Intelligent fire emergency response system and method based on cooperation of internet of things and unmanned aerial vehicle

Abstract

This invention discloses a smart fire emergency response system and method based on the Internet of Things (IoT) and drone collaboration. Based on detection data generated by a cluster of sensors under the IoT, the system determines the spatial characteristics of a fire accident and assigns task strategies to a portion of the drones in the drone swarm. It monitors the execution of these task strategies by a subset of drones, identifying processed and unprocessed sub-regions within the fire accident area. Based on the spatial relationship between the drones and the unprocessed sub-regions, it determines whether the drones are permitted to respond to the unprocessed sub-regions, thereby coordinating and adjusting the operational status of the drones and the rest of the drone swarm. By reserving a portion of drones as backups during task allocation, the system addresses the problem of some drones being unable to complete their originally assigned tasks, improving fire rescue efficiency and enhancing the operational coordination and reliability of the drone swarm.

Description

Technical Field

[0001] This invention relates to the field of unmanned aerial vehicle (UAV) control technology, and in particular to a smart fire emergency response system and method based on the collaboration between the Internet of Things (IoT) and UAVs. Background Technology

[0002] Unmanned aerial vehicles (UAVs), with their flexible flight and ability to integrate multiple operational functions, are widely used in fire rescue and fire emergency search scenarios. To maximize the speed of emergency response to fire incidents, UAV swarms are often used to divide the area into zones, with each UAV responsible for a specific zone's rescue and search. This method ensures synchronized processing across the entire area, improving rescue efficiency. However, due to environmental factors, it cannot be guaranteed that each UAV will completely and accurately complete its assigned zone, potentially resulting in incomplete or missed zones. Given that all UAVs in the swarm are assigned zones, no idle UAVs can take over the handling of these incomplete or missed zones, reducing the reliability of fire rescue operations. Therefore, coordinating the task allocation of UAVs within the swarm to the fire incident area is crucial for improving fire rescue efficiency and preventing missed zones. Summary of the Invention

[0003] Considering that during fire rescue operations using drone swarms, each drone is assigned a specific area processing task, but an effective drone redundancy mechanism is not established, when a drone is unable to complete its task, it cannot find another drone to take over, reducing fire rescue efficiency and affecting the operational coordination and reliability of the drone swarm. In view of the above problems, this invention is proposed to provide a smart fire emergency response system based on the Internet of Things and drone collaboration to overcome or at least partially solve the above problems, comprising: The fire accident identification module is used to acquire detection data generated by the IoT-based sensor cluster and determine the spatial characteristics of the fire accident based on the detection data. The task allocation module is used to allocate task strategies to a portion of the drones in the drone swarm based on the spatial characteristics of the fire accident. The partition identification module is used to monitor the real-time execution of the mission strategy of a portion of the drones and identify the processed and unprocessed sub-regions of the fire accident area. The response situation determination module is used to determine whether the portion of drones is allowed to respond to the unprocessed sub-region based on the spatial relationship between the portion of drones and the unprocessed sub-region; The collaborative adjustment module is used to collaboratively adjust the working status of the group of drones and another group of drones in the drone cluster based on the judgment result of whether the group of drones is allowed to deal with the unprocessed sub-region.

[0004] Optionally, the fire accident identification module is used to acquire detection data generated by the IoT-based sensor cluster, and determine the spatial characteristics of the fire accident based on the detection data, including: Monitor the operation logs of the IoT-based sensor cluster to obtain the response latency characteristics of all sensor devices; based on the response latency characteristics, determine all valid operating sensor devices within the sensor cluster. Based on the access node of the Internet of Things, acquire the detection data generated by all the validly operating sensing devices; Based on the spatial layout of all operational sensing devices, the abnormal data components of the detection data are spatially mapped to determine the spatial characteristics of the fire accident; wherein the spatial characteristics of the fire accident refer to the spatial range in which the fire accident occurred within the detection coverage area of ​​the sensing device cluster. The task allocation module is used to allocate task strategies to a portion of the drones in the drone swarm based on the spatial characteristics of the fire accident, including: By comparing the spatial characteristics of the fire accident, the spatial layout of the drone swarm, and the layout of obstacles in the surrounding environment, a task strategy is assigned to a portion of the drones in the drone swarm.

[0005] Optionally, the partition identification module is used to monitor the real-time execution of the mission strategy of the portion of drones, and to identify the processed and unprocessed sub-regions of the fire accident area, including: Based on the communication node of the Internet of Things, the task strategy execution real-time record of the aforementioned drones is monitored, and the data geographic tags generated by the drones during the execution of the task strategy are extracted from the real-time record of the task strategy execution. Based on the final data geotags generated by each drone and the planned response spatial areas of the aforementioned drones, the processed and unprocessed sub-areas of the fire accident area are identified; The response situation determination module is used to determine whether the portion of drones is allowed to respond to the unprocessed sub-region based on the spatial relationship between the portion of drones and the unprocessed sub-region, including: Based on the remaining battery status of the drones, the relative distance between the drones and the unprocessed sub-region, and the spatial range of the unprocessed sub-region, it is determined whether the drones have sufficient battery power to fully cover and deal with the unprocessed sub-region.

