamically collected and allocated according to the regional impact rating in the event impact analysis record. The accuracy of resource allocation and the utilization rate of resources are significantly improved, ensuring that key resources and personnel can be quickly dispatched to where they are most needed. The scenario simulation rehearsal module adopts an individual-based model, and by simulating different response strategies, it improves the practicality and reliability of emergency plans, ensures the speed and accuracy of emergency response, and effectively reduces casualties and property losses. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] Figure 1 The module diagram of the emergency response coordination system based on the Internet of Things is proposed for the present invention;

[0059] Figure 2 The present invention proposes a system framework diagram of an emergency response coordination system based on the Internet of Things;

[0060] Figure 3 The present invention proposes a flow chart of an abnormal event identification module in an emergency response coordination system based on the Internet of Things;

[0061] Figure 4 The present invention proposes a flow chart of an event impact analysis module in an emergency response coordination system based on the Internet of Things;

[0062] Figure 5 The present invention proposes a flow chart of a resource dynamic matching module in an emergency response coordination system based on the Internet of Things;

[0063] Figure 6 The present invention proposes a flow chart of an emergency plan formulation module in an emergency response coordination system based on the Internet of Things;

[0064] Figure 7The present invention proposes a flow chart of a scenario simulation rehearsal module in an emergency response coordination system based on the Internet of Things;

[0065] Figure 8 The present invention proposes a flow chart of a priority adjustment module in an emergency response coordination system based on the Internet of Things;

[0066] Fig. 9 The present invention proposes a flow chart of a real-time monitoring module in an emergency response coordination system based on the Internet of Things;

[0067] Fig.10 The present invention proposes a flow chart of an intelligent dispatching and commanding module in an emergency response coordination system based on the Internet of Things. DETAILED DESCRIPTION

[0068] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0069] In the description of the present invention, it should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating positions or positional relationships, are based on the positions or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, in the description of the present invention, the meaning of "multiple" is two or more, unless otherwise clearly and specifically defined. Example

[0070] See also Figure 1 The present invention provides a technical solution: an emergency response coordination system based on the Internet of Things includes:

[0071] The abnormal event identification module removes noise and normalizes the data based on the multi-dimensional time series data collected by IoT devices, detects abnormal points, and identifies potential abnormal events in the data to generate abnormal event identification data;

[0072] The event impact analysis module is based on the abnormal event identification data. By constructing the event impact diagram, the boundaries of the impact area are demarcated, and the potential impact of the abnormal event on the area, including the impact range and severity, is calculated to obtain the event impact analysis record;

[0073] The resource dynamic matching module collects resource information, including type, quantity and location, based on event impact analysis records and discrete event simulation, and allocates resources according to the matching degree between resources and demand, and obtains resource dynamic matching measures;

[0074] The emergency plan formulation module analyzes the dispatch timeliness and effectiveness of various emergency resources based on dynamic resource matching measures, formulates emergency response and action plans based on event characteristics and urgency, and establishes emergency action plans;

[0075] The scenario simulation rehearsal module is based on the emergency action plan and adopts an individual-oriented model to build a simulation environment for strategy testing, simulate differentiated response strategies and action paths, and evaluate potential problems in operations to generate scenario simulation rehearsal data;

[0076] The priority adjustment module analyzes the effectiveness and criticality of emergency measures based on scenario simulation and rehearsal data, dynamically adjusts the priorities of tasks and resources according to the effect evaluation results, and obtains priority adjustment indicators;

[0077] The real-time monitoring module collects the development data of emergency events and the progress information of rescue operations in real time based on the priority adjustment indicators, adjusts the monitoring focus based on the priority adjustment results, and obtains real-time monitoring data;

[0078] The intelligent dispatching and commanding module analyzes the current event status and the execution effect of the response action based on real-time monitoring data, and intelligently dispatches rescue resources, including adjusting the deployment of resources and personnel, continuously optimizing the response plan, and generating intelligent dispatching instructions.

[0079] Abnormal event identification data includes the timestamp, location information, and abnormal level of the abnormal event. Event impact analysis records include the geographical scope of the affected area, the estimated impact duration, and the impact severity rating. Dynamic resource matching measures include the type, quantity, and estimated arrival time of resources allocated to multiple regions. Emergency action plans include emergency evacuation routes and locations of relief material distribution points. Scenario simulation rehearsal data include key issues in the simulation, proposed solutions, and rehearsal success rate. Real-time monitoring data include the real-time speed of event development, the efficiency of the current rescue operation, and the remaining status of on-site resources.

