Urban public place gas emergency system and method based on Internet of Things large model

Abstract

The invention provides an urban public place gas emergency system and method based on an Internet of Things large model, and relates to the field of public place gas emergency. The system comprises an emergency supervision and management platform which is configured to execute the method, and the method comprises the following steps: acquiring gas monitoring data of a target area; when the evacuation condition is satisfied, generating evacuation parameters based on the gas monitoring data and the area data of the target area; and sending an evacuation control signal to an evacuation device deployed in the target area based on the evacuation parameter to control the evacuation device to guide personnel evacuation, including: controlling a display device to display an evacuation path; based on the lamp board control parameters, the display color and the indication direction of the electronic indication board are controlled; controlling the brightness and mode of the lighting device based on the lighting control parameter; and controlling the gate to be turned on based on the gate control parameter. According to different environments and gas leakage conditions, an evacuation scheme can be formulated in a targeted mode, and the evacuation device is controlled to guide people to be evacuated rapidly and effectively.

Description

TECHNICAL FIELD

[0001] The present specification relates to the field of gas emergency in public places, in particular to a city public place gas emergency system and method based on Internet of Things large model. BACKGROUND

[0002] In the process of urban development, the safety management of public places is facing multiple bottlenecks. In the event of gas leakage in places such as scenic spots, squares, and transportation hubs, the complex space and high population density may lead to evacuation difficulties, resulting in regional stampede risks and secondary disaster hazards.

[0003] Therefore, it is necessary to provide a city public place gas emergency system and method based on Internet of Things large model, which formulates evacuation plans for different environments and different gas leakage situations, sends evacuation control signals to evacuation devices to control the evacuation devices to guide personnel to evacuate quickly and effectively. SUMMARY

[0004] In order to solve the problem of how to formulate individualized evacuation plans for different environments and different gas leakage situations, the present application provides a city public place gas emergency system and method based on Internet of Things large model.

[0005] The summary includes a city public place gas emergency system based on Internet of Things large model, which comprises an emergency supervision management platform and an emergency supervision object platform; the emergency supervision management platform is configured to execute a city public place gas emergency Internet of Things large model method.

[0006] The summary includes a city public place gas emergency method based on Internet of Things large model, characterized in that the method is executed by an emergency supervision management platform in a city public place gas emergency system based on Internet of Things large model, and the method comprises: based on an emergency supervision object platform, obtaining gas monitoring data of a target area through a monitoring device deployed in the monitoring area; in response to meeting the evacuation conditions, generating evacuation parameters based on the gas monitoring data and the regional data of the target area, the evacuation parameters including evacuation paths and light board control parameters, lighting control parameters, and gate control parameters; and based on the evacuation parameters, sending evacuation control signals to evacuation devices deployed in the target area to control the evacuation devices to guide personnel in the target area to evacuate, including: controlling the display device to display the evacuation path; based on the light board control parameters, controlling the display color and direction of the electronic sign; based on the lighting control parameters, controlling the lighting brightness and mode of the lighting equipment; and based on the gate control parameters, controlling the on-off state of the gate.

[0007] The beneficial effects brought by the above invention content include but are not limited to: (1) when the evacuation condition is reached, the evacuation parameters are generated by the gas monitoring data and the regional data for controlling the evacuation device to guide the personnel in the evacuation target area, which can effectively improve the crowd evacuation efficiency, reduce the risk of congestion and trampling, enhance the emergency response capability, and protect public safety. The accurate regulation of the light board control parameter can enhance the dynamic adaptability of the direction mark, meet the guiding needs of different scenes. The adjustment of the lighting control parameter can ensure the visibility in the low visibility environment, and further enhance the guiding nature of the path. The intelligent control of the gate machine state realizes the precise cooperation of physical isolation and path control, effectively preventing personnel from mistakenly entering the dangerous area. The whole set of control signal linkage mechanism transmits parameterized instructions to ensure the reliability and response speed of the collaborative work of multiple devices, and significantly improves the emergency disposal efficiency of public safety events in complex environments; (2) the evacuation path is generated by comprehensively monitoring the gas data, regional data, and the actual regional personnel data and obstacle data, and the evacuation path is screened, which effectively balances the feasibility and rationality of the evacuation path while ensuring the evacuation efficiency, avoiding congestion caused by insufficient evacuation paths or chaos caused by unreasonable evacuation channels; (3) through the dynamic correction of the alarm threshold and the accurate regulation of the monitoring frequency of the image acquisition device, the system can adapt to the change of environmental conditions, so as to reasonably allocate energy consumption while ensuring the evacuation efficiency. BRIEF DESCRIPTION OF DRAWINGS

[0008] The present application will be further illustrated in the form 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 numbers represent the same structures, wherein: Figure 1 is a platform structure diagram of a city public place gas emergency system based on an Internet of Things large model according to some embodiments of the present application; Figure 2 is an exemplary flowchart of a city public place gas emergency method based on an Internet of Things large model according to some embodiments of the present application; Figure 3 is an exemplary flowchart of determining an evacuation path according to some embodiments of the present application; Figure 4 is an exemplary flowchart of updating a safe area and an alternative evacuation path according to some embodiments of the present application; Figure 5 is a schematic diagram of determining a modal parameter according to some embodiments of the present application. DETAILED DESCRIPTION

[0009] The drawings needed in the embodiment description will be briefly introduced as follows. The drawings do not represent all the embodiments.

[0010] In the embodiments of the present application, the operations performed in the steps are described, and the order of the steps is exchangeable, the steps can be omitted, and other steps can be included in the operations.

[0011] Figure 1 is a platform structure diagram of an urban public place gas emergency system based on an Internet of Things large model according to some embodiments of the present application.

