Smart city fire extinguishing system, method and medium based on internet of things large model

Abstract

The embodiment of the application provides a kind of based on Internet of Things big model's wisdom city fire-fighting automatic fire extinguishing system, method and medium, belong to city fire-fighting technical field.The system includes emergency supervision management platform and emergency supervision sensor network platform, emergency supervision management platform is configured as: obtaining emergency monitoring data;Determine the emergency prevention data of the prevention area based on emergency monitoring data and regional characteristic data;Determine emergency control parameters based on emergency prevention data;Based on emergency control parameters, send fire extinguishing control signals to fire extinguishing device installed in the prevention area through the emergency supervision sensor network platform, to drive fire extinguishing device to execute emergency fire extinguishing according to emergency control parameters.The system can improve the speed of disaster response and resource utilization efficiency, and then improve the fire extinguishing efficiency and reduce the disaster loss.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of urban fire fighting, and in particular to a smart city fire fighting automatic extinguishing system, method and medium based on an Internet of Things large model. BACKGROUND

[0002] With the high concentration of urban population and the continuous rise of building density, urban fires often show the characteristics of fast spreading speed, strong destructive nature and multiple secondary hazards. For example, in a large commercial complex, if the fire source is not accurately located, on the one hand, it is easy to cause resource waste, and on the other hand, it may lead to rapid spread of the fire to the adjacent area. In densely populated areas, the delay of manual monitoring response may lead to rapid deterioration of the disaster situation. Therefore, the response efficiency and accuracy of urban fire safety management are facing severe challenges.

[0003] In view of this, it is urgent to provide a smart city fire fighting automatic extinguishing system, method and medium based on an Internet of Things large model, to improve the disaster response speed and resource utilization efficiency, and thus improve the extinguishing efficiency and reduce the disaster loss. SUMMARY

[0004] One or more embodiments of the present application provide a smart city fire fighting automatic extinguishing method based on an Internet of Things large model, the method comprising: acquiring emergency monitoring data; determining emergency prevention data of a prevention area based on the emergency monitoring data and regional characteristic data; determining emergency control parameters based on the emergency prevention data, the emergency control parameters including prevention start conditions, fire extinguishing targets and prevention fire extinguishing parameters; based on the emergency control parameters, sending fire extinguishing control signals to fire extinguishing devices installed in the prevention area to drive the fire extinguishing devices to perform emergency fire extinguishing according to the emergency control parameters, including: controlling the rotation of the spray head of the fire extinguishing device to face the fire extinguishing target; in response to the prevention start conditions being met, starting the fire extinguishing device for fire extinguishing based on the prevention fire extinguishing parameters with a preset coverage area and a preset injection flow rate.

[0005] One or more embodiments of the present application provide a smart city fire fighting automatic extinguishing system based on an Internet of Things large model. The system comprises an emergency supervision management platform, which is configured to execute a smart city fire fighting automatic extinguishing method based on an Internet of Things large model according to any one of the embodiments of the present application.

[0006] One or more embodiments of the present application provide a computer readable storage medium, which stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes a smart city fire fighting automatic extinguishing method based on an Internet of Things large model according to any one of the embodiments of the present application.

[0007] The beneficial effects of the present invention include, but are not limited to: the smart city fire-fighting automatic extinguishing method and system based on the above-mentioned Internet of Things big model can dynamically generate prevention levels and prevention characteristics based on emergency monitoring information of different fire-monitoring buildings, so as to automatically control the activation of fire extinguishing devices and execute fire extinguishing according to the prevention and extinguishing parameters, reduce the risk of fire spread, improve the speed of disaster response and resource utilization efficiency, thereby improving fire extinguishing efficiency and reducing disaster losses. Attached Figure Description

[0008] The present invention will be further described by way of exemplary embodiments, which will be described in detail with reference to the accompanying drawings. These embodiments are not limiting, and in these embodiments, the same reference numerals denote the same structures, wherein:

[0009] Figure 1 This is a schematic diagram of the platform structure of a smart city fire-fighting automatic extinguishing system based on a large Internet of Things model, according to some embodiments of the present invention.

[0010] Figure 2 This is an exemplary flowchart of a smart city fire-fighting automatic extinguishing method based on an Internet of Things (IoT) big data model, according to some embodiments of the present invention.

[0011] Figure 3 This is an exemplary schematic diagram of a risk prediction model according to some embodiments of the present invention;

[0012] Figure 4 This is an exemplary schematic diagram of an effect determination model according to some embodiments of the present invention. Detailed Implementation

[0013] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are merely some examples or embodiments of the present invention. For those skilled in the art, these drawings can be applied to other similar scenarios without creative effort. Unless obvious from the context or otherwise specified, the same reference numerals in the drawings represent the same structures or operations.

[0014] It should be understood that the terms "system," "device," and / or "module" used herein are one way to distinguish different components, elements, parts, sections, or assemblies at different levels. However, if other terms can achieve the same purpose, they may be replaced by other expressions.

[0015] As indicated in this invention and the claims, unless the context clearly indicates otherwise, the words "a," "an," "an," and / or "the" do not specifically refer to the singular and may also include the plural. Generally speaking, the terms "comprising" and "including" only indicate the inclusion of explicitly identified steps and elements, which do not constitute an exclusive list, and the method or apparatus may also include other steps or elements.

[0016] This invention uses flowcharts to illustrate the operations performed by the system according to embodiments of the invention. It should be understood that the preceding or following operations are not necessarily performed precisely in sequence. Instead, the steps can be processed in reverse order or simultaneously. Furthermore, other operations can be added to these processes, or one or more steps can be removed from them.

[0017] Figure 1 This is a schematic diagram of the platform structure of a smart city fire-fighting automatic extinguishing system based on an Internet of Things (IoT) big data model, according to some embodiments of the present invention.

[0018] In some embodiments, such as Figure 1 As shown, the smart city fire automatic extinguishing system 100 based on the Internet of Things big data model may include an emergency monitoring and sensing control platform 110, an emergency monitoring sensor network platform 120, an emergency monitoring management platform 130, an emergency monitoring service platform 140, and an emergency monitoring user platform 150.

