A forest fire early monitoring and warning method and system

Abstract

The present invention provides a forest fire early monitoring and early warning method and system, which belongs to the field of monitoring and early warning technology, and specifically includes: dividing a target forest area into multiple sub-areas according to a preset area, determining the wind direction of the target forest area based on the weather data of the current date, determining the affected adjacent areas when a fire occurs in the target forest area according to the wind direction, determining the impact of different affected adjacent areas on Internet of Things devices in other areas, and combining the interval distances between different sub-areas and the affected adjacent areas and the distribution data of Internet of Things gateway devices to determine the fire monitoring and early warning method of the target forest area, thereby improving the efficiency of fire monitoring and early warning processing.

Description

Technical Field

[0001] The present invention belongs to the technical field of monitoring and early warning, and in particular relates to a method and system for early monitoring and early warning of forest fires. Background Art

[0002] To achieve early monitoring and early warning of forest fires, the invention patent application CN202510287490.6, "A Forest Fire Prevention Method Based on Smoke Recognition," automatically learns and extracts key features of smoke, such as color, texture, and morphology, from preprocessed image data to obtain feature representations. When the fire level judgment result meets the warning conditions, an early warning signal is automatically triggered, and early warning of the fire is achieved through message push, sound and light alarms, and other methods. However, the following technical problems exist:

[0003] Existing technical solutions use IoT devices, gateways, etc. to monitor and warn of forest fires. However, once a fire occurs, it will inevitably cause damage to the IoT devices and gateways, which may make it difficult for the monitoring and warning reliability of some monitoring areas to meet the requirements. Therefore, how to generate targeted monitoring and warning processing strategies has become a technical problem that needs to be solved urgently.

[0004] To solve the above technical problems, the present application provides a forest fire early warning method and system. Summary of the Invention

[0005] To achieve the purpose of the present invention, the present invention adopts the following technical solutions:

[0006] Specifically, this application provides a forest fire early warning method, which specifically includes:

[0007] S1 uses the IoT gateway device in the target forest area as the target gateway device, and uses the IoT devices in other areas that use the target gateway device as the influencing devices, and determines the influencing areas in other areas based on the installation distribution of the influencing devices in the other areas;

[0008] S2, based on the distribution of the affected area and the distribution data of IoT devices in the affected area, determines that the target forest area does not belong to the risk area, and proceeds to the next step;

[0009] S3: dividing the target forest area into a plurality of sub-areas according to a preset area, determining the wind direction of the target forest area based on weather data of a current date, and determining the adjacent areas affected by a fire in the target forest area according to the wind direction;

[0010] S4 determines the impact of different IoT devices in the affected adjacent areas on other areas, and determines the fire monitoring and early warning method for the target forest area based on the interval distances between different sub-areas and the affected adjacent areas and the distribution data of IoT gateway devices.

[0011] The beneficial effects of the present invention are:

[0012] Based on the distribution of the affected areas and the distribution data of IoT devices in the affected areas, it is determined whether the target forest area belongs to the risk area. This enables the screening of risk areas from the perspective of the monitoring impact of the target forest area on other areas when a fire occurs. It also lays the foundation for generating differentiated fire monitoring and early warning strategies based on the differences in the impact conditions, ensuring the timeliness and reliability of fire monitoring and early warning.

[0013] Based on the impact of different IoT devices in the adjacent areas on other areas, the distances between different sub-areas and the affected adjacent areas, and the distribution data of IoT gateway devices, the fire monitoring and early warning method of the target forest area is determined. It takes into account the impact of fire on adjacent areas and the impact of adjacent areas on other areas when a fire occurs, as well as the difference in the degree of impact of fire in adjacent areas due to the difference in interval distance. It is further combined with the distribution data of IoT gateway devices to determine the impact of fire on other areas when the fire occurs itself, thereby achieving differentiated determination of the fire monitoring and early warning method of the target forest area, ensuring the timeliness of fire monitoring and early warning, and reducing the probability of impact on other areas.

