Intelligent city high-rise fire emergency evacuation method and system based on internet of things large model

Abstract

This invention provides a smart city high-rise fire emergency evacuation method and system based on an Internet of Things (IoT) big data model, relating to the field of urban fire safety monitoring. The system includes an emergency monitoring and management platform configured to: monitor environmental parameters of a geographical area using a multimodal sensor array; identify fire risk areas based on environmental parameters and building information model (BIM) data; determine a first emergency kit and evacuation route based on the fire risk areas, and send early warning notifications to user terminals in the fire risk areas and adjacent geographical areas; control a first emergency robot to move along the evacuation route and issue guidance signals to users; in response to the presence of a fire, identify safe areas and send the safe areas to user terminals on designated floors; determine a second emergency kit and temporary evacuation route based on the distribution of safe areas; and control a second emergency robot to move along the temporary evacuation route to the nearest safe area and issue guidance signals.

Description

Technical Field

[0001] This manual relates to the field of urban fire safety monitoring, and in particular to a smart city high-rise fire emergency evacuation method and system based on an Internet of Things (IoT) big data model. Background Technology

[0002] With the acceleration of urbanization, high-rise buildings, due to their long vertical evacuation routes and high population density, pose a severe challenge to traditional fire emergency systems. Currently, mainstream fixed fire alarm systems and static evacuation plans have significant shortcomings. The deployment of single sensors leads to frequent false alarms and makes it difficult to assess the fire situation; pre-set fixed escape routes cannot be dynamically adjusted according to changes in the fire situation; and manual dispatching results in a lag in the response speed of emergency resources.

[0003] Therefore, there is a need to provide a smart city high-rise fire emergency evacuation method and system based on the Internet of Things big data model, so as to achieve accurate monitoring and early warning of urban high-rise fire risks and improve the effectiveness and timeliness of urban high-rise fire emergency evacuation. Summary of the Invention

[0004] The invention includes a smart city high-rise fire emergency evacuation system based on an Internet of Things (IoT) big data model, comprising an emergency monitoring and management platform. The emergency monitoring and management platform includes a processor and a database, and is configured to execute a smart city high-rise fire emergency evacuation method based on an IoT big data model.

[0005] The invention includes a smart city high-rise fire emergency evacuation method based on an Internet of Things (IoT) big data model, comprising: monitoring environmental parameters of a geographic area using a multimodal sensor group, the multimodal sensor group including at least one of a smoke sensor, a temperature sensor, and an oxygen sensor; identifying fire risk areas from the geographic area using a processor based on the environmental parameters and building information model data; determining a first emergency box and an evacuation route from the building by searching a database based on the fire risk areas, controlling the first emergency box to automatically open its airtight door, releasing a first emergency robot, and sending a warning notification to user terminals in the fire risk areas and adjacent geographic areas; controlling the first emergency robot to move along the evacuation route via a wireless network and sending guidance signals to users; in response to the presence of a fire, identifying safe areas within the building from the geographic area using the processor, and sending the safe areas to user terminals on designated floors via the wireless network; determining a second emergency box and a temporary evacuation route based on the distribution of safe areas, and controlling the second emergency box to automatically open its airtight door and release a second emergency robot; controlling the second emergency robot to move along the temporary evacuation route to the nearest safe area via the wireless network and sending guidance signals to users.

[0006] The invention includes 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 high-rise fire emergency evacuation method based on an Internet of Things (IoT) big data model.

[0007] The beneficial effects of the above invention include, but are not limited to: (1) Through real-time multimodal monitoring, early identification of fire risk areas, dynamic generation of safe areas, and precise deployment and guidance of emergency robots, the efficiency and safety of personnel evacuation in high-rise building fires are greatly improved, and casualties are reduced. At the same time, the use of the Internet of Things big model makes data fusion, analysis and decision-making more efficient and comprehensive; (2) Based on environmental parameters and the rate of change of environmental parameters, collaborative analysis of multiple geographical areas can improve the accuracy of fire risk identification and early detection capability, overcome the limitations of traditional single parameter or single area judgment, reduce false alarms caused by temperature fluctuations or local anomalies, make the confidence of fire confirmation higher, thereby avoiding unnecessary panic and waste of emergency resources, and ensuring the accuracy and reliability of emergency response; (3) By dynamically updating unsafe areas to fire risk areas, temporary evacuation routes can be updated in a timely manner, avoiding personnel being stranded in potential risk areas, and significantly improving real-time safety assurance. (4) By using different types of emergency robots to undertake different tasks and release them precisely according to the actual situation of the fire, the allocation and utilization efficiency of emergency resources are optimized, ensuring that emergency robots are involved in different stages of the fire, and improving the timeliness and effectiveness of initial reconnaissance and mid-term fire extinguishing; (5) By integrating BIM data with sensor data (e.g., environmental parameters) to generate a three-dimensional dynamic model, users can see the real-time spread of flames and smoke, RSI heat maps of various geographical areas and evacuation routes, thereby significantly improving the trapped personnel's awareness of the fire situation, helping the trapped personnel to make correct evacuation decisions quickly, and greatly improving the decision-making efficiency and accuracy of the emergency command center. Attached Figure Description

[0008] This specification 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; 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 high-rise fire emergency evacuation system based on an Internet of Things (IoT) big data model, as shown in some embodiments of this specification.

[0010] Figure 2 This is an exemplary flowchart of a smart city high-rise fire emergency evacuation method according to some embodiments of this specification;

[0011] Figure 3 This is an exemplary structural diagram of a fire spread model shown in some embodiments of this specification;

[0012] Figure 4 This is an exemplary flowchart of a method for determining fire risk areas according to some embodiments of this specification;

[0013] Figure 5 These are exemplary schematic diagrams illustrating a three-dimensional dynamic model according to some embodiments of this specification. Detailed Implementation

[0014] To more clearly illustrate the technical solutions of the embodiments in this specification, 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 this specification. 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.

[0015] It should be understood that the terms “system,” “device,” “unit,” 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.

[0016] Flowcharts are used in this specification to illustrate the operations performed by the system according to embodiments of this specification. It should be understood that the preceding or following operations are not necessarily performed in exact order. 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 high-rise fire emergency evacuation system based on an Internet of Things (IoT) big data model, as shown in some embodiments of this specification.

[0018] In some embodiments, the smart city high-rise fire emergency evacuation system 100 based on an IoT big data model may include an emergency monitoring user platform 110, an emergency monitoring service platform 120, an emergency monitoring management platform 130, an emergency monitoring sensor network platform 140, an emergency monitoring object platform 150, a multimodal sensor group 160, an emergency kit 170, and an emergency robot 180. The IoT big data model refers to an IoT model architecture used to enable the efficient operation of large amounts of data within the smart city high-rise fire emergency evacuation system 100 based on the IoT big data model. In some embodiments, artificial intelligence models (e.g., ChatGPT, Gemini, Deepseek) can be applied to the IoT model architecture for data perception and processing.

[0019] In some embodiments, the multimodal sensor group 160, the emergency kit 170, and the emergency robot 180 are disposed in the emergency monitoring object platform 150.

[0020] The emergency monitoring user platform 110 refers to an interactive platform for emergency management personnel and users. In some embodiments, the emergency monitoring user platform 110 may include a processor, server, gateway, display screen, etc. In some embodiments, the emergency monitoring user platform 110 can communicate with user terminals (e.g., mobile phones, computers, personal digital assistants, etc.), and communicate and transmit data with user terminals based on instructions sent by the emergency monitoring management platform 130, for example, displaying fire risk areas, potential risk areas, and safe areas to user terminals, and receiving location information sent by user terminals, etc. For more information on fire risk areas, potential risk areas, and safe areas, please refer to [link to relevant documentation]. Figure 2 And its related descriptions.