[0080] See also Figure 2 and Figure 3 ,The abnormal event identification module includes a data processing submodule, an abnormal point detection submodule, and an abnormal event marking submodule;

[0081] The data processing submodule filters the multidimensional time series data collected by IoT devices to remove noise and normalize the data to obtain a processed data set;

[0082] The outlier detection submodule analyzes the difference between each data point and its neighboring data points based on the processed data set, identifies potential abnormal data points that deviate from the normal state, and generates an outlier set;

[0083] The abnormal event marking submodule analyzes the concentration trend and time distribution of abnormal points based on the abnormal point set, identifies potential abnormal events in the data, and performs marking processing to generate abnormal event identification data.

[0084] In the data processing submodule, based on the multidimensional time series data collected by IoT devices, the Kalman filtering algorithm is adopted. The Kalman filter is implemented using Python's SciPy library. The initial state estimate is set to a zero matrix, the noise covariance matrix is ​​set to a unit matrix, and the observation matrix is ​​adjusted according to the data dimension for data denoising. The Min-Max normalization method is used to scale the data values ​​to between 0 and 1. Python's NumPy library is used to implement data normalization. The minimum normalization value is set to 0 and the maximum value is set to 1 to generate a processed data set.

[0085] In the outlier detection submodule, based on the processed data set, the local outlier factor detection algorithm (LOF) is adopted. The LocalOutlierFactor function in the Sklearn library of Python is used. The number of neighbors is set to 20 and the outlier factor ratio is set to 1%. The difference between each data point and its neighboring data points is analyzed to identify potential abnormal data points that deviate from the normal state and generate an outlier point set.

[0086] In the abnormal event marking submodule, a clustering algorithm is adopted based on the abnormal point set, specifically the DBSCAN algorithm. The DBSCAN function in Python's Sklearn library is used, the neighborhood radius is set to 0.3, and the minimum number of samples is set to 10. The concentration trend and time distribution of abnormal points are analyzed, potential abnormal events in the data are identified, and marking processing is performed to generate abnormal event identification data.

[0087] See also Figure 2 and Figure 4 ,The event impact analysis module includes the impact area boundary division submodule, the impact intensity calculation submodule, and the impact analysis recording submodule;

[0088] The impact area boundary division submodule determines the geographical location of the abnormal event based on the abnormal event identification data, and estimates the impact radius according to the abnormal intensity to obtain the area boundary data;

[0089] The impact intensity calculation submodule calculates the potential impact intensity of abnormal events on the region based on the regional boundary data, and estimates the degree and urgency of the impact on the corresponding region based on the type and intensity of the abnormal event, and generates impact intensity information;

[0090] The impact analysis record submodule records the impact analysis of each impact area based on the impact intensity information, including the expected scope, severity and duration of the impact, and obtains the event impact analysis record.

[0091] In the submodule of impact area boundary division, based on the abnormal event identification data, the geographic information system (GIS) technology is adopted, and ArcGIS software is used to accurately locate the geographical location, and the impact radius of the abnormal intensity estimation is determined by the buffer analysis tool. This tool sets the radius parameter of the buffer analysis to the numerical value representing the abnormal intensity in meters based on the input abnormal event geographic coordinates, and generates a regional boundary data set, which presents the geographic area boundaries affected by the abnormal event in vector form.

[0092] In the impact intensity calculation submodule, based on the regional boundary data, a multi-level weighted scoring system is adopted. Python programming is used to define a function to calculate the weighted score of each influencing factor (including abnormal event type and intensity). Different weight values ​​are assigned to the abnormal event type. For the abnormal intensity, a linear ratio is used to convert it into a score. These weighted scores are combined to calculate the potential impact intensity score of each region, and the impact intensity information is generated. This information is expressed in the form of a score, which provides a quantitative basis for subsequent impact analysis.

[0093] In the impact analysis record submodule, based on the impact intensity information, data visualization methods are used to graphically display the impact intensity of each affected area using the Matplotlib and Pandas libraries. Different colors and sizes are set to represent the severity and urgency of the impact intensity. Combined with time series analysis, the expected impact range, severity and duration are dynamically displayed to generate event impact analysis records, which present the specific impact on each area in detail in the form of charts and timelines.