[0014] A further technical solution is that the other area is an area located in the same forest location as the target forest area.

[0015] A further technical solution is that the Internet of Things device is a device for fire risk monitoring.

[0016] A further technical solution is that the Internet of Things device includes a monitoring device, a smoke sensing device and an infrared monitoring device.

[0017] A further technical solution is that the method for determining the influence area in the other areas is:

[0018] Determining the number of influencing devices in the other areas based on the installation distribution of the influencing devices in the other areas;

[0019] Whether the other area is an impact area is determined according to a proportion of the number of IoT devices in the other area among the impact devices in the other area.

[0020] A further technical solution is that when the proportion of the number of influencing devices in the other areas to the number of Internet of Things devices in the other areas is greater than the proportion of the preset number of influencing devices, the other areas are determined to be the influencing areas.

[0021] A further technical solution is that the method for determining the fire monitoring and early warning method in the target forest area is:

[0022] Determine the number of IoT devices in other sub-regions that use different methods to influence IoT gateway devices in adjacent regions based on the impact of IoT devices in other regions, the proportion of the number of IoT devices in the other sub-regions, and determine the device impact area in the other region based on the proportion of the number;

[0023] Based on the distance between the sub-region and the affected adjacent region, determine the sub-region whose distance is less than a preset distance threshold and regard it as the adjacent sub-region;

[0024] According to the distribution data of the Internet of Things gateway devices in the sub-area, the sub-areas of other areas where the Internet of Things gateway devices utilizing the sub-area exist are determined, and used as the fault-affected sub-areas. According to the number of the equipment-affected areas, the number of adjacent sub-areas and the number of the fault-affected sub-areas, the fire monitoring and early warning method of the target forest area is determined.

[0025] A further technical solution is that the device-affected area is other areas whose proportion is greater than a preset proportion threshold.

[0026] A further technical solution is to determine a fire monitoring and early warning method for the target forest area based on the number of areas affected by the equipment, the number of adjacent sub-areas, and the number of sub-areas affected by the fault, specifically including:

[0027] When the number of equipment-affected areas in the target forest area is greater than a preset equipment-affected area number threshold, when any monitoring device in the target forest area detects a fire signal, the target forest area outputs an early warning signal;

[0028] When the number of equipment-affected areas in the target forest area is not greater than a preset equipment-affected area number threshold, a fire monitoring and early warning method for the target forest area is determined based on the number of adjacent sub-areas and fault-affected sub-areas.

[0029] A further technical solution is to determine a fire monitoring and early warning method for the target forest area based on the number of adjacent sub-areas and fault-affected sub-areas, specifically including:

[0030] When the sum of the number of adjacent sub-areas and the fault-affected sub-areas in the target forest area accounts for a greater proportion of the number of sub-areas in the target forest area than the preset proportion of the number of affected sub-areas, then when any monitoring device in the target forest area detects a fire signal, the target forest area outputs an early warning signal;

[0031] When the sum of the number of adjacent sub-areas and fault-affected sub-areas in the target forest area accounts for no more than the preset number of affected sub-areas: when the monitoring equipment in the adjacent sub-areas or fault-affected sub-areas in the target forest area obtains a fire signal or the number of sub-areas that obtain a fire signal is greater than the preset fire risk sub-area number threshold, the target forest area outputs an early warning signal.

[0032] In a second aspect, the present invention provides a computer system comprising: a memory and a processor in communication connection, and a computer program stored in the memory and capable of running on the processor, wherein the processor executes the above-mentioned forest fire early monitoring and early warning method when running the computer program.

[0033] Other features and advantages will be described in the following description. The objectives and other advantages of the present invention are realized and obtained by the structures particularly pointed out in the description and drawings.