[0021] Emergency monitoring service platform 120 refers to a platform that provides emergency monitoring services. In some embodiments, emergency monitoring service platform 120 can be configured as a server to perform bidirectional data interaction with emergency monitoring user platform 110 and emergency monitoring management platform 130.

[0022] The emergency monitoring and management platform 130 refers to a platform used for monitoring and managing information related to high-rise fires in cities. In some embodiments, the emergency monitoring and management platform 130 may include a server, a data storage system, a large-screen display system, IoT platform software, communication components (e.g., communication interfaces, gateways), etc. In some embodiments, the emergency monitoring and management platform 130 may be a software platform running on a server or in the cloud, used to process data and / or information obtained from other platforms (e.g., emergency monitoring service platform 120, emergency monitoring sensor network platform 140). Based on the acquired data, information, and / or corresponding processing results, the emergency monitoring and management platform 130 may execute program instructions to perform the functions and / or steps described in this specification.

[0023] In some embodiments, the emergency monitoring and management platform 130 may include a data center. The data center includes a database, a data processing model library, and computing units.

[0024] Databases are used to collect, store, and manage data related to emergency evacuation in high-rise fires, such as building information modeling (BIM) data, sensor monitoring and data acquisition (e.g., temperature, smoke concentration, oxygen concentration), etc. Databases can include MySQL, PostgreSQL, InfluxDB, and Prometheus. For information on BIM data and sensor monitoring and data acquisition, please refer to [link to relevant documentation]. Figure 2 And its related descriptions.

[0025] The data processing model library is used to store pre-trained large-scale data processing models. In some embodiments, the data processing model library may include chatbots, fire spread models, etc. For more information on fire spread models, please refer to [link to relevant documentation]. Figure 3 And its related descriptions.

[0026] A computing unit refers to a functional module that performs arithmetic, logical, and other instruction operations. A computing unit may include a processor. Processors may include a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), a Field-Programmable Gate Array (FPGA), an Application-Specific Integrated Circuit (ASIC), an Application-Specific Instruction Set Processor (ASIP), etc. In some embodiments, the processor may be used for algorithm execution, data processing, and issuing control signals; for example, the processor may identify fire risk areas and determine the release time of emergency robots. For more information on fire risk area identification and emergency robot release time, please refer to [link to relevant documentation]. Figure 2 , Figure 4 And its related descriptions.

[0027] The emergency monitoring sensor network platform 140 refers to a platform for the comprehensive management of sensor information related to high-rise fires in smart cities. In some embodiments, the emergency monitoring sensor network platform 140 may include a processor, server, gateway, etc. In some embodiments, the emergency monitoring sensor network platform 140 can perform bidirectional data interaction with the emergency monitoring management platform 130 and the emergency monitoring object platform 150. In some embodiments, the emergency monitoring sensor network platform 140 can control the operation of the multimodal sensor group 160, for example, by adjusting the frequency at which the multimodal sensor group 160 monitors and collects sensor data.

[0028] The emergency monitoring object platform 150 refers to a platform for monitoring entities or systems, used to display, manage, and analyze the operational status and data of the monitored entities or systems. In some embodiments, the emergency monitoring object platform 150 may include a processor, server, gateway, etc. In some embodiments, the emergency monitoring object platform 150 can be used to monitor the multimodal sensor group 160, emergency box 170, and emergency robot 180 installed on it. For example, the emergency monitoring object platform 150 can communicate with the emergency box 170 and the emergency robot 180 to achieve bidirectional data interaction. The emergency monitoring object platform 150 can receive instructions from the emergency monitoring management platform 130 through the emergency monitoring sensor network platform 140 to control the emergency box 170 to open and release the emergency robot 180, and control the operation of the emergency robot 180 (e.g., adjusting its movement speed, indicator light flashing frequency, etc.).

[0029] The multimodal sensor group 160 is a collection of various types of sensors. In some embodiments, the multimodal sensor group 160 may include smoke sensors, temperature sensors, oxygen sensors, thermal imaging sensors, toxic gas sensors, and miniature wind speed and direction sensors, etc. Sensors can periodically send heartbeat packets to the emergency monitoring sensor network platform 140 to indicate that the sensors are still functioning normally and connected to the network. If the emergency monitoring sensor network platform 140 does not receive a heartbeat packet from a sensor within a preset time period (e.g., 30 minutes), it can mark the sensor as a failed sensor. When sensors upload data, they can attach verification information. If the verification information indicates that the data was damaged or lost during transmission, the emergency monitoring sensor network platform 140 can request the sensor to retransmit the data. In geographical areas requiring focused monitoring (e.g., computer rooms), the smart city high-rise fire emergency evacuation system 100 based on an IoT big data model can deploy multiple sensors of the same type to achieve sensor and sensor data backup. For more information on the multimodal sensor group 160 and geographical areas, please refer to [link to relevant documentation]. Figure 2 And its related descriptions.

[0030] Emergency Box 170 refers to an intelligent storage device installed on the emergency monitoring platform 150. In some embodiments, Emergency Box 170 is used to store emergency robots or other rescue equipment (e.g., window breaker hammers, fire extinguishers). Emergency Robot 180 refers to a robot used to perform tasks such as rescue, environmental detection, and evacuation guidance. In some embodiments, Emergency Robot 180 may include a reconnaissance robot, a fire-fighting robot, and a guidance robot. The reconnaissance robot is used to determine the location and extent of the fire and can detect at the edge of the fire risk area. The fire-fighting robot has the function of automatically spraying extinguishing agents or cooling, and is used to locally control the fire as it spreads, creating conditions for personnel evacuation or firefighters to enter. The guidance robot is used to guide the evacuation of people. For example, the guidance robot can provide clear evacuation route navigation for trapped people through LED signs, voice broadcasts, etc. For more information on fire risk areas, please refer to [link to relevant documentation]. Figure 2 And its related descriptions.

[0031] In some embodiments, the emergency monitoring platform 150 may further include a wireless network. The wireless network is used to enable wireless communication connections between devices or platforms. In some embodiments, the wireless network includes Wi-Fi, 5G, LoRa, Bluetooth, etc.

[0032] In the embodiments described in this specification, the smart city high-rise fire emergency evacuation system 100 based on an IoT big data model can automatically and intelligently handle emergency evacuations in high-rise building fires. Through real-time multimodal monitoring, early identification of fire risk areas, dynamic generation of safe zones, and precise deployment and guidance of emergency robots, it significantly improves the efficiency and safety of personnel evacuation in high-rise building fires, reducing casualties. Simultaneously, the use of the IoT big data model makes data fusion, analysis, and decision-making more efficient and comprehensive.

[0033] Figure 2 This is an exemplary flowchart illustrating a smart city high-rise fire emergency evacuation method according to some embodiments of this specification. Figure 2 As shown, process 200 includes the following steps. In some embodiments, process 200 may be executed by an emergency monitoring and management platform.

[0034] Step 210: Monitor environmental parameters of the geographic area using a multimodal sensor array.

[0035] A geographic area refers to a unit within a building. For example, a geographic area can include a floor, room, corridor, fire compartment, or a specific space. A geographic area can be equipped with corresponding sensors; for example, smoke sensors can be installed in a corridor.

[0036] Environmental parameters refer to parameters used to describe environmental conditions that are monitored and collected by sensors. For example, environmental parameters may include at least one of temperature, smoke concentration, and oxygen concentration. Temperature, smoke concentration, and oxygen concentration can be monitored and collected using temperature sensors, smoke sensors, and oxygen sensors, respectively. As another example, environmental parameters may also include wind speed and direction. Wind speed and direction can be monitored and collected using miniature anemometers and wind direction sensors.