[0094] See also Figure 2 and Figure 5 ,The resource dynamic matching module includes a resource information collection submodule, a matching degree analysis submodule, and a resource allocation plan submodule;

[0095] The resource information collection submodule is based on the event impact analysis record. If the regional impact rating exceeds the preset threshold, it collects the available resource information in the region, including type, quantity and current location, and generates a resource information list;

[0096] The matching degree analysis submodule is based on the resource information list and uses a long short-term memory network. If the resource type meets the emergency demand, the matching degree between the resource and the demand is calculated, and the resource matching degree information is obtained by combining the coverage, response time and efficiency of the resource;

[0097] The resource allocation planning submodule uses discrete event simulation based on resource matching information. If the matching degree meets the requirements, a resource allocation plan is formulated and dynamic resource matching measures are obtained based on the optimal resource utilization and response requirements, including allocation location, time and quantity.

[0098] In the resource information collection submodule, based on the event impact analysis records, database query technology is used to search the regional database using SQL query statements. If the regional impact rating exceeds the preset threshold, the query operation is executed, and the resource information in the region is extracted through the SELECT statement, including resource type, quantity and current location fields. The query associates different resource data tables through JOIN operations to ensure the integrity and accuracy of the data and generate a resource information list, which is presented in a tabular form, detailing the type, quantity and current location of each resource.

[0099] In the matching analysis submodule, based on the resource information list, the long short-term memory network (LSTM) model is adopted, and the model is constructed using the Python programming language and the TensorFlow library. If the resource type meets the urgent needs, the resource information is input as the input parameter of the model. By setting the number of units in the LSTM layer to 128, using the ReLu activation function, setting the batch size to 32, and the number of iterations to 100, the model is trained to calculate the matching degree between resources and needs, and combining the coverage, response time and efficiency of the resources to calculate the resource matching score, and generate resource matching information. This information is presented in the form of a score, which reflects the matching degree between each resource and the current demand.

[0100] In the resource allocation plan submodule, discrete event simulation technology is used based on resource matching information, and the SimPy library is used for simulation. If the matching degree meets the requirements, the resource matching score and emergency demand information are input as simulation parameters. By defining the simulation environment and events, the simulation time step is set to 1 minute, and the simulation model is run to formulate a resource allocation plan. According to the optimal resource utilization and response requirements, the optimal solution of allocation location, time and quantity is calculated, and the dynamic resource matching measures are obtained. The measures are output in the form of a decision report, which details the resource allocation plan, including the allocation location, time and quantity of each resource.

[0101] Discrete event simulation, according to the formula:

[0102]

[0103] Calculate resource allocation decisions and obtain dynamic resource matching measures;

[0104] in, For the The utilization score of each resource indicates the efficiency of each resource's contribution to the overall goal. Represents whether to select the resource for allocation (1 for selection, 0 for non-selection), which is a decision variable. Score the resource match, that is, the degree to which resources match needs, represents the cost of resources, including acquisition, maintenance, and allocation costs, Indicates resource response time, which is the time required for resources to be deployed and reach the point of use. are weight coefficients, corresponding to the importance of resource matching, resource cost, and resource response time, respectively. Represents the decision variables The choice of maximizes the total value of the objective function, in which the objective function is achieved by adjusting (i.e., choosing which resources to allocate) to find the combination that maximizes total utility.

[0105] In the formula, The utilization score of a resource can be measured based on the efficiency of the resource, its past performance, or its expected contribution. For example, if a resource has performed efficiently in past tasks, it will receive a higher score.

[0106] The resource matching score reflects the matching degree between the resource and the target demand, which can be calculated by analyzing the resource characteristics and the specific requirements of the demand. For example, if the resource fully meets the technical specifications of the demand, the matching score may be the highest;

[0107] The cost of resources, including the acquisition, maintenance and allocation costs of resources, is collected and the total cost of each resource is calculated. This information is usually known or can be obtained through resource management systems;

[0108] Resource response time refers to the time required from resource allocation to resource use. It can be obtained from previous deployment history, classify different types of resources, and record the average response time.

[0109] Execution process:

[0110] S1: Collect the utilization score of each resource , resource matching score ,cost , and response time The relevant data of the resource allocation should be collected and the weight coefficient should be determined. The weight coefficient should be set according to the priority of resource allocation and should be adjusted through sensitivity analysis.

[0111] S2: Use the formula to calculate the resource utilization, matching, cost and response time;

[0112] S3: Solve the objective function through linear programming method to determine whether each resource is selected for allocation, as well as its optimal allocation location, time and quantity, and output a report that details the allocation plan for each resource, including location, time and quantity.