[0019] The emergency monitoring and control platform 110 refers to an object platform that generates sensing information and executes control information. In some embodiments, the emergency monitoring and control platform may include monitoring devices and fire extinguishing devices.

[0020] A monitoring device refers to a device that monitors emergency monitoring data and regional characteristic data of a protected area. In some embodiments, the monitoring device may be configured as an environmental sensor, image sensor, RFID tag, etc.

[0021] Environmental sensors can include temperature sensors, smoke sensors, humidity sensors, and gas sensors, etc.

[0022] Image sensors can include cameras, infrared cameras, and other similar devices. They can monitor open flame operations and temperature distribution data.

[0023] RFID tags are used to identify the status of fire-fighting equipment (e.g., fire extinguishing devices).

[0024] Fire extinguishing devices refer to devices that perform fire extinguishing operations, such as fire extinguishers and sprinkler heads. Fire extinguishing devices may include multiple devices pre-installed inside buildings, around buildings, along roadsides, on streetlights, and / or on building exteriors.

[0025] The emergency monitoring sensor network platform 120 refers to a functional platform for managing sensor communications. The emergency monitoring sensor network platform 120 can be configured as a communication network and gateway to achieve functions such as network management, protocol management, command management, and data parsing.

[0026] In some embodiments, the emergency monitoring sensor network platform may include multiple sensor network sub-platforms, each of which corresponds to the sensor communication management of a protected area.

[0027] In some embodiments, the emergency monitoring sensor network platform 120 can interact with the emergency monitoring perception and control platform 110 and the emergency monitoring management platform 130. For example, the emergency monitoring sensor network platform 120 can receive emergency monitoring data sent by the emergency monitoring perception and control platform 110 and send it to the emergency monitoring management platform 130 for processing. As another example, the emergency monitoring sensor network platform 120 can receive emergency control parameters sent by the emergency monitoring management platform 130 and send them to the emergency monitoring perception and control platform 110 for execution.

[0028] The Emergency Supervision and Management Platform 130 refers to a comprehensive platform that coordinates the connection and collaboration between various functional platforms, gathers all information from the Internet of Things, and provides sensing management and control management functions.

[0029] In some embodiments, the emergency monitoring and management platform 130 may include a processor, a server, or a server cluster.

[0030] A processor can process data and / or information obtained from other devices or system components. Based on this data, information, and / or processing results, the processor can execute program instructions to perform one or more functions described in this invention. In some embodiments, the processor may include one or more sub-processing devices (e.g., a single-core processing device or a multi-core multi-chip processing device). By way of example only, a processor may include a central processing unit (CPU), a controller, a microprocessor, or any combination thereof. In some embodiments, the processor may include multiple modules, each of which can be used to execute different program instructions.

[0031] In some embodiments, the emergency monitoring and management platform may include a data center equipped with storage. The data center may store all data from the smart city fire automatic extinguishing system 100 based on an IoT big data model, such as historical fire-related data, emergency monitoring data, and regional characteristic data.

[0032] In some embodiments, the emergency monitoring and management platform may include multiple emergency management sub-platforms. These multiple emergency management sub-platforms may communicate with each other in a one-to-one correspondence with multiple sensor network sub-platforms.

[0033] In some embodiments, the emergency monitoring and management platform can be configured to implement the smart city fire automatic extinguishing method based on the Internet of Things big model as described in any embodiment of the present invention.

[0034] Emergency monitoring service platform 140 refers to a platform that provides emergency monitoring services to users. Emergency monitoring service platform 140 can be configured as a server, gateway, router, etc.

[0035] In some embodiments, the emergency monitoring service platform 140 can interact with the emergency monitoring management platform and the emergency monitoring user platform 150. For example, the emergency monitoring service platform 140 can receive fire-related information sent by the emergency monitoring user platform 150 and send it to the emergency monitoring management platform 130 for processing. As another example, the emergency monitoring service platform 140 can receive emergency monitoring information sent by the emergency monitoring management platform 130 and send it to the emergency monitoring user platform 150.

[0036] Fire-related information can be any information related to a fire, such as the location of the fire or the malfunction of fire-fighting equipment.

[0037] Emergency monitoring information can be any information related to fire monitoring, such as fire warnings, the location of a fire, and escape route data.

[0038] The Emergency Monitoring User Platform 150 refers to the platform that interacts with users. The Emergency Monitoring User Platform 150 can be configured as a terminal device, such as a smartphone, tablet PC, or smartwatch.

[0039] In some embodiments, users can view fire monitoring information (e.g., fire warnings, resource status, etc.) through the emergency monitoring user platform. In some embodiments, users can upload fire-related information (e.g., emergency events such as fire location, equipment failure, etc.) to the emergency monitoring user platform.

[0040] It should be noted that the above description of the smart city fire automatic extinguishing system 100 based on the Internet of Things big data model is for ease of description only and should not limit the invention to the scope of the embodiments described.

[0041] Figure 2 This is an exemplary flowchart of a smart city fire-fighting automatic extinguishing method based on an Internet of Things (IoT) big data model, according to some embodiments of the present invention. In some embodiments, process 200 of the smart city fire-fighting automatic extinguishing method based on an IoT big data model can be executed by an emergency monitoring and management platform 130 or a processor. See [link to platform details] for more information. Figure 1 And related explanations. For example... Figure 2 As shown, the process 200 of the smart city fire automatic extinguishing method based on the Internet of Things big model includes the following steps.

[0042] Step 210: Obtain emergency monitoring data.

[0043] Emergency monitoring data refers to data that reflects whether a fire has occurred at the monitored site. For example, whether there are flames on the exterior walls of a building, or whether the temperature has risen abnormally.

[0044] The monitoring target refers to the pre-defined building components that require fire monitoring. For example, the walls of a building.

[0045] In some embodiments, emergency monitoring data may include image data and temperature data of the monitored object. For example, image data may include wall image data of a building, and temperature data may include wall temperature distribution data.

[0046] In some embodiments, the processor can acquire emergency monitoring data monitored by an emergency monitoring perception and control platform (e.g., a monitoring device) through an emergency monitoring sensor network platform. This data may include image data acquired by an image sensor and temperature data acquired by an environmental sensor. The processor may acquire emergency monitoring data periodically in a first cycle. Further details regarding the first cycle can be found in the description of step 220.