[0006] Optionally, the coordinated adjustment module is used to coordinately adjust the working status of the portion of drones and another portion of the drone cluster based on the determination result of whether the portion of drones is allowed to deal with the unprocessed sub-region, including: When a subset of drones is able to handle the unprocessed sub-region, a task strategy is redistributed to the subset of drones based on their respective busy / idle status and real-time updated detection data of the unprocessed sub-region. If one group of drones is not allowed to handle the unprocessed sub-area, then a task strategy is assigned to the other group of drones based on their respective historical task execution logs.

[0007] As one aspect of the present invention, embodiments of the present invention also provide a smart fire emergency response method based on the collaboration of the Internet of Things and drones, including: Acquire detection data generated by the IoT-based sensor cluster, determine the spatial characteristics of the fire accident based on the detection data, and assign task strategies to a portion of the drones in the drone cluster based on the spatial characteristics of the fire accident. Monitor the execution of the mission strategy of the aforementioned drones, identify the processed and unprocessed sub-areas of the fire accident area; determine whether the aforementioned drones are allowed to respond to the unprocessed sub-areas based on the spatial relationship between the aforementioned drones and the unprocessed sub-areas; Based on the determination result of whether a portion of the drones are allowed to deal with the unprocessed sub-region, the working status of the portion of drones and another portion of the drone cluster are adjusted in a coordinated manner.

[0008] Optionally, acquire detection data generated by a cluster of sensor devices under the Internet of Things (IoT), determine the spatial characteristics of the fire accident based on the detection data, and assign task strategies to a portion of the drones in the drone cluster based on the spatial characteristics of the fire accident, including: Monitor the operation logs of the IoT-based sensor cluster to obtain the response latency characteristics of all sensor devices; based on the response latency characteristics, determine all valid operating sensor devices within the sensor cluster. Based on the access node of the Internet of Things, acquire the detection data generated by all the validly operating sensing devices; Based on the spatial layout of all operational sensing devices, the abnormal data components of the detection data are spatially mapped to determine the spatial characteristics of the fire accident; wherein the spatial characteristics of the fire accident refer to the spatial range in which the fire accident occurred within the detection coverage area of ​​the sensing device cluster. By comparing the spatial characteristics of the fire accident, the spatial layout of the drone swarm, and the layout of obstacles in the surrounding environment, a task strategy is assigned to a portion of the drones in the drone swarm.

[0009] Optionally, the system monitors the execution of the mission strategy of a subset of drones, identifies the processed and unprocessed sub-areas of the fire incident area, and determines whether the subset of drones is permitted to handle the unprocessed sub-areas based on the spatial relationship between the subset of drones and the unprocessed sub-areas, including: Based on the communication node of the Internet of Things, the task strategy execution real-time record of the aforementioned drones is monitored, and the data geographic tags generated by the drones during the execution of the task strategy are extracted from the real-time record of the task strategy execution. Based on the final data geotags generated by each drone and the planned response spatial areas of the aforementioned drones, the processed and unprocessed sub-areas of the fire accident area are identified; Based on the remaining battery status of the drones, the relative distance between the drones and the unprocessed sub-region, and the spatial range of the unprocessed sub-region, it is determined whether the drones have sufficient battery power to fully cover and deal with the unprocessed sub-region.

[0010] Optionally, based on the determination result of whether the portion of drones is allowed to deal with the unprocessed sub-region, the working status of the portion of drones and another portion of the drone cluster are coordinated and adjusted, including: When a subset of drones is able to handle the unprocessed sub-region, a task strategy is redistributed to the subset of drones based on their respective busy / idle status and real-time updated detection data of the unprocessed sub-region. If one group of drones is not allowed to handle the unprocessed sub-area, then a task strategy is assigned to the other group of drones based on their respective historical task execution logs.

[0011] The beneficial effects of the above-mentioned technical solutions provided in the embodiments of the present invention include at least the following: This invention provides a smart fire emergency response system and method based on the Internet of Things (IoT) and drone collaboration. The system acquires detection data generated by a cluster of sensors under the IoT network. Based on the detection data, it determines the spatial characteristics of a fire accident. Based on these characteristics, it assigns task strategies to a portion of the drones in the drone cluster. It monitors the execution of these task strategies by a portion of the drones, identifying processed and unprocessed sub-regions within the fire accident area. Based on the spatial relationship between the drones and the unprocessed sub-regions, it determines whether the drones are permitted to handle the unprocessed sub-regions. Based on this determination, it coordinates and adjusts the operational status of the drones and another portion of the drone cluster. By reserving a portion of drones as backups during task allocation, the system addresses the problem of some drones being unable to complete their assigned tasks, thereby improving fire rescue efficiency and enhancing the operational coordination and reliability of the drone cluster.

[0012] Other features and advantages of the invention will be set forth in the following description, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention may be realized and obtained by means of the structures particularly pointed out in the written description and the accompanying drawings.

