Fire prevention and control intelligent network method and system based on Beidou satellite navigation

Abstract

The invention relates to a fire prevention and control smart network method and system based on Beidou satellite navigation. The method comprises the following steps: firstly, acquiring real-time operation data of fire-fighting equipment in a building, and scanning a building structure through a three-dimensional imaging device to generate a three-dimensional digital model; secondly, fusing the real-time operation data, the three-dimensional digital model and preset environment parameters to form a fire prevention and control reference data set; thirdly, carrying out multi-dimensional data comparison on the reference data set based on a preset fire-fighting standard program, and generating an alarm signal with spatial positioning information; then, determining a fire-fighting facility failure area according to the alarm signal, and calculating a fire risk diffusion parameter; and finally, generating a grading early warning instruction according to the risk diffusion parameters, and constructing an electronic combat map containing the optimal rescue path. The method provides global and accurate basic data support for fire prevention and control, improves the timeliness and accuracy of early warning, optimizes the rescue path, and improves the fire disposal efficiency.

Description

Technical Field

[0001] The present invention belongs to the technical field of fire safety, and particularly relates to a fire prevention and control intelligent network method and system based on Beidou satellite navigation. Background Technique

[0002] With the continuous advancement of the urbanization process in China, the number of high-rise and super high-rise buildings has increased significantly, the urban population density has been rising continuously, and the fire risk has intensified accordingly, resulting in a substantial increase in the complexity and workload of fire prevention and control work. There are obvious shortcomings in the current fire prevention and control system in aspects such as project construction, operation supervision, and emergency rescue: the fire protection acceptance inspection of projects consumes a large amount of manpower and material resources due to the huge building volume and complex fire protection systems; during the later operation, it is difficult for the fire department to comprehensively grasp the status of facilities due to the wide supervision scope and insufficient real-time performance, and the maintenance and management of building users lags behind, which is likely to cause damage or paralysis of fire protection facilities; when a fire occurs, the fire rescue team is often unable to reach the scene in time due to factors such as traffic and distance, and there are problems such as incomplete information acquisition and communication obstruction at the rescue scene, resulting in low command efficiency and difficulty in accurately positioning the location of the rescued personnel. Summary of the Invention

[0003] Based on this, it is necessary to provide a fire prevention and control intelligent network method and system based on Beidou satellite navigation, which can improve the fire disposal efficiency and enhance the overall fire prevention and control ability, aiming at the above technical problems.

[0004] In the first aspect, the present application provides a fire prevention and control intelligent network method based on Beidou satellite navigation, including:

[0005] Obtain the real-time operation data of fire protection facilities in the building; use a three-dimensional imaging device to scan the building structure and generate a three-dimensional digital model.

[0006] Fuse the real-time operation data, the three-dimensional digital model and the preset environmental parameters to obtain a fire prevention and control benchmark data set.

[0007] Based on the preset fire protection specification procedures, perform multi-dimensional data comparison on the fire prevention and control benchmark data set, judge and identify abnormal parameter combinations exceeding the preset threshold, and generate an alarm signal including spatial positioning information.

[0008] Determine the area where the fire protection facilities fail according to the alarm signal, and combine the alternative prevention and control resources and the preset rescue resource distribution map to calculate the fire risk diffusion parameter.

[0009] Generate a hierarchical early warning instruction according to the fire risk diffusion parameter, and construct an electronic operation map including the optimal rescue path.

[0010] In one of the embodiments, fusing the real-time operation data, the three-dimensional digital model and the preset environmental parameters to obtain a fire prevention and control benchmark data set includes:

[0011] Extract the fire access topology based on the road topology data in the preset environmental parameters; the fire access topology includes node spacing and passing height.

[0012] Map the water source coordinates and pressure data in the preset environmental parameters to the fire access topology to generate a weighted path network.

[0013] Based on the building structure model and the weighted path network in the 3D digital model, use the path planning algorithm to generate a dynamic evacuation path; the building structure model includes wall thickness and material parameters.

[0014] Overlay and analyze the temperature field distribution in the real-time operation data with the dynamic evacuation path, and output the path availability matrix under the influence of heat radiation.

[0015] Update the emergency response parameters according to the path availability matrix to obtain the fire prevention and control benchmark data set.

[0016] In one embodiment, based on the preset fire protection specification program, perform multi-dimensional data comparison on the fire prevention and control benchmark data set, determine and identify abnormal parameter combinations exceeding the preset threshold, and generate an alarm signal including spatial positioning information, including:

[0017] Obtain the multi-dimensional parameter sequence in the fire prevention and control benchmark data set; the multi-dimensional parameter sequence includes temperature gradient, smoke concentration and gas composition ratio.

[0018] Match the parameter combination pattern in the preset fire protection specification program according to the multi-dimensional parameter sequence; the parameter combination pattern is generated by training with Beidou historical monitoring data and historical fire event data.

[0019] Extract the abnormal parameter interval exceeding the preset threshold in the parameter combination pattern; the abnormal parameter interval includes the intersection fluctuation range of at least two parameters.

[0020] Combine the equipment node topology map corresponding to the abnormal parameter interval and use the Beidou indoor positioning technology to generate spatial positioning information including floor number and equipment identification.

[0021] Input the spatial positioning information into the dynamic threshold model to obtain the dynamic threshold updated based on environmental variables.

[0022] Wherein, if the duration of the abnormal parameter interval exceeds the dynamic threshold, an alarm signal is triggered and the spatial positioning information is bound.

[0023] In one embodiment, determine the fire protection facility failure area according to the alarm signal, and combine the alternative prevention and control resources and the preset rescue resource distribution map to calculate the fire risk diffusion parameters, including:

[0024] Match the corresponding preset failure weight parameters according to the equipment failure types in the alarm signal; the preset failure weight parameters are dynamically adjusted based on the historical failure frequencies of the equipment recorded by Beidou.