[0047] Step 220: Based on emergency monitoring data and regional characteristic data, determine the emergency prevention data for the prevention area.

[0048] Regional characteristic data refers to data that reflects the characteristics of buildings within a protected area.

[0049] A protected area refers to a pre-defined area that requires fire prevention measures. This could be a single building or multiple buildings within a region. A protected area may include multiple monitored objects, such as multiple walls within a building.

[0050] In some embodiments, regional feature data may include building structural feature data and wall feature data. Building structural feature data refers to data characterizing the distribution of buildings. For example, building structural feature data includes the layout, design, location, and density of buildings. Wall feature data refers to data characterizing the features of the monitored object. For example, wall feature data includes the wall thickness, wall area, and material type of the building.

[0051] In some embodiments, the government or enterprise may collect regional feature data and store it in the data center of the emergency monitoring and management platform, and the processor may retrieve the regional feature data through the data center.

[0052] Emergency preparedness data refers to data reflecting the fire prevention status of buildings within a protected area. In some embodiments, emergency preparedness data may include prevention characteristics and prevention levels.

[0053] The fire prevention level refers to the degree of fire prevention required. The higher the fire prevention level, the greater the degree of fire prevention required, meaning that the building needs to be monitored more frequently.

[0054] Fire prevention features refer to fire ignition points that require fire prevention (e.g., high-risk fire ignition points). Examples include locations within walls where potential fire ignition points exist, and building exterior walls with fire resistance below a threshold. Fire prevention features may also include the number of fire ignition points.

[0055] In some embodiments, the processor can determine the level of protection in a variety of ways based on emergency monitoring data and regional characteristic data.

[0056] In some embodiments, the processor can determine the security level by matching wall feature data and wall location in a first vector database.

[0057] The first vector database is a pre-defined database containing multiple reference protection feature vectors and corresponding protection tags. The processor can construct reference protection feature vectors based on wall feature data and wall locations from a large amount of historical or experimental data in the data center, and use the fire resistance capability of the reference wall corresponding to the reference protection feature vector as the protection tag.

[0058] The location of a wall refers to its position within a building.

[0059] Fire resistance of a wall refers to its ability to resist fire. Reference fire resistance can be determined based on historical data of the rate of fire ignition on the exterior wall and the degree of damage to the wall before and after a fire. For example, the higher the rate of fire ignition and the greater the degree of damage, the lower the reference fire resistance. The degree of wall damage can be measured by both visual and structural damage.

[0060] In some embodiments, the processor can construct a fire prevention feature vector based on wall feature data and wall location; match the fire prevention feature vector in a first vector database to determine the wall's fire resistance capability; and determine the fire prevention level based on the wall's fire resistance capability. The fire prevention level is negatively correlated with the wall's fire resistance capability. The processor can search the first vector database for the fire prevention label corresponding to the reference fire prevention feature vector with the highest similarity (e.g., smallest vector distance) to determine the wall's fire resistance capability.

[0061] In some embodiments, the processor can determine prevention characteristics in a variety of ways based on emergency monitoring data and regional feature data.

[0062] In some embodiments, the processor may determine high-risk ignition points based on image data and temperature data, and add the high-risk ignition points to the prevention features to determine the prevention features.

[0063] In some embodiments, the processor can acquire wall appearance features based on image data; acquire temperature distribution features based on temperature data; determine high-risk ignition points of the monitored object based on the wall appearance features and temperature distribution features; and add the high-risk ignition points to the prevention features to determine the prevention features. The processor can repeat the above steps to continuously determine the latest protection features.

[0064] Wall appearance features refer to data characterizing the appearance of a wall. Wall appearance features may include the locations of wear points on the exterior wall and the corresponding degree of wear. In some embodiments, the processor may acquire wall appearance features based on image data using image recognition algorithms. For example, image recognition algorithms may include edge detection algorithms, trained machine learning models, etc.

[0065] Temperature distribution characteristics refer to data that characterizes the temperature distribution on a wall. Temperature distribution characteristics can include a set of temperatures at multiple locations on the object being measured.

[0066] High-risk ignition points refer to locations where fires are likely to occur. In some embodiments, the processor can identify locations where the wear level of the exterior wall exceeds a wear threshold and the temperature exceeds a high-risk temperature threshold as high-risk ignition points. In some embodiments, the processor can also perform a weighted summation of the wear level and temperature of the exterior wall, and identify locations where the weighted sum exceeds a weighted threshold as high-risk ignition points. The wear threshold, high-risk temperature threshold, and weighted threshold can be preset based on experience or manually.

[0067] In some embodiments, the processor may acquire open flame characteristics of the operation based on the first cycle and emergency monitoring data; determine the estimated fire risk based on the open flame characteristics of the operation and emergency monitoring data; and determine emergency prevention data based on the estimated fire risk.

[0068] Operational open flame characteristics refer to features related to open flames. In some embodiments, operational open flame characteristics include the location, type, scale, and duration of the open flame. The processor can identify open flames in image data within a first cycle using an image recognition algorithm to obtain operational open flame characteristics.

[0069] The first cycle refers to the preset cycle for determining emergency preparedness data. Every first cycle, the processor can acquire the emergency monitoring data within that cycle and determine the emergency preparedness data accordingly.

[0070] In some embodiments, the processor may determine the length of the first cycle based on emergency preparedness data and / or characteristics of open flames during operations.

[0071] The length of the first monitoring cycle is related to the fire resistance of the building walls within the protected area. The worse the fire resistance of the walls, the more frequently the building needs to be monitored, and therefore the shorter the first monitoring cycle.

[0072] The length of the first cycle is also related to the characteristics of open flames in the protected area. The more frequent and larger the open flames, the shorter the length of the first cycle.

[0073] In this embodiment of the invention, by using emergency prevention data and / or open flame characteristics, the length of the first cycle can be determined in a targeted manner based on the fire prevention situation and the occurrence of open flames in the prevention area, thereby determining an appropriate monitoring frequency.

[0074] Fire risk assessment refers to the quantitative evaluation of the likelihood of a fire occurring within a protected area and the degree of its potential harm.