[0034] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] The above and other features and advantages of the present invention will become more apparent by describing in detail example embodiments thereof with reference to the accompanying drawings;

[0036] Figure 1 It is a flow chart of a forest fire early warning method;

[0037] Figure 2 is a flow chart of a method for determining an influencing area among other areas;

[0038] Figure 3 It is a flow chart to determine that the target forest area does not belong to the risk area;

[0039] Figure 4 It is a flow chart of a method for determining a fire monitoring and early warning method for a target forest area;

[0040] Figure 5 It is a framework diagram of a computer system. DETAILED DESCRIPTION

[0041] To help those skilled in the art better understand the technical solutions in this specification, the following will provide a clear and complete description of the technical solutions in the embodiments of this specification, in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of this specification, not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of this specification without creative work should fall within the scope of protection of this specification.

[0042] In this application, the setting data of the IoT gateway devices in the target forest area is used to determine the IoT devices in other areas that use IoT gateway devices, and the number of IoT devices in other areas that use IoT gateway devices is used to generate differentiated fire monitoring and early warning methods, thereby avoiding the impact of fire on the monitoring reliability of other areas.

[0043] Example 1 Figure 1 As shown, the present application provides a forest fire early warning method, which specifically includes:

[0044] S1 uses the IoT gateway device in the target forest area as the target gateway device, and uses the IoT devices in other areas that use the target gateway device as the influencing devices, and determines the influencing areas in other areas based on the installation distribution of the influencing devices in the other areas;

[0045] The affected areas are other areas where the number of affected devices in the IoT devices is greater than 0.2.

[0046] S2, based on the distribution of the affected area and the distribution data of IoT devices in the affected area, determines that the target forest area does not belong to the risk area, and proceeds to the next step;

[0047] The affected area where the number of IoT devices is within the preset range of the number of IoT devices is taken as the monitoring deviation area. When the number of monitoring deviation areas is greater than 3, the target forest area is determined to be a risk area.

[0048] S3: dividing the target forest area into a plurality of sub-areas according to a preset area, determining the wind direction of the target forest area based on weather data of a current date, and determining the adjacent areas affected by a fire in the target forest area according to the wind direction;

[0049] The affected adjacent areas are other areas that are located downwind of the target forest area and whose distance from the target forest area is less than a preset distance threshold.

[0050] S4 determines the impact of different IoT devices in the affected adjacent areas on other areas, and determines the fire monitoring and early warning method for the target forest area based on the interval distances between different sub-areas and the affected adjacent areas and the distribution data of IoT gateway devices.

[0051] When the number of IoT gateway devices used by IoT devices in other areas that affect adjacent areas is greater than a threshold value for the number of gateway devices, then when any monitoring device in the target forest area detects a fire signal, the target forest area will output an early warning signal;

[0052] When the number of IoT gateway devices used by IoT devices in other areas that affect adjacent areas is not greater than the gateway device number threshold, then when a sub-area whose interval distance from the affected adjacent area is less than the preset interval distance threshold or a sub-area where IoT gateway devices are used in other areas monitors a fire signal or the number of sub-areas that monitor a fire signal is greater than 5, the target forest area outputs a warning signal.

[0053] Furthermore, the other area is an area located in the same forest location as the target forest area.

[0054] Specifically, the IoT device is a device used for fire risk monitoring.

[0055] It should be noted that the IoT devices include monitoring devices, smoke sensing devices and infrared monitoring devices.

[0056] Specifically, such as Figure 2 As shown, the method for determining the influencing area in the other areas is:

[0057] Determining the number of influencing devices in the other areas based on the installation distribution of the influencing devices in the other areas;

[0058] Whether the other area is an impact area is determined according to a proportion of the number of IoT devices in the other area among the impact devices in the other area.

[0059] Furthermore, when the proportion of the number of influencing devices in the other areas to the number of IoT devices in the other areas is greater than the proportion of the preset number of influencing devices, the other areas are determined to be the influencing areas.