[0037] In some embodiments, the multimodal sensor array can continuously monitor and collect environmental parameters of a geographic area. In some embodiments, the multimodal sensor array can periodically monitor and collect environmental parameters of a geographic area based on a preset collection period. The preset collection period can be set manually or through a smart city high-rise fire emergency evacuation system based on an IoT big data model. For example, the preset collection period can be set to 30 minutes.

[0038] In some embodiments, the multimodal sensor group can control the smoke sensor, temperature sensor, oxygen sensor, thermal imaging sensor, toxic gas sensor, and miniature wind speed and direction sensor to collect and upload monitoring data (e.g., environmental parameters) at appropriate monitoring frequencies based on instructions sent by the processor, and to mark the smoke sensor, temperature sensor, oxygen sensor, thermal imaging sensor, toxic gas sensor, and miniature wind speed and direction sensor that have not uploaded monitoring data.

[0039] In some embodiments, the processor can send instructions to the multimodal sensor array to adjust the frequency of sensor data acquisition and uploading based on monitoring needs. For example, when a smoke sensor detects abnormal data (e.g., smoke concentration exceeding a preset concentration threshold), the processor can increase the frequency of data acquisition and uploading. In some embodiments, the processor can allocate appropriate monitoring frequencies based on the type of sensor. For example, the monitoring frequency of a temperature sensor can be higher than that of an oxygen sensor. In some embodiments, the number of sensors can be negatively correlated with the frequency of data acquisition and uploading. For example, when the number of sensors deployed in a geographical area exceeds a preset number threshold, the processor can decrease the frequency of data acquisition and uploading. For more information on multimodal sensor arrays, please refer to [link to relevant documentation]. Figure 1 And its related descriptions.

[0040] In some embodiments, when the sensor's heartbeat packet or monitoring data upload fails, the processor can mark the sensor's status as "offline" or "faulty" in the sensor status table. The sensor status table is stored in a database. The emergency monitoring and management platform can send the sensor's "offline" or "faulty" status to the emergency monitoring object platform for visual display, facilitating maintenance personnel to repair and replace the sensor.

[0041] The embodiments in this specification ensure the timeliness and accuracy of collected monitoring data by controlling different sensors to collect and upload monitoring data at different monitoring frequencies, and by quickly adjusting the monitoring frequency when an anomaly occurs. By marking sensors that have not uploaded monitoring data, the embodiments in this specification can improve the reliability and robustness of smart city high-rise fire emergency evacuation systems based on IoT big data models, promptly identify and repair fault points, avoid information blind spots and decision-making errors caused by sensor malfunctions, and ensure the coverage and connectivity of the monitoring network.

[0042] Step 220: Based on environmental parameters and building information model data, fire risk areas are identified from the geographic region using a processor.

[0043] Building Information Modeling (BIM) data refers to a collection of data based on a three-dimensional model, integrating various types of information throughout the entire lifecycle of a building project. For example, BIM data may include geometric features (e.g., dimensions, location, shape) and physical properties (e.g., materials, energy consumption).

[0044] A fire risk area is a geographical area where environmental parameters are abnormal. For example, the temperature and / or smoke concentration in a geographical area may rise sharply in a short period of time.

[0045] In some embodiments, the emergency monitoring and management platform can identify fire-risk areas based on environmental parameters of a geographical region. For example, in response to environmental parameters of a geographical region meeting a first preset condition, the emergency monitoring and management platform can identify the geographical region as a fire-risk area. Exemplarily, the first preset condition may include at least one of temperature higher than a preset temperature threshold, smoke concentration higher than a preset smoke concentration threshold, and oxygen concentration lower than a preset oxygen concentration threshold.

[0046] In some embodiments, the emergency monitoring and management platform can determine whether a geographical area is a fire risk area based on the fire confidence level of that area. For more details, please refer to [link to relevant documentation]. Figure 4 And its related descriptions.

[0047] Step 230: Based on the fire risk area, determine the evacuation routes of the first emergency box and the evacuation building by searching the database, control the first emergency box to automatically open the airtight door, release the first emergency robot, and send a warning notification to the user terminals in the fire risk area and adjacent geographical areas.

[0048] The first emergency kit refers to an emergency kit located on and / or near the evacuation route. The first emergency robot refers to the emergency robot placed inside the first emergency kit. For more information on emergency kits and emergency robots, please refer to [link to relevant documentation]. Figure 1And its related descriptions.

[0049] Adjacent geographical regions refer to other geographical regions that are directly adjacent to and / or indirectly adjacent to a geographical region. For example, a geographical region may share a boundary or boundary point with adjacent geographical regions. Another example is that a geographical region and its adjacent geographical regions are spatially connected and reachable from each other.

[0050] A warning notification is a notification message issued in response to a potential fire. In some embodiments, a warning notification may include text, voice, animation, etc.

[0051] In some embodiments, the emergency monitoring and management platform can determine the first emergency kit and evacuation route by searching a database based on the three-dimensional coordinates of the fire risk area, the extent of the fire risk area (e.g., the number of geographical areas covered), and the three-dimensional coordinates of the user terminal.

[0052] For example, the emergency monitoring and management platform can construct a first feature vector based on the three-dimensional coordinates of the fire risk area, the extent of the fire risk area, and the three-dimensional coordinates of the user terminal. Based on this first feature vector, the platform can then search a first vector database to obtain the first emergency kit and evacuation routes.

[0053] The 3D coordinates and extent of fire risk areas can be determined based on BIM. The 3D coordinates of user terminals can be obtained through the emergency monitoring user platform. The emergency monitoring user platform can obtain the 3D coordinates of user terminals through the Global Navigation Satellite System (GNSS). A vector database is a database used for storing, indexing, and querying vectors. Through a vector database, similarity queries and other vector management can be performed quickly on a large number of vectors. Vector databases can be stored within a database.

[0054] In some embodiments, the emergency monitoring and management platform can obtain the three-dimensional coordinates of a reference fire risk area of ​​a simulated building, the extent of the reference fire risk area, and the three-dimensional coordinates of a reference user terminal based on BIM and simulation experiment data (e.g., simulated fire data, simulated user terminal distribution, simulated user terminal 3D coordinates, etc.). Based on these data, it can construct multiple first reference vectors. Each first reference vector has a corresponding first vector label, which may include a reference emergency kit and a reference evacuation route that minimizes the simulated rescue time and / or maximizes the number of evacuees. The emergency monitoring and management platform can store the multiple first reference vectors and their corresponding first vector labels in a first vector database. In some embodiments, the calculation unit can calculate the similarity (e.g., cosine similarity, Euclidean distance) between a first feature vector and multiple first reference vectors, and determine the first vector label of the first reference vector with the highest similarity as the first emergency kit and evacuation route.

[0055] In some embodiments, the emergency monitoring and management platform can send an unlocking command to the emergency monitoring target platform based on the evacuation route. The emergency monitoring target platform then sends the unlocking command to the first emergency container via a wireless network, controlling the first emergency container to automatically open its airtight door and release the first emergency robot.

[0056] Step 240: Control the first emergency robot to move along the evacuation route via wireless network and send guidance signals to the user.

[0057] Guidance signals refer to the indicator light signals and / or voice broadcast signals of an emergency robot. For example, the LED lights on an emergency robot can guide users to evacuate along an evacuation route by flashing at a specific frequency or changing color.

[0058] In some embodiments, the emergency monitoring and management platform can send guidance instructions to the emergency monitoring target platform. The emergency monitoring target platform sends guidance instructions to the first emergency robot via a wireless network, controlling the first emergency robot to move forward along the evacuation route at a preset speed. The preset speed can be determined based on factors such as the width of the evacuation route, the complexity of the terrain, and the density of people. For example, the preset speed can be increased in a wide and flat corridor, while it can be decreased in narrow areas or areas with obstacles.