[0075] In some embodiments, the processor can determine the estimated fire risk based on the characteristics of open flames during operations and emergency monitoring data, using a risk prediction model.

[0076] In some embodiments, the risk prediction model is a machine learning model. For example, a neural network model, a recurrent neural network (RNN) model, etc.

[0077] Figure 3 This is an exemplary schematic diagram of a risk prediction model according to some embodiments of the present invention. In some embodiments, such as Figure 3 As shown, the inputs of the risk prediction model 320 may include the open flame characteristics 311 of operation of A in the previous first cycle, the fire resistance of the wall 312, emergency monitoring data 313, historical maintenance records 314 and historical fire records 315, and the output of the risk prediction model 320 may include the predicted fire risk 330.

[0078] More information on open flame characteristics, fire resistance of walls, and emergency monitoring data can be found in [link to relevant documentation]. Figure 2 And its related descriptions.

[0079] Historical maintenance records refer to the maintenance and inspection records of fire extinguishing devices or open flame devices in historical data. Open flame devices are devices that produce open flames, such as gas stoves. These devices are installed within the protected area. Historical fire records refer to fire records in historical data (e.g., fire location, scale, etc.) and records of historical emergency control parameters of fire extinguishing devices during fires. Historical maintenance records and historical fire records can be obtained from historical data stored in the data center. The estimated fire risk includes the fire location, scale, and corresponding probability of occurrence at each time point within the next first period (B) after period A. Periods A and B are two adjacent periods.

[0080] In some embodiments, the risk prediction model can be trained based on training data. In some embodiments, the processor can acquire multiple first training samples with a first label to form a first training sample set, and perform multiple rounds of iteration based on the first training sample set.

[0081] The first training sample may include the open flame characteristics of sample operations, the fire resistance of sample walls, sample emergency monitoring data, sample historical maintenance records, and sample historical fire records from the previous first period in historical data. The first label may be the location, scale, and corresponding circumstances of a fire recorded in the next first period corresponding to the first training sample. The processor can mark the occurrence of open flames in the first training sample as 1, and the absence of open flames as 0.

[0082] In some embodiments, the processor can input a first training sample set into an initial risk prediction model to perform multiple rounds of iteration. At least one round of iteration includes: selecting one or more first training samples from the first training sample set; inputting the one or more first training samples into the initial risk prediction model to obtain the model prediction output corresponding to the one or more first training samples; substituting the model prediction output corresponding to the one or more first training samples, and the first label of these one or more first training samples, into a predefined formula for a loss function to calculate the value of the loss function; iteratively updating the model parameters in the initial risk prediction model based on the value of the loss function until the iteration termination condition is met, at which point the iteration ends, and the trained risk prediction model is obtained. The iteration termination condition may include loss function convergence, the number of iterations reaching a threshold, etc.

[0083] In some embodiments, the training of the risk prediction model may include an initial training phase and a reinforcement training phase. The initial training phase may use a large amount of sample data, including other defense areas, for training, while the reinforcement training phase may use sample data from the current defense area or adjacent defense areas for training.

[0084] In this embodiment of the invention, the predicted fire risk is determined by a risk prediction model. The self-learning capability of the machine learning model can be used to find patterns from a large amount of historical data, thereby improving the accuracy and efficiency of determining the predicted fire risk.

[0085] In some embodiments, the processor can determine the degree of device aging based on emergency monitoring data; and determine the estimated fire risk based on the degree of device aging, open flame characteristics during operation, and emergency monitoring data.

[0086] Device aging level refers to a parameter reflecting the degree of performance degradation of a device. In some embodiments, device aging level includes the aging level of the fire extinguishing device and the aging level of the electrical wiring. The processor can determine the aging level of the fire extinguishing device based on its usage time and the aging level of the electrical wiring based on its usage time. The longer the usage time, the higher the aging level. Usage time can be obtained from a data center.

[0087] In some embodiments, the processor can acquire device appearance characteristics based on emergency monitoring data. Appearance characteristics include defect type, defect area, and density. Defect types may include rust, cracks, coating peeling, etc.

[0088] In some embodiments, the processor can calculate an initial total score based on appearance features; the initial total score is then multiplied by a density correction factor to obtain a comprehensive score. For example, the processor can assign type weights based on the impact of different types of defects on device functionality; calculate the area percentage of a single defect and the total defect density of all defects based on appearance features; multiply the area percentage of each type of defect by its type weight to obtain a defect score for each type; and sum the scores of all types of defects to obtain the initial total score. The density correction factor can be determined based on the total defect density. The processor can directly use the comprehensive score as the degree of device aging. A higher comprehensive score indicates a higher degree of device aging.

[0089] In some embodiments, the processor can input the device aging level into a risk prediction model to determine the predicted fire risk. The first training samples of the risk prediction model may also include the aging level of sample devices.

[0090] In this embodiment of the invention, fire risk can be predicted more accurately by determining the degree of aging of the device.

[0091] In some embodiments, the processor may determine preventative features based on an estimated fire risk.

[0092] For example, the processor can identify walls and worn areas on those walls within a radius Y around locations where the estimated fire probability exceeds a preset fire threshold as potential fire hazards, and use these as the walls and ignition points to be protected in the prevention features. Here, Y can be positively correlated with the scale of the estimated fire risk.

[0093] In this embodiment of the invention, by estimating fire risk and determining emergency prevention data, more accurate and efficient fire prevention and emergency response can be achieved.

[0094] Step 230: Determine emergency control parameters based on emergency preparedness data.

[0095] Emergency control parameters refer to parameters related to emergency firefighting. In some embodiments, emergency control parameters include prevention activation conditions, firefighting targets, and prevention and firefighting parameters.

[0096] Pre-set activation conditions refer to the pre-defined activation conditions for fire extinguishing devices. For example, pre-set activation conditions may include threshold values ​​for determining whether a fire extinguishing device should activate, such as temperature thresholds, humidity thresholds, and smoke concentration thresholds. The processor can pre-set pre-set activation conditions based on experience or human intervention.