[0060] In another possible embodiment, a method for determining the influencing area in the other areas is:

[0061] Determining the number of influencing devices in the other areas based on the installation distribution of the influencing devices in the other areas;

[0062] Divide the other area into a plurality of sub-areas using a preset area, and determine the monitoring influence coefficient in each sub-area based on the ratio of the number of IoT devices influencing the devices in the sub-area;

[0063] Whether the other areas are impact areas is determined according to monitoring impact coefficients in different sub-areas.

[0064] Furthermore, when there is a sub-region whose monitoring influence coefficient is greater than a preset monitoring influence coefficient threshold, the other region is determined to be an influence region.

[0065] It can be understood that when the monitoring impact value of the other area is greater than the preset monitoring impact threshold, the other area is determined to be the impact area.

[0066] It should be noted that the distribution of the affected areas includes the number of affected areas and their distribution locations in the forest.

[0067] Specifically, the distribution data of the Internet of Things devices is determined according to the installation locations of the Internet of Things devices in the impact area.

[0068] Specifically, such as Figure 3 As shown, it is determined that the target forest area does not belong to the risk area, specifically including:

[0069] Based on the distribution of the affected areas, determine the ratio of the number of forest areas in the affected areas in the forest location, and use it as the ratio of the number of affected areas;

[0070] Determine the proportion of IoT devices in the affected area based on the distribution data of IoT devices in the affected area, and use the proportion as the regional impact coefficient.

[0071] Based on the proportion of the number of affected areas and the regional impact coefficients of different affected areas, the regional impact risk coefficient of the target forest area is determined, and based on the regional impact risk coefficient, it is determined whether the target forest area belongs to a risk area.

[0072] Furthermore, the regional impact risk coefficient of the target forest area is determined according to the product of the proportion of the number of affected areas and the average value of the regional impact coefficients of different affected areas.

[0073] It can be understood that the value range of the regional impact risk coefficient is between 0 and 1, wherein when the regional impact risk coefficient is greater than a preset regional impact risk coefficient threshold, it is determined that the target forest area belongs to a risk area.

[0074] Furthermore, when the target forest area belongs to a risk area, when any monitoring device in the target forest area detects a fire signal, the target forest area outputs an early warning signal.

[0075] Specifically, the fire signal includes smoke, flames and smoldering.

[0076] In another possible embodiment, determining that the target forest area does not belong to a risk area specifically includes:

[0077] Determine the number of impact areas in the forest location based on the distribution of the impact areas;

[0078] Based on the distribution data of IoT devices in different impact areas, determine the impact area where the number of IoT devices is less than the preset device number threshold, and use it as the monitoring deviation impact area;

[0079] Based on the number of areas affected by the monitoring deviation, it is determined whether the target forest area belongs to a risk area.

[0080] Furthermore, when the number of the monitoring deviation affected areas is greater than a preset monitoring deviation affected area number threshold, the target forest area is determined to be a risk area.

[0081] It can be understood that the adjacent areas affected when a fire occurs in the target forest area are other areas whose distance from the target forest area in the wind direction is less than a preset distance threshold.

[0082] Specifically, such as Figure 4 As shown, the method for determining the fire monitoring and early warning method of the target forest area is:

[0083] Determine the number of IoT devices in other sub-regions that use different methods to influence IoT gateway devices in adjacent regions based on the impact of IoT devices in other regions, the proportion of the number of IoT devices in the other sub-regions, and determine the device impact area in the other region based on the proportion of the number;

[0084] Based on the distance between the sub-region and the affected adjacent region, determine the sub-region whose distance is less than a preset distance threshold and regard it as the adjacent sub-region;

[0085] According to the distribution data of the Internet of Things gateway devices in the sub-area, the sub-areas of other areas where the Internet of Things gateway devices utilizing the sub-area exist are determined, and used as the fault-affected sub-areas. According to the number of the equipment-affected areas, the number of adjacent sub-areas and the number of the fault-affected sub-areas, the fire monitoring and early warning method of the target forest area is determined.

