Beidou dual-network channel control method and system based on AI control device

Abstract

The invention discloses a Beidou dual-network channel control method and system based on an AI control device, and the method comprises the steps: judging whether a Beidou communication channel is an optimal communication channel or not when a transmission signal transmitted by central control equipment is received; when the Beidou communication channel is not the optimal communication channel, constructing a water conservancy monitoring ad hoc network according to the position of the AI control device of each water conservancy monitoring area; screening communication abnormal nodes in the water conservancy monitoring ad hoc network to obtain communication coverage blind area nodes; networking a communication coverage blind area node and a node with the strongest communication signal, and judging whether a direct connection condition is met or not; if a direct connection condition is met, carrying out direct connection; if the communication coverage blind area node and the node with the strongest communication signal do not meet the direct connection condition, obtaining a relay node of the water conservancy monitoring ad hoc network; and connecting the relay node with the communication coverage blind area node to obtain the target water conservancy monitoring ad hoc network. The accuracy of water regimen monitoring can be effectively improved.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of communication technology, and in particular to a Beidou dual-network channel control method and system based on an AI control device. Background Art

[0002] Water conservancy projects are an important part of the water conservancy project system. They are usually composed of various types of hydraulic structures, which work together to complete the task of preventing and controlling floods and developing and utilizing water resources. The water management of water conservancy projects is of vital importance. It is directly related to the safe operation of the project, the effect of flood prevention and disaster reduction, the efficient use of water resources and the protection of the ecological environment.

[0003] At present, water conditions of water conservancy hub projects are mainly monitored through hydrological monitoring stations, which are usually set up in remote areas, such as near rivers, lakes, reservoirs and other water bodies, in order to directly monitor and record hydrological data. These areas often lack stable communication network coverage, such as 4G / 5G signals, fiber optic networks, etc., due to remote geographical locations, complex terrains, and weak infrastructure. As a result, communication data cannot be transmitted in a timely manner, affecting the efficiency and accuracy of hydrological monitoring.

[0004] Therefore, there is an urgent need for a Beidou dual-network channel control method and system based on an AI control device to improve the accuracy of water situation monitoring. Summary of the invention

[0005] The embodiments of the present application provide a Beidou dual-network channel control method and system based on an AI control device, which are used to improve the accuracy of water condition monitoring.

[0006] To achieve the above objectives, the embodiments of the present application adopt the following technical solutions:

[0007] In a first aspect, a Beidou dual-network channel control method based on an AI control device is provided, which is applied to the AI ​​control device, the number of which is at least two, and the AI ​​control device is arranged in a water conservancy monitoring area, and the water conservancy monitoring area is connected to a central control device, and the method includes:

[0008] In response to receiving a transmission signal sent by the central control device, determining whether the Beidou communication channel is the best communication channel, wherein the transmission signal is used to transmit water conservancy monitoring data;

[0009] When the Beidou communication channel is not the optimal communication channel, obtaining the positions of all the AI ​​control devices in each of the water conservancy monitoring areas;

[0010] Building a water conservancy monitoring ad hoc network based on the locations of all the AI ​​control devices in each of the water conservancy monitoring areas, wherein each of the AI ​​control devices is a node of the water conservancy monitoring ad hoc network;

[0011] Obtaining node information of the water conservancy monitoring ad hoc network;

[0012] According to the node information, the communication abnormal nodes in the water conservancy monitoring ad hoc network are screened to obtain the communication coverage blind area nodes in the water conservancy monitoring ad hoc network;

[0013] Obtaining the node with the strongest communication signal in the water conservancy monitoring ad hoc network;

[0014] Networking the node in the communication blind area with the node with the strongest communication signal, and determining whether the node in the communication blind area and the node with the strongest communication signal meet direct connection conditions;

[0015] If the communication coverage blind area node and the node with the strongest communication signal meet the direct connection condition, the communication coverage blind area node and the node with the strongest communication signal are directly connected to obtain the target water conservancy monitoring ad hoc network, wherein the direct connection condition is that the communication protocol of the communication coverage blind area node and the node with the strongest communication signal is the same;

[0016] If the communication coverage blind area node and the node with the strongest communication signal do not meet the direct connection condition, obtain the relay node of the water conservancy monitoring ad hoc network;

[0017] The relay node is connected to the communication coverage blind area node to obtain a target water conservancy monitoring self-organizing network.

[0018] In another possible implementation manner of the first aspect, the method further includes:

[0019] When the Beidou communication channel is the best communication channel, converting the water conservancy monitoring data into a water conservancy monitoring digital signal;

[0020] Transmitting the water conservancy monitoring digital signal to the Beidou satellite using the AI ​​control device;

[0021] Acquire a target area covered by the signal of the Beidou satellite, and determine the central control device in the target area;

[0022] Transmitting the water conservancy monitoring digital signal to the central control device;

[0023] The water conservancy monitoring digital signal transmitted by the Beidou satellite is decoded by the central control device to obtain readable water conservancy monitoring data.