[0012] In some embodiments, as shown in Figure 1 , the urban public place gas emergency system based on the Internet of Things large model 100 can include an emergency supervision user platform 110, an emergency supervision service platform 120, an emergency supervision management platform 130, an emergency supervision sensor network platform 140, and an emergency supervision object platform 150.

[0013] The emergency supervision user platform 110 refers to an interactive platform for providing emergency service operations for users, including user terminals. For example, a computer or other device with input and / or output functions.

[0014] The users include superior supervision department users and citizen users. The superior supervision department users refer to the superior management departments of the emergency supervision management platform 130, which can deploy emergency supervision tasks to the emergency supervision management platform 130 through the emergency supervision user platform 110, and receive emergency supervision dynamic information fed back by the emergency supervision management platform 130. The citizen users refer to personnel in public places who have evacuation needs. For example, tourists in shopping malls, hotel residents, and staff of catering enterprises.

[0015] The emergency supervision service platform 120 refers to an interactive service platform for receiving and transmitting data, including servers, gateways, routers, and the like.

[0016] In some embodiments, the emergency supervision service platform 120 interacts with the emergency supervision user platform 110 upwardly and with the emergency supervision management platform 130 downwardly.

[0017] The emergency supervision management platform 130 refers to a comprehensive platform for processing and managing emergency supervision data.

[0018] In some embodiments, the emergency supervision management platform includes processors and / or servers, data centers, and the like. The data center is configured with a storage device.

[0019] In some embodiments, the emergency supervision management platform 130 can be configured to perform an urban public place gas emergency method based on an Internet of Things large model. For more information about this method, see the related description of Figure 2 .

[0020] The emergency supervision sensor network platform 140 refers to a management platform for transmitting emergency supervision related sensor data or information, including a communication transmission network and a routing device.

[0021] In some embodiments, the emergency supervision sensor network platform 140 interacts with the emergency supervision management platform 130 upwardly and with the emergency supervision object platform 150 downwardly.

[0022] The emergency supervision object platform 150 refers to a platform for collecting emergency supervision data and implementing execution instructions.

[0023] In some embodiments, the emergency supervision object platform is configured with various monitoring devices, storage devices, and evacuation devices. The monitoring devices can include image acquisition devices, environmental monitoring devices, gas monitoring devices, etc.

[0024] The image acquisition device refers to a device for acquiring image data, such as an electronic camera, etc. The image data can include image sensor data and external image data, etc.

[0025] The environmental monitoring device refers to a device for monitoring environmental data, such as a temperature sensor, a humidity sensor, a wind direction detector, etc.

[0026] The gas monitoring device refers to a device for monitoring gas data, such as a gas concentration monitoring device, etc.

[0027] The evacuation device refers to a device that provides evacuation support for emergency situations. In some embodiments, the evacuation device includes a gate, an electronic sign, lighting equipment, a display device, a ventilation device, a projection device, a broadcasting device, etc.

[0028] The electronic sign is used to guide directions or provide prompts. The display device is used to present visual information (such as evacuation paths). The ventilation device is used to evacuate harmful gases to reduce the concentration of gas in the air. For example, fans, exhaust fans, air purifiers, etc. The projection device is used to project images to guide directions. For example, projecting evacuation paths, etc. The broadcasting device is used to transmit audio information. For example, broadcasting evacuation paths, etc.

[0029] In some embodiments, the emergency supervision object platform is also configured with sensing equipment, such as an illumination sensor, a volume detector, etc. The sensing equipment is used to acquire environmental perception data. For example, the illumination sensor can detect the intensity of environmental light, and the volume detector can monitor the intensity of environmental sound.

[0030] In some embodiments of the present specification, the city public place gas emergency system based on the Internet of Things large model can form an information operation closed loop between the functional platforms, coordinate and operate regularly, and determine the actual evacuation control parameters efficiently and accurately to improve the efficiency of emergency evacuation and avoid stampede accidents.

[0031] Figure 2 is an exemplary flowchart of an Internet of Things large model-based urban public place gas emergency method according to some embodiments of the present specification. In some embodiments, the Internet of Things large model-based urban public place gas emergency method can be executed by an emergency supervision management platform. As shown in Figure 2 , the flow 200 includes the following steps.

[0032] Step 210, based on the emergency supervision object platform, obtaining gas monitoring data of the target area through the monitoring device deployed in the monitoring area.

[0033] The monitoring area refers to an area that needs to be monitored and controlled for safety. In some embodiments, the monitoring area includes the target area and the external environment area.

[0034] The target area refers to an area that has a gas safety evacuation requirement. For example, the internal area of a public place such as a shopping mall, a hotel, a catering enterprise, etc. that uses gas.

[0035] The external environment area refers to the external surrounding environment of the target area. For example, the roads, buildings, etc. around the target area.

[0036] The gas monitoring data refers to the relevant parameters of the gas in the target area. For example, the concentration of gas, the concentration of oxygen, etc. in the target area. The concentration of gas can be represented by the concentration of harmful gas (such as methane).

[0037] In some embodiments, the gas monitoring data can be obtained through a gas monitoring device.

[0038] In some embodiments, in response to satisfying the evacuation condition, the emergency supervision management platform can execute step 220, which includes step 221 and step 222.

[0039] The evacuation condition refers to a critical condition that triggers personnel to evacuate when a gas leakage hazard occurs.

[0040] In some embodiments, the evacuation condition can include that the concentration of gas in the gas monitoring data is higher than a first preset concentration threshold. The first preset concentration threshold can be preset by a person according to experience or set by default by a processor.

[0041] Step 221, generating evacuation parameters based on the gas monitoring data and the area data of the target area.