[0013] The technical solution of the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. Attached Figure Description

[0014] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used in conjunction with embodiments of the invention to explain the invention and do not constitute a limitation thereof. In the drawings: Figure 1 This is a schematic diagram of the structure of the smart fire emergency response system based on the collaboration of the Internet of Things and drones provided in an embodiment of the present invention; Figure 2 This is a flowchart illustrating the intelligent fire emergency response method based on the collaboration of the Internet of Things and drones provided in this embodiment of the invention. Detailed Implementation

[0015] Exemplary embodiments of the present disclosure will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.

[0016] In the description of this invention, it should be noted that the terms "center," "upper," "lower," "left," "right," "vertical," "horizontal," "inner," "outer," "far," "near," "front," and "rear," etc., indicating the orientation or positional relationship, are based on the orientation or positional relationship shown in the accompanying drawings and are only for the convenience of describing this invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of this invention. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0017] In the description of this invention, it should be noted that, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0018] Please see Figure 1 As shown, one embodiment of this application provides a smart fire emergency response system based on the collaboration of the Internet of Things (IoT) and drones. This smart fire emergency response system based on the collaboration of the IoT and drones includes: The fire accident identification module is used to acquire detection data generated by the IoT-based sensor cluster and determine the spatial characteristics of the fire accident based on the detection data. The task allocation module is used to assign task strategies to a portion of the drones in the drone swarm based on the spatial characteristics of the fire accident. The partition identification module is used to monitor the real-time execution of mission strategies by a portion of the drones and identify the processed and unprocessed sub-regions of the fire accident area. The response situation determination module is used to determine whether a subset of drones are allowed to respond to the unprocessed sub-region based on the spatial relationship between a subset of drones and the unprocessed sub-region. The collaborative adjustment module is used to collaboratively adjust the working status of a group of drones and another group of drones in the drone swarm based on the judgment result of whether a group of drones are allowed to deal with unprocessed sub-regions.

[0019] The IoT-based sensor cluster comprises a distributed deployment of various types of sensors to acquire multi-dimensional environmental information related to fires. These include smoke sensors (detecting smoke particles generated in the early stages of a fire for early warning), temperature sensors (monitoring abnormal increases in ambient temperature to help confirm the fire and identify high-temperature areas), flame sensors (rapidly detecting open flames by sensing the unique ultraviolet or infrared radiation spectrum of flames), gas sensors (detecting characteristic gases such as carbon monoxide associated with fires to help determine the fire type and toxicity risk), and image / video sensors (collecting visible light and thermal images of the scene, providing the most intuitive visual information about the fire's spatial situation and posture, serving as a key basis for subsequent UAV mission planning and adjustments). These sensors are connected through IoT nodes, and their detection data collectively constitute the multi-source information foundation for the system's fire identification and spatial feature analysis. Multiple sensors can be deployed at the same monitoring location, forming a sensor cluster at each location.

[0020] The beneficial effects of the above embodiments are that the smart fire emergency response system based on the Internet of Things and drone collaboration solves the problem that some drones cannot complete their originally assigned tasks by reserving some drones as backups during the task allocation of drone swarms, thereby improving fire rescue efficiency and enhancing the operational coordination reliability of drone swarms.

[0021] In another embodiment, the fire accident identification module is used to acquire detection data generated by the IoT-based sensor cluster, and determine the spatial characteristics of the fire accident based on the detection data, including: Monitor the operation logs of the IoT sensor cluster to obtain the response latency characteristics of all sensor devices; based on the response latency characteristics, determine all valid operating sensor devices within the sensor cluster. Based on the access nodes of all operating sensors in the Internet of Things, acquire the detection data generated by all operating sensors. Based on the spatial layout of all operational sensors, the abnormal data components of the detection data are spatially mapped to determine the spatial characteristics of fire accidents; whereby the spatial characteristics of fire accidents refer to the spatial range within the detection coverage area of ​​the sensor cluster where a fire accident occurred. The task allocation module is used to assign task strategies to a portion of the drones in the drone swarm based on the spatial characteristics of a fire accident, including: By comparing the spatial characteristics of fire accidents, the spatial layout of drone swarms, and the layout of obstacles in the surrounding environment, a task allocation strategy is developed for a portion of the drones in the drone swarm.

[0022] The beneficial effects of the above embodiments are that, in order to enable the drone swarm to respond promptly to changes in the external environment and to achieve timely and efficient communication control of the drone swarm, the drone swarm is connected to the Internet of Things (IoT), and the IoT is also connected to a cluster of sensor devices. This cluster of sensor devices may include, but is not limited to, a distributed array of temperature sensors, camera sensors, smoke sensors, etc., which acquire multimodal data of the external environment to facilitate accurate determination of whether a fire has occurred and the scope of such an incident. Considering the differences in response delay characteristics (i.e., the waiting time from receiving the start command to beginning detection) of each sensor within the cluster to its surrounding environment, generally speaking, a smaller response delay indicates a higher sensor response speed, and the more accurately the generated detection data reflects the real-time situation of the external environment. To accurately identify the occurrence of fire incidents in the external environment and their spatial location, it is necessary to select sensors with good response delay characteristics. To this end, the response latency characteristics of each sensor device are first obtained from the operation logs of the IoT sensor device cluster. Sensor devices with response latency less than a preset time length are identified as valid operating sensor devices. Then, based on the access nodes of all valid operating sensor devices in the IoT, the detection data generated by all valid operating sensor devices are obtained. It can be understood that the above detection data accurately represents the actual temperature, smoke, and visual state of the external environment.