[0113] Discrete event simulation requires the construction of a simulation environment, in which the allocation and use of resources occur in chronological order. The SimPy library can be used to simulate the occurrence and processing of various events, such as resource arrival, task start and end. In the simulation, the simulation time step is set, for example, each step represents 1 minute or 1 hour, and the time series of the entire resource allocation process is simulated. State transitions and event handling functions are defined for each resource, including how to respond to resource allocation requests, how to move and change states in the simulation, and how to define parameters and collect data. The resource allocation problem is calculated through linear programming, the total utility of each resource configuration scheme is calculated, and the configuration with the greatest utility is selected. The goal of the selection is to maximize the overall objective function while satisfying all given constraints, thereby achieving optimal resource configuration and improving efficiency and response speed.

[0114] See also Figure 2 and Figure 6 ,The emergency plan formulation module includes a resource scheduling analysis submodule, an urgency assessment submodule, and an action plan formulation submodule;

[0115] The resource scheduling analysis submodule analyzes the scheduling timeliness and effectiveness of resources based on dynamic resource matching measures, and generates resource scheduling analysis records based on resource arrival time, coverage, and contribution to emergency response;

[0116] The urgency assessment submodule evaluates the characteristics and current urgency of emergency events based on resource scheduling analysis records, and obtains urgency assessment results based on the spread speed, impact scope and potential losses caused by the event;

[0117] The action plan formulation submodule designs response measures and action plans based on the results of the urgency assessment, including personnel evacuation, material allocation and rescue team deployment, and establishes an emergency action plan.

[0118] In the resource scheduling analysis submodule, based on the dynamic matching measures of resources, an optimization algorithm is adopted, and linear programming technology is used to analyze the scheduling timeliness and effectiveness of resources. By defining the objective function and constraints, the objective function is to minimize the arrival time of resources and maximize the coverage and contribution to emergency response. The constraints include resource type, quantity and location restrictions. The optimization model is constructed using the Python programming language and the PuLP library. The resource type, quantity and current location are input as variables, and the linear programming solution process is executed to generate a resource scheduling analysis record. The record is presented in a tabular form, which lists in detail the scheduling timeliness, coverage and contribution score to emergency response of each resource.

[0119] In the urgency assessment submodule, based on the resource scheduling analysis records, the decision tree algorithm is adopted, and the decision tree model is constructed using the Python programming language and the Scikit-learn library to evaluate the characteristics and current urgency of the emergency. The input includes the spread speed of the event, the scope of impact, and the potential losses caused as features. By setting the decision tree depth to 5 and using the information gain ratio as the node splitting criterion, the model is trained to obtain the urgency assessment result, which is expressed in the form of a score, reflecting the severity of the emergency and the priority of emergency treatment.

[0120] In the action plan formulation submodule, based on the results of the urgency assessment, project management technology is adopted, and Gantt charts and critical path method (CPM) are used to design response measures and action plans. By defining the various activities, durations and dependencies of the project, a Gantt chart is constructed using Project software, and activities on the critical path are identified to optimize the timing and sequence of personnel evacuation, material allocation, and rescue team deployment, to ensure the effective implementation of the emergency action plan, and to generate an emergency action plan, which is output in the form of a document that describes the location, time, and quantity arrangements for the evacuation of personnel, material allocation, and rescue team deployment.

[0121] See also Figure 2 and Figure 7 ,The scenario simulation rehearsal module includes the environment parameter setting submodule, the ,strategy testing submodule, and the problem identification submodule;

[0122] The environmental parameter setting submodule is based on the emergency action plan and adopts an individual-oriented model to establish an initial environmental model and set initial conditions, including the terrain characteristics of the incident location, the density of surrounding buildings and people, determine the basic parameters of the simulated environment, and generate an environmental basic model;

[0123] The strategy testing submodule is based on the environment basic model and uses support vector machines to cyclically execute differentiated response strategies and action paths, record the execution results and key event points of each strategy, and generate a strategy execution result set;

[0124] The problem identification submodule makes execution strategy judgments based on the strategy execution result set, identifies problems that occur during the process, including low evacuation efficiency or improper resource allocation, summarizes potential improvement targets, and generates scenario simulation rehearsal data.

[0125] In the environmental parameter setting submodule, based on the emergency action plan, an individual-oriented model is adopted, and the initial environmental model is established using NetLogo software to set the initial conditions. The parameters of the simulated terrain features, the layout of surrounding buildings, and the density of people are set through programming instructions. Specifically, it includes inputting terrain height data, building location coordinates, and personnel distribution density values, determining the basic parameters of the simulated environment, and generating an environmental basic model. The model is displayed in a three-dimensional view, which details the terrain, buildings, and personnel layout of the incident location.