[0059] Step 250: In response to the presence of a fire, the processor identifies safe zones within the building from the geographic area and sends the safe zones to user terminals on designated floors via a wireless network.

[0060] A safe zone is a geographical area where one can temporarily take refuge after a fire breaks out. For example, a safe zone can be a geographical area where the temperature is below a preset temperature threshold.

[0061] In some embodiments, the emergency monitoring and management platform can identify safe areas based on environmental parameters of a geographic region. For example, in response to the environmental parameters of a geographic region not meeting a first preset condition, the emergency monitoring and management platform can identify the geographic region as a safe area. For more information on the first preset condition, please refer to step 220 and its related description.

[0062] For more information on identifying safe zones from geographic regions, please see [link to relevant documentation]. Figure 4 And its related descriptions.

[0063] Step 260: Based on the distribution of the safe area, determine the second emergency box and the temporary evacuation route, and control the second emergency box to automatically open the airtight door and release the second emergency robot.

[0064] The distribution of safe zones refers to their spatial distribution within a building. For example, safe zones can be distributed on the same floor and / or different floors of a building.

[0065] A temporary evacuation route is an emergency evacuation route that is quickly planned and established to reach a safe area in the event of a fire. In some embodiments, a temporary evacuation route may be part of an evacuation route.

[0066] The second emergency kit refers to an emergency kit located on and / or near a temporary evacuation route. The second emergency robot refers to an emergency robot placed inside the second emergency kit. In some embodiments, the first emergency kit may be the same as or different from the second emergency kit, and the first emergency robot may be the same as or different from the second emergency robot. For more information on emergency kits and emergency robots, please refer to [link to relevant documentation]. Figure 1 And its related descriptions.

[0067] In some embodiments, the emergency monitoring and management platform can determine the second emergency box and temporary evacuation routes based on the distribution of safe areas using a path planning algorithm. The path planning algorithm may include Dijkstra's algorithm, genetic algorithm, Ant Colony Optimization (ACO), etc. In some embodiments, the determination of the second emergency box and temporary evacuation routes is similar to the determination of the first emergency box and evacuation routes; for more details, please refer to step 230 and its related description.

[0068] The process of controlling the second emergency box to automatically open the airtight door and release the second emergency robot is similar to the process of controlling the first emergency box to automatically open the airtight door and release the first emergency robot. For more details, please refer to step 230 and its related description.

[0069] Step 270: Control the second emergency robot via wireless network to move along the temporary evacuation route to the nearest safe area and send guidance signals to the user.

[0070] In some embodiments, the emergency monitoring and management platform can send guidance instructions to the emergency monitoring object platform. The emergency monitoring object platform sends guidance instructions to the second emergency robot via a wireless network, controlling the second emergency robot to proceed to the nearest safe area at a preset speed along a temporary evacuation route. For more information on the preset speed and guidance signals, please refer to step 240 and its related description.

[0071] In some embodiments, adjacent geographical areas may include potentially risky areas, and process 200 may further include step 280.

[0072] Step 280: Based on the location of the fire risk area, wind direction, and the operation of the ventilation system, predict the potential risk area.

[0073] A potential risk area refers to an area that has not yet been affected by a fire, but where there is a possibility of the fire spreading. For example, if a fire is located on the third floor of a building, but due to wind direction and speed, a geographical area on the fourth floor may be affected by the fire, then that geographical area on the fourth floor is a potential risk area.

[0074] The location of a fire risk area refers to the spatial location of the geographical area where a fire may occur within a building. In some embodiments, the location of a fire risk area may be the point of ignition or the center of the fire risk area. For example, the location of a fire risk area may be the three-dimensional coordinates of the point of ignition or the three-dimensional coordinates of the center of the fire risk area.

[0075] In some embodiments, miniature wind speed sensors can collect wind speed in real time and upload the collected wind speed to an emergency monitoring and management platform via an emergency monitoring sensor network platform. The emergency monitoring and management platform can combine BIM data and ventilation system design data to predict the direction and / or path of smoke and / or heat spread based on wind speed. The ventilation system design data may include air volume, wind speed and velocity, duct size and orientation, and vent arrangement.

[0076] The operational status of a ventilation system refers to its working condition and performance during operation. For example, the operational status of a ventilation system can include its operating status (e.g., start-up or shutdown) and performance data (e.g., wind speed, air volume, energy consumption, etc.).

[0077] In some embodiments, the emergency monitoring and management platform can predict potential risk areas based on the location of fire risk areas, wind direction, and the operation of ventilation systems, using a fire spread model. For more details, please refer to... Figure 3 And its related descriptions.

[0078] The embodiments in this specification are based on the location of fire risk areas, wind direction, and the operation of ventilation systems. They can identify potential hazardous areas, enabling emergency response to shift from passive firefighting to proactive prevention and early intervention. This provides a basis for the deployment of emergency robots, thereby gaining more preparation time for personnel evacuation and subsequent rescue.

[0079] The embodiments described in this specification can automate and intelligently handle emergency evacuation in high-rise building fires. Through real-time monitoring by multimodal sensor arrays, early identification of fire risk areas, identification of safe areas, and precise deployment and guidance of emergency robots, the efficiency and safety of personnel evacuation in high-rise building fires can be significantly improved, casualties can be reduced, and the shortcomings of traditional manual evacuation instructions, such as lag, incomplete information, and insufficient guidance capabilities can be overcome, thus providing strong support for the safe operation of smart cities.

[0080] Figure 3 This is an exemplary structural diagram of a fire spread model shown in some embodiments of this specification.

[0081] In some embodiments, such as Figure 3 As shown, the emergency monitoring and management platform can construct a predictive map 350 based on the location 310, wind direction 320, ventilation system operation status 330, and BIM data 340 of the fire risk area. The predictive map 350 can be a data structure composed of nodes 351 and edges 352, with edges 352 connecting nodes 351. Nodes 351 and edges 352 have node attributes and edge attributes, respectively.

[0082] Node 351 may include multiple geographic regions. Node attributes may include whether a fire has occurred (e.g., 0 indicates no fire, 1 indicates a fire), environmental parameters (e.g., temperature, smoke concentration, oxygen concentration), and structural data (e.g., length, width, shape, floor height, wall type, etc.). Edge 352 is used to represent the connection between multiple geographic regions. Edge attributes may include distance, wind speed, and wind direction. In some embodiments, wind direction is the direction of edge 352. Node 351 may have outgoing edges and / or incoming edges. An incoming edge is an edge pointing to node 351, and an outgoing edge is an edge originating from node 351 and pointing to another node 351.

[0083] In some embodiments, the fire spread model 360 takes a prediction map 350 as input and outputs a potential risk area 370. In some embodiments, the fire spread model 360 can be acquired through training based on at least one set of training samples and their corresponding labels. In some embodiments, the training samples can be constructed based on historical data or experimental data, which can be obtained from a database. The training samples may include at least one set of sample prediction maps of sample buildings, and the labels may be potential risk areas of the sample buildings. In some embodiments, the labels may be determined and annotated based on historical fire data or experimental data of the sample buildings. For example, under conditions similar to the sample prediction map, the emergency monitoring and management platform can mark the node 351 corresponding to the geographical area affected by the fire in the historical fire data or experimental data of the sample buildings as a potential risk area.

