Area monitoring method, device and system

Abstract

The invention discloses an area monitoring method, device and system. The method comprises the following steps: acquiring meteorological factors of a monitored area through a target wireless sensor; wherein the target wireless sensor is determined from the plurality of wireless sensors after the plurality of wireless sensors are clustered according to the residual energy of each wireless sensor and the distance between each wireless sensor and the edge computing server; and the target wireless sensor is used for receiving the meteorological factors sent by other wireless sensors in the corresponding cluster, so that the stability of network transmission data is improved, and the life cycle of the network at the end side is prolonged. Calculating a risk value of the monitoring area according to each meteorological factor; and the monitoring area is monitored according to the risk value, so that the monitoring area is monitored on the edge side, and the efficiency and the real-time performance of end side area monitoring are improved.

Description

Technical Field

[0001] The present invention relates to the field of communication technology, and in particular to a regional monitoring method, device and system. Background Art

[0002] Fires, floods and other disasters caused by natural and man-made factors around the world have caused hundreds of millions of property losses and even casualties. Therefore, in order to reduce the negative impact of disasters such as fires and floods, it is necessary to monitor fires, floods and other disasters and issue early warnings or alarms in a timely manner.

[0003] At present, monitoring mainly adopts manual inspection, ground terminal monitoring and drone monitoring. However, the manual inspection method has a small range, low efficiency and poor real-time performance; ground terminal monitoring mainly realizes monitoring by deploying temperature, smoke, humidity and other sensors in the forest area, as well as infrared detection systems and visible light search systems. However, this method requires supporting ground cables for power supply, which makes it impossible to apply on a large scale and has high costs; drone monitoring has a small range and poor real-time performance.

[0004] Therefore, how to improve the efficiency, scope, and real-time performance of regional monitoring and avoid excessively high monitoring costs is a technical problem that urgently needs to be solved. Summary of the invention

[0005] The embodiments of the present invention provide a regional monitoring method, device and system for improving the efficiency, scope and real-time performance of regional monitoring without increasing the monitoring cost.

[0006] In a first aspect, an embodiment of the present invention provides a regional monitoring method, which is applied to an edge computing server, including:

[0007] Acquire various meteorological factors of the monitoring area through a target wireless sensor; the target wireless sensor is determined from the multiple wireless sensors after clustering the multiple wireless sensors according to the residual energy of each wireless sensor and the distance between each wireless sensor and the edge computing server; the target wireless sensor is used to receive meteorological factors sent by other wireless sensors in the cluster to which the target wireless sensor belongs;

[0008] Calculate the risk value of the monitored area according to the meteorological factors;

[0009] The monitoring area is monitored according to the risk value.

[0010] In the above technical solution, the edge computing server is deployed in the monitoring area, and the risk value of the monitoring area is calculated by the edge computing server, so as to realize monitoring of the monitoring area on the edge side, thereby improving the efficiency and real-time performance of the end-side area monitoring. Multiple wireless sensors are deployed in the monitoring area, and the meteorological factors of the monitoring area are collected based on the multiple wireless sensors deployed in the monitoring area, so as to ensure the scope of regional monitoring. In addition, because the edge computing server obtains the meteorological factors of the monitoring area through the target wireless sensor among the multiple wireless sensors, the target wireless sensor is determined based on the residual energy of the multiple wireless sensors and the distance between the multiple wireless sensors and the edge computing server, so as to improve the stability of network transmission data and extend the life cycle of the end-side network.

[0011] In some embodiments, the target wireless sensor is determined from the multiple wireless sensors after clustering the multiple wireless sensors according to the residual energy of each wireless sensor and the distance between each wireless sensor and the edge computing server, including:

[0012] Determine a similarity matrix corresponding to the plurality of wireless sensors according to the residual energy of each wireless sensor and the distance between each wireless sensor and the edge computing server; the similarity matrix represents the similarity of the kth node as the cluster center of the i-th node; the kth node is any wireless sensor among the plurality of wireless sensors, and the i-th node is any wireless sensor among the plurality of wireless sensors except the kth node;

[0013] Determine an attraction matrix according to the similarity matrix; the attraction matrix represents the degree to which the k-th node serves as the cluster center of the i-th node;

[0014] Determine an evaluation matrix according to the attraction matrix and the attribution matrix, and determine a cluster center node from the evaluation matrix; the attribution matrix is ​​calculated based on the own parameters of multiple wireless sensors, and the attribution matrix is ​​used to characterize the degree to which the i-th node selects the k-th node as the cluster center;

[0015] The cluster center node is used as the target wireless sensor.

[0016] In some embodiments, determining the similarity matrix corresponding to the plurality of wireless sensors according to the residual energy of each wireless sensor and the distance between each wireless sensor and the edge computing server includes:

[0017] Calculating the similarity of the kth node becoming the target wireless sensor of the i-th node according to the distance between the i-th node and the k-th node and the residual energy of the k-th node; the similarity is inversely proportional to the distance between the i-th node and the k-th node, and the similarity is proportional to the residual energy of the k-th node;

[0018] Calculating a preference value of the kth node according to the distance between the kth node and the edge computing server and the residual energy of the kth node; the preference value of the kth node is inversely proportional to the distance between the kth node and the edge computing server, and the preference value of the kth node is proportional to the residual energy of the kth node;

[0019] The similarity matrix is ​​determined according to the similarity of the k-th node becoming a target wireless sensor of the i-th node and the preference value of the k-th node.

[0020] In some embodiments, the similarity of the k-th node becoming the target wireless sensor of the i-th node is calculated according to the following formula (1);

[0021]

[0022] Wherein, s(i, k) is the similarity of the k-th node becoming the target wireless sensor of the i-th node, that is, s(i, k) is the value of the (i, k)-th element in the similarity matrix (equivalent to the value of the element in the i-th row and k-th column in the similarity matrix) and the value of the (k, i)-th element (equivalent to the value of the element in the k-th row and i-th column in the similarity matrix); d i，k represents the distance between the i-th node and the k-th node, which is the Euclidean distance; E avg is the average energy of multiple wireless sensors; E k is the residual energy of the kth node.