[0126] The individual-based model follows the formula:

[0127]

[0128] Calculate the distribution density of personnel safety paths and generate the basic model of the environment;

[0129] in, Represents the distribution density of personnel safety paths, is the total number of personnel, is the area of ​​the region considered, is the terrain height factor, which is adjusted according to the complexity of the terrain and is represented by a value between 0 and 1, with higher values ​​representing more complex terrain. It is the building layout factor, which is also expressed as a value between 0 and 1. It reflects the impact of the building layout on the movement of personnel. The larger the value, the greater the restriction of the building layout on the safety path of personnel. It is a risk assessment factor, which conducts a comprehensive assessment based on the surrounding environmental risks and the risks that may be caused by the event itself. The value is between 0 and 1. The larger the value, the higher the associated risk.

[0130] Execution process:

[0131] S1: Determine the total number of personnel , area , collect terrain, building layout and risk assessment data to initialize , , ;

[0132] S2: Calculate the impact factor value based on terrain complexity analysis. Normalized to 0 to 1, depending on building density and layout, Normalized to 0 to 1, based on the assessment of potential risk, The impact is quantified from 0 to 1, and the personnel distribution density is calculated using the formula ;

[0133] S3: Using the calculated density , generating an environmental base model that reflects the impact of terrain, building layout, and risk factors.

[0134] In the strategy testing submodule, based on the basic environment model, the support vector machine (SVM) algorithm is used, implemented using the Python programming language and the scikit-learn library, and differentiated response strategies and action paths are executed cyclically. By setting the kernel function of SVM to the radial basis function (RBF), adjusting the C parameter to 1.0, the model is trained to adapt to different response strategies, recording the execution results and key event points of each strategy, and generating a strategy execution result set. The result set is recorded in a tabular form, listing the effects of each strategy after execution and the key event points that occurred.

[0135] In the problem identification submodule, the execution strategy is judged based on the strategy execution result set. The decision tree analysis method is adopted, and the decision tree model is built using the Python programming language and the scikit-learn library. The strategy execution results are input as data. By setting the decision tree depth to 5 and using the information gain ratio as the splitting criterion, problems that arise in the identification process, including low evacuation efficiency or improper resource allocation, are identified. Potential improvement targets are summarized and scenario simulation rehearsal data is generated. The data is output in the form of a report, which lists in detail the identified problems and potential improvement suggestions.

[0136] See also Figure 2 and Figure 8 ,The priority adjustment module includes the effect analysis submodule, the criticality assessment submodule, and the priority adjustment strategy submodule;

[0137] The effect analysis submodule analyzes the effect of emergency measures based on scenario simulation rehearsal data, including evacuation speed and resource arrival time, and obtains effect analysis results;

[0138] The criticality assessment submodule evaluates the criticality of emergency measures based on the results of effect analysis and obtains criticality assessment records based on the contribution to the success of emergency response;

[0139] The priority adjustment strategy submodule dynamically adjusts the priorities of tasks and resources based on criticality assessment records, continuously optimizes response efficiency and effectiveness, and obtains priority adjustment indicators.

[0140] In the effect analysis submodule, based on the scenario simulation rehearsal data, statistical analysis methods are adopted, and R language is used for data processing and analysis to analyze the effectiveness of the implementation of emergency measures. Specifically, linear regression is used to analyze the relationship between evacuation speed and resource arrival time. By setting the independent variables as the length of the evacuation route and the type of resources, and the dependent variables as the evacuation completion time and the resource arrival time, the regression coefficient is calculated to obtain the effect analysis results. The results are presented in the form of graphics and numerical reports, which describe in detail the statistical characteristics of the implementation effects of different emergency measures.

[0141] In the criticality assessment submodule, based on the results of effect analysis, the network analysis method is adopted, and the Python programming language and NetworkX library are used to establish a relationship network diagram between emergency measures. Combined with the contribution to the success of the emergency response, the key emergency measures are identified by calculating the centrality index of the nodes in the network, and the criticality assessment record is obtained. The record is presented in the form of a network diagram, highlighting the key emergency measure nodes and marking their contribution with numerical values.

[0142] In the priority adjustment strategy submodule, based on the criticality assessment records, a genetic algorithm is used and MATLAB is used for programming to dynamically adjust the priorities of tasks and resources. By defining the fitness function as the probability of successful emergency response, setting the population size to 50, the crossover rate to 0.8, and the mutation rate to 0.05, iterative calculations are performed to continuously optimize the response efficiency and effect, and the priority adjustment index is obtained. The index is output in the form of a list, which lists in detail the order of tasks and resources after sorting by priority.