[0084] During training, training samples are input into the initial fire spread model. A loss function is constructed based on the output and labels of the initial fire spread model. The parameters of the initial fire spread model are iteratively updated (e.g., using gradient descent) based on the loss function until preset training conditions are met. Training then ends, and the trained fire spread model is obtained. This trained fire spread model is then used as the fire spread model 360. The preset training conditions may include, but are not limited to, loss function convergence and reaching a threshold training period.

[0085] For more information regarding the location 310, wind direction 320, ventilation system operation status 330, BIM data 340, and potential risk areas 370, please refer to [link / reference needed]. Figure 2 And its related descriptions.

[0086] The embodiments in this specification construct a predictive map based on the location of the fire risk area, wind direction, and the operation of the ventilation system. Using a trained fire spread model, it predicts potential risk areas and can combine the actual situation to more accurately predict dangerous areas where fires may occur, reducing the manpower costs and resource waste required for human assessment.

[0087] Figure 4 This is an exemplary flowchart illustrating a method for determining fire risk areas according to some embodiments of this specification. Figure 4 As shown, process 400 includes the following steps. In some embodiments, process 400 may be executed by an emergency monitoring and management platform.

[0088] Step 410: For one of the multiple geographic regions, the processor collects and analyzes the rate of change of environmental parameters in that geographic region and the rate of change of environmental parameters in adjacent geographic regions.

[0089] The rate of change of an environmental parameter refers to the amount of change of the environmental parameter per unit time. For example, the rate of change of temperature can be expressed as: (current temperature - last collected temperature) / time interval.

[0090] In some embodiments, the processor continuously collects environmental parameters of a geographic region and its neighboring geographic regions, and calculates the change in these parameters within a unit of time. In some embodiments, the processor can periodically collect environmental parameters of a geographic region and its neighboring geographic regions based on a preset collection period, and calculate the change in these parameters within a unit of time. In some embodiments, the processor can set the preset collection period to a unit of time; for example, the preset collection period can be set to 1 hour, in which case the unit of time is 1 hour.

[0091] Step 420: Determine the fire confidence level of the geographical area based on the rate of change of environmental parameters in the geographical area and the rate of change of environmental parameters in adjacent geographical areas.

[0092] Fire confidence is used to characterize the degree of anomaly in environmental parameters of a geographic area. In some embodiments, fire confidence can be expressed as a dimensionless numerical value.

[0093] In some embodiments, the emergency monitoring and management platform can determine the regional confidence level of a geographic area based on the rate of change of environmental parameters within that area. Regional confidence level refers to the baseline risk of a fire occurring in the geographic area. Regional confidence level can be expressed as a dimensionless numerical value.

[0094] The emergency monitoring and management platform can determine the fire confidence level of a geographical area based on the positive correlation between the fire confidence level of that area and the regional confidence level of its adjacent geographical areas.

[0095] In some embodiments, the region confidence level can be determined by formula (1):

[0096] (1)

[0097] in, For regional confidence, For the rate of temperature change, Temperature weighting, The rate of change of smoke concentration. Weighted by smoke concentration, This represents the rate of change in oxygen concentration. The oxygen concentration is the weight. , and It can be set based on experience, or it can be set by a smart city high-rise fire emergency evacuation system based on a large IoT model.

[0098] The fire confidence level can be determined by formula (2):

[0099] (2)

[0100] in, Fire confidence level for a geographical region. The regional confidence level for a geographical area. For the first n Regional confidence level of adjacent geographical regions For geographical regions and the first n The degree of correlation between adjacent geographical regions n A positive integer greater than or equal to 1. Relevance It can be based on the distance between a geographic region and its neighboring geographic regions. d Determined. For example, distance. d The larger the value, the smaller the correlation. The correlation can be represented by a dimensionless numerical value. For example, the correlation value can range from 0 to 1.

[0101] It is known that there are two cases: the fire confidence level is greater than the confidence threshold, and the fire confidence level is less than or equal to the confidence threshold.

[0102] Step 430: In response to a fire confidence level greater than a confidence threshold, the geographical area is determined to be a fire risk area. The confidence threshold varies for different geographical areas.

[0103] In some embodiments, the confidence threshold for a geographic area can be represented by a dimensionless numerical value. The emergency monitoring and management platform can obtain information such as gas usage, historical temperature, alarm information, and geographic area type from the database.

[0104] Gas usage information may include historical gas consumption; historical temperature information may include extreme temperature values; alarm information may include the number of historical false alarms and the total number of alarms; the type of geographical area may include offices, corridors, kitchens, computer rooms, etc.; geographical areas of the same type can form the first area cluster. The confidence threshold of a geographical area can be determined by formula (3):

[0105] (3)

[0106] in, For the first i Confidence threshold for each geographical region For the first i Temperature extremes in a geographical region For the first i The mean of the temperature extremes of the first regional cluster to which each geographical region belongs. For the firsti The historical average gas consumption of a geographical region For the first i The average historical gas consumption of each geographical region within its first regional cluster. For the first i Historical false alarm count for a geographical region For the first i The total number of alarms for the first region cluster to which each geographical region belongs. i It is a positive integer greater than or equal to 1. When and / or When it is 0, it satisfies .

[0107] In some embodiments, the emergency monitoring and management platform can identify safe zones based on environmental parameters of multiple geographical areas, and update safe zones as fire risk zones based on the rate of change of environmental parameters of the safe zones.

[0108] In some embodiments, the emergency monitoring and management platform can continuously analyze environmental parameters (e.g., temperature, smoke concentration, and oxygen concentration) across multiple geographic areas, and predict the diffusion paths of smoke and / or heat based on prediction maps using Gaussian plume models or computational fluid dynamics (CFD). The Gaussian plume model and CFD can be stored in a data processing model library. Based on the environmental parameters of multiple geographic areas and the diffusion paths of smoke and / or heat, the emergency monitoring and management platform can identify geographic areas that are not on the diffusion paths of smoke and / or heat, and whose rate of change of environmental parameters is less than a first rate of change threshold, and define these geographic areas as safe zones. The first rate of change threshold can be set based on experience or by a smart city high-rise fire emergency evacuation system based on an IoT-based large-scale model.

[0109] In some embodiments, the calculation unit can calculate the fire confidence level of a safe area based on the rate of change of environmental parameters of the safe area. If the fire confidence level of a safe area exceeds a confidence threshold, the safe area is updated to a fire risk area. For more information on fire risk areas and safe areas, please refer to [link to relevant documentation]. Figure 2 And its related description. For more information on the predicted map, please refer to... Figure 3 And its related description. For more information on fire confidence levels, please refer to step 420 and its related description.

[0110] In some embodiments, the emergency monitoring and management platform can dynamically assess the real-time survival index of multiple geographical areas through a processor; identify safe areas based on the real-time survival index of multiple geographical areas; analyze the rate of change of the real-time survival index through the processor, determine the target time based on the rate of change of the real-time survival index, and send an early warning notification to user terminals within the safe area at the target time.

[0111] The Real-time Survival Index (RSI) is used to characterize the suitability of a geographical area for trapped individuals to survive. In some embodiments, the RSI can be a score between 0 and 100, with higher scores indicating greater safety and suitability for trapped individuals.

[0112] In some embodiments, the processor or computing unit can calculate the RSI of a geographic region in real time based on formula (4):

[0113] (4)

[0114] in, Indicates the first i RSI of a geographical region Indicates the first i Temperature of a geographical region Indicates the first i Smoke concentration in a geographical area Indicates the first i Oxygen concentration in a geographical region Weighted by oxygen concentration, Temperature weighting, Weighted by smoke concentration, This represents the penalty factor. The penalty factor is used for punitive downregulation. When the concentration of toxic gases (e.g., CO / CO2) in a geographic area increases or the geographic area is located in a smog diffusion path, the RSI of that geographic area is lowered. , , and It can be set based on experience, or it can be set by a smart city high-rise fire emergency evacuation system based on a large IoT model.