[0023] Each operational sensor is located at a corresponding position in the external environment, and its detection space covers a certain spatial range. Therefore, based on the spatial layout of all operational sensors, the abnormal data components of the detection data are spatially mapped to determine the spatial characteristics of the fire accident, thereby accurately determining the spatial range of the fire accident in the external environment. The aforementioned spatial characteristics of the fire accident refer to the spatial range within the detection coverage space of the sensor cluster where the fire accident occurred.

[0024] Drone swarms are typically dispersed across different locations. To ensure that drones can reach the location of a fire incident quickly and efficiently, a selection of drones within the swarm is chosen based on the spatial characteristics of the fire incident, the spatial layout of the drone swarm (e.g., the location of each drone within the swarm), and the layout of obstacles in the surrounding environment (e.g., the location of obstacles that might interfere with drone flight). Task strategies are then assigned to a subset of drones within the swarm that can avoid these obstacles and fly to the fire incident location from their current positions within a predetermined timeframe. These task strategies refer to the drones' tasks of inspecting the fire incident location and detecting different types of parameters.

[0025] In another embodiment, the partition identification module is used to monitor the real-time execution of the mission strategy of a portion of the drones, and to identify the processed and unprocessed sub-regions of the fire accident area, including: Based on the communication nodes of some drones in the Internet of Things, the real-time record of the task strategy execution of some drones is monitored, and the data geotags generated by the drones during the execution of the task strategy are extracted from the real-time record of the task strategy execution. Based on the final data geotags generated by each drone and a portion of the drone's planned response space area, the processed and unprocessed sub-areas of the fire accident area are identified; The response situation determination module is used to determine whether a subset of drones is permitted to respond to the unprocessed sub-region based on the spatial relationship between a subset of drones and the unprocessed sub-region, including: Based on the remaining battery status of a subset of drones, the relative distance between a subset of drones and the unprocessed sub-region, and the spatial extent of the unprocessed sub-region, it is determined whether a subset of drones has sufficient battery power to fully cover and deal with the unprocessed sub-region.

[0026] The beneficial effects of the above embodiments are as follows: After the UAV is assigned a task strategy, it will inspect a portion of the spatial area where the fire accident occurred and detect different types of parameters according to the instructions of the task strategy. During the inspection and detection, it will simultaneously generate detection data, which will have corresponding data geographic tags. It can be understood that the aforementioned data geographic tags refer to the geographical location information of the UAV itself when generating the detection data. After the UAV completes the task strategy, it will finally generate a detection data set. Each piece of detection data in the detection data set will have a corresponding data geographic tag. The data geographic tags corresponding to the detection data sets generated by each UAV will be compared with the planned response spatial area formed when a portion of the UAVs was assigned a task strategy, thereby identifying and distinguishing the processed and unprocessed sub-areas of the fire accident area. The processed sub-areas refer to the sub-areas within the fire accident area that have been detected and covered by the UAVs; the unprocessed sub-areas refer to the sub-areas within the fire accident area that have not been detected and covered by the UAVs. This partitioning and identification of the fire accident area facilitates subsequent coordination of the detection operations of another set of backup UAVs in the unprocessed sub-areas.

[0027] Furthermore, based on the remaining battery status of a portion of the drones, the relative distance between a portion of the drones and the unprocessed sub-region, and the spatial range of the unprocessed sub-region, it is determined whether the aforementioned portion of the drones has sufficient power to support drone flight inspection of the aforementioned unprocessed sub-region, providing a basis for subsequent coordinated adjustment of the working status of a portion of the drones and another portion of the drone swarm.

[0028] In another embodiment, the collaborative adjustment module is used to collaboratively adjust the operating status of a subset of drones and another subset of drones in a drone swarm based on the determination result of whether a subset of drones is allowed to respond to unprocessed sub-regions, including: When some drones are allowed to handle unprocessed sub-regions, task strategies are redistributed to some drones based on their respective busy / idle status and real-time updated detection data of the unprocessed sub-regions. If a group of drones is not allowed to handle unprocessed sub-regions, then task strategies are assigned to the other group of drones based on their respective historical task execution logs.

[0029] The beneficial effects of the above embodiments are that, considering that a portion of the drones in the large drone swarm, besides the aforementioned portion, are in a standby state as backup drones, directly calling upon these other drones would take time. Therefore, in the actual collaborative calling process of the drone swarm, the aforementioned portion of drones will be given priority. Specifically, when a portion of drones is able to handle unprocessed sub-areas, task strategies are redistributed to these drones based on their respective busy / idle status and real-time updated detection data of the unprocessed sub-areas. When a portion of drones is not allowed to handle unprocessed sub-areas, task strategies are assigned to the other portion of drones based on their respective historical task execution logs, thereby efficiently coordinating and allocating the task execution status of drones within the drone swarm in the fire accident area.