[0042] The area data refers to data describing the situation of the target area. For example, the terrain data in the target area, the location of each passage, the passage size, etc. The area data can be obtained based on the planar structure diagram and / or the three-dimensional structure diagram of the target area.

[0043] The evacuation parameter refers to a parameter for guiding personnel to evacuate, including an evacuation path, a light board control parameter, a lighting control parameter, and a gate control parameter.

[0044] The evacuation path refers to a passing route for personnel to evacuate.

[0045] The light board control parameter refers to an operating parameter of an electronic signboard for guiding personnel to evacuate. For example, a direction of the electronic signboard, a display color.

[0046] The lighting control parameter refers to an operating parameter of a lighting device for guiding personnel to evacuate. For example, a lighting brightness of the lighting device, a lighting mode. The lighting mode can include a constant light intensity mode, a flashing mode, and the like.

[0047] The gate control parameter refers to an operating parameter of a gate for guiding personnel to evacuate. For example, an on-off state of the gate.

[0048] In some embodiments, the emergency supervision management platform can generate a plurality of connected paths according to the region data of the target region through a path planning algorithm, and select one or more connected paths as the evacuation path according to a selection condition. For example, the selection condition can be that the path length is the shortest or the path score is the highest.

[0049] The connected path refers to a path connecting the inside of the target region to the outside environment region. The path score can be represented by a first weighted sum value of the path length after normalization processing and the exit capacity. The exit capacity refers to the capacity of the exit corresponding to the connected path. The exit capacity of each region can be manually preset. Based on the region where the exit of each connected path is located, the path score of each connected path can be determined. The path planning algorithm can be a Dijkstra algorithm. The normalization processing method can be Min-Max normalization.

[0050] In some embodiments, the emergency supervision management platform can determine the light board control parameter, the lighting control parameter, and the gate control parameter based on the evacuation path.

[0051] For example, the emergency supervision management platform can set the direction of the evacuation path as the direction of the electronic signboard on the evacuation path, and set the display color as a preset emergency display color (such as red); set a first preset brightness as the lighting brightness of the lighting device on the evacuation path, and set the lighting mode as a flashing mode; set a second preset brightness as the lighting brightness of the lighting device on the non-evacuation path, and set the lighting mode as a constant light intensity mode; turn on the gate on the evacuation path, and turn off the gate outside the evacuation path. The first preset brightness is higher than the second preset brightness, and the first preset brightness, the second preset brightness, and the preset emergency display color are manually preset.

[0052] In some embodiments, the emergency supervision management platform can acquire image sensing data of the target area, and then acquire regional personnel data and obstacle data of the target area; determine a safe area and generate an alternative evacuation path based on the gas monitoring data and the regional data; and determine an evacuation path from the alternative evacuation path based on the regional personnel data and the obstacle data. For more information about this part, please refer to Figure 3 and the related description thereof.

[0053] Step 222, based on the evacuation parameters, an evacuation control signal is sent to the evacuation device deployed in the target area to control the evacuation device to guide the evacuation of personnel in the target area.

[0054] The evacuation control signal refers to a signal used to control the evacuation device to operate according to the evacuation parameters during the evacuation process.

[0055] In some embodiments, the evacuation control signal can be used to control the evacuation device to guide the evacuation of personnel in the target area, including controlling the display device to display the evacuation path; controlling the display color and direction of the electronic sign based on the sign control parameter; controlling the lighting brightness and lighting mode of the lighting device based on the lighting control parameter; and controlling the on-off state of the gate based on the gate control parameter.

[0056] In some embodiments of the present specification, when the evacuation condition is reached, the evacuation parameters are generated by the gas monitoring data and the regional data to control the evacuation device to guide the evacuation of personnel in the target area, which can effectively improve the crowd evacuation efficiency, reduce the risk of stampede, enhance the ability to respond to emergencies, and protect public safety. The precise regulation of the sign control parameter can enhance the dynamic adaptability of the direction identification, meet the guidance needs of different scenarios. The adjustment of the lighting control parameter can ensure the visibility in low-visibility environments and further enhance the guidance of the path. The intelligent control of the gate state realizes the precise cooperation of physical isolation and path control, effectively preventing personnel from entering dangerous areas by mistake. The whole control signal linkage mechanism transmits parameterized instructions to ensure the reliability and response speed of the collaborative work of multiple devices, and significantly improves the emergency disposal efficiency of public safety events in complex environments.

[0057] In some embodiments, the evacuation parameters further include ventilation control parameters.

[0058] In some embodiments, the emergency supervision management platform can control the air supply intensity and air supply direction of the ventilation device based on the ventilation control parameters.

[0059] The ventilation control parameter refers to a parameter used to control the operation of the ventilation device, including the air supply direction and the air supply intensity.

[0060] In some embodiments, the emergency supervision management platform can determine the ventilation control parameter based on the gas monitoring data and the area data. For example, the emergency supervision management platform can generate an evacuation path based on the gas monitoring data and the area data; determine a gas diffusion direction as a direction in which the gas concentration decreases based on the gas monitoring data, and determine a gas diffusion speed as a gas leakage speed; turn on a ventilation device located on the evacuation path and determine a ventilation direction of the ventilation device as a reverse direction of the gas diffusion direction; and perform a second weighted summation on the normalized gas leakage speed and the length of the evacuation path, and the air supply intensity of the ventilation device is positively correlated with the result of the second weighted summation. For details about how to generate the evacuation path based on the gas monitoring data and the area data, please refer to the relevant description in step 221.