[0115] In some embodiments, it is known that there are two scenarios: RSI greater than a preset RSI threshold and RSI less than or equal to a preset RSI threshold. For one geographic region among multiple geographic regions, in response to the RSI of that geographic region being greater than the preset RSI threshold, the emergency monitoring and management platform can determine that geographic region as a safe region. The preset RSI threshold can be set based on experience or by a smart city high-rise fire emergency evacuation system based on an IoT big data model. For example, the preset RSI threshold can be set to 80.

[0116] The rate of change of RSI refers to the amount of change in RSI per unit time. For example, the rate of change of RSI can be represented as: (current RSI - last acquired RSI) / time interval.

[0117] In some embodiments, the processor continuously collects the RSI of a geographic area and calculates the change in the RSI of that geographic area per unit time. In some embodiments, the processor can periodically collect the RSI of a geographic area based on a preset collection period and calculate the change in the RSI of that geographic area per unit time. In some embodiments, the processor can set the preset collection period to a unit time; for example, the preset collection period can be set to 1 hour, in which case the unit time is 1 hour.

[0118] The target time refers to the moment when the RSI of a geographic area decreases to a preset RSI threshold. In some embodiments, the processor can determine the target time based on the difference between the current time and the safe time of the safe area. The safe time of the safe area can be determined based on the rate of change of the RSI of the safe area. More information about safe time can be found below and in its related description.

[0119] In some embodiments, the emergency monitoring and management platform can estimate the safe time of a safe area based on the rate of change of the real-time survival index of the safe area; and predict the trend of the real-time survival index of the safe area in the future. User terminals within the safe area are configured to display the real-time survival index and remaining safe time of the safe area.

[0120] Safe time refers to the duration during which a safe area can remain in a safe state. For example, if the time from when a geographical area is identified as a safe area to when it becomes a potential risk area or a fire risk area is 30 minutes, then that time period is the safe time for that geographical area.

[0121] In some embodiments, the emergency monitoring and management platform can estimate the safe time of a safe area based on the RSI of the safe area, the rate of change of the RSI, and a preset RSI threshold. For example, the safe time can be represented as: (RSI - preset RSI threshold) / rate of change of RSI.

[0122] In some embodiments, the emergency monitoring and management platform can predict the trend of the RSI of a safe area over a future time period (e.g., a decrease or fluctuation around a certain value) using exponential smoothing or machine learning models. Machine learning models can include Long Short-Term Memory (LSTM), Transformer, Random Forest, etc. The future time period can be set based on experience or by a smart city high-rise fire emergency evacuation system based on a large IoT model. For example, the future time period can be set to one hour from the current moment.

[0123] In some embodiments, the emergency monitoring management platform can send the Reliability Status Index (RSI) and remaining safe time of a safe area to the emergency monitoring user platform via the emergency monitoring service platform. The emergency monitoring user platform then displays the RSI and remaining safe time of the safe area to the user through their user terminal.

[0124] The embodiments described in this manual achieve transparency and personalization of evacuation information by visually presenting the estimated safe time on the user terminal. Trapped individuals not only know the safety of their current geographical area but also clearly understand the remaining safe time for that area, thereby enhancing their self-rescue capabilities and optimizing evacuation efficiency.

[0125] The embodiments described in this manual provide a quantitative, intuitive, and comprehensive safety assessment standard through the Real-Time Survival Index (RSI), making the identification of safe zones more scientific and accurate. By analyzing the rate of change of the RSI and issuing early warnings, valuable "remaining safe time" can be provided to trapped personnel, enabling predictive evacuation and avoiding last-minute hasty evacuations, thereby greatly improving evacuation efficiency.

[0126] The embodiments described in this specification implement dynamic updating of safe zones. The smart city high-rise fire emergency evacuation system based on an IoT big data model can identify and adjust safe zones in real time according to the development of the fire, rather than relying on static presets. By dynamically updating areas that are no longer safe as fire risk areas, the embodiments in this specification can promptly update temporary evacuation routes, preventing people from being stranded in potentially risky areas and significantly improving real-time safety assurance capabilities.

[0127] In some embodiments, the emergency monitoring and management platform can, based on changes in the number of potential risk areas, determine the release time of the reconnaissance robot via a processor, and control the emergency boxes in the potential risk areas to automatically open their airtight doors and release the reconnaissance robot; based on the fire confidence level of a geographical area and the fire confidence level of adjacent geographical areas, the platform can, based on a processor, determine the release time of the fire extinguishing robot, and control the emergency boxes in the fire risk areas and adjacent geographical areas to automatically open their airtight doors and release the fire extinguishing robot.

[0128] The change in the number of potential risk areas refers to the change in the number of potential risk areas from none to many. In some embodiments, the processor can continuously monitor and analyze the changes in the number of potential risk areas.

[0129] In some embodiments, in response to the first appearance of a potential risk area, the emergency monitoring and management platform can determine the moment of the appearance of the potential risk area as the release time of the reconnaissance robot, and identify the potential risk area as the geographical area for releasing the reconnaissance robot. For example, in response to the emergency monitoring and management platform predicting for the first time, based on the edge properties of the prediction map using a Gaussian plume model or CFD, that a geographical area is located on the diffusion path of smoke and / or heat, the emergency monitoring and management platform can determine the moment of prediction of the geographical area as the release time of the reconnaissance robot, and identify the geographical area as the geographical area for releasing the reconnaissance robot. For more information on prediction maps, please refer to [link to relevant documentation]. Figure 3 And its related descriptions.

[0130] In some embodiments, given two scenarios—that the number of known potential risk areas is greater than a preset threshold and less than or equal to a preset threshold—the emergency monitoring and management platform can determine the release time of the reconnaissance robot based on the moment when the number of potential risk areas exceeds the preset threshold, and increase the number of reconnaissance robots based on the number of potential risk areas. The preset threshold can be set based on experience or by a smart city high-rise fire emergency evacuation system based on an IoT big data model. For example, the preset threshold can be set to 3.

[0131] In some embodiments, the emergency monitoring and management platform can determine the release time based on the rate of change in the number of potentially risky areas. For example, the release time can be characterized as: baseline release time. (1 - Quantity Change Rate). The baseline release time refers to the preset release time for the reconnaissance robot in the smart city high-rise fire emergency evacuation system based on the IoT big data model. The quantity change rate refers to the change in the number of potential risk areas per unit time. For example, the quantity change rate can be represented as: (Current number of potential risk areas - Last identified number of potential risk areas) / Time interval. When the quantity change rate increases, the release time can be shortened based on the baseline release time, thereby releasing the reconnaissance robot earlier.

[0132] In some embodiments, in response to a fire confidence level in a geographic area reaching or exceeding a confidence threshold, the emergency monitoring and management platform can determine the moment when the fire confidence level in a geographic area reaches or exceeds the confidence threshold as the release time of the fire-fighting robot.

[0133] The process of automatically opening the airtight door of the emergency box in the potential risk area and releasing the reconnaissance robot, as well as the process of automatically opening the airtight door of the emergency box in the fire risk area and adjacent geographical areas and releasing the fire-fighting robot, is similar to the process of automatically opening the airtight door of the first emergency box and releasing the first emergency robot. For more details, please refer to [link to relevant documentation]. Figure 2 And its related descriptions.

[0134] In some embodiments, the emergency monitoring and management platform can also determine the release time of the guided robot based on the real-time survival index and the rate of change of the real-time survival index in multiple geographical areas.