[0024] In another possible implementation manner of the first aspect, determining whether the Beidou communication channel is an optimal communication channel includes:

[0025] Determining the communication scenario of each of the water conservancy monitoring areas through the geographical location information;

[0026] By means of the communication scenario, the water conservancy monitoring area is divided into a plurality of target monitoring areas;

[0027] Obtaining signal strength change data and data volume change values ​​of the water conservancy monitoring data transmitted by each target monitoring area within a preset time period;

[0028] Determine the communication stability threshold of each target monitoring area by using the signal strength change data and the signal data volume change data within a preset time period;

[0029] Acquiring communication parameters of each target monitoring area;

[0030] Inputting the communication parameters into the pre-trained model to obtain the current communication stability value of each target monitoring area;

[0031] Comparing the communication stability value corresponding to each of the communication scenarios with the communication stability threshold, and marking the number of the communication scenarios whose communication stability value is greater than the communication stability threshold;

[0032] If the number is greater than a preset threshold, determining that the Beidou communication channel is the best communication channel;

[0033] If the number is less than a preset threshold, it is determined that the Beidou communication channel is not the best communication channel.

[0034] In another possible implementation manner of the first aspect, determining the communication stability threshold of each target monitoring area by using the signal strength change data and the signal data volume change data within a preset time period includes:

[0035] Using a preset recognition algorithm, identifying data whose signal-to-noise ratio is less than a preset noise ratio threshold and data whose signal-to-noise ratio is greater than a preset noise ratio threshold in the signal strength change data of each target monitoring area;

[0036] Using a preset recognition algorithm, identifying data whose signal packet loss rate is less than a preset packet loss rate threshold and data whose signal packet loss rate is greater than a preset packet loss rate threshold in the signal data volume change data of each target monitoring area;

[0037] Marking the data whose signal-to-noise ratio is less than a preset noise ratio threshold and the data whose signal packet loss rate is less than a preset packet loss rate threshold as true stable cases;

[0038] Marking the data whose signal-to-noise ratio is greater than a preset noise ratio threshold and the data whose signal packet loss rate is greater than a preset packet loss rate threshold as false stable cases;

[0039] Inputting the true stable examples into the trained binary classification algorithm, and outputting true positive examples and false positive examples;

[0040] Inputting the false stable example into the binary classification algorithm, and outputting true negative examples and false negative examples;

[0041] Calculating a true stability rate through the true positive examples and the false negative examples;

[0042] Calculating a false stability rate through the false positive examples and the true negative examples;

[0043] Using the false stability rate as the horizontal axis and the true stability rate as the vertical axis, a communication stability threshold curve of each target monitoring area is drawn;

[0044] Determine the threshold boundary point of the communication stability threshold curve of each target monitoring area by a preset optimal threshold judgment formula;

[0045] The communication stability threshold of each target monitoring area is determined by the threshold boundary point.

[0046] In another possible implementation of the first aspect, screening, according to the node information, nodes with abnormal communication in the water conservancy monitoring ad hoc network to obtain nodes with blind area of ​​communication coverage in the water conservancy monitoring ad hoc network includes:

[0047] In the node information, the total number of times each node sends data and the number of times the data is successfully sent are obtained;

[0048] Calculate the communication success rate of each node according to the total number of times the data is sent and the number of times the data is successfully sent;

[0049] Calculate the correlation coefficient between any two nodes according to the communication success rate;

[0050] Performing cluster analysis on the correlation coefficient to obtain nodes with abnormal correlation coefficients;

[0051] Determine the target monitoring area where the node with abnormal correlation coefficient is located, and obtain the abnormal target detection area;

[0052] Obtaining all node information within the abnormal target detection area;

[0053] Acquire the topological structure of the abnormal target detection area and extract the topological structure features;

[0054] Inputting the topological structure features and all node information in the abnormal target detection area into the trained communication connection effect level model, and outputting the target connection effect of the abnormal target detection area;

[0055] The target connection effect is compared with a preset standard connection effect. If the target connection effect is less than the pre-calculated standard connection effect, a communication coverage blind area node in the water conservancy monitoring ad hoc network is obtained.