[0061] In some embodiments of the present specification, the evacuation path is ventilated by automatically starting the ventilation device of the corresponding area, effectively preventing the invasion of toxic and harmful gases or smoke, and ensuring the safety and smoothness of the evacuation path.

[0062] Figure 3 is an exemplary flowchart for determining an evacuation path according to some embodiments of the present specification. In some embodiments, the method for determining an evacuation path can be performed by an emergency supervision management platform. As shown in Figure 3 , the flowchart 300 includes the following steps.

[0063] Step 310: Acquire image sensing data of the target area based on the image acquisition device.

[0064] The image sensing data refers to image data acquired by monitoring the image acquisition device.

[0065] Step 320: Acquire area personnel data and obstacle data of the target area based on the image sensing data.

[0066] The area personnel data refers to data describing the personnel situation of the target area. For example, the number of personnel, the personnel density, and the moving direction of the crowd.

[0067] In some embodiments, the emergency supervision management platform can acquire the number of personnel, the moving direction of the crowd, and the size of the area by image recognition algorithm based on the image sensing data, and determine the personnel density as the ratio of the number of personnel to the size of the area. The image recognition algorithm can be Haar feature cascade algorithm.

[0068] The obstacle data refers to data describing the situation of obstacles in the target area. For example, the size of the obstacle, the position of the obstacle, the area ratio of the obstacle, and the number of obstacles.

[0069] In some embodiments, the emergency supervision management platform can acquire the obstacle data by image recognition algorithm based on the image sensing data.

[0070] At step 330, a safety zone is determined based on the gas monitoring data and the zone data, and an alternative evacuation path is generated.

[0071] The safety zone refers to a zone that can effectively avoid gas hazards. In some embodiments, the safety zone can refer to a zone in which the gas concentration is lower than a second preset concentration threshold.

[0072] In some embodiments, the emergency supervision and management platform can divide the target zone into a plurality of functional sub-zones based on the terrain data in the zone data. The functional sub-zone refers to a sub-zone that is divided according to the function of the target zone, such as a corridor, a stairwell, an elevator, a lobby, a room, etc. Then, the emergency supervision and management platform can input the gas monitoring data and the zone data into a Gaussian Plume Model to output the estimated gas concentration of each functional sub-zone, and determine the functional sub-zone with an estimated gas concentration lower than the second preset concentration threshold as a safety zone, and determine the functional sub-zone with an estimated gas concentration higher than a third preset concentration threshold as a high-risk zone.

[0073] The preset grid size, the second preset concentration threshold, and the third preset concentration threshold can be set by a person according to experience. The second preset concentration threshold is less than the first preset concentration threshold, and the first preset concentration threshold is less than the third preset concentration threshold.

[0074] The alternative evacuation path refers to a candidate path for determining an evacuation path.

[0075] In some embodiments, the emergency supervision and management platform can eliminate the connected paths passing through the high-risk zones, and take the remaining connected paths as the alternative evacuation paths. For more information about the connected paths and the evacuation paths, please refer to the relevant description above.

[0076] At step 340, an evacuation path is determined from the alternative evacuation paths based on the zone personnel data and the obstacle data.

[0077] In some embodiments, the emergency supervision and management platform can determine the obstacle influence degree and the congestion degree of the alternative evacuation paths according to the zone personnel data and the obstacle data, determine the path length and the path complexity of the alternative evacuation paths based on the zone data, determine the evacuation difficulty based on the path complexity, the path length, the obstacle influence degree, and the congestion degree of the alternative evacuation paths by querying an evacuation difficulty table, and select N alternative evacuation paths with the smallest evacuation difficulty as the evacuation paths. The evacuation difficulty table can be constructed according to historical data or experimental data. The greater the path complexity, the path length, the obstacle influence degree, and the congestion degree of the alternative evacuation paths, the greater the evacuation difficulty.

[0078] For example, the emergency supervision management platform can determine the area proportion of obstacles on the alternative evacuation path, the number of obstacles, perform third weighted summation on the normalized area proportion of obstacles and the number of obstacles to obtain the obstacle influence degree of the alternative evacuation path, the congestion degree of the alternative evacuation path is positively correlated with the personnel density, and the ratio of the straight line distance between the start and end points of the alternative evacuation path to the path length is determined, and the product of the ratio and the bending weight is determined as the path complexity of the alternative evacuation path.

[0079] The bending weight is positively correlated with the number of right-angle bends in the alternative evacuation path, and the value of N is positively correlated with the number of personnel in the target area. The weight of the third weighted summation can be preset by a person according to experience. The number of right-angle bends can be obtained based on an angle point detection algorithm such as Harris angle point detection.

[0080] In some embodiments, the emergency supervision management platform can acquire external image data based on an image acquisition device, determine the evacuation efficiency of the alternative evacuation path based on the area personnel data, the obstacle data, and the area data, and determine the evacuation path from the alternative evacuation paths based on the external image data and the evacuation efficiency.

[0081] The external image data refers to image data of an external environment area acquired by the image acquisition device.

[0082] The evacuation efficiency of the alternative evacuation path refers to the number of people evacuated per unit time through the alternative evacuation path, which can be used to measure the evacuation capacity of the alternative evacuation path.

[0083] In some embodiments, the emergency supervision management platform can construct a first target feature vector based on the area personnel data, the obstacle data, and the area data of each functional sub-area passed by the alternative evacuation path, and perform retrieval on the first target feature vector in a first vector database to determine a first reference feature vector with the highest vector similarity with the first target feature vector, and determine the corresponding first reference evacuation efficiency as the evacuation efficiency of the alternative evacuation path. The first vector database includes a plurality of first reference feature vectors and corresponding first reference evacuation efficiencies, which can be constructed according to historical data. For example, the first reference feature vector can be constructed based on historical area personnel data, historical obstacle data, and historical area data of each functional sub-area passed by a historical evacuation path, and the first reference evacuation efficiency can be represented by the actual number of people evacuated per unit time through the historical evacuation path. The vector similarity can be represented by cosine similarity, Euclidean distance, etc.