[0030] Please see Figure 2 As shown, an embodiment of this application provides a smart fire emergency response method based on the collaboration of the Internet of Things (IoT) and unmanned aerial vehicles (UAVs). This smart fire emergency response method based on the collaboration of IoT and UAVs includes: Acquire detection data generated by the IoT-based sensor cluster, determine the spatial characteristics of the fire accident based on the detection data, and assign task strategies to a portion of the drones in the drone cluster based on the spatial characteristics of the fire accident. Monitor the real-time execution of mission strategies by a subset of drones, and identify the processed and unprocessed sub-areas of the fire incident area; based on the spatial relationship between the subset of drones and the unprocessed sub-areas, determine whether the subset of drones is permitted to respond to the unprocessed sub-areas; Based on the determination of whether a portion of the drones are allowed to deal with unprocessed sub-regions, the working status of a portion of the drones and another portion of the drone swarm are adjusted in a coordinated manner.

[0031] The beneficial effects of the above embodiments are that the smart fire emergency response method based on the Internet of Things and drone collaboration solves the problem that some drones cannot complete their originally assigned tasks by reserving some drones as backups during the task allocation of drone swarms, thereby improving fire rescue efficiency and enhancing the operational coordination reliability of drone swarms.

[0032] In another embodiment, detection data generated by a cluster of sensing devices under the Internet of Things is acquired; based on the detection data, spatial characteristics of the fire accident are determined; and based on the spatial characteristics of the fire accident, task strategies are assigned to a portion of the drones in the drone cluster, including: Monitor the operation logs of the IoT sensor cluster to obtain the response latency characteristics of all sensor devices; based on the response latency characteristics, determine all valid operating sensor devices within the sensor cluster. Based on the access nodes of all operating sensors in the Internet of Things, acquire the detection data generated by all operating sensors. Based on the spatial layout of all operational sensors, the abnormal data components of the detection data are spatially mapped to determine the spatial characteristics of fire accidents; whereby the spatial characteristics of fire accidents refer to the spatial range within the detection coverage area of ​​the sensor cluster where a fire accident occurred. By comparing the spatial characteristics of fire accidents, the spatial layout of drone swarms, and the layout of obstacles in the surrounding environment, a task allocation strategy is developed for a portion of the drones in the drone swarm.

[0033] In another embodiment, the execution status of the mission strategy of a portion of the drones is monitored, and the processed and unprocessed sub-regions of the fire accident area are identified; based on the spatial relationship between the portion of drones and the unprocessed sub-regions, it is determined whether the portion of drones is allowed to respond to the unprocessed sub-regions, including: Based on the communication nodes of some drones in the Internet of Things, the real-time record of the task strategy execution of some drones is monitored, and the data geotags generated by the drones during the execution of the task strategy are extracted from the real-time record of the task strategy execution. Based on the final data geotags generated by each drone and a portion of the drone's planned response space area, the processed and unprocessed sub-areas of the fire accident area are identified; Based on the remaining battery status of a subset of drones, the relative distance between a subset of drones and the unprocessed sub-region, and the spatial extent of the unprocessed sub-region, it is determined whether a subset of drones has sufficient battery power to fully cover and deal with the unprocessed sub-region.

[0034] In another embodiment, based on the determination result of whether a portion of the drones are allowed to handle unprocessed sub-regions, the working status of a portion of the drones and another portion of the drone swarm are coordinated and adjusted, including: When some drones are allowed to handle unprocessed sub-regions, task strategies are redistributed to some drones based on their respective busy / idle status and real-time updated detection data of the unprocessed sub-regions. If a group of drones is not allowed to handle unprocessed sub-regions, then task strategies are assigned to the other group of drones based on their respective historical task execution logs.

[0035] The intelligent fire emergency response method based on the collaboration of the Internet of Things and drones of the present invention has the same operation and effect as the intelligent fire emergency response system based on the collaboration of the Internet of Things and drones mentioned above, and will not be described again here.

[0036] In one embodiment, the step of acquiring detection data generated by a cluster of sensor devices under the Internet of Things (IoT), determining the spatial characteristics of a fire accident based on the detection data, and allocating task strategies to a portion of the drones in the drone cluster based on the spatial characteristics of the fire accident can also be implemented as follows: S601. Based on the detection data generated by various sensors in the IoT-based sensing device cluster, perform multi-source data fusion processing on each spatial location to obtain the comprehensive anomaly degree of each spatial location; the comprehensive anomaly degree is used to characterize the probability of a fire accident occurring at the corresponding spatial location. Preferably, the comprehensive anomaly degree Calculated using the following formula (1): (1) in, Indicates spatial location The overall anomaly degree at the location is dimensionless and takes the range of real numbers. The larger the value, the higher the probability of a fire. This represents the number of sensor types; it is a positive integer and is obtained from the system configuration. For the first Sensor-like fusion weights, dimensionless, with a range of values. And satisfy The data is dynamically adjusted based on sensor reliability. Indicates the first Sensor-like sensors in spatial position The detected values ​​at the location, with units related to the sensor type, are acquired in real time via the Internet of Things. Indicates the first The global historical mean of all detected values ​​of this type of sensor under normal conditions is obtained by collecting data from this type of sensor during periods without fire and calculating its arithmetic mean. Indicates the first The global historical standard deviation of all detection values ​​of the sensor under normal conditions is calculated using the same historical dataset mentioned above.