[0097] In some embodiments, the processor can determine whether to activate a fire suppression system to extinguish a fire based on emergency preparedness data. Activation of the fire suppression system may require only one threshold condition to be met, or it may require the simultaneous fulfillment of multiple threshold conditions. For example, activation can be determined when the temperature is above a temperature threshold. Alternatively, activation may be determined when the temperature is above a temperature threshold, the humidity is below a humidity threshold, and the smoke concentration is above a smoke concentration threshold.

[0098] In some embodiments, the processor can determine the condition thresholds in the prevention activation conditions based on the associated range corresponding to the prevention and extinguishing parameters. For example, if there are more walls with a prevention level higher than a preset threshold or a larger wall area within the associated range corresponding to the prevention and extinguishing parameters, the processor can set lower temperature and smoke concentration thresholds and higher humidity thresholds. The associated range refers to the area within a radius of X meters around the fire extinguishing device. The value of X can be preset according to the model and type of the fire extinguisher.

[0099] A fire-fighting target refers to a location where a fire has occurred and firefighting efforts are required. For example, a fire-fighting target could be a building with exterior walls.

[0100] In some embodiments, the processor can determine fire suppression targets in a variety of ways based on the protection level and / or protection characteristics of the monitored objects within the associated range.

[0101] In some embodiments, the processor may identify the building or wall with the highest protection level and / or the most fire ignition points requiring protection within the associated range as the fire suppression target. The processor may also perform a weighted summation of the protection level and the number of fire ignition points in the protection features of the building or wall within the associated range, and identify the building or wall with the largest weighted sum as the fire suppression target.

[0102] In some embodiments, the processor may divide the associated range of the fire extinguishing device into multiple associated sub-ranges; calculate the average protection level of all walls within the associated sub-ranges; and calculate the average number of fire ignition points among the protection features of all walls within the associated sub-ranges. The processor may select the associated sub-range with the largest average value as the fire extinguishing target of the fire extinguisher. The processor may also perform a weighted summation of the average protection level and the average number of fire ignition points, and determine the associated sub-range with the largest weighted sum as the fire extinguishing target. For example, the processor may divide the associated range into multiple associated sub-ranges, and an associated sub-range may be a sector-shaped area of ​​15 degrees, 30 degrees, 45 degrees, 60 degrees, etc.

[0103] Fire prevention and extinguishing parameters refer to parameters used to perform emergency fire suppression. In some embodiments, fire prevention and extinguishing parameters include activation time control values, extinguishing angle parameters, and extinguishing intensity parameters.

[0104] In some embodiments, the activation time control value includes activation duration and activation interval. The processor can control the activation duration and activation interval of the fire extinguishing device when extinguishing a fire based on the activation time control value.

[0105] In some embodiments, the extinguishing angle parameter includes a preset orientation angle of the fire extinguisher. The processor can control the orientation angle of the fire extinguisher based on the extinguishing angle parameter.

[0106] In some embodiments, the extinguishing intensity parameters include extinguishing pressure, preset coverage area, and preset spray flow rate. The processor can control the extinguishing pressure, coverage area, and spray flow rate of the fire extinguishing device based on these parameters.

[0107] In some embodiments, the processor can determine fire prevention and extinguishing parameters based on the different wall protection characteristics and protection levels.

[0108] In some embodiments, the processor can determine the activation duration and activation interval based on the protection level or the number of fire points within the associated sub-range. The higher the average protection level of the building or wall within the associated sub-range, the larger the average number of fire points, or the larger the weighted sum of the average protection level and the average number of fire points, the longer the activation duration and the shorter the activation interval can be set by the processor.

[0109] In some embodiments, the processor can determine a preset coverage area and a preset spray flow rate based on the protection level or the number of fire points within the associated sub-range. The higher the average protection level of the buildings or walls within the associated sub-range, the larger the average number of fire points, or the larger the weighted sum of the average protection level and the average number of fire points, the larger the preset coverage area and the larger the preset spray flow rate can be.

[0110] In some embodiments, the processor can acquire multiple sets of candidate control parameters; determine the fire prevention effect corresponding to the multiple sets of candidate parameters based on the multiple sets of candidate control parameters and the estimated fire risk; and determine emergency control parameters based on the fire prevention effect.

[0111] Candidate control parameters are parameters that serve as alternatives to emergency control parameters. In some embodiments, candidate control parameters include candidate prevention activation conditions and prevention and extinguishing parameters. The processor can randomly set candidate control parameters, or it can select cases of successful fire control from historical fire events (e.g., fire did not spread, property damage was low), and extract the corresponding emergency control parameters as candidate control parameters.

[0112] In some embodiments, the processor can determine multiple sets of candidate control parameters based on historical fire data. For example, the processor can use an association rule mining algorithm (e.g., the Apriori algorithm) to mine strong association rules between emergency control parameters and fire prevention effectiveness in historical fire data, thereby obtaining candidate control parameters.

[0113] For example, if a strong association rule is determined as {low start-up temperature threshold, high jet flow rate} - high fire suppression effect, the processor can select from the range of low start-up temperature threshold and the range of high jet flow rate to generate one or more candidate control parameters.

[0114] In some embodiments, for each set of candidate control parameters, the processor can determine the fire prevention effect corresponding to the set of candidate control parameters based on the set of candidate control parameters and the estimated fire risk, through an effect determination model.

[0115] In some embodiments, the performance determination model is a machine learning model. For example, a neural network model, a recurrent neural network (RNN) model, etc.

[0116] Figure 4 This is an exemplary schematic diagram of an effect determination model according to some embodiments of the present invention. In some embodiments, such as Figure 4 As shown, the inputs to the effect determination model 420 may include candidate control parameters 411, estimated fire risk 412, equipment aging degree 413, area structure data 414, and emergency prevention data 415. The output of the effect determination model 420 may include the fire prevention effect 430 corresponding to the candidate control parameters 411.

[0117] More information on candidate control parameters, estimated fire risk, equipment aging status, and emergency preparedness data can be found in [link to relevant documentation]. Figure 2 And its related descriptions.

[0118] Regional structural data can include building floor plans and fire safety facility distribution data within the protected area. This data can be retrieved directly from a data center or acquired through drone photography.