[0084] In some embodiments, the emergency supervision management platform can determine the evacuation efficiency of the alternative evacuation path based on the area personnel data, the obstacle data, the area data, and the passageway control data.

[0085] The passage control data refers to relevant data of a passage control device. The passage control device can include a gate, and the passage control data can include the position, opening speed, maximum passage capacity, door opening size, and the like of the gate.

[0086] In some embodiments, the passage control data can be obtained by manual input.

[0087] In some embodiments, the emergency supervision and management platform can construct a second target feature vector based on the regional personnel data, obstacle data, regional data, and passage control data of each functional sub-region passed by the alternative evacuation path, and perform a search on the second target feature vector in a second vector database to determine a second reference feature vector with the highest vector similarity to the second target feature vector, and determine the corresponding second reference evacuation efficiency as the evacuation efficiency of the alternative evacuation path. The second vector database includes multiple sets of second reference feature vectors and corresponding second reference evacuation efficiencies. The construction method of the second vector database is the same as that of the first vector database, and will not be described here.

[0088] In some embodiments of the present specification, by considering the passage control data, the evacuation efficiency of each path can be more accurately calculated to facilitate the system to quickly match the optimal evacuation scheme, shorten the decision-making time, and improve the decision-making accuracy.

[0089] In some embodiments, the emergency supervision and management platform can identify the personnel density, vehicle density, and environment type (such as a road, a square, and the like) of the external environment region based on external image data through an image recognition algorithm, determine a correction coefficient by querying a correction coefficient reference table based on the environment type, personnel density, and vehicle density of the external environment region, determine a corrected evacuation efficiency as the product of the evacuation efficiency and the correction coefficient, and sort the multiple alternative evacuation paths in descending order according to the corrected evacuation efficiency to select the top M alternative evacuation paths as the evacuation paths. The values of M and N can be the same or different.

[0090] The correction coefficient reference table is determined by a human being based on historical data or experimental data. In some embodiments, the emergency supervision and management platform determines a demand evacuation efficiency as the ratio of the number of personnel in the target region to a preset evacuation time, sorts the multiple alternative evacuation paths in descending order according to the corrected evacuation efficiency, sequentially accumulates and sums the corrected evacuation efficiencies of the sorted alternative evacuation paths to obtain a total evacuation efficiency, and determines the minimum number of alternative evacuation paths required when the total evacuation efficiency is greater than the demand evacuation efficiency as M. The demand evacuation efficiency refers to the lowest evacuation efficiency required for the safe evacuation of personnel in the target region, and the preset evacuation time is set by a human being based on experience.

[0091] In some embodiments of the present disclosure, by comprehensively evaluating the evacuation path inside the building and the external environmental conditions of the exit, the risk of congestion caused by insufficient capacity of the evacuation path can be effectively reduced, thereby improving the safety and efficiency of the evacuation process.

[0092] In some embodiments of the present disclosure, by integrating gas monitoring data, regional data generation, and alternative evacuation paths, and by filtering evacuation paths through actual regional personnel data and obstacle data, the feasibility and rationality of the evacuation path can be effectively balanced while ensuring the efficiency of the evacuation, thereby avoiding congestion caused by insufficient number of evacuation paths or confusion caused by unreasonable selection of evacuation channels.

[0093] Figure 4 is an exemplary flowchart of updating the safety zone and the alternative evacuation path according to some embodiments of the present disclosure. In some embodiments, the method of updating the safety zone and the alternative evacuation path can be performed by the emergency supervision management platform. As shown in Figure 4 , the flow 400 includes the following steps.

[0094] Step 410, based on the environmental monitoring device, obtaining environmental monitoring data of the target region.

[0095] The environmental monitoring data refers to the environmental condition related data obtained by the environmental monitoring device. For example, environmental temperature, environmental humidity, wind direction data, etc.

[0096] In some embodiments, in response to satisfying the preliminary evacuation condition, the emergency supervision management platform can perform step 420, which includes step 421 and step 422.

[0097] The preliminary evacuation condition refers to the condition that triggers the preliminary warning when a gas leakage danger occurs. In some embodiments, the preliminary evacuation condition can refer to the condition that needs to be warned before the evacuation condition is reached.

[0098] In some embodiments, the preliminary evacuation condition can include that the gas concentration in the gas monitoring data is higher than the fourth preset concentration threshold. The fourth preset concentration threshold can be preset by a person according to experience, and the fourth preset concentration threshold is lower than the first preset concentration threshold. For more information about the evacuation condition and the first preset concentration threshold, please refer to Figure 2 and the related description thereof.

[0099] Step 421, determining the estimated leakage data based on the regional data, the obstacle data, the gas monitoring data, and the environmental monitoring data.

[0100] The estimated leakage data refers to predicted data of gas leakage in the target area. In some embodiments, the estimated leakage data can be a sequence of gas concentrations at a plurality of future time points in a future time period in a plurality of functional sub-areas of the target area. The future time period and the future time points can be preset by a person according to actual conditions.

[0101] In some embodiments, the emergency supervision and management platform can determine the estimated leakage data based on the area data, the obstacle data, the gas monitoring data, and the environmental monitoring data through a safety area determination model.

[0102] In some embodiments, the safety area determination model can be a machine learning model, such as a Graph Neural Network (GNN) model.

[0103] In some embodiments, the input of the safety area determination model can include a leakage feature graph, and the output can be the estimated leakage data of each node of the leakage feature graph.