[0037] S602. Based on the comprehensive anomaly degree and the preset anomaly degree threshold of each spatial location, determine the set of fire areas, and based on the set of fire areas and the preset fire accident spatial feature algorithm, determine the quantified fire accident spatial features. In one embodiment, the quantified spatial characteristics of the fire accident are represented by the weighted fire area. In this case, step S602 can be implemented as the following sub-steps A1-A2: A1. Identify all spatial locations where the overall anomaly degree is greater than a preset anomaly degree threshold T. These spatial locations constitute a set of fire zones. ; A2. Assemble the fire area. Divide into M areas with an area of The square grid cells; for the first Each grid cell, with its center point coordinates taken. The spatial weight value of the grid cell is determined based on the location attribute of the center point and the preset spatial weight function. Based on the spatial weight values ​​and areas of all grid cells. Determine the weighted fire area.

[0038] Specifically, preferably, the formula for calculating the weighted fire area is as follows: Formula (2): (2) Where A is the weighted fire area; Assembly in the fire area The grid contained within Total number of units.

[0039] in, The value quantifies the performance of the j-th grid cell in fire emergency response. The relative importance of [something] is calculated using the following formula: in, The normalized fire intensity term represents the fire intensity of the j-th grid unit. The severity of the fire at the location of the fire is calculated as follows: . yes The overall anomaly degree of this point, To preset the anomaly threshold, It is a collection of fire zones. The maximum value of the overall anomaly score for all points within the region; This is the proximity term to critical areas, representing the distance between the j-th grid cell and the nearest pre-defined critical facility area (such as a densely populated area, hazardous materials storage area, or main evacuation route). Its calculation method is as follows: . yes The distance from this point to the edge of the area where its nearest pre-designated critical facility is located. This is a preset maximum impact distance (e.g., 200 meters). This ensures that areas closer to critical facilities receive higher processing priority.

[0040] and The preset weighting coefficients satisfy... > 0, > 0, and .

[0041] S603. Based on the quantified spatial characteristics of the fire accident and the preset effective processing area of ​​a single UAV, determine the estimated number of UAVs required corresponding to the quantified spatial characteristics of the fire accident. Preferably, the estimated number of UAVs corresponding to the quantified spatial characteristics of the fire accident is calculated according to the following formula (3): (3) in, This represents an estimated number of drones that need to be deployed. The preset effective processing area for a single drone is obtained by presetting it based on the drone's performance. This represents the maximum number of drones that the system is allowed to call upon. This is the floor function.

[0042] S604. Based on the quantified spatial characteristics of the fire accident, the estimated number of drones required, the real-time status of the drone cluster, environmental obstacle information, and preset task requirements, determine the task priority score for each drone in the drone cluster.

[0043] Preferably, the mission priority score for each UAV is calculated according to the following formula (4): (4) in, denoted as the mission priority score of the i-th drone, which is dimensionless. The larger the value, the more suitable the drone is for performing the mission. This represents the reachability score of the i-th drone, which is dimensionless and has a range of values, for example, . This value indicates how easily the drone can reach the fire scene; a higher value indicates that the drone can reach the fire area. The more convenient the middle position, the better the calculation formula, for example: , For the first The distance from the drone to the aforementioned intermediate position; This represents the distance attenuation coefficient, expressed in distance units. The value of L can be flexibly configured. A preferred method is as follows: Calculate the equivalent radius of the fire zone. Then let ,in It is a preset empirical coefficient (preferably 2); Preset weighting coefficients greater than 0 are used to adjust the accessibility scores separately. With ability rating Relative importance in priority assessment; The capability score for the i-th drone is dimensionless, and its value range is, for example, . The acquisition is pre-set based on the performance of the equipment carried by the drone; for example, one acquisition method. The method is as follows: Based on the statically preset normalized value of the hardware configuration of the i-th UAV, the value range is [0, 1]. Specifically, it can be obtained by evaluating its configuration level in core mission dimensions such as reconnaissance and perception, fire fighting and disposal, and endurance and maneuverability, and then weighted summing. This score is determined and entered into the system when the UAV is added to the cluster, and is called as a constant during mission scheduling; the higher the score, the stronger the UAV's capabilities and the higher the priority it is to be called. The comprehensive cost score for the i-th drone is dimensionless; the smaller the value, the lower the cost of the drone performing the mission. Its value can be calculated using the following formula (5): (5) in, The baseline cost constant characterizes the inherent basis for initiating an unmanned aerial vehicle (UAV) mission. The cost, which includes communication connectivity, basic hovering energy consumption, etc., is dimensionless and is a small normal number. The preferred value range is between [0.01, 0.1], for example, it can be fixed at 0.05.