[0086] Furthermore, the device impact area is other areas whose proportion is greater than a preset proportion threshold.

[0087] It is understandable that, based on the number of the equipment-affected areas, the number of adjacent sub-areas, and the number of fault-affected sub-areas, the fire monitoring and early warning method for the target forest area is determined, specifically including:

[0088] When the number of equipment-affected areas in the target forest area is greater than a preset equipment-affected area number threshold, when any monitoring device in the target forest area detects a fire signal, the target forest area outputs an early warning signal;

[0089] When the number of equipment-affected areas in the target forest area is not greater than a preset equipment-affected area number threshold, a fire monitoring and early warning method for the target forest area is determined based on the number of adjacent sub-areas and fault-affected sub-areas.

[0090] Specifically, according to the number of adjacent sub-areas and fault-affected sub-areas, a fire monitoring and early warning method for the target forest area is determined, which specifically includes:

[0091] When the sum of the number of adjacent sub-areas and the fault-affected sub-areas in the target forest area accounts for a greater proportion of the number of sub-areas in the target forest area than the preset proportion of the number of affected sub-areas, then when any monitoring device in the target forest area detects a fire signal, the target forest area outputs an early warning signal;

[0092] When the sum of the number of adjacent sub-areas and fault-affected sub-areas in the target forest area accounts for no more than the preset number of affected sub-areas: when the monitoring equipment in the adjacent sub-areas or fault-affected sub-areas in the target forest area obtains a fire signal or the number of sub-areas that obtain a fire signal is greater than the preset fire risk sub-area number threshold, the target forest area outputs an early warning signal.

[0093] In another possible embodiment, the method for determining the fire monitoring and early warning method for the target forest area is:

[0094] S41 determines the number of IoT devices in other sub-regions that use different IoT gateway devices that affect the adjacent regions based on the impact of IoT devices in different impact regions on other regions, and the proportion of the number of IoT devices in the other sub-regions; determines the device impact area in the other region based on the proportion; and determines the spillover risk coefficient of the target forest region based on the number of impacted adjacent regions and the number of device impact areas.

[0095] S42: Based on the distance between the sub-region and the affected adjacent region, determine the sub-region whose distance is less than a preset distance threshold, and use it as the adjacent sub-region; based on the distribution data of the IoT gateway devices in the sub-region, determine the sub-region of other regions that use the IoT gateway device in the sub-region, and use it as the fault-affected sub-region; determine the target forest region's own risk factor based on the number of adjacent sub-regions and fault-affected sub-regions in the target forest region, and the number of IoT devices in other regions that use the IoT gateway device in the sub-region in different fault-affected sub-regions;

[0096] S43 determines a risk coefficient assessment value for the target forest area based on an average value of the spillover risk coefficient and the self-risk coefficient, and determines a fire monitoring and early warning method for the target forest area based on the risk coefficient assessment value.

[0097] Furthermore, a fire monitoring and early warning method for the target forest area is determined based on the risk coefficient assessment, specifically including:

[0098] When the risk coefficient assessment value of the target forest area is greater than the preset risk assessment value threshold, when any monitoring device in the target forest area detects a fire signal, the target forest area outputs an early warning signal;

[0099] When the risk coefficient assessment value of the target forest area is not greater than the preset risk assessment value threshold, when the monitoring equipment of the adjacent sub-area or fault-affected sub-area in the target forest area monitors a fire signal or the number of sub-areas that monitor a fire signal is greater than the preset fire risk sub-area number threshold, the target forest area outputs a warning signal.