[0104] The leakage feature graph refers to a graph describing the gas leakage in the target area. The leakage feature graph can be composed of at least one node and at least one edge.

[0105] In some embodiments, one node corresponds to one functional sub-area of the target area. The node attribute of the node can include the area data, the obstacle data, the gas monitoring data, the environmental monitoring data, the gas leakage speed, and the wind direction data in the functional sub-area. For more information about the functional sub-area, the area data, the gas monitoring data, the gas leakage speed, and the wind direction data, please refer to Figure 2 Related description.

[0106] In some embodiments, the edge of the leakage feature graph can be a physical connection edge. When there is a spatial physical connection between two functional sub-areas corresponding to two nodes, there is an edge between the two nodes. The attribute of the edge includes the connection data of the two functional sub-areas connected by the edge.

[0107] The connection data includes the connection mode, the connection type, and the connection size of the spatial physical connection. The connection mode of the spatial physical connection includes direct connection and indirect connection. The direct connection refers to a connection mode in which two functional sub-areas interact with gas through tangible channels (such as doors, windows, etc.). The indirect connection refers to a connection mode in which two functional sub-areas interact with gas through other ways (such as ventilation systems, etc.) other than tangible channels. The connection type of the spatial physical connection refers to the device type through which two functional sub-areas interact with gas, such as a bidirectional door, a sliding window, etc. The connection size of the spatial physical connection refers to the device size through which two functional sub-areas interact with gas, such as the size of a one-way door, etc.

[0108] In some embodiments, the safety area determination model can be trained by a large number of first training samples with first labels. The first training samples can include a sample leakage feature graph constructed based on historical data collected at a first historical time point, and the first label can be historical leakage data at a plurality of second historical time points within a second historical period for each node in the sample leakage feature graph. The first historical time point is before the second historical period. The first training samples can be obtained by manually constructing based on historical data, and the first labels can be obtained by manually labeling based on historical data.

[0109] In some embodiments, the emergency supervision and management platform can train the safety area determination model based on the first training samples and the first labels. The training method can include but is not limited to gradient descent method, etc. For example, the emergency supervision and management platform can input a plurality of first training samples into an initial safety area determination model, construct a loss function based on the first labels and the output of the initial safety area determination model, and update the parameters of the initial safety area determination model based on the loss function. When the preset condition is met, the model training is completed, and the trained safety area determination model is obtained. The preset condition can be that the loss function converges, the number of iterations reaches a preset number threshold, etc.

[0110] Step 422, updating the safety area and the alternative evacuation path based on the estimated leakage data.

[0111] In some embodiments, the emergency supervision and management platform can take the functional sub-area with gas concentration lower than the second preset concentration threshold and no continuous leakage source at a plurality of future time points in the estimated leakage data as the updated safety area. For the description of the second preset concentration threshold, please refer to the above.

[0112] In some embodiments, the emergency supervision and management platform can take the alternative evacuation path with all the passing areas being the updated safety area as the updated alternative evacuation path.

[0113] In some embodiments, the emergency supervision and management platform can update the safety area and the alternative evacuation path based on the estimated leakage data and the ventilation device data of the target area.

[0114] The ventilation device data refers to the working parameter related data of the ventilation device, such as maximum air volume, etc. In some embodiments, the ventilation device data can be input by human in advance.

[0115] In some embodiments, the emergency supervision and management platform can determine the actual gas concentration of the functional sub-area according to the following formula: .

[0116] Wherein, is the actual gas concentration, is the estimated leakage data, a region volume of the target region, a maximum air volume of the ventilation device, a correction coefficient, a ventilation time; ventilation time pre-input by a human, the correction coefficient set by a human according to experience.

[0117] The emergency supervision management platform can take a functional sub-region with an actual gas concentration lower than the second preset concentration threshold and no continuous leakage source as an updated safe region, and take an alternative evacuation path passing through the updated safe region as an updated alternative evacuation path.

[0118] In some embodiments of the present specification, considering the dilution of the ventilation device in the space to the gas concentration in the space, the subsequent determination of the evacuation path can be more in line with the development of the actual evacuation situation.

[0119] In some embodiments of the present specification, the evacuation path selected by considering the gas concentration everywhere in the space avoids, to some extent, secondary damage that can be caused during the evacuation process, and improves the safety and effectiveness of the evacuation path.

[0120] In some embodiments, the emergency supervision management platform can update the alarm threshold and the monitoring frequency based on the estimated leakage data and the updated alternative evacuation path, send an alarm control signal to the alarm device deployed in the target region based on the updated alarm threshold, to control the alarm device to update the setting based on the updated alarm threshold, and send a monitoring control signal to the image acquisition device based on the updated monitoring frequency, to control the image acquisition device to update the setting based on the updated monitoring frequency.

[0121] The alarm threshold refers to the gas concentration threshold at which the alarm device triggers an alarm. In some embodiments, the alarm threshold can be the same as or close to the first preset concentration threshold (e.g., the difference is not more than 5%).

[0122] In some embodiments, the alarm threshold can be preset by a human.

[0123] The monitoring frequency refers to the frequency at which the image acquisition device performs monitoring.

[0124] In some embodiments, when the number of updated alternative evacuation paths is less than a preset number, the emergency supervision management platform can calculate the gas leakage rate according to the estimated leakage data by a rate formula, determine the reduction amplitude of the alarm threshold and the reduction amplitude of the monitoring frequency according to the gas leakage rate, and update the alarm threshold and the monitoring frequency according to the reduction amplitude, wherein the reduction amplitude is positively correlated with the gas leakage rate. The preset number can be preset by a human.