[0143] See also Figure 2 and Fig. 9 ,The real-time monitoring module includes a data collection submodule, a monitoring focus adjustment submodule, and a real-time information updating submodule;

[0144] The data collection submodule collects the development data of emergency events and the progress information of rescue operations in real time based on the priority adjustment indicators, and integrates the information data to generate a real-time data set;

[0145] The monitoring focus adjustment submodule analyzes the current emergency situation based on the real-time data set, adjusts the monitoring focus, and generates an adjusted monitoring focus;

[0146] The real-time information update submodule updates the real-time monitoring information based on the adjusted monitoring focus, reflects the emergency event status and the progress of the rescue operation, and obtains real-time monitoring data.

[0147] In the data collection submodule, based on the priority adjustment index, real-time database query technology is adopted, and SQL query statements are used to access the emergency event and rescue operation database in real time, execute query operations, and collect the development data of emergency events and the progress information of rescue operations in real time through SELECT statements. Combined with JOIN operations, different data tables are associated to integrate information data and generate real-time data sets. The data sets are presented in tabular form, which lists in detail the development data of emergency events and the progress information of rescue operations.

[0148] In the monitoring focus adjustment submodule, based on the real-time data set, the decision support system (DSS) is used to perform data analysis using the Python programming language and the Pandas library to analyze the current emergency situation. By applying the decision tree algorithm, the real-time data is input as the input parameter of the decision tree, the decision tree depth is set to 4, and the Gini coefficient is used as the splitting criterion to adjust the monitoring focus and generate the adjusted monitoring focus. The focus is presented in text form, which clearly points out the key points of the emergency situations and rescue operations that the monitoring should focus on.

[0149] In the real-time information update submodule, based on the adjusted monitoring focus, a publish / subscribe model is adopted, and the MQTT protocol is used for information transmission to update real-time monitoring information. By defining the topics as emergency event status and rescue operation progress, the latest monitoring information is sent to the publisher, and the subscribers receive the updated information in real time and obtain real-time monitoring data. The data is presented in the form of real-time push notifications, which promptly reflects the emergency event status and the latest progress of the rescue operation.

[0150] See also Figure 2 and Fig.10 ,The intelligent scheduling and command module includes the event status analysis submodule, the resource scheduling ,optimization submodule, and the instruction generation submodule;

[0151] The event status analysis submodule analyzes the current status and changing trends of emergency events based on real-time monitoring data, evaluates the effectiveness of response actions, including rescue speed and coverage, and generates event analysis records;

[0152] The resource scheduling optimization submodule identifies the shortcomings and advantages in resource allocation based on event analysis records, and re-evaluates and optimizes the deployment strategy of resources and personnel by comparing expected results with the situation to obtain a resource optimization plan;

[0153] The instruction generation submodule formulates scheduling measures based on the resource optimization plan, including resource reallocation, personnel transfer and task priority adjustment, and generates intelligent scheduling instructions.

[0154] In the event status analysis submodule, based on real-time monitoring data, time series analysis methods are adopted, and data processing is performed using the Python programming language and the Pandas library to analyze the current status and changing trends of emergency events. Specifically, the autoregressive moving average (ARMA) model is used to analyze the time series data of rescue speed and coverage. By setting the order of the model to 2 and 1 respectively, the parameter values ​​are estimated, and event analysis records are generated. The records are presented in the form of charts, which describe in detail the time-varying characteristics of the response action effects.

[0155] In the resource scheduling optimization submodule, based on event analysis records, a multi-objective optimization method is adopted and implemented by programming with MATLAB to identify the shortcomings and advantages in resource allocation. By comparing the expected results with the actual situation, the resource and personnel deployment strategies are re-evaluated and optimized. Specifically, the optimization goals are set to maximize the rescue speed and minimize the resource arrival time. The genetic algorithm is used for solving the problem, and the population size is set to 100, the crossover rate is 0.8, and the mutation rate is 0.05. The resource optimization plan is obtained, which is output in the form of an optimization report, which lists the resource and personnel redeployment strategies in detail.

[0156] In the instruction generation submodule, based on the resource optimization plan, the decision support system method is adopted, and the Java programming language is used to develop applications to formulate scheduling measures, including resource reallocation, personnel transfers and task priority adjustments. By setting decision rules, intelligent scheduling instructions are generated according to the optimization plan. The instructions are presented in text form, detailing the specific content and execution steps of each scheduling measure.

[0157] The above are only preferred embodiments of the present invention and are not intended to limit the present invention in other forms. Any technician familiar with the profession may use the technical contents disclosed above to change or modify them into equivalent embodiments with equivalent changes and apply them to other fields. However, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention without departing from the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.

