Intelligent emergency command method for urban public safety

Abstract

The invention discloses an urban public safety intelligent emergency command method, and relates to the technical field of urban public safety, and the method comprises the following steps: pre-constructing a multi-source sensing network to collect fire data in real time, the fire data at least comprising smoke concentration, temperature change and flame images; based on a multi-source data fusion and early warning analysis model, a fire risk value is calculated in real time, and early warning is triggered; predicting a fire occurrence probability by using a Bayesian network model, and simulating a fire spreading trend and speed; emergency resource scheduling is carried out based on the multi-objective optimization model; and performing post-disaster evaluation. According to the method, the analytic hierarchy process is adopted to fuse the multi-source data and calculate the weight, the fire probability is predicted through the Bayesian network model, the improved CellarAutomata model is constructed to simulate the spreading trend, the emergency resources are scheduled in combination with the multi-target optimization model, risk quantitative evaluation and accurate resource configuration are achieved, and decision deviation and resource waste caused by empirical judgment are avoided.

Description

Technical Field

[0001] The present invention relates to the field of urban public safety technology, and in particular to an urban public safety intelligent emergency command method. Background Art

[0002] Urban public safety is the bottom line requirement for urban development. Fires, as frequent public safety emergencies in cities, pose a serious threat to people's lives and property, as well as urban operations. The current urban fire emergency command system faces multiple technical bottlenecks in its digital and intelligent transformation. Specific issues are as follows:

[0003] Traditional fire monitoring methods are limited, relying on manual inspections or a small number of fixed sensors. This makes it difficult to achieve real-time monitoring across the entire city, which can lead to delayed fire detection. During emergency response, departments lack information sharing, resulting in inefficient resource allocation and an inability to quickly form an effective rescue force. Furthermore, decision-making lacks scientific evidence and real-time data support, often relying on empirical judgment, making it difficult to accurately respond to complex and ever-changing fire situations. These issues severely impact the efficiency and effectiveness of fire emergency response, increasing the risk of casualties and property damage.

[0004] Currently, no effective solutions have been proposed for the problems in related technologies. Summary of the Invention

[0005] In response to the problems in related technologies, the present invention proposes an intelligent emergency command method for urban public safety, which solves the problems in the existing technology such as incomplete fire monitoring, poor coordination of emergency command, and unscientific decision-making, and realizes rapid monitoring and early warning of fire, efficient coordinated command and accurate decision-making, thereby improving the city's public safety protection capabilities in response to fire.

[0006] The technical solution of the present invention is achieved as follows:

[0007] A smart emergency command method for urban public safety, comprising the following steps:

[0008] Pre-building a multi-source sensing network to collect fire data in real time, wherein the fire data includes at least smoke concentration, temperature change and flame image;

[0009] Based on multi-source data fusion and early warning analysis models, fire risks are obtained in real time and early warnings are triggered. The early warning analysis model includes the use of Bayesian network models to predict the probability of fire occurrence and simulate the trend and speed of fire spread;

[0010] Emergency resource scheduling based on multi-objective optimization model;

[0011] Conduct post-disaster assessments, including at least casualties assessment, property loss assessment, and environmental impact assessment.

[0012] Furthermore, the multi-source data fusion includes the following steps:

[0013] After the multi-source data is time-space aligned, it is expressed as:

[0014]

[0015] Among them, D i represents the sensor data of the i-th category, w i is the corresponding weight;

[0016] The weight of each sensor data is calculated by the analytic hierarchy process (AHP), which is expressed as:

[0017]

[0018] Among them, λ max is the maximum eigenvalue of the judgment matrix, v i is the corresponding eigenvector component.

[0019] Furthermore, the Bayesian network model is used to predict the probability of fire occurrence, which is expressed as:

[0020]

[0021] Among them, F represents the fire event, E n Represents various types of monitoring evidence, such as abnormal temperature, smoke concentration, etc.