[0125] In some embodiments, the emergency supervision management platform can issue an alarm control signal to the alarm device deployed in the target area according to the updated alarm threshold, to drive the alarm device to perform an alarm threshold updating operation; and send a monitoring control signal to the image acquisition device according to the updated monitoring frequency, to drive the image acquisition device to perform a monitoring frequency updating operation.

[0126] In some embodiments of the present specification, the emergency supervision management platform ensures that the system can adapt to changes in environmental conditions by dynamically modifying the alarm threshold and accurately regulating the monitoring frequency of the image acquisition device, so as to achieve reasonable allocation of energy consumption while ensuring evacuation efficiency.

[0127] Figure 5 is a schematic diagram of determining the modal parameter according to some embodiments of the present specification.

[0128] In some embodiments, the evacuation parameter further includes a modal parameter of the evacuation device. As shown in Figure 5 the emergency supervision management platform can obtain a candidate modal parameter 514; based on the evacuation path 512, the area data 513, the gas monitoring data 511 and the candidate modal parameter 514, determine the emergency evacuation data 530 corresponding to the candidate modal parameter through a parameter determination model 520, and the parameter determination model is a machine learning model; and based on the emergency evacuation data 530, determine the modal parameter 540.

[0129] The modal parameter refers to the setting parameter of the specific form of the evacuation device when guiding evacuation. For example, the display brightness of an electronic sign, the flashing frequency of a lighting device, the display brightness of a display device, the projection brightness of a projection device, the volume of a broadcast device, etc.

[0130] The candidate modal parameter refers to the modal parameter that can be selected in the process of confirming the modal parameter. The candidate modal parameter can be pre-set by a human or randomly generated by a system.

[0131] The emergency evacuation data refers to data describing the estimated evacuation situation of the evacuation path. In some embodiments, the emergency evacuation data can include the evacuation rate of each evacuation path during evacuation, and the evacuation completion time.

[0132] In some embodiments, the emergency supervision management platform can determine the emergency evacuation data corresponding to the candidate modal parameter through a parameter determination model based on the evacuation path, the area data, the gas monitoring data and the candidate modal parameter.

[0133] The parameter determination model is a model for determining the modal parameter.

[0134] In some embodiments, the parameter determination model is a machine learning model, such as a multimodal fusion model (MFM).

[0135] In some embodiments, such as Figure 5 As shown, the inputs to the parameter determination model can include evacuation routes (512), area data (513), gas monitoring data (511), candidate modal parameters (514), area personnel data (516), environmental perception data (517), and obstacle data (518). The output can be emergency evacuation data (530) corresponding to the candidate modal parameters. For more information on evacuation routes, area data, area personnel data, gas monitoring data, and obstacle data, please refer to [link to relevant documentation]. Figure 2 and Figure 3 Related descriptions.

[0136] Environmental sensing data refers to environmental data related to sensing. Examples include ambient light levels and ambient noise levels. In some embodiments, environmental sensing data can be acquired by sensing devices. For more information on sensing devices, please see [link to relevant documentation]. Figure 1 And its related descriptions.

[0137] In some embodiments, the parameter determination model can be obtained by training a large number of second training samples with second labels. The second training samples may include sample evacuation routes, sample area data, sample gas monitoring data, sample modal parameters, sample area personnel data, sample environmental perception data, and sample obstacle data. The second training samples can be obtained based on historical data. The second label can be the actual emergency evacuation data corresponding to the second training sample, and the second label corresponding to the second training sample can be obtained manually.

[0138] The training process for the parameter determination model is similar to that for the safe region determination model, as described above, and will not be repeated here.

[0139] In some embodiments, such as Figure 5 As shown, the input to the parameter determination model 520 can also include environmental monitoring data 515 of the target area. For more information on environmental monitoring data, please refer to [link to relevant documentation]. Figure 4 Related descriptions.

[0140] In some embodiments, the second training sample may further include environmental monitoring data, and the second label may be the actual emergency evacuation data corresponding to the second training sample. The methods for obtaining the second training sample and the second label, as well as the training process of the parameter determination model, can be found in the description above.

[0141] In some embodiments of the present specification, environmental parameters such as temperature and humidity are key regulating factors of human physiological state, and environmental monitoring data of the target area is taken as a model input variable to quantitatively analyze the dynamic influence of the environment on the path passing efficiency and improve the prediction accuracy of personnel behavior response, thereby optimizing the effectiveness of the evacuation strategy.

[0142] In some embodiments, the emergency supervision and management platform can select the candidate modal parameter with the best evacuation effect as the modal parameter. Wherein, the best evacuation effect can refer to that the weighted score of the evacuation rate and the evacuation completion time in the emergency evacuation data corresponding to the candidate modal parameter is the highest, the faster the evacuation rate is, the shorter the evacuation completion time is, and the higher the score is, and the weighted weight can be preset by artificial.

[0143] In some embodiments of the present specification, the evacuation control accuracy and response efficiency under complex emergency scenarios are significantly improved by considering multi-dimensional dynamic parameter optimization, the autonomous adaptation ability of the system to sudden variable factors is enhanced, and the dynamic allocation efficiency of emergency resources is optimized while ensuring the safety of evacuation.

[0144] The embodiments in the present application are only for example and illustration, and do not limit the scope of application of the present application. Various modifications and changes made by those skilled in the art under the guidance of the present application are still within the scope of the present application.

[0145] In addition, some features, structures or characteristics in one or more embodiments of the present application can be properly combined.

[0146] If the description, definition and / or use of the terms in the accompanying materials of the present application are inconsistent or conflicting with the description, definition and / or use of the terms in the present application, the description, definition and / or use of the terms in the present application shall prevail.