[0044] Estimated flight time For the first The estimated total time required for a drone to fly from its current location to a safe approach point at the fire scene and complete operational preparations can be determined as follows: First, take the... The straight-line distance from the drone to the approach point This is used as the path length; then, the path length is divided by the preset cruising speed of the drone swarm. Finally, add a preset fixed preparation time for the task. ,Right now Among them, the fire safety operation approach point refers to a safe space location pre-demarcated outside the fire on the upwind side of the fire, in order to avoid drones entering the dangerous airspace in the center of the fire and to ensure their efficient operation, so that all drones can fly to it and start carrying out reconnaissance or firefighting missions.

[0045] This is the maximum permissible flight time for a drone, usually preset based on the drone's endurance.

[0046] Let be the obstacle risk coefficient for the i-th drone, representing the complexity of obstacles encountered by the i-th drone on its planned path from its current position to the fire safety operation approach point. It is a dimensionless number, ranging from [0,1]. Here, 0 indicates a completely open path, and 1 indicates an extremely complex and dangerous path. The coefficient can be determined based on a two-dimensional electronic map: a buffer zone of fixed width (e.g., 20 meters) is drawn on both sides of the straight line connecting the drone and the target point. The proportion of pixels within this buffer zone covered by fixed obstacles such as buildings and high-voltage lines is calculated, and this proportion is then linearly mapped to the [0,1] interval to obtain the coefficient. .

[0047] Let be the remaining battery percentage of the i-th drone, which is the ratio of the drone's current remaining battery to its full charge state, and is a dimensionless number. This is the energy consumption weighting coefficient, used to adjust the importance of electricity consumption factors in the total cost. It is a dimensionless positive number, for example, the value range is between [0.5, 3], and can be preset as needed; This is the risk weighting coefficient, used to adjust the importance of obstacle risk in the total cost calculation. It is a dimensionless positive number, for example, the value range is between [0.5, 3], and can be preset as needed.

[0048] S605. Sort all drones by their respective mission priority scores from highest to lowest, and select the top-ranked drones. A drone is included as part of the drones, and tasks are assigned to it; Y is a positive integer equal to or greater than 1.

[0049] The intelligent task allocation process implemented through steps S601-S605 in this embodiment of the invention brings the following beneficial effects: First, through multi-source data fusion and standardized processing, high-precision and interference-resistant perception of fire conditions is achieved. Second, by introducing quantified spatial characteristics of fire accidents, the system can automatically identify and prioritize high-priority locations with intense fires or those near critical areas, achieving precise guidance of rescue resources. Third, the system can estimate the required number of drones based on the fire situation, achieving adaptive matching of resources and disaster conditions. Finally, by constructing a priority scoring model that comprehensively considers drone reachability, mission capabilities, and execution costs, efficient and optimal scheduling of drone swarms is achieved while ensuring safety and endurance. The entire process operates in a closed loop, systematically improving the speed, success rate, and overall reliability of fire emergency response.

[0050] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. This disclosure is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this disclosure is limited only by the appended claims. Thus, if these modifications and variations of the invention fall within the scope of the claims of the invention and their equivalents, the invention is also intended to include these modifications and variations.

Claims

1. A smart fire emergency response system based on the collaboration of the Internet of Things and drones, characterized in that, include: The fire accident identification module is used to acquire detection data generated by the IoT-based sensor cluster and determine the spatial characteristics of the fire accident based on the detection data. The task allocation module is used to allocate task strategies to a portion of the drones in the drone swarm based on the spatial characteristics of the fire accident. The partition identification module is used to monitor the real-time execution of the mission strategy of a portion of the drones and identify the processed and unprocessed sub-regions of the fire accident area. The response situation determination module is used to determine whether the portion of drones is allowed to respond to the unprocessed sub-region based on the spatial relationship between the portion of drones and the unprocessed sub-region; The collaborative adjustment module is used to collaboratively adjust the working status of the group of drones and another group of drones in the drone cluster based on the judgment result of whether the group of drones is allowed to deal with the unprocessed sub-region.

2. The intelligent fire emergency response system based on the Internet of Things and drone collaboration as described in claim 1, characterized in that: The fire accident identification module is used to acquire detection data generated by the IoT-based sensor cluster, and to determine the spatial characteristics of the fire accident based on the detection data, including: Monitor the operation logs of the IoT-based sensor cluster to obtain the response latency characteristics of all sensor devices; based on the response latency characteristics, determine all valid operating sensor devices within the sensor cluster. Based on the access node of the Internet of Things, acquire the detection data generated by all the validly operating sensing devices; Based on the spatial layout of all operational sensing devices, the abnormal data components of the detection data are spatially mapped to determine the spatial characteristics of the fire accident; wherein the spatial characteristics of the fire accident refer to the spatial range in which the fire accident occurred within the detection coverage area of ​​the sensing device cluster. The task allocation module is used to allocate task strategies to a portion of the drones in the drone swarm based on the spatial characteristics of the fire accident, including: By comparing the spatial characteristics of the fire accident, the spatial layout of the drone swarm, and the layout of obstacles in the surrounding environment, a task strategy is assigned to a portion of the drones in the drone swarm.