[0022] Furthermore, the simulation of fire spreading trend and speed includes the following steps:

[0023] The spread trend prediction includes constructing an improved CellularAutomata model, which is expressed as:

[0024] S t+1 (i,j)=f[S t (i,j),N t (i, j), W(t), T(t)];

[0025] Among them, S t (i, j) is the state of cell (i, j) at time t, N t (i, j) is the neighborhood state, W(t) and T(t) are the wind speed and temperature field functions respectively;

[0026] Get the spreading speed, expressed as:

[0027]

[0028] Among them, V0 is the reference speed, a and b are material coefficients, and T0 is the ambient temperature.

[0029] Furthermore, the emergency resource scheduling includes the following steps:

[0030] Establish a multi-objective optimization model, expressed as:

[0031]

[0032] The calibration constraints are expressed as:

[0033]

[0034] x ij ∈{0,1};

[0035] Among them, c ij is the cost of deploying resource i to demand point j, t j is the response time of demand point j, r j is the resource demand of demand point j, s i is the available amount of resource i, and α is the time weight coefficient.

[0036] Furthermore, the casualty assessment is expressed as:

[0037]

[0038] Among them, T i is the exposure time, P i is the position parameter, E i is the environmental parameter, w i The personnel type weight.

[0039] Furthermore, the property loss assessment is expressed as:

[0040]

[0041] Among them, V j is the property value, d j is the degree of damage, r j is the residual value rate.

[0042] Furthermore, the environmental impact assessment is expressed as:

[0043]

[0044] Among them, CO(t,x,y) and PM2.5(t,x,y) are the spatiotemporal distribution functions of pollutants, which respectively represent the distribution of different pollutants in time and space, and a and b are environmental damage coefficients.

[0045] Beneficial effects of the present invention:

[0046] 1. This invention builds a multi-source perception system by deploying Internet of Things sensor networks (smoke sensors, temperature sensors, gas leak sensors, etc.), video surveillance equipment (Eagle Eye cameras, thermal imaging cameras), satellite remote sensing and drone inspections, and realizes the real-time collection of fire data (smoke concentration, temperature changes, flame images, etc.) across the city, solving the problems of single traditional monitoring methods and delayed detection, and ensuring accurate early identification of fires.

[0047] 2. The present invention adopts the analytic hierarchy process (AHP) to fuse multi-source data and calculate weights, and predicts the fire probability through the Bayesian network model. It constructs an improved CellularAutomata model to simulate the spread trend, combines the multi-objective optimization model to dispatch emergency resources, realizes risk quantitative assessment and precise resource allocation, and avoids decision-making bias and resource waste caused by empirical judgment.

[0048] 3. This invention covers the entire chain of monitoring and early warning, risk assessment, emergency command, and post-disaster assessment. Through post-disaster assessment models (casualties, property losses, and environmental impacts), it quantifies the impact of disasters, providing data support for subsequent rescue optimization and urban safety planning. This completes the emergency management closed loop and enhances the systematic and sustainable nature of urban public safety. Furthermore, model parameters can be dynamically adjusted based on actual scenarios, making it suitable for high-risk scenarios such as commercial complexes, industrial parks, and transportation hubs. It can also be integrated with other urban public safety systems to build a more comprehensive intelligent safety assurance system, promising broad application prospects and widespread promotional value. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0050] Figure 1 The present invention is a flowchart of an intelligent emergency command method for urban public safety according to an embodiment of the present invention. DETAILED DESCRIPTION

[0051] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention are within the scope of protection of the present invention.

[0052] According to an embodiment of the present invention, a method for intelligent emergency command of urban public safety is provided.

[0053] like Figure 1 As shown, the urban public safety intelligent emergency command method according to an embodiment of the present invention includes the following steps:

[0054] Step S1: pre-build a multi-source sensing network to collect fire data in real time, wherein the fire data includes at least smoke concentration, temperature change and flame image;

[0055] Specifically, when applied, this technical solution includes: deploying an Internet of Things sensor network, including smoke sensors, temperature sensors, gas leak sensors, etc., installed at key locations inside buildings; setting up eagle-eye cameras, thermal imaging cameras and other video surveillance equipment at high points and important areas in the city; using satellite remote sensing technology to conduct macro-monitoring of large areas of the city; and equipping drones for flexible and mobile patrols.