[0119] In some embodiments, the effect determination model can be trained based on training data. In some embodiments, the processor can acquire multiple second training samples with second labels to form a second training sample set, and perform multiple rounds of iteration based on the second training sample set. The training process of the effect determination model is similar to that of the risk prediction model.

[0120] The second training sample may include candidate control parameters obtained from historical data, estimated fire risk, aging status of sample devices, structural data of sample areas, and emergency response data. The second label can be the actual fire prevention effectiveness assessed corresponding to the second training sample. For example, the processor can evaluate the fire duration, fire spread range, and property damage to assess the fire prevention effectiveness. The smaller the fire duration, fire spread range, and property damage, the better the fire prevention effectiveness.

[0121] In this embodiment of the invention, the fire prevention effect is determined by the effect determination model. The self-learning ability of the machine learning model can be used to find patterns from a large amount of historical data, thereby improving the accuracy and efficiency of determining the fire prevention effect.

[0122] In some embodiments, the processor may select the set of candidate control parameters that have the best fire prevention effect as the determined emergency control parameters.

[0123] In some embodiments, the emergency control parameters also include monitoring and control parameters. The processor can determine the monitoring and control parameters based on emergency prevention data and the quality of the acquisition bandwidth. Based on the monitoring and control parameters, a monitoring control signal is sent to the monitoring device installed in the prevention area to control the monitoring device to adjust the monitoring frequency and monitoring angle according to the monitoring and control parameters.

[0124] Monitoring and control parameters refer to the parameters used to control monitoring devices. For more information on monitoring devices, please refer to [link / reference needed]. Figure 1 And related descriptions. In some embodiments, the monitoring and control parameters include the monitoring frequency and monitoring angle of the monitoring equipment.

[0125] For example, when the density of high-risk fire points within the monitoring range is high, the processor can appropriately increase the monitoring frequency of the monitoring device to ensure the monitoring effect on the high-risk area. As another example, the processor can acquire the clustered location of high-risk fire points and adjust the monitoring angles of multiple monitoring devices so that the overlap coverage of the monitoring range of multiple monitoring devices at that clustered location exceeds a threshold, thereby ensuring the monitoring effect on the clustered location.

[0126] Bandwidth acquisition quality refers to a performance indicator reflecting data transmission capability. Higher monitoring frequencies result in more data collection; insufficient bandwidth acquisition quality can lead to data congestion. Bandwidth acquisition quality is an inherent performance characteristic of the monitoring device and can be directly obtained from it.

[0127] In some embodiments, the processor can determine monitoring and control parameters by querying a bandwidth quality table based on the density of fire locations and the bandwidth acquisition quality. The bandwidth quality table may include the density of different fire locations, the bandwidth acquisition quality, and the corresponding monitoring frequency.

[0128] In this embodiment of the invention, by determining the monitoring and control parameters through emergency prevention data and the quality of the acquisition bandwidth, the monitoring frequency and monitoring angle of the monitoring device can be controlled, thereby achieving optimal allocation of monitoring device resources and improving system efficiency while ensuring monitoring effectiveness.

[0129] Step 240: Based on the emergency control parameters, send a fire extinguishing control signal to the fire extinguishing device installed in the protected area to drive the fire extinguishing device to perform emergency fire extinguishing according to the emergency control parameters.

[0130] In some embodiments, the processor can send fire extinguishing control signals to the fire extinguishing device through an emergency monitoring sensor network platform based on emergency control parameters.

[0131] In some embodiments, the processor can control the nozzle of the fire extinguishing device to rotate toward the fire target; in response to meeting the prevention activation conditions, based on the prevention extinguishing parameters, and with a preset coverage area and preset spray flow rate, the processor can activate the fire extinguishing device to extinguish the fire. The processor can control the fire extinguishing device to start or stop according to an activation time control value. The processor can control the nozzle of the fire extinguishing device to rotate according to the extinguishing angle parameters, so that the nozzle sprays at a preset directional angle.

[0132] In some embodiments, the processor may determine false triggering data based on the second cycle, emergency monitoring data, and emergency control parameters; determine correction parameters based on the false triggering data; update the emergency control parameters based on the correction parameters to obtain updated emergency control parameters; and send the updated emergency control parameters to the fire extinguishing devices installed in the protected area.

[0133] The second cycle refers to the preset cycle for determining false trigger data. Every second cycle, the processor can acquire emergency monitoring data and emergency control parameters within that cycle and determine the false trigger data accordingly. The length of the second cycle is shorter than the length of the first cycle.

[0134] False trigger data refers to data related to false triggering. In some embodiments, false trigger data includes the number of false triggers in the previous second cycle, environmental data at the time of each false trigger, and the corresponding activation conditions. The processor can extract false trigger data based on emergency monitoring data or emergency control parameters at the time of each false trigger in the second cycle. Whether a false trigger has occurred can be determined by reports from staff. For example, a resident may report a false trigger, or staff may discover a false trigger while reviewing historical records.

[0135] Correction parameters refer to data that corrects emergency control parameters (e.g., prevention activation conditions). In some embodiments, correction parameters may include correction items and adjustment amounts. For example, the correction item may be a temperature threshold, and the adjustment amount may be the degree by which the current temperature threshold is modified, the degree by which the temperature threshold is reduced, etc.

[0136] In some embodiments, the processor may determine correction parameters in a variety of ways based on false trigger data.

[0137] In some embodiments, the processor can adjust the preventive startup conditions based on environmental data and corresponding startup conditions during multiple false triggers. For example, when the number of false triggers due to meeting a temperature threshold reaches a false trigger threshold, the processor can increase the temperature threshold in the preventive startup conditions.

[0138] In some embodiments, the processor can determine the adjustment amount of the prevention activation conditions based on the fire resistance of the walls of multiple fire-monitored buildings surrounding the fire extinguishing device. For example, when the fire resistance of the walls of the surrounding fire-monitored buildings is weak, the processor can reduce the adjustment amount in the correction parameters to ensure the sensitivity of the fire extinguishing device and minimize the spread of fire.

[0139] In this embodiment of the invention, by determining the false triggering data and correcting the parameters to update the emergency control parameters, the damage caused by false triggering can be reduced, the control of the fire extinguishing device can be optimized, and the efficiency and accuracy of disaster response can be improved.