[0100] Example 2 In another possible embodiment, determining that the target forest area does not belong to a risk area specifically includes:

[0101] determining the number of affected areas in the target forest area based on the distribution of the affected areas, and determining that the target forest area is a risk area when the number of affected areas in the target forest area does not meet the requirement;

[0102] When the number of affected areas in the target forest area meets the requirements:

[0103] Determine the proportion of the number of forest areas in the forest location by the affected areas, and use the proportion as the number of affected areas. Combined with the number and spacing of the affected areas in the target forest area, determine the monitoring impact coefficient of the target forest area. When the monitoring impact coefficient of the target forest area is less than a preset impact coefficient threshold, determine that the target forest area does not belong to the risk area.

[0104] When the monitoring impact coefficient of the target forest area is not less than the preset impact coefficient threshold:

[0105] Determining, based on the distribution data of IoT devices in different impact areas, the proportion of the number of IoT devices in the impact area by the influencing devices; and determining that the target forest area is a risk area when the average proportion of the number of IoT devices in the impact area by the influencing devices in the different impact areas does not meet the requirements;

[0106] When the average ratio of the number of IoT devices in different impact areas to the number of impact devices in the impact areas meets the requirements:

[0107] Obtaining the proportion of the number of IoT devices in different impact areas by the influencing devices in the impact areas, and determining the monitoring impact values ​​of the different impact areas based on the number of IoT devices in the different impact areas. If there is an impact area whose monitoring impact value does not meet the requirements, the target forest area is determined to be a risk area.

[0108] When there is no impact area where the monitoring impact value does not meet the requirements:

[0109] Based on the proportion of the number of affected areas and the monitoring impact values ​​of different affected areas, the regional impact risk coefficient of the target forest area is determined, and based on the regional impact risk coefficient, it is determined whether the target forest area belongs to a risk area.

[0110] In the second aspect of embodiment 3, Figure 5 As shown, the present invention provides a computer system comprising: a memory and a processor in communication connection, and a computer program stored in the memory and capable of running on the processor, wherein the processor executes the above-mentioned forest fire early monitoring and warning method when running the computer program.

[0111] Optionally, the above step S41 includes the following contents:

[0112] S411 determines the number of IoT devices affecting the adjacent area based on the impact of IoT devices in different adjacent areas on other areas and the number of IoT devices in other sub-areas that use different IoT gateway devices that affect the adjacent area. If the number of IoT devices affecting the adjacent area does not meet the requirement, then when any monitoring device in the target forest area detects a fire signal, the target forest area outputs a warning signal. If the number of IoT devices affecting the adjacent area meets the requirement, the process proceeds to step S412.

[0113] At step S412, when the number of IoT devices affecting the adjacent area is less than the preset value of the number of affected areas, and the number of sub-areas where fire signals are monitored is greater than the preset threshold of the number of fire risk sub-areas, the target forest area outputs a warning signal; when the number of IoT devices affecting the adjacent area is not less than the preset value of the number of affected areas, the process proceeds to step S413;

[0114] S413 determines the number of IoT devices in other sub-regions that use different methods to influence IoT gateway devices in adjacent regions, and the proportion of the number of IoT devices in the other sub-regions. Based on the proportion of the number, the device impact area in the other region is determined. If the number of the device impact areas does not meet the requirement, then when any monitoring device in the target forest region detects a fire signal, the target forest region outputs a warning signal. If the number of the device impact areas meets the requirement, the process proceeds to step S414.

[0115] S414 determines the spillover risk coefficient of the target forest area based on the number of affected adjacent areas and the number of equipment affected areas. When the spillover risk coefficient of the target forest area does not meet the requirements, when any monitoring device in the target forest area detects a fire signal, the target forest area outputs a warning signal. When the spillover risk coefficient of the target forest area meets the requirements, proceed to step S42.

[0116] Optionally, the above step S42 includes the following contents:

[0117] S421: Determine, based on the distance between the sub-region and the affected adjacent region, sub-regions whose distance is less than a preset distance threshold, and define them as adjacent sub-regions. Determine, based on the distribution data of IoT gateway devices in the sub-regions, sub-regions in other regions where IoT gateway devices utilizing the sub-region exist, and define them as sub-regions affected by the fault.