[0023] In some embodiments, the preference value of the kth node is calculated according to the following formula (2);

[0024]

[0025] Wherein, s(k, k) represents the preference value of the kth node, that is, s(k, k) is the value of the (k, k)th element in the similarity matrix (equivalent to the value of the element in the kth row and kth column in the similarity matrix); P is the preset preference coefficient; C0 is the preset distance weight coefficient; d k is the distance between the kth node and the edge computing server, d min is the minimum distance between multiple wireless sensors and the edge computing server; d max is the maximum distance between multiple wireless sensors and the edge computing server.

[0026] In some embodiments, determining an evaluation matrix according to the attraction matrix and the attribution matrix, and determining a cluster center node from the evaluation matrix includes:

[0027] Iterating the attraction matrix and the attribution matrix based on a preset attenuation coefficient to obtain an iterated attraction matrix and an iterated attribution matrix;

[0028] Calculate the sum of the iterative attraction matrix and the iterative attribution matrix to obtain the evaluation matrix;

[0029] Clustering the plurality of wireless sensors according to the evaluation matrix;

[0030] For any cluster, the node corresponding to the maximum value in the cluster is used as the cluster center node.

[0031] In some embodiments, after the cluster center node is used as a target wireless sensor, the method further includes:

[0032] The target identifier of the target wireless sensor is sent to all wireless sensors in the cluster to which the target wireless sensor belongs.

[0033] In some embodiments, calculating the risk value of the monitored area according to the meteorological factors includes:

[0034] For any meteorological factor, a first contribution value corresponding to the meteorological factor is calculated according to the meteorological factor and a preset coefficient; the meteorological factor is proportional to the first contribution value corresponding to the meteorological factor;

[0035] Calculating the product of the first contribution value corresponding to the meteorological factor and the weight of the meteorological factor to obtain a second contribution value of the meteorological factor;

[0036] The sum of the second contribution values ​​of the meteorological factors is calculated to obtain the risk value of the monitored area.

[0037] In some embodiments, the first contribution value corresponding to the meteorological factor is calculated according to the following formula (3);

[0038]

[0039] or,

[0040] Calculate the first contribution value corresponding to the meteorological factor according to the following formula (4);

[0041]

[0042] Among them, u m represents the first contribution value corresponding to the mth meteorological factor, x mrepresents the mth meteorological factor, a is the first preset coefficient, and c is the second preset coefficient.

[0043] In some embodiments, monitoring the monitoring area according to the risk value includes:

[0044] If the risk value of the monitoring area is greater than or equal to the risk threshold, collecting image information in the monitoring area;

[0045] The image information is sent to a monitoring center via a satellite network.

[0046] In a second aspect, an embodiment of the present invention provides a method for monitoring an area, which is applied to any wireless sensor among a plurality of wireless sensors, and includes:

[0047] Receive a target identifier sent by an edge computing server; the target identifier represents an identifier corresponding to a target wireless sensor, and the target wireless sensor is determined from the multiple wireless sensors after the edge computing server clusters the multiple wireless sensors according to the residual energy of each wireless sensor and the distance between each wireless sensor and the edge computing server;

[0048] If its own identifier is consistent with the target identifier, it receives meteorological factors sent by other wireless sensors in the cluster to which it belongs as a target wireless sensor, and sends the meteorological factors to the edge computing server;

[0049] If its own identification is inconsistent with the target identification, the meteorological factors of the area where the own area is located are collected and sent to the target wireless sensor corresponding to the target identification.

[0050] In the above technical solution, multiple wireless sensors are clustered into at least one cluster, any cluster includes at least one wireless sensor, and each cluster includes target wireless sensors and non-target wireless sensors (i.e. other sensors). The meteorological factors in the monitoring area are sent to the edge computing server through multiple wireless sensors, and the edge computing server calculates the risk value of the monitoring area, so as to monitor the monitoring area on the edge side, thereby improving the efficiency and real-time performance of the end-side area monitoring.

[0051] In a third aspect, an embodiment of the present invention provides a regional monitoring device, including:

[0052] A first acquisition module is used to acquire various meteorological factors of the monitoring area through a target wireless sensor; the target wireless sensor is determined from the multiple wireless sensors after clustering the multiple wireless sensors according to the residual energy of each wireless sensor and the distance between each wireless sensor and the edge computing server; the target wireless sensor is used to receive meteorological factors sent by other wireless sensors in the cluster to which the target wireless sensor belongs;

[0053] A first processing module, used for calculating the risk value of the monitored area according to the meteorological factors;

[0054] The monitoring area is monitored according to the risk value.

[0055] In some embodiments, the first processing module is specifically used to:

[0056] A similarity matrix corresponding to the multiple wireless sensors is determined according to the residual energy of each wireless sensor and the distance between each wireless sensor and the edge computing server; the similarity matrix represents the similarity of the kth node as the cluster center of the ith node; the kth node is any wireless sensor among the multiple wireless sensors, and the ith node is any wireless sensor among the multiple wireless sensors except the kth node; an attraction matrix is ​​determined according to the similarity matrix; the attraction matrix represents the degree to which the kth node is the cluster center of the ith node; an evaluation matrix is ​​determined according to the attraction matrix and the attribution matrix, and a cluster center node is determined from the evaluation matrix; the attribution matrix is ​​calculated based on the own parameters of the multiple wireless sensors, and the attribution matrix is ​​used to represent the degree to which the ith node selects the kth node as the cluster center; the cluster center node is used as the target wireless sensor.

[0057] In some embodiments, the first processing module is specifically used to:

[0058] The similarity of the kth node becoming a target wireless sensor of the i-th node is calculated based on the distance between the i-th node and the k-th node and the residual energy of the k-th node; the similarity is inversely proportional to the distance between the i-th node and the k-th node, and the similarity is proportional to the residual energy of the k-th node; the preference value of the k-th node is calculated based on the distance between the k-th node and the edge computing server and the residual energy of the k-th node; the preference value of the k-th node is inversely proportional to the distance between the k-th node and the edge computing server, and the preference value of the k-th node is proportional to the residual energy of the k-th node; the similarity matrix is ​​determined based on the similarity of the k-th node becoming a target wireless sensor of the i-th node and the preference value of the k-th node.

[0059] In some embodiments, the first processing module is specifically used to:

[0060] The attraction matrix and the attribution matrix are iterated based on a preset attenuation coefficient to obtain an iterated attraction matrix and an iterated attribution matrix; the sum of the iterated attraction matrix and the iterated attribution matrix is ​​calculated to obtain the evaluation matrix; the multiple wireless sensors are clustered according to the evaluation matrix; for any cluster, the node corresponding to the maximum value in the cluster is used as the cluster center node.