[0025] Obtain a list of alternative prevention and control resource identifiers in the vicinity based on the position coordinates in the alarm signal; the list of alternative prevention and control resource identifiers includes resource types and real-time availability status.

[0026] Generate a coordinate set of the prevention and control coverage gap area based on the failure weight parameters and the list of alternative resource identifiers.

[0027] Extract the response path node data corresponding to the coordinate set of the gap area in the preset rescue resource distribution map; the response path node data includes road topology and resource transportation rate.

[0028] Calculate the correlation matrix between the response path node data and the coordinate set of the gap area using the path weight algorithm.

[0029] Input the correlation matrix into the spatio-temporal risk diffusion model to obtain the fire risk diffusion parameters; the fire risk diffusion parameters include the risk level and the diffusion boundary coordinates.

[0030] In one embodiment, the risk level is calculated by the following formula:

[0031]

[0032] Q(t)=[q1(t),q2(t),...,q m (t)] T

[0033] Wherein, L represents the finally output fire risk level, k represents the category index of the risk level, μ k (·) represents the membership function of the k-th level risk, Q(t) represents the risk cumulative value vector of each gap area at time t, m represents the total number of gap areas, and q m (t) represents the risk cumulative value of the m-th gap area at time t.

[0034] In one embodiment, generate a hierarchical early warning instruction according to the fire risk diffusion parameters, and construct an electronic operation map including the optimal rescue path, including:

[0035] Generate a dynamic diffusion coefficient matrix for describing the propagation probability of the fire in the spatial grid according to the fire risk diffusion parameters.

[0036] Input the dynamic diffusion coefficient matrix into the multi-level fire spread model to obtain a three-dimensional risk field including heat radiation intensity and smoke concentration.

[0037] Extract the risk level boundary based on the three-dimensional risk field and trigger the early warning signal of the corresponding level.

[0038] Obtain real-time road condition data for the early warning signal coverage area; the data includes the coordinates of traffic control points and obstacles.

[0039] Fuse the three-dimensional risk field and real-time road condition data to generate a path weight map; the weight map includes the road passage cost and the fire threat value.

[0040] Use the hierarchical Dijkstra algorithm to traverse the path weight map to obtain the optimal rescue trajectory with an obstacle avoidance path point sequence.

[0041] Overlay the optimal rescue trajectory with the dynamic risk field contour line and the rescue resource distribution mark to obtain an electronic combat map.

[0042] In one of the embodiments, overlaying the optimal rescue trajectory with the dynamic risk field contour line and the rescue resource distribution mark to obtain an electronic combat map includes:

[0043] Perform spatial registration based on the risk intensity gradient of the dynamic risk field contour line and the path node coordinates of the optimal rescue trajectory to obtain the registration data of the risk field and the trajectory.

[0044] Extract the resource type code and the real-time available quantity of the rescue resource distribution mark, and establish a corresponding mapping relationship based on the resource type code and the risk intensity gradient.

[0045] Calculate the fusion weight parameter of the rescue resource distribution mark and the registration data based on the mapping relationship.

[0046] Input the fusion weight parameter into the path optimization model and output the rescue trajectory distribution map.

[0047] Generate a resource scheduling instruction according to the rescue trajectory distribution map, and update the layer data to obtain an electronic combat map.

[0048] In a second aspect, the present application also provides a fire prevention and control intelligent network system based on Beidou satellite navigation. The system includes:

[0049] A data acquisition and fusion module, which is used to obtain the real-time operation data of the fire protection facilities in the building; scan the building structure with a three-dimensional imaging device to generate a three-dimensional digital model; and is also used to fuse the real-time operation data, the three-dimensional digital model and the preset environmental parameters to obtain a fire prevention and control reference data set.

[0050] An intelligent monitoring and alarm module, which is used to perform multi-dimensional data comparison on the fire prevention and control reference data set based on a preset fire protection specification program, judge and identify abnormal parameter combinations exceeding the preset threshold, and generate an alarm signal including spatial positioning information.

[0051] A risk assessment and planning module is used to determine the failure area of fire protection facilities based on alarm signals, calculate fire risk diffusion parameters by combining alternative prevention and control resources and a preset rescue resource distribution map; it is also used to generate hierarchical early warning instructions according to the fire risk diffusion parameters and construct an electronic operation map containing the optimal rescue path.

[0052] In a third aspect, the present application also provides a computer device, including a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, the foregoing method is implemented.

[0053] In a fourth aspect, the present application also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the foregoing method is implemented.

[0054] The above-mentioned fire prevention and control intelligent network method, system, computer device and storage medium based on Beidou satellite navigation first obtain the real-time operation data of fire protection facilities in a building and generate a three-dimensional digital model by scanning the building structure with a three-dimensional imaging device; secondly, fuse the real-time operation data, the three-dimensional digital model and preset environmental parameters to form a fire prevention and control benchmark data set; furthermore, conduct multi-dimensional data comparison on the benchmark data set based on a preset fire protection specification program, identify abnormal parameter combinations exceeding the preset threshold, and generate an alarm signal with spatial positioning information; then, determine the failure area of fire protection facilities according to the alarm signal, calculate fire risk diffusion parameters by combining alternative prevention and control resources and a preset rescue resource distribution map; finally, generate hierarchical early warning instructions according to the risk diffusion parameters and construct an electronic operation map containing the optimal rescue path. It provides all-round and accurate basic data support for fire prevention and control, can timely detect abnormalities and risk hidden dangers of fire protection facilities, improve the timeliness and accuracy of early warning, optimize the rescue path, improve the efficiency of fire handling, and thus enhance the overall fire prevention and control ability. Description of the Drawings

[0055] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following will briefly introduce the drawings required for use in the description of the embodiments or related technologies. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0056] Figure 1 It is a flowchart of the fire prevention and control intelligent network method based on Beidou satellite navigation provided by the embodiment of the present invention;

[0057] Figure 2A flowchart for multi-dimensional data comparison of a fire prevention and control benchmark data set based on a preset fire protection specification program according to an embodiment of the present invention, to determine and identify abnormal parameter combinations exceeding a preset threshold, and generate an alarm signal including spatial positioning information;

[0058] Figure 3 A structural block diagram of a fire prevention and control intelligent network system based on Beidou satellite navigation according to an embodiment of the present invention. Detailed implementation manners

[0059] In order to make the objectives, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0060] In one embodiment, as Figure 1 shown, the present application provides a fire prevention and control intelligent network method based on Beidou satellite navigation, which may include the following steps:

[0061] Step S101, obtain real-time operation data of fire protection facilities in a building; scan the building structure using a three-dimensional imaging device to generate a three-dimensional digital model.