[0056] Step S2: Based on multi-source data fusion and early warning analysis model, fire risk is obtained in real time and early warning is triggered. The early warning analysis model includes using a Bayesian network model to predict the probability of fire occurrence and simulate the trend and speed of fire spread;

[0057] The multi-source data fusion includes the following steps:

[0058] After the multi-source data are time-space calibrated in advance, data fusion is performed, which can be expressed as:

[0059]

[0060] Among them, D i represents the sensor data of the i-th category, w i The corresponding weight is calculated by the analytic hierarchy process (AHP) and is expressed as:

[0061]

[0062] Among them, λ max is the maximum eigenvalue of the judgment matrix, v i is the corresponding eigenvector component.

[0063] This technical solution determines the weight of each sensor data through the analytic hierarchy process (AHP) to achieve effective fusion of multi-source data.

[0064] Among them, the early warning analysis model includes: building a fire probability prediction model based on the Bayesian network, which is expressed as:

[0065]

[0066] Among them, F represents the fire event, E n Represents various types of monitoring evidence, such as abnormal temperature, smoke concentration, etc.

[0067] Specifically, through the Bayesian network model, combined with the probability distribution of each monitoring evidence, the probability of fire occurrence can be accurately predicted, and early assessment of fire risks can be achieved.

[0068] The spread trend prediction includes constructing an improved CellularAutomata model, which is expressed as:

[0069] S t+1 (i,j)=f[S t (i,j),N t (i, j), W(t), T(t)];

[0070] Among them, S t (i, j) is the state of cell (i, j) at time t, N t (i, j) is the neighborhood state, W(t) and T(t) are the wind speed and temperature field functions respectively.

[0071] At the same time, the spreading speed is obtained, which is expressed as:

[0072]

[0073] Among them, V0 is the reference speed, a and b are material coefficients, and T0 is the ambient temperature.

[0074] This technical solution, through this model, can comprehensively consider factors such as wind speed, temperature field, material properties, etc., accurately predict the spread trend and speed of fire, and provide important decision-making basis for emergency command.

[0075] Step S3, performing emergency resource scheduling based on a multi-objective optimization model; at least including: performing resource scheduling.

[0076] The resource scheduling includes establishing a multi-objective optimization model, which is expressed as:

[0077]

[0078] Among them, the constraints are:

[0079]

[0080] x ij ∈{0,1};

[0081] Among them, c ij is the cost of deploying resource i to demand point j, t j is the response time of demand point j, r j is the resource demand of demand point j, s i is the available amount of resource i, and α is the time weight coefficient.

[0082] This technical solution, through the multi-objective optimization model, rationally dispatches emergency resources while taking into account resource allocation costs and response time, ensuring that the resource requirements of demand points are met, while keeping the response time within an acceptable range, and realizing efficient utilization of emergency resources.

[0083] Step S4: Conduct a post-disaster assessment, which at least includes casualty assessment, property loss assessment, and environmental impact assessment.

[0084] The casualty assessment is expressed as:

[0085]

[0086] Among them, T i is the exposure time, P i is the location parameter (e.g. the location closer to the fire source has a higher risk), E i are environmental parameters (temperature, toxic gas concentration, etc.), w i The weight of the personnel type (for example, the vulnerability of different groups of people such as the elderly and children is different).

[0087] Among them, the property loss assessment is expressed as:

[0088]

[0089] Among them, V j is the property value, d j is the degree of damage (between 0 and 1), r j is the residual value rate.

[0090] Among them, environmental impact assessment is expressed as:

[0091]

[0092] Among them, CO(t,x,y) and PM2.5(t,x,y) are the spatiotemporal distribution functions of pollutants, which respectively represent the distribution of different pollutants in time and space, and a and b are environmental damage coefficients.