[0118] In step S422, when the sum of the number of adjacent sub-regions and sub-regions affected by the fault in the target forest area does not meet the requirements, when any monitoring device in the target forest area detects a fire signal, the target forest area outputs an early warning signal. When the sum of the number of adjacent sub-regions and sub-regions affected by the fault in the target forest area meets the requirements, the process proceeds to step S423.

[0119] S423 determines a fault impact coefficient based on the number of fault-affected sub-areas and the number of IoT devices in other areas that utilize the IoT gateway device of the sub-area in each fault-affected sub-area. If the fault impact coefficient is greater than a preset fault impact coefficient threshold, the process proceeds to step S424. If the fault impact coefficient is not greater than the preset fault impact coefficient threshold, the process proceeds to step S425.

[0120] At step S424, when the number of adjacent sub-regions is within the preset adjacent sub-region number range, when any monitoring device in the target forest area detects a fire signal, the target forest area outputs an early warning signal. When the number of adjacent sub-regions is not within the preset adjacent sub-region number range, the process proceeds to step S425.

[0121] S425 determines the inherent risk coefficient of the target forest area based on the number of adjacent sub-areas and fault-affected sub-areas in the target forest area, and in combination with the number of IoT devices in other areas that utilize IoT gateway devices in the sub-areas in different fault-affected sub-areas. When the inherent risk coefficient of the target forest area does not meet the requirements, when any monitoring device in the target forest area detects a fire signal, the target forest area outputs an early warning signal. When the inherent risk coefficient of the target forest area meets the requirements, proceed to step S43.

[0122] A further technical solution of Example 4 is that the method for determining the influence area in the other areas is:

[0123] Determine the number of influencing devices in the other areas based on the installation distribution of the influencing devices in the other areas; if either the number of influencing devices in the other areas or the ratio of the influencing devices in the other areas to the number of IoT devices in the other areas does not meet the requirements, determine the other areas as the influencing areas;

[0124] When the number of influencing devices in the other areas and the ratio of the influencing devices in the other areas to the number of IoT devices in the other areas both meet the requirements:

[0125] Divide the other area into multiple sub-areas using a preset area, and determine the monitoring influence coefficient of each sub-area based on the proportion of the number of IoT devices in the sub-area that have influencing devices in the sub-area. If there is a sub-area whose monitoring influence coefficient does not meet the requirement, determine the other area as an influencing area;

[0126] When there is no sub-area whose monitoring impact coefficient does not meet the requirements:

[0127] The sub-regions whose monitored influence coefficients are within a preset influence coefficient range are regarded as influence sub-regions. If the number of influence sub-regions in the other regions or the proportion of the influence sub-regions in the other regions does not meet the requirement, the other regions are determined to be influence regions.

[0128] When the number of affected sub-regions in the other regions or the ratio of the number of affected sub-regions in the other regions meets the requirements:

[0129] Determining a distribution clustering coefficient of the influence sub-regions based on the spacing between different influence sub-regions and the number of influence sub-regions; and determining the other regions as influence regions when the distribution clustering coefficient of the influence sub-regions in the other regions does not meet the requirements;

[0130] When the distribution clustering coefficient of the influencing sub-regions in the other regions meets the requirements:

[0131] The monitoring influence coefficients of different sub-regions are combined with the distribution clustering coefficients of the influencing sub-regions in other regions to determine the monitoring influence values ​​of the other regions, and whether the other regions are influencing regions is determined based on the monitoring influence values.

[0132] The various embodiments in this specification are described in a progressive manner. Similar portions between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from the other embodiments. In particular, the device, apparatus, and non-volatile computer storage medium embodiments are generally similar to the method embodiments, so their descriptions are relatively simplified. For relevant details, refer to the descriptions of the method embodiments.