[0062] Specifically, obtain the real-time position data of fire protection facilities in the building through the high-precision positioning function of the Beidou satellite navigation system (horizontal accuracy ≤ 1 m, elevation accuracy ≤ 2 m). Sensors (such as NB-IoT / LoRa sensors) are implanted in the fire protection facilities (such as fire hydrants, sprinkler systems) to collect real-time equipment operation state parameters (such as water pressure, temperature, valve opening and closing) and maintenance data (such as maintenance time, component life), and the unique identification of the facilities is associated with the data through RFID tags or two-dimensional codes. At the same time, obtain the building point cloud data using lidar (LiDAR) scanning or unmanned aerial vehicle oblique photography technology, and combine with the BIM model to construct a three-dimensional digital model including semantic information such as floor structure, fire prevention zone, and safety exit.

[0063] Step S102, fuse the real-time operation data, the three-dimensional digital model and the preset environmental parameters to obtain a fire prevention and control benchmark data set.

[0064] Specifically, connect the real-time operation data, the three-dimensional digital model and the preset environmental parameters (including road topology data, water source distribution coordinates, meteorological data, etc.) to a spatio-temporal database (such as PostGIS), and realize the spatio-temporal alignment of multi-source data (time synchronization accuracy ≤ 100 ns) through the Beidou spatio-temporal benchmark to achieve the spatio-temporal unity of multi-source data. Use a feature-level fusion algorithm (such as Kalman filtering) to eliminate sensor noise, and integrate structured data (such as facility status tables) and unstructured data (such as three-dimensional models, images) into a standardized fire prevention and control benchmark data set.

[0065] Step S103: Based on a preset fire protection code procedure, perform multi-dimensional data comparison on the fire prevention and control benchmark dataset, determine and identify abnormal parameter combinations that exceed the preset threshold, and generate an alarm signal containing spatial positioning information.

[0066] Based on a preset fire protection code procedure (such as the "Code for Fire Protection Design of Buildings"), use a rule engine (such as Drools) to perform real-time verification on multi-dimensional parameters in the benchmark dataset (such as temperature gradient, smoke concentration, gas composition ratio). Establish an abnormal parameter combination pattern library (generated by training based on historical fire data), and identify abnormal intervals that exceed the preset threshold through a pattern matching algorithm (such as the smoke concentration exceeding 500 ppm for 30 consecutive minutes and the temperature rising rate > 5°C / min). Combine with Beidou satellite positioning technology to determine the spatial coordinates of the facilities corresponding to the abnormal parameters (such as a certain floor and a certain fire compartment), generate an alarm signal containing the floor number and equipment identification, and push it to the fire control room and the emergency command center through short message communication technology.

[0067] Step S104: According to the alarm signal, determine the area where the fire protection facilities fail, and combine with alternative prevention and control resources and a preset rescue resource distribution map to calculate the fire risk diffusion parameters.

[0068] According to the equipment failure type in the alarm signal (such as the main fire pump failure, the smoke detector malfunction), use the geographical fence and spatial analysis technology of the Beidou satellite to determine the area where the fire protection facilities fail, obtain the Beidou positioning coordinates and real-time status of alternative prevention and control resources in the surrounding area, and match the preset failure weight parameters (reflecting the impact of the equipment on fire prevention and control, such as the main pump failure weight coefficient is 0.8). Based on the failure location coordinates, obtain the types, locations, and real-time availability status of alternative prevention and control resources in the surrounding area (such as adjacent fire hydrants, fire extinguishers) through spatial query, and generate a coordinate set of the prevention and control coverage gap area. Extract the response path node data (including road topology, traffic speed, resource transportation rate) corresponding to the gap area from the preset rescue resource distribution map constructed based on the Beidou electronic map, use the path weight algorithm to calculate the correlation matrix between the nodes and the gap area, and finally output the risk level (1-5 levels) and the diffusion boundary coordinates through a spatio-temporal risk diffusion model (such as cellular automata).

[0069] Step S105: Generate a graded early warning instruction according to the fire risk diffusion parameters, and construct an electronic operation map containing the optimal rescue path.

[0070] According to the risk diffusion parameters (such as risk level 4 and diffusion speed 2 m / min), trigger the corresponding level of warning instructions (such as the first-level emergency response), and dynamically display the risk diffusion range through an electronic map. Integrate the three-dimensional risk field (including heat radiation intensity and smoke concentration) with real-time road condition data (traffic control points and obstacle coordinates) to construct a path weight map containing road passage costs (time and distance) and fire threat values. Use the hierarchical Dijkstra algorithm to traverse the weight map and generate an optimal rescue path point sequence that avoids high-risk areas and traffic congestion points. Finally, use the Beidou visualization engine to overlay the rescue trajectory with the contour lines of the dynamic risk field and the markings of rescue resource distribution (such as the location of fire stations and water source points) to form a visual electronic combat map, supporting real-time dispatching and dynamic path adjustment by the emergency command center.