Claims

1. Emergency response coordination system based on the Internet of Things, characterized by: The system comprises: The abnormal event identification module removes noise and normalizes the data based on the multi-dimensional time series data collected by IoT devices, detects abnormal points, and identifies potential abnormal events in the data to generate abnormal event identification data; The event impact analysis module constructs an event impact diagram based on the abnormal event identification data, demarcates the boundaries of the impact area, calculates the potential impact of the abnormal event on the area, including the impact range and severity, and obtains an event impact analysis record; The resource dynamic matching module collects resource information, including type, quantity and location, based on the event impact analysis record and discrete event simulation, and allocates resources according to the matching degree between resources and demand, and obtains resource dynamic matching measures; The emergency plan formulation module analyzes the dispatch timeliness and effectiveness of various emergency resources based on the dynamic resource matching measures, formulates emergency response and action plans based on the characteristics and urgency of the event, and establishes an emergency action plan; The scenario simulation rehearsal module uses an individual-oriented model based on the emergency action plan to build a simulation environment for strategy testing, simulate differentiated response strategies and action paths, and evaluate potential problems in operations to generate scenario simulation rehearsal data; The priority adjustment module analyzes the effects and criticality of emergency measures based on the scenario simulation rehearsal data, dynamically adjusts the task and resource priorities according to the effect evaluation results, and obtains the priority adjustment index; The real-time monitoring module collects the development data of the emergency event and the progress information of the rescue operation in real time based on the priority adjustment index, adjusts the monitoring focus in combination with the priority adjustment result, and obtains the real-time monitoring data; The intelligent dispatching and commanding module analyzes the current event status and the execution effect of the response action based on the real-time monitoring data, and intelligently dispatches rescue resources, including adjusting the deployment of resources and personnel, continuously optimizing the response plan, and generating intelligent dispatching instructions; The emergency plan formulation module includes a resource scheduling analysis submodule, an emergency assessment submodule, and an action plan formulation submodule; The resource scheduling analysis submodule analyzes the scheduling timeliness and effectiveness of resources based on dynamic resource matching measures, and generates resource scheduling analysis records in combination with resource arrival time, coverage and contribution to emergency response; The urgency assessment submodule assesses the characteristics and current urgency of the emergency event based on the resource scheduling analysis record, and obtains an urgency assessment result in combination with the spread speed, impact scope and potential losses caused by the event; The action plan formulation submodule designs response measures and action plans based on the emergency assessment results, including personnel evacuation, material allocation and rescue team deployment, and establishes an emergency action plan; The scenario simulation rehearsal module includes an environment parameter setting submodule, a strategy testing submodule, and a problem identification submodule; The environmental parameter setting submodule is based on the emergency action plan and adopts an individual-based model to establish an initial environmental model and set initial conditions, including the terrain characteristics of the event location, the surrounding buildings and the density of people, determine the basic parameters of the simulated environment, and generate an environmental basic model; The individual-based model is based on the formula: ； Calculate the distribution density of personnel safety paths and generate the basic model of the environment; in, Represents the distribution density of personnel safety paths, is the total number of personnel, is the area of ​​the region considered, is the terrain height factor, is the building layout factor, is the risk assessment factor; The strategy testing submodule is based on the environment basic model and uses a support vector machine to cyclically execute differentiated response strategies and action paths, record the execution results and key event points of each strategy, and generate a strategy execution result set; The problem identification submodule makes execution strategy judgments based on the strategy execution result set, identifies problems that occur during the process, including low evacuation efficiency or improper resource allocation, summarizes potential improvement targets, and generates scenario simulation rehearsal data.

2. The emergency response coordination system based on the Internet of Things according to claim 1, characterized in that: The abnormal event identification data includes the timestamp, location information, and abnormal level of the abnormal event; the event impact analysis record includes the geographical scope of the affected area, the estimated impact duration, and the impact severity rating; the resource dynamic matching measures include the type, quantity, and estimated arrival time of resources allocated to multiple regions; the emergency action plan includes the emergency evacuation route and the location of the rescue material distribution point; the scenario simulation rehearsal data includes key issues in the simulation, proposed solutions, and the rehearsal success rate; the real-time monitoring data includes the real-time speed of event development, the current rescue operation efficiency, and the remaining status of on-site resources.