[0093] With the help of the above technical solution, fire data is collected in real time through multi-source sensing equipment, and early warning analysis models are used for data fusion, risk assessment and spread trend prediction. Emergency resource scheduling is based on a multi-objective optimization model, and casualties, property losses and environmental impacts are evaluated through a post-disaster assessment model. This has achieved rapid monitoring and early warning of fires, efficient coordinated command and accurate decision-making, and improved the city's public safety protection capabilities in response to fires.

[0094] It is important to note that the parameters of each model and algorithm in this technical solution can be adjusted and optimized based on actual conditions to improve the accuracy and adaptability of the model. Furthermore, this method can be integrated with other urban public safety systems to form a more comprehensive urban public safety guarantee system.

[0095] In addition, specifically, when applying it, taking a fire incident in a commercial complex in a certain city as an example, it occurred at 10:00 am on a certain day of a certain month of a certain year. A fire broke out in the fourth-floor dining area of ​​a large commercial complex in the core business district of a certain city (building area of ​​100,000 square meters, average daily passenger flow of 20,000 people) due to a leak in the kitchen fume pipe. The fire was small in the early stage but the smoke spread rapidly.

[0096] Multi-source sensing devices collected real-time data in advance, including: IoT sensors triggered an early warning. A smoke sensor in the dining area's kitchen detected a sudden rise in smoke concentration to 80% LEL (Lower Explosive Limit), and a temperature sensor indicated a temperature increase from 25°C to 65°C, exceeding a preset threshold of 40°C. The system automatically marked the sensor location (longitude X, latitude Y) and transmitted the data to the emergency command center via the LoRa wireless communication network. Video surveillance equipment assisted in confirming that thermal imaging cameras within the commercial complex had captured an abnormally hot spot in the kitchen area. Hawkeye cameras transmitted footage showing localized open flames and spreading smoke. The command center dispatched a drone to the scene, capturing real-time footage from a low altitude to confirm the fire's location and the distribution of nearby personnel. Furthermore, satellite remote sensing data, integrated with the city model, indicated no large-scale heat sources in the area. However, combined with the city's 3D building model (including material properties and floor layout), the system initially determined that the fire was in its early stages and had not yet broken through the ceiling.

[0097] The early warning analysis model calculates risks in real time as follows:

[0098] Multi-source data was fused using the Analytic Hierarchy Process (AHP) to calculate weights: smoke sensor data (0.5) > temperature sensor data (0.3) > video data (0.2). The resulting risk score is: F = 0.5 × 80 + 0.3 × 65 + 0.2 × 70 = 73.5 (out of 100), triggering a Level 2 orange alert (threshold 60-80).

[0099] Fire probability and spread prediction, including calculations by the Bayesian network model: combined with historical data (the fire incidence rate in the area in the past five years was 0.05%), the probability of fire occurrence under current evidence (temperature, smoke, open flames) increases to 92%.

[0100] A modified CellularAutomata model simulation was conducted, including wind speed v = 3 m / s (southeast wind), temperature field T = 65°C, material coefficients a = 0.02 (metal pipes), b = 0.01 (wooden decoration). The spread velocity V = 0.5 m / min × (1 + 0.02 × (65 - 25) + 0.01) = 0.91 m / min. The fire was predicted to spread to adjacent restaurants within 15 minutes and could reach the upper floors within 30 minutes.

[0101] Make emergency command decisions and resource dispatch, as follows:

[0102] The multi-objective optimization scheduling model has the objective function of minimizing scheduling costs (manpower, equipment) and minimizing response time, with a weight of ω = 0.7 (prioritizing time). Constraints: Water demand at the demand point (commercial complex) ≥ 500m 3 , the arrival time of fire trucks is ≤10 minutes. Available resources: There are 8 water tankers (each with a water capacity of 20m3) at 3 nearby fire stations. 3 ), 4 ladder trucks, and 50 firefighters.