[0061] In some embodiments, the first processing module is further configured to:

[0062] After the cluster center node is used as the target wireless sensor, the target identifier of the target wireless sensor is sent to all wireless sensors in the cluster to which the target wireless sensor belongs.

[0063] In some embodiments, the first processing module is specifically used to:

[0064] For any meteorological factor, the first contribution value corresponding to the meteorological factor is calculated according to the meteorological factor and the preset coefficient; the meteorological factor is proportional to the first contribution value corresponding to the meteorological factor; the product of the first contribution value corresponding to the meteorological factor and the weight of the meteorological factor is calculated to obtain the second contribution value of the meteorological factor; the sum of the second contribution values ​​of each meteorological factor is calculated to obtain the risk value of the monitored area.

[0065] In some embodiments, the first processing module is specifically used to:

[0066] If the risk value of the monitoring area is greater than or equal to the risk threshold, image information in the monitoring area is collected; and the image information is sent to the monitoring center via a satellite network.

[0067] In a fourth aspect, an embodiment of the present invention provides a regional monitoring device, including:

[0068] A second acquisition module is configured to receive a target identifier sent by an edge computing server; the target identifier represents an identifier corresponding to a target wireless sensor, and the target wireless sensor is determined from the plurality of wireless sensors after the edge computing server clusters the plurality of wireless sensors according to the remaining energy of each wireless sensor and the distance between each wireless sensor and the edge computing server;

[0069] The second processing module is used to, if its own identification is consistent with the target identification, receive the meteorological factors sent by other wireless sensors in the cluster to which it belongs as a target wireless sensor, and send the meteorological factors to the edge computing server; if its own identification is inconsistent with the target identification, collect the meteorological factors of its own area, and send the meteorological factors of its own area to the target wireless sensor corresponding to the target identification.

[0070] In a fifth aspect, an embodiment of the present invention provides a regional monitoring device, including an edge computing server and a plurality of wireless sensors;

[0071] The edge computing server is used to: obtain various meteorological factors of the monitoring area through the target wireless sensor; the target wireless sensor is determined from the multiple wireless sensors after clustering the multiple wireless sensors according to the residual energy of each wireless sensor and the distance between each wireless sensor and the edge computing server; the target wireless sensor is used to receive meteorological factors sent by other wireless sensors in the cluster to which the target wireless sensor belongs; calculate the risk value of the monitoring area according to the various meteorological factors; and monitor the monitoring area according to the risk value;

[0072] Any wireless sensor among the multiple wireless sensors is used for: if its own identification is consistent with the target identification, then, as a target wireless sensor, receiving meteorological factors sent by other wireless sensors in the cluster to which it belongs, and sending the meteorological factors to the edge computing server; if its own identification is inconsistent with the target identification, then collecting meteorological factors of its own area, and sending the meteorological factors of its own area to the target wireless sensor corresponding to the target identification.

[0073] In a sixth aspect, an embodiment of the present invention further provides a computer device, including:

[0074] A memory for storing program instructions;

[0075] The processor is used to call the program instructions stored in the memory and execute the area monitoring method described in the first aspect or the second aspect according to the obtained program.

[0076] In a seventh aspect, an embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are used to enable a computer to execute the area monitoring method described in the first aspect or the second aspect above. BRIEF DESCRIPTION OF THE DRAWINGS

[0077] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0078] Figure 1 A schematic diagram of a system architecture provided for an embodiment of the present invention;

[0079] Figure 2 A schematic diagram of a flow chart of a regional monitoring method applied to an edge computing server provided in an embodiment of the present invention;

[0080] Figure 3 A schematic diagram of a flow chart of a method for regional monitoring applied to a wireless sensor provided by an embodiment of the present invention;

[0081] Figure 4 A schematic diagram of the structure of a regional monitoring device corresponding to an edge computing server provided in an embodiment of the present invention;

[0082] Figure 5 A schematic diagram of the structure of an area monitoring device corresponding to a wireless sensor provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0083] In order to make the purpose, technical scheme and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0084] Before introducing a service processing method provided by an embodiment of the present application, in order to facilitate understanding, the technical background of the embodiment of the present application is first introduced in detail.

[0085] Every year, tens of thousands of disasters are caused by natural and human factors around the world, such as forest fires, earthquakes, floods, etc., causing hundreds of millions of property losses and even casualties. In recent years, global warming has led to unpredictable climate change, intensified extreme weather, frequent forest fires, floods, earthquakes, etc. Based on the principle of early detection, early warning, and early measures, it is necessary to monitor and warn the monitoring area.

[0086] Taking forest fire as an example, the current forest fire monitoring and early warning mainly adopts manual inspection, ground terminal monitoring and drone monitoring. However, manual inspection has a small scope, low efficiency, poor real-time performance, and is greatly affected by the subjective behavior of the inspectors; ground terminal monitoring mainly realizes forest fire monitoring by deploying temperature, smoke, humidity and other sensors in the forest area, as well as infrared detection systems, visible light search systems, etc. When a suspicious fire is detected, the alarm mechanism will be triggered and the information will be transmitted back to the monitoring center through the communication terminal, but this method generally requires supporting ground cables for power supply and ground communication edge computing servers for data transmission, which makes it impossible to apply on a large scale and has high costs; the drone monitoring method is to integrate various modules into drones and realize the inspection of forest areas through drones, but drones face problems of power supply and communication, small monitoring range, poor real-time performance, and poor economy.

[0087] Therefore, the present application provides a regional monitoring method and device for improving the efficiency, scope, and real-time performance of regional monitoring without increasing the monitoring cost.

[0088] Figure 1 An exemplary system architecture applicable to an embodiment of the present invention is shown, which includes multiple wireless sensors ( Figure 1 The wireless sensor 1, wireless sensor 2, ..., wireless sensor n) shown in the figure and the determined target wireless sensor among the multiple wireless sensors also include an edge computing server, a satellite network and a monitoring center. The target wireless sensor is determined from the multiple wireless sensors based on the residual energy of the multiple wireless sensors and the distance between the multiple wireless sensors and the edge computing server. It can be understood that there can be multiple wireless sensors in the present application, and the target wireless sensor can be several of the multiple wireless sensors.