[0071] The above-mentioned intelligent network method for fire prevention and control based on Beidou satellite navigation first obtains the real-time operation data of fire protection facilities in the building and scans the building structure through a three-dimensional imaging device to generate a three-dimensional digital model; secondly, fuses the real-time operation data, the three-dimensional digital model and the preset environmental parameters to form a fire prevention and control benchmark data set; furthermore, conducts multi-dimensional data comparison on the benchmark data set based on the preset fire protection specification procedures, identifies abnormal parameter combinations exceeding the preset thresholds, and generates an alarm signal with spatial positioning information; then, determines the area where the fire protection facilities fail according to the alarm signal, combines the alternative prevention and control resources and the preset rescue resource distribution map, and calculates the fire risk diffusion parameters; finally, generates hierarchical warning instructions according to the risk diffusion parameters and constructs an electronic combat map containing the optimal rescue path. It provides all-round and accurate basic data support for fire prevention and control, can timely detect abnormalities of fire protection facilities and risk hazards, improve the timeliness and accuracy of early warning, optimize the rescue path, improve the efficiency of fire handling, and thus enhance the overall fire prevention and control ability.

[0072] In one of the embodiments, fusing the real-time operation data, the three-dimensional digital model and the preset environmental parameters to obtain a fire prevention and control benchmark data set may include the following steps:

[0073] Step S201, extract the fire passage topology according to the road topology data in the preset environmental parameters; the fire passage topology includes node spacing and passing height.

[0074] Step S202, map the water source coordinates and pressure data in the preset environmental parameters to the fire passage topology to generate a weighted path network.

[0075] Step S203, based on the building structure model in the three-dimensional digital model and the weighted path network, use a path planning algorithm to generate a dynamic evacuation path; the building structure model includes wall thickness and material parameters.

[0076] Step S204: Superimpose and analyze the temperature field distribution in the real-time operation data with the dynamic evacuation path, and output the path availability matrix under the influence of heat radiation.

[0077] Step S205: Update the emergency response parameters according to the path availability matrix to obtain the fire prevention and control benchmark data set.

[0078] Specifically, first, extract the fire channel topological structure from the road topological data of the preset environmental parameters, clarify key parameters such as node spacing and passing height, and form the spatial skeleton of the fire channel; second, map the water source coordinates and pressure data in the preset environmental parameters to the fire channel topology, and generate a weighted path network with the water source location as the node, the pressure value and the passing distance as the weights to realize the spatial association of fire resources and channels; third, combine the building structure model (including wall thickness, material parameters, etc.) in the three-dimensional digital model, and use the path planning algorithm to generate a dynamic evacuation path in the weighted path network to ensure that the path meets the building structure safety requirements; then, perform a spatial superposition analysis of the temperature field distribution in the real-time operation data and the dynamic evacuation path, calculate the temperature threshold exceeding situation in different path areas through the heat radiation model, and output the availability matrix reflecting the path passing safety; finally, adjust the emergency response parameters (such as evacuation route priority, rescue force deployment plan) according to the path availability matrix to form a fire prevention and control benchmark data set containing multi-dimensional information such as channel topology, resource distribution, and path safety.

[0079] In this embodiment, by integrating environmental parameters, building structures, and real-time monitoring data, a refined fire prevention and control data foundation is constructed. Through the weighted mapping of the fire channel topology and water source data, the visualization and computability of fire resource distribution are realized, providing a quantitative basis for emergency dispatching; the dynamic evacuation path generated in combination with building structure parameters ensures that the path planning meets the actual spatial constraints and improves the feasibility of the evacuation plan; the superposition analysis of the temperature field and path availability enables the system to evaluate the impact of the fire on the evacuation path in real time, dynamically update the emergency response strategy, and enhance the timeliness and accuracy of fire prevention and control.

[0080] In one of the embodiments, as Figure 2 shown, based on the preset fire protection specification program, perform multi-dimensional data comparison on the fire prevention and control benchmark data set, judge and identify abnormal parameter combinations exceeding the preset threshold, and generate an alarm signal including spatial positioning information, which may include the following steps:

[0081] Step S301: Obtain the multi-dimensional parameter sequence in the fire prevention and control benchmark data set; the multi-dimensional parameter sequence includes temperature gradient, smoke concentration, and gas component ratio.

[0082] Step S302: Match the multi-dimensional parameter sequence with the parameter combination patterns in the preset fire protection specification procedures; the parameter combination patterns are generated by training with Beidou historical monitoring data and historical fire incident data.

[0083] Step S303: Extract the abnormal parameter intervals that exceed the preset thresholds in the parameter combination patterns; the abnormal parameter intervals include the intersection fluctuation ranges of at least two parameters.

[0084] Step S304: Combine the topological graph of the device nodes corresponding to the abnormal parameter intervals and use Beidou indoor positioning technology to generate spatial positioning information including floor numbers and device identifiers.

[0085] Step S305: Input the spatial positioning information into the dynamic threshold model to obtain the dynamically updated threshold based on environmental variables.

[0086] Among them, if the duration of the abnormal parameter interval exceeds the dynamic threshold, an alarm signal is triggered and the spatial positioning information is bound.

[0087] First, extract the multi-dimensional parameter sequence from the fire prevention benchmark dataset, covering real-time monitoring data such as temperature gradient, smoke concentration, and gas component ratio; secondly, match the multi-dimensional parameter sequence with the parameter combination patterns in the preset fire protection specification procedures, which are generated by training with Beidou historical monitoring data and historical fire incident data and contain typical characteristics of parameter associations in different scenarios; thirdly, identify the abnormal parameter intervals that exceed the preset thresholds in the parameter combination patterns, and this interval should include the intersection fluctuation ranges of at least two parameters (such as temperature gradient > 2°C / m and smoke concentration > 800 ppm) to exclude false alarms of single parameters; then, combine the topological graph of the device nodes corresponding to the abnormal parameters and use Beidou indoor positioning technology (such as the network connection relationship of fire protection facilities) to locate the physical space where the abnormality occurs and generate spatial positioning information including floor numbers and device identifiers; finally, input the spatial positioning information into the dynamic threshold model, which adjusts the alarm threshold in real time based on environmental variables (such as wind speed, building materials), and if the duration of the abnormal parameter interval exceeds the dynamic threshold, an alarm signal is triggered and the spatial positioning information is bound.