[0133] The foregoing description of this specification describes specific embodiments. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in an order different from that described in the embodiments and still achieve the desired results. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order shown or the sequential order to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0134] The foregoing description is merely one or more embodiments of this specification and is not intended to limit this specification. It will be apparent to those skilled in the art that various modifications and variations may be made to one or more embodiments of this specification. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of one or more embodiments of this specification are intended to be within the scope of the claims of this specification.

Claims

1. A forest fire early warning method, characterized in that: Specifically include: The IoT gateway device in the target forest area is used as the target gateway device, and the IoT devices in other areas using the target gateway device are used as influencing devices. The influencing areas in other areas are determined based on the installation distribution of the influencing devices in the other areas. If it is determined that the target forest area is not a risk area based on the distribution of the affected area and the distribution data of the IoT devices in the affected area, proceed to the next step; Dividing the target forest area into a plurality of sub-areas according to a preset area, determining the wind direction of the target forest area based on weather data of a current date, and determining the adjacent areas affected by a fire in the target forest area according to the wind direction; Determine the impact of different adjacent impact areas on IoT devices in other areas, and determine a fire monitoring and early warning method for the target forest area based on the distances between different sub-areas and the adjacent impact areas and the distribution data of IoT gateway devices; Determine that the target forest area is not a risk area, including: Based on the distribution of the affected areas, determine the ratio of the number of forest areas in the affected areas in the forest location, and use it as the ratio of the number of affected areas; Determine the proportion of IoT devices in the affected area based on the distribution data of IoT devices in the affected area, and use the proportion as the regional impact coefficient. Determining a regional impact risk coefficient of the target forest area based on the proportion of the number of affected areas and the regional impact coefficients of different affected areas, and determining whether the target forest area belongs to a risk area based on the regional impact risk coefficient; The method for determining the fire monitoring and early warning method of the target forest area is: Determine the number of IoT devices in other sub-regions that use different methods to influence IoT gateway devices in adjacent regions based on the impact of IoT devices in other regions, the proportion of the number of IoT devices in the other sub-regions, and determine the device impact area in the other region based on the proportion of the number; Based on the distance between the sub-region and the affected adjacent region, determine the sub-region whose distance is less than a preset distance threshold and regard it as the adjacent sub-region; According to the distribution data of the Internet of Things gateway devices in the sub-area, the sub-areas of other areas where the Internet of Things gateway devices utilizing the sub-area exist are determined, and used as the fault-affected sub-areas. According to the number of the equipment-affected areas, the number of adjacent sub-areas and the number of the fault-affected sub-areas, the fire monitoring and early warning method of the target forest area is determined.

2. The forest fire early warning method according to claim 1, characterized in that: The other area is an area located in the same forest location as the target forest area.

3. The forest fire early warning method according to claim 1, characterized in that: The IoT device is a device used for fire risk monitoring.

4. The forest fire early warning method according to claim 1, characterized in that: The method for determining the influence area in the other areas is: Determining the number of influencing devices in the other areas based on the installation distribution of the influencing devices in the other areas; Whether the other area is an impact area is determined according to a proportion of the number of IoT devices in the other area among the impact devices in the other area.

5. The forest fire early warning method according to claim 1, characterized in that: The distribution of the affected areas includes the number of affected areas and their distribution locations in the forest.

6. The forest fire early warning method according to claim 1, characterized in that: The distribution data of the Internet of Things devices is determined according to the installation locations of the Internet of Things devices in the impact area.

7. The forest fire early warning method according to claim 1, characterized in that: When the target forest area belongs to a risk area, when any monitoring device in the target forest area detects a fire signal, the target forest area outputs an early warning signal.

8. A computer system comprising: A memory and a processor in communication connection, and a computer program stored in the memory and capable of running on the processor, characterized in that when the processor runs the computer program, it executes a forest fire early monitoring and early warning method as described in any one of claims 1-7.

Images