[0089] Multiple wireless sensors are used to collect various meteorological factors in the monitoring area through temperature, smoke, humidity and other sensors. Meteorological factors include but are not limited to smoke concentration, wind speed, temperature and humidity. The target wireless sensor is equivalent to the cluster head node among multiple wireless sensors. For any target wireless sensor, the meteorological factors collected by other sensors in the same cluster as the target wireless sensor are obtained, and then the obtained meteorological factors are sent to the edge computing server.

[0090] The edge computing server is used to obtain various meteorological factors in the monitoring area through the target wireless sensor, and then calculate the risk value of the monitoring area based on the meteorological factors, and monitor the monitoring area according to the risk value. When it is determined that the risk value of the monitoring area is greater than or equal to the risk threshold, the image information in the monitoring area is collected and sent to the monitoring center through the satellite network, thereby reminding the monitoring personnel to confirm whether a disaster has occurred in the monitoring area.

[0091] It should be noted that the above Figure 1 The structure shown is only an example and is not limited to this embodiment of the present invention.

[0092] Based on the above description, Figure 2 The following is a flow chart of a regional monitoring method applied to an edge computing server provided by an embodiment of the present invention. Figure 2 As shown, the process includes:

[0093] Step 210: Acquire various meteorological factors of the monitoring area through the target wireless sensor.

[0094] In the embodiment of the present application, the target wireless sensor is the cluster center of multiple wireless sensors; the target wireless sensor is determined from multiple wireless sensors after clustering the multiple wireless sensors according to the residual energy of each wireless sensor and the distance between each wireless sensor and the edge computing server. The multiple wireless sensors are deployed in the monitoring area. For the convenience of description, the wireless sensors are referred to as nodes below. It can be understood that the residual energy of the wireless sensor can also be referred to as the residual power of the wireless sensor. The wireless sensor can be powered by a mobile power supply, so there is no need to deploy power cables and other equipment, thereby avoiding excessive monitoring costs. The monitoring area can be a forest area, a desert area, etc. Taking the monitoring area as a forest area as an example, the meteorological factors include but are not limited to smoke concentration, wind speed, temperature, humidity and other related parameter factors that characterize the disaster situation in the monitoring area.

[0095] In some embodiments, based on the AP (affinity propagation) clustering algorithm, the edge computing server determines the similarity matrix corresponding to the multiple wireless sensors according to the residual energy of each wireless sensor and the distance between each wireless sensor and the edge computing server; wherein the similarity matrix represents the similarity of the kth node as the cluster center of the i-th node, the kth node is any wireless sensor among the multiple wireless sensors, and the i-th node is any wireless sensor among the multiple wireless sensors except the kth node. In this way, clustering based on the residual energy and the distance from the edge computing server is achieved, and the reliability and accuracy of clustering are improved.

[0096] Exemplarily, the edge computing server calculates the similarity of the kth node becoming the target wireless sensor of the i-th node based on the distance between the i-th node and the k-th node and the residual energy of the k-th node; wherein the similarity is inversely proportional to the distance between the i-th node and the k-th node, and the similarity is proportional to the residual energy of the k-th node. The similarity of the k-th node becoming the target wireless sensor of the i-th node is calculated as follows:

[0097]

[0098] Wherein, s(i, k) is the similarity of the kth node becoming the target wireless sensor of the ith node, which can also be called the similarity between the kth node and the ith node, that is, s(i, k) is the value of the (i, k)th element in the similarity matrix (equivalent to the value of the element in the i-th row and k-th column in the similarity matrix) and the value of the (k, i)th element (equivalent to the value of the element in the k-th row and i-th column in the similarity matrix); d i，k represents the Euclidean distance between the i-th node and the k-th node; E avg is the average energy of multiple wireless sensors; E k is the residual energy of the kth node. For example, there are 5 wireless sensors, which are deployed as nodes q1, q2, q3, q4 and q5 in the monitoring area. The similarity between node q1 and node q2 is -7, the similarity between node q1 and node q3 is -6, the similarity between node q1 and node q4 is -12, the similarity between node q1 and node q5 is -17, the similarity between node q2 and node q3 is 17, the similarity between node q2 and node q4 is -17, the similarity between node q2 and node q5 is -22, the similarity between node q3 and node q4 is -18, the similarity between node q3 and node q5 is -21, and the similarity between node q4 and node q5 is -3.

[0099] For each node's own similarity (hereinafter referred to as preference value), the edge computing server calculates the preference value of the kth node based on the distance between the kth node and the edge computing server and the residual energy of the kth node; wherein the preference value of the kth node is inversely proportional to the distance between the kth node and the edge computing server, and the preference value of the kth node is proportional to the residual energy of the kth node. The preference value of the kth node is calculated as follows:

[0100]

[0101] Wherein, s(k, k) represents the preference value of the kth node, that is, s(k, k) is the value of the (k, k)th element in the similarity matrix (equivalent to the value of the element in the kth row and kth column in the similarity matrix); P is the preset preference coefficient; C0 is the preset distance weight coefficient; d k is the distance between the kth node and the edge computing server, d min is the minimum distance between multiple wireless sensors and the edge computing server; d maxis the maximum distance between multiple wireless sensors and the edge computing server. Based on the above description, for example, the preference value of node q1 is -22, the preference value of node q2 is -12, the preference value of node q3 is -18, the preference value of node q4 is -20, and the preference value of node q5 is -16.

[0102] Based on the above description, because the similarity is proportional to the remaining energy of the kth node, it means that the node with more remaining energy is more likely to become the target wireless sensor, thereby preventing the node from consuming energy too quickly and dying, resulting in energy holes in the network; because the similarity is inversely proportional to the distance between the kth node and the edge computing server, it means that the wireless sensor closer to the edge computing server is more likely to become the target wireless sensor, thereby avoiding the situation where the target wireless sensor cannot connect and transmit because it is too far away from the edge computing server.