[0088] In this embodiment, through multi-dimensional data correlation analysis and dynamic threshold mechanism, the accuracy and reliability of fire warning are improved. Based on the parameter combination mode trained by historical data, the upgrade from single-parameter monitoring to multi-parameter correlation analysis is realized, which can more accurately identify the real fire risk; it is required that the abnormal parameter interval contains the intersection fluctuation of at least two parameters, effectively reducing the false alarm rate of a single sensor; combined with the device node topology map to generate spatial positioning information, ensuring that the alarm signal has an accurate physical location indication, which is convenient for firefighters to respond quickly; the dynamic threshold model introduces environmental variables to adjust the alarm threshold in real time, enabling the system to adapt to the monitoring requirements under different building structures and meteorological conditions, and avoiding missed alarms or false alarms caused by static thresholds; the finally formed alarm mechanism realizes the full-process intelligence of "data acquisition - pattern matching - spatial positioning - dynamic verification", provides key technical support for early fire intervention, and improves the timeliness and pertinence of fire emergency response.

[0089] In one of the embodiments, according to the alarm signal, the fire-fighting facility failure area is determined, and combined with the alternative prevention and control resources and the preset rescue resource distribution map, the fire risk diffusion parameter can be calculated, which may include the following steps:

[0090] Step S401, matching the corresponding preset failure weight parameter according to the device failure type in the alarm signal; the preset failure weight parameter is dynamically adjusted based on the historical failure frequency of the device recorded by Beidou.

[0091] Step S402, obtaining the list of alternative prevention and control resource identifiers around according to the position coordinates in the alarm signal; the list of alternative prevention and control resource identifiers includes the resource type and the real-time available status.

[0092] Step S403, generating a coordinate set of the prevention and control coverage gap area based on the failure weight parameter and the list of alternative resource identifiers.

[0093] Step S404, extracting the response path node data corresponding to the coordinate set of the gap area in the preset rescue resource distribution map; the response path node data includes the road topology and the resource transportation rate.

[0094] Step S405, calculating the correlation matrix between the response path node data and the coordinate set of the gap area by using the path weight algorithm.

[0095] Step S406, inputting the correlation matrix into the spatio-temporal risk diffusion model to obtain the fire risk diffusion parameter; the fire risk diffusion parameter includes the risk level and the diffusion boundary coordinates.

[0096] Specifically, when an alarm signal containing the device failure type and location coordinates is received, the calculation of the fire risk diffusion parameters will be carried out according to the following steps. First, according to the device failure type in the alarm signal, the corresponding failure weight parameter is matched from the preset rules, and this parameter reflects the impact degree of the device failure on fire prevention and control. Then, relying on the location coordinates in the alarm signal and with the help of tools such as geographic information systems, a list of identifiers of available alternative prevention and control resources in the vicinity is obtained. This list details the resource types (such as fire extinguishers, fire hydrants, etc.) and the real-time available status. After that, considering the failure weight parameter and the situation of alternative resources comprehensively, through spatial analysis and calculation, a coordinate set of the prevention and control coverage gap areas is generated. These areas are places where the current prevention and control forces are difficult to effectively cover. Then, the response path node data corresponding to the coordinate set of the gap areas is extracted from the preset rescue resource distribution map. This data contains information such as road topology and resource transportation rate. The path weight algorithm is used to calculate the response path node data and the coordinate set of the gap areas to obtain the correlation matrix, which reflects the degree of tight correlation between each rescue path and the gap areas. Finally, the correlation matrix is input into the spatio-temporal risk diffusion model, which will combine time and space factors and output the fire risk diffusion parameters, including the risk level and the diffusion boundary coordinates.

[0097] On the one hand, through the comprehensive consideration of the device failure weight parameter and alternative resources, the weak areas of prevention and control can be accurately located, avoiding blind investment of rescue forces and improving the resource utilization efficiency. On the other hand, by using the path weight algorithm and the spatio-temporal risk diffusion model, the risk level and diffusion boundary of the fire can be accurately predicted, providing a reliable basis for the fire control department to formulate scientific rescue strategies and path planning, helping to control the spread of the fire in time and reduce the losses caused by the fire.

[0098] In one of the embodiments, the risk level can be calculated by the following formula:

[0099]

[0100] Q(t)=[q1(t),q2(t),...,q m (t)] T

[0101] Where L represents the finally output fire risk level, k represents the category index of the risk level, μ k (·) represents the membership function of the k-level risk, Q(t) represents the risk cumulative value vector of each gap area at time t, m represents the total number of gap areas, and q m (t) represents the risk cumulative value of the mth gap area at time t.

[0102] Based on the risk accumulation values and their spatial distributions in each gap area, through L1 norm summation and mean calculation, this embodiment realizes the standardized measurement of the overall risk scale, avoids scale deviation caused by differences in the number of regions, and makes the risk levels in different scenarios comparable. The membership function is generated by training historical fire data and can depict the fuzzy relationship between risk values and levels (such as the boundary transition between "medium risk" and "higher risk"), which conforms to the actual evolution law of fire risk. The maximum membership degree principle ensures clear results of level division and provides an intuitive decision-making basis for emergency response. The risk accumulation value Q(t) is dynamically updated with time and the progress of rescue, supporting the model to reflect the risk change trend in real time. Combining with the spatio-temporal risk diffusion model, it can achieve the upgrade from "single-point failure assessment" to "overall risk evolution analysis" and improve the dynamic response ability of fire prevention and control.

[0103] In one embodiment, a hierarchical early warning instruction is generated according to the fire risk diffusion parameter, and an electronic operation map including the optimal rescue path can be constructed, which may include the following steps:

[0104] Step S501, generating a dynamic diffusion coefficient matrix for describing the propagation probability of the fire in the spatial grid according to the fire risk diffusion parameter.