[0103] Generate the best solution: dispatch 5 water tankers (100m 3 ) Two aerial ladder trucks departed from the nearest station (3 km away, estimated arrival time 8 minutes), and simultaneously notified surrounding stations to prepare for reinforcements. Traffic police were coordinated to implement traffic control on surrounding roads and open emergency lanes.

[0104] In addition, cross-departmental coordination and command were implemented as follows: The command center pushed real-time data to the fire, public security, medical, and power supply departments via a smart emergency platform. The fire department initiated an internal firefighting and search and rescue plan, prioritizing the rescue of those trapped on the fourth floor. The public security department organized the evacuation of the mall (using broadcasts and emergency lighting guidance) and established an outer cordon. The medical department established a temporary emergency point in the open space east of the complex and prepared five ambulances. The power supply department shut off non-fire-related electricity to the fourth floor to prevent an electrical short from exacerbating the fire.

[0105] Conduct post-disaster assessment and disposal, as follows:

[0106] The casualty assessment included exposure time (20 minutes average exposure for trapped individuals), location parameters (weighted 1.5 for proximity to the fire source), and environmental parameters (CO concentration 500 ppm, temperature 90°C). The model calculated 12 minor injuries (with children and the elderly receiving higher weights), 3 serious injuries, and no deaths, which is consistent with the actual search and rescue results.

[0107] The property damage assessment covers approximately 500 square meters of the restaurant area and adjacent shops, with a total property value of 20 million yuan. The damage level is 0.6, and the residual value is 0.1. Loss calculation: L = 2000 × (1 - 0.6 - 0.1) = 6 million yuan.

[0108] The environmental impact assessment determined that the diffusion range of pollutants (PM2.5 and CO) was short-term exceeding standards within a 200-meter radius centered on the complex, with environmental damage coefficients a = 0.8 and b = 0.5. The assessment concluded that air purification measures must be initiated and that continuous monitoring of surrounding soil and water bodies is required.

[0109] With the help of the above cases, the present invention has achieved a significant improvement in efficiency. It only takes 8 minutes from early warning to the arrival of the first batch of fire trucks, which is more than 50% shorter than the traditional command mode. At the same time, the decision-making is scientific, and the risk and resource requirements are quantified through the model to avoid the waste of resources caused by empirical judgment (for example, the traditional solution may dispatch 10 fire trucks, but only 5 are actually needed). In addition, real-time sharing of data from multiple departments is achieved, and evacuation, fire fighting, and rescue are carried out simultaneously, without delays in handling caused by information islands. In summary, this scenario reflects the advantages of the present invention in rapid response, precise scheduling, and scientific evaluation in complex urban environments, and can be extended to other high-risk scenarios such as industrial parks and transportation hubs.

[0110] In summary, with the help of the above technical solution of the present invention, the following effects can be achieved:

[0111] 1. This invention builds a multi-source perception system by deploying Internet of Things sensor networks (smoke sensors, temperature sensors, gas leak sensors, etc.), video surveillance equipment (Eagle Eye cameras, thermal imaging cameras), satellite remote sensing and drone inspections, and realizes the real-time collection of fire data (smoke concentration, temperature changes, flame images, etc.) across the city, solving the problems of single traditional monitoring methods and delayed detection, and ensuring accurate early identification of fires.

[0112] 2. The present invention adopts the analytic hierarchy process (AHP) to fuse multi-source data and calculate weights, and predicts the fire probability through the Bayesian network model. It constructs an improved CellularAutomata model to simulate the spread trend, combines the multi-objective optimization model to dispatch emergency resources, realizes risk quantitative assessment and precise resource allocation, and avoids decision-making bias and resource waste caused by empirical judgment.