[0103] After determining the similarity between the kth node and the i-th node and the preference value of the kth node, the edge computing server determines the similarity matrix according to the similarity of the kth node becoming the target wireless sensor of the i-th node and the preference value of the kth node. Based on the above description, the similarity matrix is ​​shown in the following Table 1:

[0104] Table 1

[0105] Node ID Node q1 Node q2 Node q3 Node q4 Node q5 Node q1 -22 -7 -6 -12 -17 Node q2 -7 -12 -17 -17 -22 Node q3 -6 -17 -18 -18 -21 Node q4 -12 -17 -18 -20 -3 Node q5 -17 -17 -21 -3 -16

[0106] After determining the similarity matrix, the edge computing server determines the Responsibility Matrix according to the similarity matrix; wherein the Responsibility Matrix represents the degree to which the kth node is the cluster center of the ith node. Exemplarily, the value of each element in the Responsibility Matrix (i.e., each cell in the Responsibility Matrix) is calculated according to the following formula (5):

[0107] r(i,k)=s(i,k)-max{a(i,k`)+a(i`,k)}, i`≠i, k≠k` (5);

[0108] Among them, r(i, k) represents the element corresponding to the i-th row and k-th column in the attraction matrix, a(i, k') represents the element corresponding to the i-th row and other columns in the similarity matrix, and a(i', k) represents the element corresponding to the k-th column and other rows in the similarity matrix. Based on the above Table 1, the attraction matrix is ​​shown in the following Table 2:

[0109] Table 2

[0110] Node ID Node q1 Node q2 Node q3 Node q4 Node q5 Node q1 -16 -1 1 -6 -11 Node q2 10 -5 -10 -10 -15 Node q3 11 -11 -12 -12 -15 Node q4 -9 -14 -15 -17 9 Node q5 -14 -14 -18 13 -13

[0111] After determining the attraction matrix, the edge computing server determines the evaluation matrix (Criterion Matrix) according to the attraction matrix and the availability matrix (Availability Matrix); wherein the availability matrix is ​​calculated based on the self-parameters of multiple wireless sensors, and the availability matrix is ​​used to characterize the degree to which the i-th node selects the k-th node as the cluster center. The wireless sensor's own parameters include but are not limited to its own location information, remaining energy, the distance between itself and the edge computing server, etc. Exemplarily, the value of each element in the availability matrix (i.e., each cell in the availability matrix) is calculated according to the following formula (6):

[0112]

[0113] The attraction matrix is ​​shown in Table 3 below:

[0114] Table 3

[0115] Node ID Node q1 Node q2 Node q3 Node q4 Node q5 Node q1 20 -15 -16 -5 -10 Node q2 -5 0 -15 -5 -10 Node q3 5 -15 2 -5 -10 Node q4 0 -10 -10 15 -12 Node q5 0 -10 -10 -15 8

[0116] In some embodiments, after determining the attraction matrix and the attribution matrix, the attraction matrix and the attribution matrix are iterated based on a preset attenuation coefficient to obtain the attraction matrix and the iterated attribution matrix. Exemplarily, the iterated attraction matrix is ​​calculated according to the following formula (7):

[0117] r t+1 (i, k) = λr t (i,k)+(1-λ)r t+1 (i, k) (7);

[0118] Among them, r t+1 (i, k) represents the element in the attraction matrix after the t+1th iteration; r t (i, k) represents the elements in the attraction matrix after the tth iteration; λ represents the preset attenuation coefficient, such as λ=0.5.

[0119] The iterative attribution matrix is ​​calculated according to the following formula (8):

[0120] a t+1 (i, k) = λa t (i, k)+(1-λ)a t+1 (i, k) (8);

[0121] Among them, a t+1 (i, k) represents the element in the degree matrix after the t+1th iteration; a t (i, k) represents the element in the attribution matrix after the tth iteration.

[0122] Assuming that Table 2 and Table 3 are the iterative attraction matrix and the iterative attribution matrix respectively, based on the above Table 2 and Table 3, the sum of the iterative attraction matrix and the iterative attribution matrix is ​​calculated to obtain the evaluation matrix, as shown in the following Table 4:

[0123] Table 4

[0124] Node ID Node q1 Node q2 Node q3 Node q4 Node q5 Node q1 4 -16 -15 -11 -21 Node q2 5 -20 -25 -15 -25 Node q3 16 -26 -10 -17 -25 Node q4 -9 -28 -25 -2 -3 Node q5 -14 -28 -28 --2 -5

[0125] After determining the evaluation matrix, the edge computing server determines the cluster center node from the evaluation matrix. Exemplarily, the multiple wireless sensors are clustered according to the evaluation matrix; for any cluster, the node corresponding to the maximum value in the cluster is used as the cluster center node. For example, based on the above Table 4, node q1, node q2 and node q3 are divided into the same cluster, and node q3 is used as the cluster head node in the cluster, that is, the cluster center node; node q4 and node q5 are divided into the same cluster, and node q4 is used as the cluster center node in the cluster. Then, the cluster center node is used as the target wireless sensor, and the target identifier of the target wireless sensor is sent to all wireless sensors in the cluster to which the target wireless sensor belongs, so as to notify the wireless sensors in the cluster to send the collected meteorological factors to the cluster head node (that is, the target wireless sensor) of the cluster to which it belongs. The wireless sensors in the cluster can be called member nodes.

[0126] See also Figure 3 , Figure 3 A schematic diagram of a flow chart of a method for regional monitoring of a wireless sensor provided in an embodiment of the present application, the flow chart comprising:

[0127] Step 310: Receive a target identifier sent by an edge computing server.

[0128] The target identifier is used to indicate the clustering status of the multiple wireless sensors, as well as the target wireless sensor and other wireless sensors in each cluster.

[0129] Step 320, collect meteorological factors of the area where the user is located.

[0130] For any wireless sensor, if the wireless sensor's own identifier is inconsistent with the target identifier, it means that the wireless sensor is another wireless sensor in the cluster corresponding to the target identifier, and then collects the meteorological factors of its own area and sends the meteorological factors of its own area to the target wireless sensor corresponding to the target identifier.

[0131] Step 330: Receive meteorological factors sent by other wireless sensors in the cluster.

[0132] For any wireless sensor, if the wireless sensor's own identifier is consistent with the target identifier, it means that the wireless sensor is the target wireless sensor, and then receives meteorological factors sent by other wireless sensors in its cluster (i.e., other wireless sensors that receive the target identifier and whose own identifier is inconsistent with the target identifier).

[0133] Step 340: Send the meteorological factors to the edge computing server.

[0134] The target wireless sensor sends the meteorological factors collected by other wireless sensors in its cluster to the edge computing server.