[0105] Step S502, inputting the dynamic diffusion coefficient matrix into a multi-level fire spread model to obtain a three-dimensional risk field including heat radiation intensity and smoke concentration.

[0106] Step S503, extracting the risk level boundary based on the three-dimensional risk field and triggering a warning signal corresponding to the level.

[0107] Step S504, obtaining real-time road condition data for the area covered by the warning signal; the data includes coordinates of traffic control points and obstacles.

[0108] Step S505, fusing the three-dimensional risk field and the real-time road condition data to generate a path weight map; the weight map includes the road passage cost and the fire threat value.

[0109] Step S506, traversing the path weight map using the hierarchical Dijkstra algorithm to obtain an optimal rescue trajectory with an obstacle avoidance path point sequence.

[0110] Step S507, superimposing the optimal rescue trajectory on the isopleth of the dynamic risk field and the distribution marks of rescue resources to obtain an electronic operation map.

[0111] Specifically, first, a dynamic diffusion coefficient matrix describing the probability of fire spread in a spatial grid is generated based on fire risk diffusion parameters, and the matrix elements correspond to the fire spread rates of different grid cells. Secondly, the dynamic diffusion coefficient matrix is input into a multi-level fire spread model (such as a cellular automaton model), and combined with building structure parameters and environmental variables, a three-dimensional risk field including heat radiation intensity and smoke concentration distribution is simulated and generated to realize the visualization of the space and intensity of fire spread. Thirdly, based on the threshold division of the three-dimensional risk field, the boundaries of different risk levels (such as low-risk areas and high-risk areas) are extracted to trigger warning signals of corresponding levels. Subsequently, real-time road condition data of the area covered by the warning signal is obtained, including traffic control point coordinates, obstacle distribution, etc., for evaluating the passing efficiency of the rescue route. The fire threat value in the three-dimensional risk field (such as the influence degree of heat radiation on rescue vehicles) is fused with the road passing cost in the real-time road condition data (such as travel time, distance) to generate a path weight map containing multi-dimensional weights. The hierarchical Dijkstra algorithm is used to traverse this weight map, and the search space is optimized through hierarchical processing (such as by floor, road level) to generate an optimal rescue trajectory with an obstacle avoidance path point sequence that avoids high-risk areas and traffic obstacles. Finally, the optimal rescue trajectory is spatially superimposed with the isopleth of the dynamic risk field (such as the isopleth of heat radiation intensity) and the rescue resource distribution markers (such as the location of fire stations, water source points) to form an electronic operation map integrating risk situation, path planning, and resource distribution.

[0112] In this embodiment, through the fusion of multi-source data and the optimization of intelligent algorithms, the scientificity and effectiveness of rescue command are significantly improved. The combination of the dynamic diffusion coefficient matrix and the multi-level fire model realizes the refined simulation of fire spread and provides a quantitative basis for warning classification; the fusion weight map of real-time road conditions and the three-dimensional risk field enables path planning to take into account both fire threats and passing efficiency, avoiding rescue teams from getting into high-risk areas or traffic jams; the hierarchical Dijkstra algorithm reduces the computational complexity through spatial stratification, improves the path search efficiency, and ensures the rapid generation of a feasible trajectory in an emergency scenario; the electronic operation map integrates multi-dimensional information in a visual form, provides the command center with a global situation awareness ability, supports the dynamic scheduling of rescue resources and the real-time adjustment of paths, thereby shortening the response time and improving the success rate of fire handling.

[0113] In one of the embodiments, superimposing the optimal rescue trajectory with the isopleth of the dynamic risk field and the rescue resource distribution markers to obtain an electronic operation map may include the following steps:

[0114] Step S601, perform spatial registration according to the risk intensity gradient of the isopleth of the dynamic risk field and the path node coordinates of the optimal rescue trajectory to obtain the registration data of the risk field and the trajectory.

[0115] Step S602: Extract the resource type code and the real-time available quantity marked by the rescue resource distribution, and establish a corresponding mapping relationship based on the resource type code and the risk intensity gradient.

[0116] Step S603: Calculate the fusion weight parameter of the rescue resource distribution mark and the registration data based on the mapping relationship.

[0117] Step S604: Input the fusion weight parameter into the path optimization model and output the rescue trajectory distribution map.

[0118] Step S605: Generate a resource scheduling instruction according to the rescue trajectory distribution map, and update the layer data to obtain an electronic combat map.

[0119] The electronic combat map optimization method based on the dynamic risk field and rescue resources includes the following steps: First, perform spatial registration on the risk intensity gradient (such as heat radiation intensity, smoke concentration level) of the dynamic risk field isolines and the path node coordinates of the optimal rescue trajectory. Through coordinate calibration and scale unification, generate the registration data of the risk field and the trajectory to ensure their precise correspondence in the geographical space. Second, extract the resource type code (such as fire truck type, water source category) and the real-time available quantity in the rescue resource distribution mark, and establish a mapping relationship based on the resource type code and the risk intensity gradient (such as high-risk areas require heavy fire trucks) to clarify the resource types applicable to different risk-level areas. Then, calculate the fusion weight parameter of the rescue resource distribution mark and the registration data according to the above mapping relationship. The weight value reflects the response priority of the resource to a specific risk area (such as the water source weight corresponding to a high-risk area is higher than that of an ordinary area). Input the fusion weight parameter into the path optimization model, combine the path passing cost and the risk avoidance requirement, and output the rescue trajectory distribution map including the resource scheduling priority. Finally, generate a resource scheduling instruction (such as deploying the fire truck near the high-risk area to the specified node) according to the rescue trajectory distribution map, and update the layer data of the electronic combat map to achieve the dynamic linkage of the risk situation, rescue path, and resource distribution.