[0140] In some embodiments, the processor can determine the characteristics of the open flame at the time of accidental triggering based on emergency monitoring data and accidental triggering data; determine the operational impact data based on the characteristics of the open flame at the time of accidental triggering; and determine correction parameters based on the operational impact data.

[0141] The determination of the open flame characteristics of the operation when it is accidentally triggered can be found in step 220. The difference is that the processor identifies the open flame characteristics of the operation in the accidental trigger data.

[0142] Operation impact data refers to data reflecting the degree of danger or risk of interruption of open flame operations. The degree of danger of open flame operations can be preset. Interruption risk refers to the potential losses caused by the interruption of open flame operations.

[0143] In some embodiments, the processor can determine the operation impact data by matching the open flame characteristics of the operation at the time of accidental triggering with the emergency monitoring data at the time of accidental triggering in a second vector database.

[0144] The second vector database is a pre-defined database containing multiple reference operation feature vectors and corresponding operation labels. The processor can construct reference operation feature vectors based on the characteristics of open flames during accidental triggering and emergency monitoring data from a large amount of historical or experimental data in the data center. The reference operation impact data corresponding to these feature vectors is then used as the operation labels. The reference operation impact data can be obtained by evaluating the scale, type, and duration of the corresponding open flame, as well as the economic losses caused by the interruption of the open flame.

[0145] In some embodiments, the processor can construct an operation feature vector based on the open flame characteristics of the operation at the time of accidental triggering and the emergency monitoring data at the time of accidental triggering; and match the operation feature vector in a second vector database to determine the operation impact data. The processor can search in the second vector database for the operation label corresponding to the reference operation feature vector with the highest similarity (e.g., the smallest vector distance) to the operation feature vector, and determine it as the operation impact data.

[0146] In some embodiments, the processor can determine the adjustment amount in the correction parameters based on the degree of danger and interruption risk of open flame operations in the job impact data. The lower the degree of danger and interruption risk of open flame operations, the larger the adjustment amount.

[0147] In this embodiment of the invention, by determining the operation impact data, the correction amount can be determined more accurately, avoiding the risk of open flame operation interruption caused by accidental triggering.

[0148] In some embodiments, the processor can determine correction parameters based on the estimated fire risk in the next first cycle and the false triggering data in the previous second cycle. Here, the next first cycle refers to the first cycle B following first cycle A. The previous second cycle refers to the second cycle C preceding the current second cycle D, and second cycle C and second cycle D are two adjacent second cycles.

[0149] For fire extinguishing devices, if the proportion of buildings / walls within the associated range that have a low fire risk level is greater than the risk threshold, and the number of false triggers of the fire extinguishing device in the previous second cycle is greater than the false trigger threshold, then the processor raises the condition threshold of the corresponding prevention activation condition. The risk threshold can be positively correlated with the number of buildings or walls within the associated range of the fire extinguishing device.

[0150] In this embodiment of the invention, determining the correction parameters in the above manner can improve the system's adaptability to complex environments and reduce misjudgments caused by differences in the protected areas.

[0151] In some embodiments of the present invention, the smart city fire-fighting automatic extinguishing method based on the above-mentioned Internet of Things big data model can dynamically generate prevention levels and prevention characteristics based on emergency monitoring information of different fire monitoring buildings, so as to automatically control the activation of fire extinguishing devices and execute fire extinguishing according to the prevention and extinguishing parameters, reduce the risk of fire spread, improve the speed of disaster response and resource utilization efficiency, thereby improving fire extinguishing efficiency and reducing disaster losses.

[0152] It should be noted that the above description of the process 200 of the smart city fire automatic extinguishing method based on the Internet of Things (IoT) big data model is merely for illustration and explanation, and does not limit the scope of the invention. Those skilled in the art can make various modifications and changes to the process 200 of the smart city fire automatic extinguishing method based on the IoT big data model under the guidance of this invention. However, these modifications and changes are still within the scope of this invention.

[0153] One or more embodiments of the present invention provide a smart city fire automatic extinguishing IoT big data model system. The system includes an emergency monitoring and management platform and an emergency monitoring sensor network platform. The emergency monitoring and management platform includes at least one processor and at least one memory. The at least one memory is used to store computer instructions. The at least one processor is used to execute at least a portion of the computer instructions to implement a smart city fire automatic extinguishing method based on an IoT big data model, as described in any of the above embodiments. The smart city fire automatic extinguishing IoT big data model system can be part of a smart city fire automatic extinguishing system based on an IoT big data model.

[0154] One or more embodiments of the present invention provide a computer-readable storage medium that stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes a smart city fire automatic extinguishing method as described in any of the above embodiments.

[0155] The basic concepts have been described above. It is clear that the detailed disclosure above is merely illustrative and does not constitute a limitation of the present invention. Although not explicitly stated herein, various modifications, improvements, and corrections may be made to the present invention by those skilled in the art. Such modifications, improvements, and corrections are suggested in this invention and therefore remain within the spirit and scope of the exemplary embodiments of the present invention.

[0156] Furthermore, specific terms are used to describe embodiments of the invention. For example, "an embodiment" and / or "some embodiments" refer to a particular feature, structure, or characteristic related to at least one embodiment of the invention. Therefore, it should be emphasized and noted that "an embodiment" mentioned twice or more in different locations in this invention does not necessarily refer to the same embodiment. In addition, certain features, structures, or characteristics in one or more embodiments of the invention can be appropriately combined.

[0157] Furthermore, unless expressly stated in the claims, the order of processing elements and sequences, the use of numbers and letters, or other names described in this invention are not intended to limit the order of the processes and methods of this invention. Although the foregoing disclosure has discussed some currently considered useful embodiments of the invention through various examples, it should be understood that such details are for illustrative purposes only, and the appended claims are not limited to the disclosed embodiments; rather, the claims are intended to cover all modifications and equivalent combinations that conform to the spirit and scope of the embodiments of this invention. For example, while the system components described above can be implemented by hardware devices, they can also be implemented solely by software solutions, such as installing the described system on existing servers or mobile devices.