[0135] Based on the above description, because the attraction matrix represents the degree to which the kth node is the cluster center of the i-th node, and the attribution matrix is ​​used to represent the degree to which the i-th node selects the kth node as the cluster center, the evaluation matrix representing the mutually attracted nodes is obtained by summing the attraction matrix and the attribution matrix. The mutually attracted nodes are clustered by the evaluation matrix to improve the reliability and accuracy of clustering. Because the attraction matrix and the attribution matrix are both determined based on the residual energy of the wireless sensor and the distance between the wireless sensor and the edge computing server, it is ensured that the wireless sensors with similar distances are in the same cluster, and the accuracy of data transmission and reception between the wireless sensors in the same cluster is ensured, and the situation that the wireless sensors in the same cluster cannot connect and transmit is avoided. For any cluster, the wireless sensor with higher residual energy in the cluster and closer to the edge computing server is used as the target wireless sensor, thereby avoiding the death of the target wireless sensor due to excessive energy consumption caused by the interaction with the edge computing server, preventing the network from having energy holes, and avoiding the situation that the target wireless sensor cannot connect and transmit due to the distance between the target wireless sensor and the edge computing server. Ensure the reliability of data transmission.

[0136] Step 220: Calculate the risk value of the monitored area based on the meteorological factors.

[0137] In the embodiment of the present application, for any meteorological factor, the first contribution value corresponding to the meteorological factor is calculated according to the meteorological factor and the preset coefficient; wherein the meteorological factor is proportional to the first contribution value corresponding to the meteorological factor. Exemplarily, the first contribution value corresponding to the meteorological factor is calculated according to the following formula (3);

[0138]

[0139] Or, the first contribution value corresponding to the meteorological factor is calculated according to the following formula (4);

[0140]

[0141] Among them, u mrepresents the first contribution value corresponding to the mth meteorological factor, x m Represents the mth meteorological factor (ie, actual value), a is the first preset coefficient, and c is the second preset coefficient. It can be understood that the first preset coefficient and the second preset coefficient can be different values ​​preset according to experience for different meteorological factors, such as 30%, 1m / s, etc., which are not specifically limited here. Taking the monitored area as a forest fire area, the meteorological factors include smoke concentration x1, wind speed x2, temperature x3 and humidity x4. Smoke concentration x1 is 5, wind speed x2 is 10, temperature x3 is 12, and humidity x4 is 8. It can be understood that the first contribution value corresponding to the meteorological factor can be calculated in units of one wireless sensor, that is, the first contribution values ​​corresponding to the meteorological factors of multiple wireless sensors are calculated respectively.

[0142] Based on the above description, because the units of different meteorological factors may be different, the meteorological factors are preprocessed by the above formula (3) or formula (4), and then the first contribution value in the same dimension after preprocessing is obtained, and then the subsequent comprehensive calculation is realized. It can be understood that the meteorological factors have a preset corresponding relationship with the monitoring area. For example, if the monitoring area is a forest fire area, the meteorological factors include smoke concentration, wind speed, temperature and humidity; if the monitoring area is a sandstorm disaster area, the meteorological factors include particle concentration, visibility, wind speed, temperature and humidity. The specific corresponding relationship is not limited here.

[0143] After calculating the first contribution value corresponding to each meteorological factor, the edge computing server calculates the product of the first contribution value corresponding to any meteorological factor and the weight of the meteorological factor to obtain the second contribution value of the meteorological factor; wherein the sum of the weights of the meteorological factors is 1, for example, the weight of smoke concentration x1 is 0.2, the weight of wind speed x2 is 0.4, the weight of temperature x3 is 0.3, and the weight of humidity x4 is 0.1. It can be understood that the weight of each meteorological factor can be preset based on the type of monitoring area, and is not specifically limited here.

[0144] After determining the second contribution value of each meteorological factor, the edge computing server calculates the sum of the second contribution values ​​of each meteorological factor to obtain the risk value of the monitored area.

[0145] Based on the above description, by setting corresponding weights for different meteorological factors, the importance of meteorological factors in disaster judgment in the monitored area is characterized, thereby improving the flexibility and accuracy of judging whether a disaster has occurred in the monitored area.

[0146] Step 230: monitor the monitoring area according to the risk value.

[0147] In the embodiment of the present application, if the risk value of the monitored area is greater than or equal to the risk threshold, image information in the monitored area is collected. Exemplarily, the edge computing server can call the image acquisition system so that the image acquisition system drives the infrared search system to search for suspicious fires. When the infrared search system finds a suspicious fire, the image is transmitted to the cluster head node, and the cluster head node sends the infrared image to the edge computing server.

[0148] After acquiring the image information, the edge computing server sends the image information to the monitoring center through the satellite network. Exemplarily, the edge computing server determines the azimuth and pitch angle of the current fire location, the size of the fire area, and other information through the image information, and then calculates the size of the visible light field of view (including horizontal field of view and vertical field of view) to confirm the fire. Then the visible light search system is driven, and the visible light search system automatically focuses on the center of the visible light field of view to confirm whether a fire has occurred. If so, the image information is sent to the monitoring center through the satellite network to remind the monitoring personnel to realize the monitoring and early warning of the disaster. If not (such as non-forest fire situations such as chimneys), the image information will not be sent to the monitoring center through the satellite network to improve the accuracy of the early warning.

[0149] Based on the above technical solution, by deploying wireless sensors in the monitoring area to collect meteorological factors in the monitoring area, there is no need to configure additional ground cables for power supply, thereby avoiding excessive monitoring costs. By deploying edge computing servers in the monitoring area, the monitoring area can be monitored and calculated on the edge side, thereby improving the efficiency and real-time performance of the end-side area monitoring. And through edge-side computing, it is no longer necessary to send all data to the end side, thereby reducing the communication resources of the satellite network.

[0150] And according to the residual energy of multiple wireless sensors and the distance between multiple wireless sensors and the edge computing server, multiple wireless sensors are clustered and clustered, and the target wireless sensor as the cluster head node is determined. On the one hand, it is avoided that in the case of non-optimal clustering, the wireless sensor nodes close to the edge computing server should frequently send and receive data, and eventually die due to excessive energy consumption of the nodes, resulting in energy holes in the network; on the other hand, it is avoided that the cluster head node cannot connect and transmit because it is too far away from the edge computing server, so that the wireless sensor that is closer to the edge computing server and has higher residual energy is used as the target wireless sensor, thereby ensuring the reliability of data transmission.

[0151] In addition, collaborative processing through image acquisition systems, infrared search systems, etc. can be used to improve the accuracy of disaster determination, reduce the false alarm rate of disasters, and increase the utilization rate of satellite Internet.