[0135] In some embodiments, given that there are known instances where the RSI rate of change is greater than a second rate of change threshold, and instances where it is less than or equal to the second rate of change threshold, the emergency monitoring and management platform can determine the release time of the guide robot as the moment when the RSI of a geographic area decreases to the RSI threshold and the rate of change of the RSI is greater than the second rate of change threshold. The second rate of change threshold can be determined based on experience or set by a smart city high-rise fire emergency evacuation system based on an IoT big data model. In some embodiments, in response to at least two geographic areas' RSIs decreasing to the RSI threshold, the emergency monitoring and management platform can sort the geographic areas based on the rate of change of the RSI of the at least two geographic areas and prioritize releasing the guide robot to the geographic area with the highest rate of change of the RSI.

[0136] In some embodiments, for at least two of the multiple geographic regions, the emergency monitoring and management platform may also determine the release order of the guide robot in the at least two geographic regions in response to the real-time survival index of the at least two geographic regions meeting a preset similarity condition; and release the guide robot to the at least two geographic regions based on the release order.

[0137] Preset similarity conditions refer to preset conditions for judging the similarity between multiple geographical regions based on RSI. In some embodiments, the emergency monitoring and management platform can determine the preset similarity conditions based on clustering intervals and clustering steps. The clustering interval is the interval between 0 and a preset RSI threshold (i.e., [0, preset RSI threshold]), and the clustering step can be set based on experience or by a smart city high-rise fire emergency evacuation system based on an IoT big data model. The emergency monitoring and management platform can divide the clustered area into multiple clustering sub-intervals based on the clustering step and set the preset similarity conditions to: the RSI of geographical regions belongs to the same clustering sub-interval. The emergency monitoring and management platform can divide at least one geographical region that meets the preset similarity conditions into a second regional cluster. For example, assuming the preset RSI threshold is 80 and the clustering step is 20, the clustering interval is [0, 80], and the clustering sub-intervals are {[0, 20], [20, 40], [40, 60], [60, 80]}. The emergency monitoring and management platform can divide a geographical region into four second-region clusters based on clustering sub-intervals.

[0138] In some embodiments, in response to the real-time survival indices of at least two geographical regions satisfying preset similarity conditions, the emergency monitoring and management platform can determine the release order of the guide robot in at least two geographical regions based on the number of user terminals in the at least two geographical regions, and release the guide robot to the at least two geographical regions based on the release order. For example, the emergency monitoring and management platform can obtain the number of user terminals in at least two geographical regions from the emergency monitoring user platform through the emergency monitoring service platform, sort the at least two geographical regions based on the number of user terminals in the at least two geographical regions, and prioritize releasing the guide robot to the geographical region with the largest number of user terminals. In some embodiments, the emergency monitoring and management platform can determine the number of user terminals in at least two geographical regions based on the node attributes of the prediction map.

[0139] The process of releasing the guide robot is similar to the process of controlling the first emergency box to automatically open the airtight door and release the first emergency robot. For more details, please refer to [link to relevant documentation]. Figure 2 And its related description. For more information on the predicted map, please refer to... Figure 3 And its related descriptions.

[0140] The embodiments described in this specification further incorporate the number of user terminals in a geographical area, thereby maximizing the efficiency of limited rescue resources. In geographical areas with similar RSI, the embodiments of this specification can prioritize the deployment of guiding robots to geographical areas with a greater number of user terminals, significantly improving evacuation efficiency and rescue coverage, and minimizing casualties.

[0141] The embodiments described in this specification enable the deployment timing of the guided robot to be closely linked to the actual evacuation needs and safety conditions of personnel, based on the actual fire situation. By combining the RSI and its rate of change, these embodiments allow for the early evacuation of personnel before a geographical area becomes a fire hazard zone, thus avoiding delays and panic.

[0142] The embodiments described in this specification implement the phased deployment of emergency robots. Different types of emergency robots undertake different tasks and are precisely deployed according to the actual situation of the fire, thereby optimizing the allocation and utilization efficiency of emergency resources and ensuring that emergency robots are involved at different stages of the fire, improving the timeliness and effectiveness of initial reconnaissance and mid-stage firefighting.

[0143] The embodiments in this specification are based on environmental parameters and the rate of change of environmental parameters, and conduct collaborative analysis of multiple geographical areas. This can greatly improve the accuracy of fire risk identification and early detection capability, overcome the limitations of traditional single parameter or single area judgment, reduce false alarms caused by temperature fluctuations or local anomalies, make the confidence of fire confirmation higher, thereby avoiding unnecessary panic and waste of emergency resources, and ensuring the accuracy and reliability of emergency response.

[0144] Figure 5 These are exemplary schematic diagrams illustrating a three-dimensional dynamic model according to some embodiments of this specification.

[0145] In some embodiments, such as Figure 5 The emergency monitoring and management platform can use a processor to integrate environmental parameters and building information model (BIM) data to generate a three-dimensional dynamic model of a building. User terminals can display this three-dimensional dynamic model, as well as real-time survival index, evacuation routes, and smoke spread trajectories for the geographical area.

[0146] A 3D dynamic model refers to a virtual building with spatiotemporal attributes constructed through digital modeling based on BIM and Geographic Information System (GIS). In some embodiments, the 3D dynamic model can simulate dynamic processes such as pedestrian evacuation. For example, the 3D dynamic model can be configured to dynamically display the spread trajectory and speed of flames, smoke, and heat.

[0147] In some embodiments, the emergency monitoring and management platform can align environmental parameters with BIM in both time and space, and generate a three-dimensional dynamic model of the building through dynamic model building and simulation engines (e.g., Unity 3D, Unreal Engine). For example, the emergency monitoring and management platform can map environmental parameters to the corresponding three-dimensional coordinate positions of the building model, and bind environmental parameters with geometric elements such as building facades and roofs, as well as BIM attributes (e.g., material thermal conductivity), to generate a three-dimensional dynamic model through dynamic model building and simulation engines.

[0148] In some embodiments, the emergency monitoring and management platform can also respond to changes in wind direction and speed, determine the direction and speed of smoke diffusion, and dynamically adjust safe zones and temporary evacuation routes based on the direction and speed of smoke diffusion. User terminals can display the real-time survival index of a geographical area using colors and numerical values.

[0149] In some embodiments, the emergency monitoring and management platform can continuously acquire wind direction and speed data collected by miniature anemometers from a multimodal sensor array via an emergency monitoring sensor network platform. In response to changes in wind direction and speed, the emergency monitoring and management platform can determine the smoke diffusion direction and speed based on the edge attributes of the predicted map, using a Gaussian plume model or CFD.

[0150] In some embodiments, the emergency monitoring and management platform can obtain an updated prediction map by updating the edge attributes of the prediction map based on the smoke diffusion direction and speed, and input the updated prediction map into a fire spread model to determine potential risk areas. The emergency monitoring and management platform can identify safe areas from geographical areas excluding fire risk areas and potential risk areas, obtain adjusted safe areas, and determine adjusted temporary evacuation routes based on the distribution of the adjusted safe areas.

[0151] The process of obtaining the adjusted safe zone can be found in step 250 and its related description. The process of determining the adjusted temporary evacuation routes can be found in step 260 and its related description. For more information on the prediction map, please refer to... Figure 3 And its related descriptions.

[0152] In some embodiments, the RSI of a geographic area can be displayed using a combination of color (e.g., green, yellow, red) and numerical value. For example, green indicates safe (RSI > 80), yellow indicates medium risk (40 ≤ RSI ≤ 80), and red indicates high risk (RSI < 40). When the RSI changes, the color and value of the RSI are updated in real time.