[0120] In this embodiment, through the deep integration of the risk field, rescue trajectory, and resource distribution, the decision-making support ability of the electronic combat map is improved. The overall beneficial effects are as follows: The spatial registration mechanism ensures the geographical consistency of risk assessment and path planning, avoiding decision-making biases caused by data misalignment; the mapping relationship between resource types and risk intensities realizes the refined scheduling of rescue resources, enabling high-risk areas to obtain matching disposal forces preferentially; the combination of the fusion weight parameter and the path optimization model supports multi-objective balance (such as minimizing rescue time and maximizing resource utilization efficiency), generating a rescue trajectory with greater practical value; the dynamically updated electronic combat map provides the command center with a "one-map" real-time situation awareness, facilitating the rapid adjustment of rescue strategies, optimizing resource allocation, enhancing the coordination and accuracy of emergency responses, and ultimately enhancing the overall effectiveness of the fire prevention and control system.

[0121] In one of the embodiments, as Figure 3 shown, this application also provides a fire prevention and control intelligent network system based on Beidou satellite navigation. The system may include:

[0122] A data acquisition and fusion module 701, configured to obtain real-time operation data of fire protection facilities in a building; scan the building structure using a three-dimensional imaging device to generate a three-dimensional digital model; and also fuse the real-time operation data, the three-dimensional digital model, and preset environmental parameters to obtain a fire prevention and control reference data set.

[0123] An intelligent monitoring and alarm module 702, configured to perform multi-dimensional data comparison on the fire prevention and control reference data set based on a preset fire protection specification program, determine and identify abnormal parameter combinations exceeding a preset threshold, and generate an alarm signal including spatial positioning information.

[0124] A risk assessment and planning module 703, configured to determine the area where fire protection facilities fail according to the alarm signal, combine alternative prevention and control resources and a preset rescue resource distribution map, calculate fire risk diffusion parameters; and also generate a hierarchical early warning instruction according to the fire risk diffusion parameters, and construct an electronic combat map including the optimal rescue path.

[0125] The above-mentioned intelligent network system for fire prevention and control based on Beidou satellite navigation. The data acquisition and fusion module is responsible for the acquisition and integration of multi-source data. It collects the operation data of fire-fighting facilities in real time through sensors, generates a three-dimensional digital model of the building using a three-dimensional imaging device, and fuses the real-time data, model, and preset environmental parameters into a fire prevention and control benchmark data set. The intelligent monitoring and alarm module conducts multi-dimensional data comparison on the benchmark data set based on preset fire protection specifications. By matching parameter combination patterns, identifying abnormal parameter ranges, and combining spatial positioning technology, it generates an alarm signal containing floor numbers and equipment identifiers. The risk assessment and planning module determines the areas where fire-fighting facilities fail based on the alarm signal, combines alternative prevention and control resources with the preset rescue resource distribution map, calculates the fire risk diffusion parameters, and generates a hierarchical early warning instruction accordingly. It constructs an electronic operation map containing the optimal rescue path through intelligent algorithms. It provides all-round and accurate basic data support for fire prevention and control, can timely detect abnormalities and risk hidden dangers of fire-fighting facilities, improve the timeliness and accuracy of early warning, optimize the rescue path, improve the efficiency of fire handling, and thus enhance the overall fire prevention and control ability.

[0126] It should be understood that although the steps in the flowcharts involved in the above-described embodiments are sequentially shown according to the arrows, these steps do not necessarily have to be executed in the order indicated by the arrows. Unless otherwise clearly stated in this article, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, at least some of the steps in the flowcharts involved in the above-described embodiments may include multiple steps or multiple stages. These steps or stages do not necessarily have to be executed at the same time, but can be executed at different times. The execution order of these steps or stages does not necessarily have to be sequential, but can be executed alternately or in turn with at least some of the steps or stages in other steps or other steps.

[0127] In one embodiment, a computer device is provided, including a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, it implements the steps of the above-mentioned method and system for the intelligent network for fire prevention and control based on Beidou satellite navigation.

[0128] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, it implements the steps in the above-mentioned method embodiments.

[0129] For the device embodiments, since they basically correspond to the method embodiments, the relevant parts can be referred to the partial descriptions of the method embodiments. The device embodiments described above are merely illustrative. The components described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the present disclosure solution. A person of ordinary skill in the art can understand and implement it without creative efforts.

[0130] The above embodiments only represent several implementation manners of the embodiments of the present application. The description is relatively specific and detailed, but it should not be construed as a limitation on the patent scope of the embodiments of the application. It should be noted that for those of ordinary skill in the art, without departing from the concept of the embodiments of the present application, several modifications and improvements can still be made, and these all belong to the protection scope of the embodiments of the present application.

Claims

1. A fire prevention and control intelligent network method based on Beidou satellite navigation, characterized in that The method includes: Obtaining real-time operation data of fire protection facilities in a building; Scanning the building structure using a three-dimensional imaging device to generate a three-dimensional digital model; Fusing the real-time operation data, the three-dimensional digital model, and preset environmental parameters to obtain a fire prevention and control benchmark data set; Based on a preset fire protection specification program, performing multi-dimensional data comparison on the fire prevention and control benchmark data set, identifying abnormal parameter combinations that exceed the preset threshold, and generating an alarm signal including spatial positioning information; Determining the area where the fire protection facilities fail according to the alarm signal, and combining alternative prevention and control resources and a preset rescue resource distribution map to calculate the fire risk diffusion parameter; Generating a hierarchical warning instruction according to the fire risk diffusion parameter, and constructing an electronic operation map including the optimal rescue path.

2. The method according to claim 1, wherein The fusing the real-time operation data, the three-dimensional digital model, and preset environmental parameters to obtain a fire prevention and control benchmark data set includes: Extracting the fire passage topology according to the road topology data in the preset environmental parameters; The fire passage topology includes node spacing and passing height; Mapping the water source coordinates and pressure data in the preset environmental parameters to the fire passage topology to generate a weighted path network; Based on the building structure model and the weighted path network in the three-dimensional digital model, using a path planning algorithm to generate a dynamic evacuation path; The building structure model includes wall thickness and material parameters; Performing superposition analysis on the temperature field distribution in the real-time operation data and the dynamic evacuation path, and outputting a path availability matrix under the influence of thermal radiation; Updating the emergency response parameters according to the path availability matrix to obtain a fire prevention and control benchmark data set.