[0113] 3. This invention covers the entire chain of monitoring and early warning, risk assessment, emergency command, and post-disaster assessment. Through post-disaster assessment models (casualties, property losses, and environmental impacts), it quantifies the impact of disasters, providing data support for subsequent rescue optimization and urban safety planning. This completes the emergency management closed loop and enhances the systematic and sustainable nature of urban public safety. Furthermore, model parameters can be dynamically adjusted based on actual scenarios, making it suitable for high-risk scenarios such as commercial complexes, industrial parks, and transportation hubs. It can also be integrated with other urban public safety systems to build a more comprehensive intelligent safety assurance system, promising broad application prospects and widespread promotional value.

[0114] The foregoing is merely a preferred embodiment of the present invention and is not intended to limit the present invention. A person skilled in the art will readily appreciate other embodiments of the present invention after considering the disclosure in the specification and examples. This application is intended to cover any variations, uses, or adaptations of the present invention, which follow the general principles of the present invention and include common knowledge or customary techniques in the art not disclosed herein. The description and examples are to be considered merely exemplary, and the true scope and spirit of the present invention are indicated by the claims.

[0115] It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes can be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. A smart emergency command method for urban public safety, characterized in that: The following steps are involved: Pre-building a multi-source sensing network to collect fire data in real time, wherein the fire data includes at least smoke concentration, temperature change and flame image; Based on multi-source data fusion and early warning analysis models, fire risks are obtained in real time and early warnings are triggered. The early warning analysis model includes the use of Bayesian network models to predict the probability of fire occurrence and simulate the trend and speed of fire spread; Emergency resource scheduling based on multi-objective optimization model; Conduct post-disaster assessments, including at least casualties assessment, property loss assessment, and environmental impact assessment.

2. The urban public safety intelligent emergency command method according to claim 1 is characterized in that: The multi-source data fusion includes the following steps: After the multi-source data is time-space aligned, it is expressed as: Among them, D i represents the sensor data of the i-th category, w i is the corresponding weight; The weight of each sensor data is calculated by the hierarchical analysis method, which is expressed as: Among them, λ max is the maximum eigenvalue of the judgment matrix, v i is the corresponding eigenvector component.

3. The urban public safety intelligent emergency command method according to claim 1 is characterized in that: The Bayesian network model is used to predict the probability of fire occurrence, which is expressed as: Among them, F represents the fire event, E n Represents various types of monitoring evidence, such as abnormal temperature, smoke concentration, etc.

4. The urban public safety intelligent emergency command method according to claim 4 is characterized in that: The simulation of fire spreading trend and speed includes the following steps: The spread trend prediction includes constructing an improved CellularAutomata model, which is expressed as: S t+1 (i,j)=f[S t (i,j),N t (i,j),W(t),T(t)]; Among them, S t (i, j) is the state of cell (i, j) at time t, N t (i, j) is the neighborhood state, W(t) and T(t) are the wind speed and temperature field functions respectively; Get the spreading speed, expressed as: Among them, V0 is the reference speed, a and b are material coefficients, and T0 is the ambient temperature.

5. The urban public safety intelligent emergency command method according to claim 1 is characterized in that: The emergency resource dispatching includes the following steps: A multi-objective optimization model is established, which is expressed as: The calibration constraints are expressed as: Among them, c ij is the cost of deploying resource i to demand point j, t j is the response time of demand point j, r j is the resource demand of demand point j, s i is the available amount of resource i, and α is the time weight coefficient.

6. The urban public safety intelligent emergency command method according to claim 1 is characterized in that: The casualty assessment is expressed as: Among them, T i is the exposure time, P i is the position parameter, E i is the environmental parameter, w i The personnel type weight.

7. The urban public safety intelligent emergency command method according to claim 6 is characterized in that: The property loss assessment is expressed as: Among them, V j is the property value, d j is the degree of damage, r j is the residual value rate.

8. The urban public safety intelligent emergency command method according to claim 7 is characterized in that: The environmental impact assessment is expressed as: Among them, CO(t,x,y) and PM2.5(t,x,y) are the spatiotemporal distribution functions of pollutants, which respectively represent the distribution of different pollutants in time and space, and a and b are environmental damage coefficients.

Images