[0152] Based on the same technical concept, Figure 4A schematic structural diagram of a region monitoring device corresponding to an edge computing server provided in an embodiment of the present invention is exemplarily shown, and the device can execute the process of the region monitoring method applied to wireless sensors.

[0153] like Figure 4 As shown, the device specifically includes:

[0154] The first acquisition module 410 is used to acquire various meteorological factors of the monitoring area through a target wireless sensor; the target wireless sensor is determined from the multiple wireless sensors after clustering the multiple wireless sensors according to the residual energy of each wireless sensor and the distance between each wireless sensor and the edge computing server; the target wireless sensor is used to receive meteorological factors sent by other wireless sensors in the cluster to which the target wireless sensor belongs;

[0155] A first processing module 420, configured to calculate the risk value of the monitored area according to the meteorological factors;

[0156] The monitoring area is monitored according to the risk value.

[0157] In some embodiments, the first processing module 420 is specifically used for:

[0158] A similarity matrix corresponding to the multiple wireless sensors is determined according to the residual energy of each wireless sensor and the distance between each wireless sensor and the edge computing server; the similarity matrix represents the similarity of the kth node as the cluster center of the ith node; the kth node is any wireless sensor among the multiple wireless sensors, and the ith node is any wireless sensor among the multiple wireless sensors except the kth node; an attraction matrix is ​​determined according to the similarity matrix; the attraction matrix represents the degree to which the kth node is the cluster center of the ith node; an evaluation matrix is ​​determined according to the attraction matrix and the attribution matrix, and a cluster center node is determined from the evaluation matrix; the attribution matrix is ​​calculated based on the own parameters of the multiple wireless sensors, and the attribution matrix is ​​used to represent the degree to which the ith node selects the kth node as the cluster center; the cluster center node is used as the target wireless sensor.

[0159] In some embodiments, the first processing module 420 is specifically used for:

[0160] The similarity of the kth node becoming a target wireless sensor of the i-th node is calculated based on the distance between the i-th node and the k-th node and the residual energy of the k-th node; the similarity is inversely proportional to the distance between the i-th node and the k-th node, and the similarity is proportional to the residual energy of the k-th node; the preference value of the k-th node is calculated based on the distance between the k-th node and the edge computing server and the residual energy of the k-th node; the preference value of the k-th node is inversely proportional to the distance between the k-th node and the edge computing server, and the preference value of the k-th node is proportional to the residual energy of the k-th node; the similarity matrix is ​​determined based on the similarity of the k-th node becoming a target wireless sensor of the i-th node and the preference value of the k-th node.

[0161] In some embodiments, the first processing module 420 is specifically used for:

[0162] The attraction matrix and the attribution matrix are iterated based on a preset attenuation coefficient to obtain an iterated attraction matrix and an iterated attribution matrix; the sum of the iterated attraction matrix and the iterated attribution matrix is ​​calculated to obtain the evaluation matrix; the multiple wireless sensors are clustered according to the evaluation matrix; for any cluster, the node corresponding to the maximum value in the cluster is used as the cluster center node.

[0163] In some embodiments, the first processing module 420 is further configured to:

[0164] After the cluster center node is used as the target wireless sensor, the target identifier of the target wireless sensor is sent to all wireless sensors in the cluster to which the target wireless sensor belongs.

[0165] In some embodiments, the first processing module 420 is specifically used for:

[0166] For any meteorological factor, the first contribution value corresponding to the meteorological factor is calculated according to the meteorological factor and the preset coefficient; the meteorological factor is proportional to the first contribution value corresponding to the meteorological factor; the product of the first contribution value corresponding to the meteorological factor and the weight of the meteorological factor is calculated to obtain the second contribution value of the meteorological factor; the sum of the second contribution values ​​of each meteorological factor is calculated to obtain the risk value of the monitored area.

[0167] In some embodiments, the first processing module 420 is specifically used for:

[0168] If the risk value of the monitoring area is greater than or equal to the risk threshold, image information in the monitoring area is collected; and the image information is sent to the monitoring center via a satellite network.

[0169] Based on the same technical concept, Figure 5 The schematic diagram of the structure of a region monitoring device corresponding to a wireless sensor provided in an embodiment of the present invention is exemplarily shown. The device can execute the process of the region monitoring method applied to the wireless sensor.

[0170] A second acquisition module 510 is configured to receive a target identifier sent by an edge computing server; the target identifier represents an identifier corresponding to a target wireless sensor, and the target wireless sensor is determined by the edge computing server from the multiple wireless sensors after clustering the multiple wireless sensors according to the residual energy of each wireless sensor and the distance between each wireless sensor and the edge computing server;

[0171] The second processing module 520 is used to receive the meteorological factors sent by other wireless sensors in the cluster to which it belongs as a target wireless sensor if its own identification is consistent with the target identification, and send the meteorological factors to the edge computing server; if its own identification is inconsistent with the target identification, collect the meteorological factors of the area where it is located, and send the meteorological factors of the area where it is located to the target wireless sensor corresponding to the target identification.

[0172] Based on the same technical concept, an embodiment of the present invention further provides a computer device, including:

[0173] A memory for storing program instructions;

[0174] The processor is used to call the program instructions stored in the memory and execute the above-mentioned area monitoring method according to the obtained program.

[0175] Based on the same technical concept, an embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are used to enable a computer to execute the above-mentioned area monitoring method.

[0176] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0177] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0178] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0179] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0180] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A regional monitoring method, characterized in that: Applied to edge computing servers, including: Acquire various meteorological factors of the monitoring area through a target wireless sensor; the target wireless sensor is determined from the multiple wireless sensors after clustering the multiple wireless sensors according to the residual energy of each wireless sensor and the distance between each wireless sensor and the edge computing server; the target wireless sensor is used to receive meteorological factors sent by other wireless sensors in the cluster to which the target wireless sensor belongs; Calculate the risk value of the monitored area according to the meteorological factors; The monitoring area is monitored according to the risk value.