[0153] The embodiments described in this specification implement dynamic adaptive adjustments for fire spread prediction. By monitoring changes in wind direction and speed in real time, the smart city high-rise fire emergency evacuation system based on an IoT big data model can accurately predict changes in the spread path of smoke and / or heat, thereby enabling real-time, dynamic adjustments to safe zones and temporary evacuation routes to prevent trapped personnel from entering dangerous areas. The RSI color and numerical display on the user terminal further enhances the intuitiveness of the information and the timeliness of decision-making.

[0154] The embodiments described in this specification provide comprehensive, intuitive, and real-time fire scene visualization capabilities. By fusing BIM data with sensor data (e.g., environmental parameters) to generate a three-dimensional dynamic model, users can see the real-time spread of flames and smoke, RSI heat maps of various geographical areas, and evacuation routes. This significantly improves trapped personnel's understanding of the fire situation, helps them make quick and correct evacuation decisions, and greatly enhances the decision-making efficiency and accuracy of the emergency command center.

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

Claims

1. An Internet of Things (IoT) large model-based smart city high-rise fire emergency evacuation system, characterized in that, The system includes an emergency monitoring and management platform, which includes a processor and a database. The emergency monitoring and management platform is configured as follows: The environmental parameters of a geographic area are monitored using a multimodal sensor array, which includes at least one of a smoke sensor, a temperature sensor, and an oxygen sensor. Based on the environmental parameters and building information model data, the processor identifies fire risk areas from the geographical region. Based on the fire risk area, the system retrieves the database to determine the evacuation routes of the first emergency box and the evacuation building, controls the first emergency box to automatically open its airtight door, releases the first emergency robot, and sends a warning notification to user terminals in the fire risk area and adjacent geographical areas. The first emergency robot is controlled to move along the evacuation route via a wireless network and to send guidance signals to the user. In response to the presence of a fire, the processor identifies a safe zone within the building from the geographic area and transmits the safe zone to a user terminal on a designated floor via the wireless network. Based on the distribution of safe areas, determine the second emergency box and temporary evacuation routes, and control the second emergency box to automatically open the airtight door and release the second emergency robot; The second emergency robot is controlled via the wireless network to move along the temporary evacuation route to the nearest safe area and to send the guidance signal to the user. The environmental parameters include at least one of temperature, smoke concentration, and oxygen concentration. The emergency monitoring and management platform is also configured to: For one of multiple geographical regions The processor collects and analyzes the rate of change of environmental parameters in the geographical region and the rate of change of environmental parameters in adjacent geographical regions. The fire confidence level of the geographical area is determined based on the rate of change of environmental parameters in the geographical area and the rate of change of environmental parameters in the adjacent geographical areas. In response to the fire confidence level being greater than a confidence threshold, the geographical area is determined as the fire risk area, wherein the emergency monitoring and management platform is further configured to: The fire confidence level of the geographical region is determined based on the positive correlation between the fire confidence level of the geographical region and the regional confidence level of the adjacent geographical regions. The region confidence level is expressed as follows: in, The confidence level for the region. For the rate of temperature change, Temperature weighting, The rate of change of smoke concentration. Weighted by smoke concentration, This represents the rate of change in oxygen concentration. Weighted by oxygen concentration, The fire confidence level is expressed as follows: in, The fire confidence level for the geographical area. The regional confidence level of the geographical region. For the first n Regional confidence level of adjacent geographical regions For the geographical region and the first n The degree of correlation between adjacent geographical regions n It is a positive integer greater than or equal to 1.

2. The smart city high-rise fire emergency evacuation system as described in claim 1, characterized in that, The emergency monitoring and management platform is also configured as follows: Based on the environmental parameters of the multiple geographical regions, the safe zone is identified; Based on the rate of change of the environmental parameters of the safe area, the safe area is updated to the fire risk area.

3. The smart city high-rise fire emergency evacuation system of claim 1, wherein, The first or second emergency robot includes a reconnaissance robot and a firefighting robot, and the emergency monitoring and management platform is further configured as follows: Based on the changes in the number of potential risk areas, the processor determines the release time of the reconnaissance robot and controls the emergency boxes in the potential risk areas to automatically open their airtight doors and release the reconnaissance robot. Based on the fire confidence level of the geographical area, the processor determines the release time of the fire-fighting robot and controls the emergency boxes in the fire risk area and the adjacent geographical area to automatically open the airtight doors and release the fire-fighting robot.

4. The smart city high-rise fire emergency evacuation system of claim 1, wherein, The emergency monitoring and management platform is also configured as follows: The processor integrates the environmental parameters and the building information model data to generate a three-dimensional dynamic model of the building. The user terminal is configured to display the three-dimensional dynamic model, as well as the real-time survival index of the geographical area, the evacuation route, and the smoke diffusion trajectory.

5. A smart city high-rise fire emergency evacuation method based on an Internet of Things (IoT) big data model, characterized in that, The method includes: The environmental parameters of a geographic area are monitored using a multimodal sensor array, which includes at least one of a smoke sensor, a temperature sensor, and an oxygen sensor. Based on the environmental parameters and building information model data, a processor identifies fire risk areas from the geographical region. Based on the fire risk area, the system retrieves the database to determine the evacuation routes of the first emergency box and the evacuation building, controls the first emergency box to automatically open its airtight door, releases the first emergency robot, and sends a warning notification to user terminals in the fire risk area and adjacent geographical areas. The first emergency robot is controlled to move along the evacuation route via a wireless network and to send guidance signals to the user. In response to the presence of a fire, the processor identifies a safe zone within the building from the geographic area and transmits the safe zone to a user terminal on a designated floor via the wireless network. Based on the distribution of safe areas, determine the second emergency box and temporary evacuation routes, and control the second emergency box to automatically open the airtight door and release the second emergency robot; The second emergency robot is controlled via the wireless network to move along the temporary evacuation route to the nearest safe area and to send the guidance signal to the user. The environmental parameters include at least one of temperature, smoke concentration, and oxygen concentration. Identifying fire risk areas from the geographical region includes: For one of multiple geographical regions The processor collects and analyzes the rate of change of environmental parameters in the geographical region and the rate of change of environmental parameters in adjacent geographical regions. The fire confidence level of the geographical area is determined based on the rate of change of environmental parameters in the geographical area and the rate of change of environmental parameters in the adjacent geographical areas. In response to the fire confidence level being greater than a confidence threshold, the geographical area is determined to be the fire risk area, wherein determining the fire confidence level of the geographical area includes: The fire confidence level of the geographical region is determined based on the positive correlation between the fire confidence level of the geographical region and the regional confidence level of the adjacent geographical regions. The region confidence level is expressed as: in, The confidence level for the region. For the rate of temperature change, Temperature weighting, The rate of change of smoke concentration. Weighted by smoke concentration, This represents the rate of change in oxygen concentration. Weighted by oxygen concentration, The fire confidence level is expressed as follows: in, The fire confidence level for the geographical area. The regional confidence level of the geographical region. For the first n Regional confidence level of adjacent geographical regions For the geographical region and the first n The degree of correlation between adjacent geographical regions n It is a positive integer greater than or equal to 1. 6.The smart city high-rise fire emergency evacuation method of claim 5, wherein, The method further includes: Based on the environmental parameters of the multiple geographical regions, the safe zone is identified; Based on the rate of change of the environmental parameters of the safe area, the safe area is updated to the fire risk area. 7.The smart city high-rise fire emergency evacuation method of claim 6, wherein, The process of identifying the safe zone based on the environmental parameters of the multiple geographical regions includes: The processor dynamically evaluates the real-time survival index of the multiple geographical regions. Based on the real-time survival index of the multiple geographical regions, the safe zone is identified; The processor analyzes the rate of change of the real-time survival index, determines the target time based on the rate of change of the real-time survival index, and sends the warning notification to user terminals within the safe area at the target time.

Images