3. The method according to claim 1, wherein The performing multi-dimensional data comparison on the fire prevention and control benchmark data set based on a preset fire protection specification program, identifying abnormal parameter combinations that exceed the preset threshold, and generating an alarm signal including spatial positioning information includes: Obtaining a multi-dimensional parameter sequence in the fire prevention and control benchmark data set; The multi-dimensional parameter sequence includes temperature gradient, smoke concentration, and gas composition ratio; Matching the multi-dimensional parameter sequence with the parameter combination pattern in the preset fire protection specification program; The parameter combination pattern is generated by training with Beidou historical monitoring data and historical fire event data; Extracting the abnormal parameter interval that exceeds the preset threshold in the parameter combination pattern; The abnormal parameter interval includes the intersection fluctuation range of at least two parameters; Combining the equipment node topology diagram corresponding to the abnormal parameter interval and using Beidou indoor positioning technology to generate spatial positioning information including floor number and equipment identification; Inputting the spatial positioning information into a dynamic threshold model to obtain a dynamic threshold updated based on environmental variables; Wherein, if the duration of the abnormal parameter interval exceeds the dynamic threshold, an alarm signal is triggered and the spatial positioning information is bound.

4. The method according to claim 1, wherein The determining the area where the fire protection facilities fail according to the alarm signal, and combining alternative prevention and control resources and a preset rescue resource distribution map to calculate the fire risk diffusion parameter includes: Match corresponding preset failure weight parameters according to the device failure types in the alarm signal; the preset failure weight parameters are dynamically adjusted based on the historical failure frequencies of the devices recorded by Beidou. Obtain a list of alternative prevention and control resource identifiers in the vicinity based on the position coordinates in the alarm signal; the list of alternative prevention and control resource identifiers includes resource types and real-time availability status. Generate a coordinate set of the prevention and control coverage gap area based on the failure weight parameters and the list of alternative resource identifiers. Extract response path node data corresponding to the coordinate set of the gap area from a preset rescue resource distribution map; the response path node data includes road topology and resource transportation rates. Calculate the correlation matrix between the response path node data and the coordinate set of the gap area using a path weight algorithm. Input the correlation matrix into a spatio-temporal risk diffusion model to obtain fire risk diffusion parameters; the fire risk diffusion parameters include a risk level and diffusion boundary coordinates.

5. The method according to claim 4, characterized in that The risk level is calculated through the following formula: Q(t) = [q1(t), q2(t),..., q m (t)] T Among them, L represents the final output fire risk level, k represents the category index of the risk level, and μ k (·) represents the membership function of the k-th level risk, Q(t) represents the risk cumulative value vector of each notch area at time t, m represents the total number of notch areas, and q m (t) represents the risk cumulative value of the m-th notch area at time t.

6. The method according to claim 1, wherein Generating a hierarchical early warning instruction according to the fire risk diffusion parameters and constructing an electronic operation map including an optimal rescue path, including: Generate a dynamic diffusion coefficient matrix for describing the propagation probability of the fire in the spatial grid according to the fire risk diffusion parameters. Input the dynamic diffusion coefficient matrix into a multi-level fire spread model to obtain a three-dimensional risk field including heat radiation intensity and smoke concentration. Extract the risk level boundary based on the three-dimensional risk field and trigger early warning signals at corresponding levels. Obtain real-time road condition data in the area covered by the early warning signal; the data includes traffic control points and obstacle coordinates. Fuse the three-dimensional risk field and the real-time road condition data to generate a path weight map; the weight map includes road passage costs and fire threat values. Use the hierarchical Dijkstra algorithm to traverse the path weight map to obtain an optimal rescue trajectory with an obstacle avoidance path point sequence. Overlay the optimal rescue trajectory with the isocontours of the dynamic risk field and the rescue resource distribution marks to obtain an electronic operation map.

7. The method according to claim 6, characterized in that, Overlaying the optimal rescue trajectory with the isocontours of the dynamic risk field and the rescue resource distribution marks to obtain an electronic operation map includes: Perform spatial registration according to the risk intensity gradient of the isocontours of the dynamic risk field and the path node coordinates of the optimal rescue trajectory to obtain registration data of the risk field and the trajectory. Extract the resource type codes and real-time available quantities of the rescue resource distribution marks, and establish a corresponding mapping relationship based on the resource type codes and the risk intensity gradient. Calculate the fusion weight parameters between the rescue resource distribution marks and the registration data based on the mapping relationship. Input the fusion weight parameters into a path optimization model and output a rescue trajectory distribution map. Generate a resource scheduling instruction according to the rescue trajectory distribution map and update the layer data to obtain an electronic operation map.

8. The intelligent network system for fire prevention and control based on Beidou satellite navigation is characterized in that The system includes: A data acquisition and fusion module, configured to obtain real-time operation data of fire protection facilities in a building; scan the building structure using a three-dimensional imaging device to generate a three-dimensional digital model; and also fuse the real-time operation data, the three-dimensional digital model, and preset environmental parameters to obtain a fire prevention and control benchmark data set; An intelligent monitoring and alarm module, configured to perform multi-dimensional data comparison on the fire prevention and control benchmark data set based on a preset fire protection specification program, determine and identify abnormal parameter combinations exceeding a preset threshold, and generate an alarm signal including spatial positioning information; A risk assessment and planning module, configured to determine a fire protection facility failure area according to the alarm signal, combine alternative prevention and control resources and a preset rescue resource distribution map, and calculate fire risk diffusion parameters; and also generate a graded early warning instruction according to the fire risk diffusion parameters and construct an electronic operation map including an optimal rescue path.

9. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the method according to any one of claims 1 to 7.

Images