3. The emergency response coordination system based on the Internet of Things according to claim 1, characterized in that: The abnormal event identification module includes a data processing submodule, an abnormal point detection submodule, and an abnormal event marking submodule; The data processing submodule filters the multidimensional time series data collected by the IoT device to remove noise and normalize the data to obtain a processed data set; The outlier detection submodule analyzes the difference between each data point and its neighboring data points based on the processed data set, identifies potential abnormal data points that deviate from the normal state, and generates an outlier set; The abnormal event marking submodule analyzes the concentration trend and time distribution of abnormal points based on the abnormal point set, identifies potential abnormal events in the data, performs marking processing, and generates abnormal event identification data.

4. The emergency response coordination system based on the Internet of Things according to claim 1, characterized in that: The event impact analysis module includes an impact area boundary division submodule, an impact intensity calculation submodule, and an impact analysis recording submodule; The impact area boundary division submodule determines the geographical location where the abnormal event occurs based on the abnormal event identification data, and estimates the impact radius according to the abnormal intensity to obtain the area boundary data; The impact intensity calculation submodule calculates the potential impact intensity of the abnormal event on the region based on the region boundary data, estimates the degree and urgency of the impact on the corresponding region based on the type and intensity of the abnormal event, and generates impact intensity information; The impact analysis record submodule records the impact analysis of each impact area based on the impact intensity information, including the expected scope, severity and duration of the impact, to obtain an event impact analysis record.

5. The emergency response coordination system based on the Internet of Things according to claim 1, characterized in that: The resource dynamic matching module includes a resource information collection submodule, a matching degree analysis submodule, and a resource allocation plan submodule; The resource information collection submodule is based on the event impact analysis record, and if the regional impact rating exceeds a preset threshold, it collects the resource information available in the region, including the type, quantity and current location, and generates a resource information list; The matching degree analysis submodule is based on the resource information list and uses a long short-term memory network. If the resource type meets the emergency demand, the matching degree between the resource and the demand is calculated, and the resource matching degree information is obtained by combining the coverage, response time and efficiency of the resource; The resource allocation plan submodule adopts discrete event simulation based on resource matching information. If the matching degree meets the standard, a resource allocation plan is formulated, and dynamic resource matching measures are obtained according to the optimal resource utilization and response requirements, including allocation location, time and quantity; The discrete event simulation is based on the formula: ； Calculate resource allocation decisions and obtain dynamic resource matching measures; in, For the The utilization score of the resource. Indicates whether to select the resource for allocation. Score resource matching. represents the cost of the resource, Indicates the resource response time, is the weight coefficient.

6. The emergency response coordination system based on the Internet of Things according to claim 1, characterized in that: The priority adjustment module includes an effect analysis submodule, a criticality assessment submodule, and a priority adjustment strategy submodule; The effect analysis submodule analyzes the execution effect of emergency measures based on the scenario simulation rehearsal data, including evacuation speed and resource arrival time, and obtains effect analysis results; The criticality assessment submodule assesses the criticality of the emergency measures based on the effect analysis results, and obtains a criticality assessment record in combination with the contribution to the success of the emergency response; The priority adjustment strategy submodule dynamically adjusts the priorities of tasks and resources based on the criticality assessment records, continuously optimizes the response efficiency and effect, and obtains the priority adjustment index.

7. The emergency response coordination system based on the Internet of Things according to claim 1, characterized in that: The real-time monitoring module includes a data collection submodule, a monitoring focus adjustment submodule, and a real-time information update submodule; The data collection submodule collects the development data of the emergency incident and the progress information of the rescue operation in real time based on the priority adjustment index, and integrates the information data to generate a real-time data set; The monitoring focus adjustment submodule analyzes the current emergency situation based on the real-time data set, adjusts the monitoring focus, and generates an adjusted monitoring focus; The real-time information updating submodule updates the real-time monitoring information based on the adjusted monitoring focus, reflects the emergency event status and the progress of the rescue operation, and obtains real-time monitoring data.

8. The emergency response coordination system based on the Internet of Things according to claim 1, characterized in that: The intelligent dispatching and commanding module includes an event status analysis submodule, a resource dispatching and optimization submodule, and an instruction generation submodule; The event status analysis submodule analyzes the current status and change trend of emergency events based on real-time monitoring data, evaluates the effectiveness of response actions, including rescue speed and coverage, and generates event analysis records; The resource scheduling optimization submodule identifies the shortcomings and advantages in resource allocation based on event analysis records, and re-evaluates and optimizes the deployment strategy of resources and personnel by comparing expected results and situations to obtain a resource optimization plan; The instruction generation submodule formulates scheduling measures based on the resource optimization plan, including resource reallocation, personnel transfer and task priority adjustment, and generates intelligent scheduling instructions.

Images