[0158] Similarly, it should be noted that, in order to simplify the description of this invention and thus aid in the understanding of one or more embodiments, the foregoing description of the embodiments of this invention sometimes combines multiple features into a single embodiment, drawing, or description thereof. However, this disclosure method does not imply that the subject matter of the invention requires more features than those mentioned in the claims. In fact, the embodiments contain fewer features than all the features of the single embodiment disclosed above.

[0159] Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximate values, which may be changed depending on the characteristics required by individual embodiments. In some embodiments, the numerical parameters should take into account a specified number of significant digits and employ a general method of digit preservation. Although the numerical ranges and parameters used to confirm their breadth of scope in some embodiments of the invention are approximate values, in specific embodiments, such values ​​are set as precisely as feasible.

[0160] For each patent, patent application, patent application publication, and other material, such as articles, books, specifications, publications, and documents, referenced in this invention, the entire contents of which are incorporated herein by reference. This excludes historical application documents that are inconsistent with or conflict with the content of this invention, as well as documents that limit the broadest scope of the claims of this invention (currently or subsequently appended to this invention). It should be noted that if there are any inconsistencies or conflicts between the descriptions, definitions, and / or terminology used in the appended materials of this invention and the content of this invention, the descriptions, definitions, and / or terminology used in this invention shall prevail.

[0161] Finally, it should be understood that the embodiments described in this invention are merely illustrative of the principles of the invention. Other modifications may also fall within the scope of this invention. Therefore, alternative configurations of the embodiments of this invention are considered as examples and not limitations, and are regarded as consistent with the teachings of this invention. Accordingly, the embodiments of this invention are not limited to those explicitly described and illustrated herein.

Claims

1. A smart city automatic fire extinguishing system based on an Internet of Things (IoT) big data model, characterized in that, The system includes an emergency monitoring and management platform, which is configured as follows: Obtain emergency monitoring data; Based on the first cycle and the aforementioned emergency monitoring data, the characteristics of open flames during operations are obtained; Based on the characteristics of the open flame during the operation and the emergency monitoring data, the estimated fire risk is determined; Based on the estimated fire risk, determine the emergency preparedness data for the protected area; Based on historical fire data, a strong correlation rule mining algorithm is used to mine the historical fire data to obtain multiple sets of candidate control parameters by mining the strong correlation rules between emergency control parameters and fire prevention effectiveness. Based on the multiple sets of candidate control parameters, the estimated fire risk, the aging degree of the equipment, the regional structural data, and the emergency prevention data, the fire prevention effect corresponding to the multiple sets of candidate control parameters is determined by the effect determination model, which is a machine learning model. Based on the fire prevention effect, emergency control parameters are determined, including prevention activation conditions, fire extinguishing targets, and prevention and fire extinguishing parameters. Based on the emergency control parameters, a fire extinguishing control signal is sent to the fire extinguishing device installed in the protected area through the emergency monitoring sensor network platform, so as to drive the fire extinguishing device to perform emergency fire extinguishing according to the emergency control parameters, including: Control the nozzle of the fire extinguishing device to rotate so as to face the fire extinguishing target; In response to the fulfillment of the prevention activation conditions, the fire extinguishing device is activated to extinguish the fire based on the prevention and extinguishing parameters, with a preset coverage area and a preset spray flow rate.

2. The smart city automatic fire extinguishing system based on the Internet of Things large model according to claim 1, characterized in that, The emergency monitoring and management platform is also configured as follows: Based on the emergency monitoring data, the degree of aging of the device is determined; The estimated fire risk is determined based on the aging level of the device, the characteristics of open flames during operation, and the emergency monitoring data.

3. The smart city automatic fire extinguishing system based on the Internet of Things large model according to claim 1, characterized in that, The emergency monitoring and management platform is also configured as follows: Based on the second cycle, the emergency monitoring data, and the emergency control parameters, the false triggering data is determined; Based on the false triggering data, determine the correction parameters; Based on the correction parameters, the emergency control parameters are updated to obtain the updated emergency control parameters; The updated emergency control parameters are sent to the fire extinguishing device installed in the protected area.

4. A smart city automatic fire extinguishing method based on an Internet of Things (IoT) big data model, characterized in that, The method includes: Obtain emergency monitoring data; Based on the first cycle and the aforementioned emergency monitoring data, the characteristics of open flames during operations are obtained; Based on the characteristics of the open flame during the operation and the emergency monitoring data, the estimated fire risk is determined; Based on the estimated fire risk, determine the emergency preparedness data for the protected area; Based on historical fire data, a strong correlation rule mining algorithm is used to mine the historical fire data to obtain multiple sets of candidate control parameters by mining the strong correlation rules between emergency control parameters and fire prevention effectiveness. Based on the multiple sets of candidate control parameters, the estimated fire risk, the aging degree of the equipment, the regional structural data, and the emergency prevention data, the fire prevention effect corresponding to the multiple sets of candidate control parameters is determined by the effect determination model, which is a machine learning model. Based on the fire prevention effect, emergency control parameters are determined, including prevention activation conditions, fire extinguishing targets, and prevention and fire extinguishing parameters. Based on the emergency control parameters, a fire extinguishing control signal is sent to the fire extinguishing device installed in the protected area to drive the fire extinguishing device to perform emergency fire extinguishing according to the emergency control parameters, including: Control the nozzle of the fire extinguishing device to rotate so as to face the fire extinguishing target; In response to the fulfillment of the prevention activation conditions, the fire extinguishing device is activated to extinguish the fire based on the prevention and extinguishing parameters, with a preset coverage area and a preset spray flow rate.

5. The smart city automatic fire extinguishing method based on an IoT big data model according to claim 4, characterized in that, The method further includes: Based on the second cycle, the emergency monitoring data, and the emergency control parameters, the false triggering data is determined; Based on the false triggering data, determine the correction parameters; Based on the correction parameters, the emergency control parameters are updated to obtain the updated emergency control parameters; The updated emergency control parameters are sent to the fire extinguishing device installed in the protected area.

6. A computer-readable storage medium, characterized in that, The storage medium stores computer instructions, which, when executed by a processor, implement the smart city fire automatic extinguishing method based on an Internet of Things (IoT) big data model as described in claim 4.

Images