Claims

1. A gas emergency system for urban public places based on an Internet of Things (IoT) big data model, characterized in that: This includes an emergency monitoring and management platform and an emergency monitoring target platform; The emergency monitoring and management platform is configured as follows: Based on the aforementioned emergency monitoring platform, gas monitoring data of the target area is acquired through monitoring devices deployed within the monitoring area; In response to the fulfillment of evacuation conditions, Based on the gas monitoring data and the regional data of the target area, evacuation parameters are generated, including evacuation route and sign control parameters, lighting control parameters, and gate control parameters; and... Based on the evacuation parameters, an evacuation control signal is sent to evacuation devices deployed within the target area to control the evacuation devices to guide the evacuation of personnel within the target area, including: The control display device displays the evacuation route; Based on the light sign control parameters, control the display color and direction of the electronic sign; Based on the aforementioned lighting control parameters, the lighting brightness and lighting mode of the lighting equipment are controlled; and, Based on the gate control parameters, the gate's opening and closing states are controlled.

2. The system as described in claim 1, characterized in that, The monitoring device also includes an image acquisition device, and the emergency monitoring and management platform is further configured as follows: Based on the image acquisition device, image sensing data of the target area is acquired; Based on the image sensing data, obtain the area personnel data and obstacle data of the target area; Based on the gas monitoring data and the regional data, safe areas are determined and alternative evacuation routes are generated; as well as, Based on the personnel data and obstacle data of the area, the evacuation route is determined from the alternative evacuation routes.

3. The system as described in claim 2, characterized in that, The emergency monitoring and management platform is further configured as follows: Based on the image acquisition device, external image data is acquired; Based on the personnel data, obstacle data, and area data of the region, the evacuation efficiency of the alternative evacuation routes is determined. as well as, Based on the external image data and the evacuation efficiency, the evacuation path is determined from the candidate evacuation paths.

4. The system as described in claim 2, characterized in that, The monitoring device also includes an environmental monitoring device, and the emergency monitoring and management platform is further configured as follows: Based on the environmental monitoring device, environmental monitoring data of the target area is acquired; In response to the fulfillment of pre-evacuation conditions, Based on the area data, the obstacle data, the gas monitoring data, and the environmental monitoring data, the estimated leakage data is determined; and, Based on the estimated leakage data, the safe zone and the alternative evacuation routes are updated.

5. The system as described in claim 1, characterized in that, The evacuation parameters also include the modal parameters of the evacuation device, which are configured to control the modal settings of the evacuation device; the emergency monitoring and management platform is further configured to: Obtain candidate modal parameters; Based on the evacuation routes, the regional data, the gas monitoring data, and the candidate modal parameters, an emergency evacuation data corresponding to the candidate modal parameters is determined using a parameter determination model, wherein the parameter determination model is a machine learning model; and, Based on the emergency evacuation data, the modal parameters are determined.

6. A gas emergency response method for urban public places based on an Internet of Things (IoT) big data model, characterized in that: The method is executed by an emergency monitoring and management platform in an urban public place gas emergency system based on an Internet of Things (IoT) big data model. The method includes: Based on the emergency monitoring platform, gas monitoring data of the target area is obtained through monitoring devices deployed in the monitoring area; In response to the fulfillment of evacuation conditions, Based on the gas monitoring data and the regional data of the target area, evacuation parameters are generated, including evacuation route and sign control parameters, lighting control parameters, and gate control parameters; and... Based on the evacuation parameters, an evacuation control signal is sent to evacuation devices deployed within the target area to control the evacuation devices to guide the evacuation of personnel within the target area, including: The control display device displays the evacuation route; Based on the light sign control parameters, control the display color and direction of the electronic sign; Based on the aforementioned lighting control parameters, the lighting brightness and lighting mode of the lighting equipment are controlled; and, Based on the gate control parameters, the gate's opening and closing states are controlled.

7. The method as described in claim 6, characterized in that, The step of determining the evacuation route from the candidate evacuation routes based on the area's personnel data and the obstacle data includes: Based on the image acquisition device, external image data is acquired; Based on the personnel data, obstacle data, and area data of the region, the evacuation efficiency of the alternative evacuation routes is determined; and, Based on the external image data and the evacuation efficiency, the evacuation path is determined from the candidate evacuation paths.

8. The method as described in claim 7, characterized in that, The step of determining the evacuation route from the candidate evacuation routes based on the area's personnel data and the obstacle data includes: Based on the image acquisition device, external image data is acquired; Based on the personnel data, obstacle data, and area data of the region, the evacuation efficiency of the alternative evacuation routes is determined; and, Based on the external image data and the evacuation efficiency, the evacuation path is determined from the candidate evacuation paths.

9. The method as described in claim 7, characterized in that, The monitoring device further includes an environmental monitoring device, and the method further includes: Based on the environmental monitoring device, environmental monitoring data of the target area is acquired; In response to the fulfillment of pre-evacuation conditions, Based on the area data, the obstacle data, the gas monitoring data, and the environmental monitoring data, the estimated leakage data is determined; and, Based on the estimated leakage data, the safe zone and the alternative evacuation routes are updated.

10. The method as described in claim 6, characterized in that, The evacuation parameters also include modal parameters of the evacuation device, which are configured to control the modal settings of the evacuation device; the method further includes: Obtain candidate modal parameters; Based on the evacuation routes, the regional data, the gas monitoring data, and the candidate modal parameters, an emergency evacuation data corresponding to the candidate modal parameters is determined using a parameter determination model, wherein the parameter determination model is a machine learning model; and, Based on the emergency evacuation data, the modal parameters are determined.

Images