3. The intelligent fire emergency response system based on the Internet of Things and drone collaboration as described in claim 1, characterized in that: The partition identification module is used to monitor the real-time execution of the mission strategy of a portion of the drones, and to identify the processed and unprocessed sub-regions of the fire accident area, including: Based on the communication node of the Internet of Things, the task strategy execution real-time record of the aforementioned drones is monitored, and the data geographic tags generated by the drones during the execution of the task strategy are extracted from the real-time record of the task strategy execution. Based on the final data geotags generated by each drone and the planned response spatial areas of the aforementioned drones, the processed and unprocessed sub-areas of the fire accident area are identified; The response situation determination module is used to determine whether the portion of drones is allowed to respond to the unprocessed sub-region based on the spatial relationship between the portion of drones and the unprocessed sub-region, including: Based on the remaining battery status of the drones, the relative distance between the drones and the unprocessed sub-region, and the spatial range of the unprocessed sub-region, it is determined whether the drones have sufficient battery power to fully cover and deal with the unprocessed sub-region.

4. The intelligent fire emergency response system based on the collaboration of the Internet of Things and drones as described in claim 1, characterized in that: The coordinated adjustment module is used to coordinately adjust the working status of the portion of drones and another portion of the drone cluster based on the determination result of whether the portion of drones is allowed to deal with the unprocessed sub-region, including: When a subset of drones is able to handle the unprocessed sub-region, a task strategy is redistributed to the subset of drones based on their respective busy / idle status and real-time updated detection data of the unprocessed sub-region. If one group of drones is not allowed to handle the unprocessed sub-area, then a task strategy is assigned to the other group of drones based on their respective historical task execution logs.

5. A smart fire emergency response method based on the collaboration of the Internet of Things and drones, characterized in that, include: Acquire detection data generated by the cluster of sensor devices under the Internet of Things, and determine the spatial characteristics of fire accidents based on the detection data; Based on the spatial characteristics of the fire accident, a task allocation strategy is implemented for a portion of the drones in the drone swarm. Monitor the execution of the mission strategy of the aforementioned drones, identify the processed and unprocessed sub-areas of the fire accident area; determine whether the aforementioned drones are allowed to respond to the unprocessed sub-areas based on the spatial relationship between the aforementioned drones and the unprocessed sub-areas; Based on the determination result of whether a portion of the drones are allowed to deal with the unprocessed sub-region, the working status of the portion of drones and another portion of the drone cluster are adjusted in a coordinated manner.

6. The intelligent fire emergency response method based on the collaboration of the Internet of Things and drones as described in claim 5, characterized in that: Acquire detection data generated by the cluster of sensor devices under the Internet of Things, and determine the spatial characteristics of fire accidents based on the detection data; Based on the spatial characteristics of the fire accident, a task allocation strategy is implemented for a portion of the drones in the drone swarm, including: Monitor the operation logs of the IoT-based sensor cluster to obtain the response latency characteristics of all sensor devices; based on the response latency characteristics, determine all valid operating sensor devices within the sensor cluster. Based on the access node of the Internet of Things, acquire the detection data generated by all the validly operating sensing devices; Based on the spatial layout of all operational sensing devices, the abnormal data components of the detection data are spatially mapped to determine the spatial characteristics of the fire accident; wherein the spatial characteristics of the fire accident refer to the spatial range in which the fire accident occurred within the detection coverage area of ​​the sensing device cluster. By comparing the spatial characteristics of the fire accident, the spatial layout of the drone swarm, and the layout of obstacles in the surrounding environment, a task strategy is assigned to a portion of the drones in the drone swarm.

7. The intelligent fire emergency response method based on the collaboration of the Internet of Things and drones as described in claim 5, characterized in that: Monitor the real-time execution of the mission strategy of the aforementioned drones, and identify the processed and unprocessed sub-areas of the fire accident area; based on the spatial relationship between the aforementioned drones and the unprocessed sub-areas, determine whether the aforementioned drones are permitted to respond to the unprocessed sub-areas, including: Based on the communication node of the Internet of Things, the task strategy execution real-time record of the aforementioned drones is monitored, and the data geographic tags generated by the drones during the execution of the task strategy are extracted from the real-time record of the task strategy execution. Based on the final data geotags generated by each drone and the planned response spatial areas of the aforementioned drones, the processed and unprocessed sub-areas of the fire accident area are identified; Based on the remaining battery status of the drones, the relative distance between the drones and the unprocessed sub-region, and the spatial range of the unprocessed sub-region, it is determined whether the drones have sufficient battery power to fully cover and deal with the unprocessed sub-region.

8. The intelligent fire emergency response method based on the collaboration of the Internet of Things and drones as described in claim 5, characterized in that: Based on the determination result of whether a portion of the drones is allowed to handle the unprocessed sub-region, the working status of the portion of drones and another portion of the drone cluster is coordinated and adjusted, including: When a subset of drones is able to handle the unprocessed sub-region, a task strategy is redistributed to the subset of drones based on their respective busy / idle status and real-time updated detection data of the unprocessed sub-region. If one group of drones is not allowed to handle the unprocessed sub-area, then a task strategy is assigned to the other group of drones based on their respective historical task execution logs.

Images