2. The method according to claim 1, characterized in that The target wireless sensor is determined from the multiple wireless sensors after clustering the multiple wireless sensors according to the residual energy of each wireless sensor and the distance between each wireless sensor and the edge computing server, including: Determine a similarity matrix corresponding to the plurality of wireless sensors according to the residual energy of each wireless sensor and the distance between each wireless sensor and the edge computing server; the similarity matrix represents the similarity of the kth node as the cluster center of the i-th node; the kth node is any wireless sensor among the plurality of wireless sensors, and the i-th node is any wireless sensor among the plurality of wireless sensors except the kth node; Determine an attraction matrix according to the similarity matrix; the attraction matrix represents the degree to which the k-th node serves as the cluster center of the i-th node; Determine an evaluation matrix according to the attraction matrix and the attribution matrix, and determine a cluster center node from the evaluation matrix; the attribution matrix is ​​calculated based on the own parameters of multiple wireless sensors, and the attribution matrix is ​​used to characterize the degree to which the i-th node selects the k-th node as the cluster center; The cluster center node is used as the target wireless sensor.

3. The method according to claim 2, characterized in that Determining similarity matrices corresponding to the plurality of wireless sensors according to the residual energy of each wireless sensor and the distance between each wireless sensor and the edge computing server includes: Calculating the similarity of the kth node becoming the target wireless sensor of the i-th node according to the distance between the i-th node and the k-th node and the residual energy of the k-th node; the similarity is inversely proportional to the distance between the i-th node and the k-th node, and the similarity is proportional to the residual energy of the k-th node; Calculating a preference value of the kth node according to the distance between the kth node and the edge computing server and the residual energy of the kth node; the preference value of the kth node is inversely proportional to the distance between the kth node and the edge computing server, and the preference value of the kth node is proportional to the residual energy of the kth node; The similarity matrix is ​​determined according to the similarity of the k-th node becoming a target wireless sensor of the i-th node and the preference value of the k-th node.

4. The method according to claim 2, characterized in that Determining an evaluation matrix according to the attraction matrix and the attribution matrix, and determining a cluster center node from the evaluation matrix, including: Iterating the attraction matrix and the attribution matrix based on a preset attenuation coefficient to obtain an iterated attraction matrix and an iterated attribution matrix; Calculate the sum of the iterative attraction matrix and the iterative attribution matrix to obtain the evaluation matrix; Clustering the plurality of wireless sensors according to the evaluation matrix; For any cluster, the node corresponding to the maximum value in the cluster is used as the cluster center node.

5. The method according to claim 2, characterized in that After the cluster center node is used as the target wireless sensor, the method further includes: The target identifier of the target wireless sensor is sent to all wireless sensors in the cluster to which the target wireless sensor belongs.

6. The method according to claim 1, characterized in that Calculating the risk value of the monitored area according to the meteorological factors includes: For any meteorological factor, a first contribution value corresponding to the meteorological factor is calculated according to the meteorological factor and a preset coefficient; the meteorological factor is proportional to the first contribution value corresponding to the meteorological factor; Calculating the product of the first contribution value corresponding to the meteorological factor and the weight of the meteorological factor to obtain a second contribution value of the meteorological factor; The sum of the second contribution values ​​of the meteorological factors is calculated to obtain the risk value of the monitored area.

7. The method according to claim 1, characterized in that Monitoring the monitoring area according to the risk value includes: If the risk value of the monitoring area is greater than or equal to the risk threshold, collecting image information in the monitoring area; The image information is sent to a monitoring center via a satellite network.

8. A method for regional monitoring, characterized in that: Applicable to any of a number of wireless sensors, including: Receive a target identifier sent by an edge computing server; the target identifier represents an identifier corresponding to a target wireless sensor, and the target wireless sensor is determined from the multiple wireless sensors after the edge computing server clusters the multiple wireless sensors according to the residual energy of each wireless sensor and the distance between each wireless sensor and the edge computing server; If its own identifier is consistent with the target identifier, it receives meteorological factors sent by other wireless sensors in the cluster to which it belongs as a target wireless sensor, and sends the meteorological factors to the edge computing server; If its own identification is inconsistent with the target identification, the meteorological factors of the area where the own area is located are collected and sent to the target wireless sensor corresponding to the target identification.

9. A regional monitoring device, characterized in that: include: The first acquisition module is used to acquire various meteorological factors of the monitoring area through the target wireless sensor; The target wireless sensor is determined from the multiple wireless sensors after clustering the multiple wireless sensors according to the residual energy of each wireless sensor and the distance between each wireless sensor and the edge computing server; the target wireless sensor is used to receive meteorological factors sent by other wireless sensors in the cluster to which the target wireless sensor belongs; A first processing module, used for calculating the risk value of the monitored area according to the meteorological factors; The monitoring area is monitored according to the risk value.

10. A regional monitoring device, characterized in that: include: A second acquisition module is used to receive a target identifier sent by an edge computing server; The target identifier represents an identifier corresponding to a target wireless sensor, and the target wireless sensor is determined from the multiple wireless sensors after the edge computing server clusters the multiple wireless sensors according to the residual energy of each wireless sensor and the distance between each wireless sensor and the edge computing server; The second processing module is used to, if its own identification is consistent with the target identification, receive the meteorological factors sent by other wireless sensors in the cluster to which it belongs as a target wireless sensor, and send the meteorological factors to the edge computing server; if its own identification is inconsistent with the target identification, collect the meteorological factors of its own area, and send the meteorological factors of its own area to the target wireless sensor corresponding to the target identification.

11. A regional monitoring system, characterized in that: Includes edge computing servers and multiple wireless sensors; The edge computing server is used to: obtain various meteorological factors of the monitoring area through a target wireless sensor; the target wireless sensor is determined from the multiple wireless sensors after clustering the multiple wireless sensors according to the residual energy of each wireless sensor and the distance between each wireless sensor and the edge computing server; The target wireless sensor is used to receive meteorological factors sent by other wireless sensors in the cluster to which the target wireless sensor belongs; Calculate the risk value of the monitored area according to the meteorological factors; Monitoring the monitoring area according to the risk value; Any wireless sensor among the multiple wireless sensors is used for: if its own identification is consistent with the target identification, then, as a target wireless sensor, receiving meteorological factors sent by other wireless sensors in the cluster to which it belongs, and sending the meteorological factors to the edge computing server; if its own identification is inconsistent with the target identification, then collecting meteorological factors of its own area, and sending the meteorological factors of its own area to the target wireless sensor corresponding to the target identification.

12. A computer device, characterized in that: include: A memory for storing program instructions; A processor is used to call the program instructions stored in the memory and execute the method according to any one of claims 1 to 7 or claim 8 according to the obtained program.

13. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are used to enable a computer to execute the method according to any one of claims 1 to 7 or claim 8.

Images