[0056] In another possible implementation manner of the first aspect, acquiring the relay node of the water conservancy monitoring ad hoc network, connecting the relay node with the communication coverage blind area node, and obtaining the target water conservancy monitoring ad hoc network includes:

[0057] All the node information is exchanged arbitrarily among all the nodes in the water conservancy monitoring ad hoc network through a preset communication protocol;

[0058] By using any node information received, a preliminary match is performed on the node information to obtain a candidate relay node;

[0059] Calculate the hash value of the candidate relay node and the communication coverage blind area node by using a preset hash value calculation algorithm, wherein, when the hash value is less than a preset threshold, the communication coverage blind area node is used to send a connection request to the candidate relay node;

[0060] In response to the connection request, matching the information of the candidate relay node with the information of the communication coverage blind area node again;

[0061] Among them, when the matching degree of the re-matching is greater than the preset matching degree threshold, the candidate relay node replies to the connection request of the communication coverage blind spot node and connects with the communication coverage blind spot node to obtain the target water conservancy monitoring self-organizing network. When the matching degree is less than the preset matching degree threshold, the candidate relay node does not reply to the connection request of the communication coverage blind spot node, and the communication coverage blind spot node will repeat the step of performing preliminary matching on the node information through any node information received to obtain the candidate relay node.

[0062] In another possible implementation manner of the first aspect, after the candidate relay node replies to the connection request of the communication coverage blind area node and connects with the communication coverage blind area node to obtain the target water conservancy monitoring ad hoc network, the method further includes:

[0063] Obtaining the first transmission performance of the water conservancy monitoring ad hoc network that meets the direct connection condition and the first node transmission performance between each of the AI ​​control devices;

[0064] Acquire the second transmission performance of the target water conservancy monitoring ad hoc network and the second node transmission performance between each of the AI ​​control devices and the relay node;

[0065] comparing the first transmission performance with the second transmission performance, and comparing the first node transmission performance with the second node transmission performance;

[0066] If the first transmission performance is less than or equal to the second transmission performance, and the first node transmission performance is less than or equal to the second node transmission performance, the target water conservancy monitoring ad hoc network is obtained after the communication coverage blind area node is connected to the candidate relay node.

[0067] In another possible implementation manner of the first aspect, the method further includes:

[0068] Obtain climate monitoring data for each water conservancy monitoring area in real time;

[0069] Inputting the climate monitoring data into a prediction model to obtain climate prediction information for each of the water conservancy monitoring areas;

[0070] Through the AI ​​control device, water condition monitoring data of each water conservancy monitoring area is collected in real time;

[0071] Obtaining water regime change data for each of the water conservancy monitoring areas within future trends through the water regime monitoring data and the climate forecast information;

[0072] A water control plan for each water monitoring area is generated by using the water situation change data of each water monitoring area within the future trend.

[0073] In a second aspect, the present application provides a machine-readable storage medium having instructions stored thereon, the instructions being used to enable a machine to execute a Beidou dual-network channel control method based on an AI control device.

[0074] In a third aspect, the present application provides a Beidou dual-network channel control system based on an AI control device, comprising:

[0075] a memory configured to store instructions; and

[0076] The processor is configured to call the instructions from the memory and implement the Beidou dual-network channel control method based on the AI ​​control device when executing the instructions.

[0077] Through the above technical solution, by judging whether the Beidou communication channel is the best communication channel and building a water conservancy monitoring ad hoc network under non-optimal conditions, the method can dynamically adjust the communication path to ensure the real-time and stable transmission of water conservancy monitoring data, which helps to reduce communication delays and packet loss rates and improve overall communication efficiency. By identifying nodes in communication coverage blind areas and connecting them to nodes with the strongest communication signals or relay nodes, the method can significantly optimize the network coverage of the water conservancy monitoring area. This ensures stable data transmission even in remote or weak signal areas, improving the reliability and comprehensiveness of the monitoring system. In the process of building an ad hoc network, the method enhances the security of the network by screening abnormal communication nodes and ensuring the consistency of communication protocols. This helps prevent data leakage and illegal access, and protects the security and integrity of water conservancy monitoring data. Combining AI technology and Beidou communication technology, the intelligent management of the water conservancy monitoring system is realized. By real-time monitoring and analysis of network status, the AI ​​control device can automatically adjust the communication strategy to improve the response speed and decision-making ability of the monitoring system.

[0078] Other features and advantages of the embodiments of the present application will be described in detail in the subsequent specific implementation section. BRIEF DESCRIPTION OF THE DRAWINGS

[0079] Figure 1 A flowchart of a Beidou dual-network channel control method based on an AI control device provided in an embodiment of the present application;

[0080] Figure 2 A flowchart for determining a candidate relay node provided in an embodiment of the present application;

[0081] Figure 3 A schematic diagram of the structure of a water conservancy monitoring ad hoc network provided in an embodiment of the present application. DETAILED DESCRIPTION

[0082] In order to make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. It should be understood that the specific implementation methods described herein are only used to illustrate and explain the embodiments of the present application, and are not used to limit the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0083] It should be noted that if the embodiments of the present application involve directional indications (such as up, down, left, right, front, back...), the directional indications are only used to explain the relative position relationship, movement status, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication will also change accordingly.

[0084] In addition, if there are descriptions involving "first", "second", etc. in the embodiments of the present application, the descriptions of "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or suggesting their relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the technical solutions between the various embodiments can be combined with each other, but they must be based on the ability of ordinary technicians in the field to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such combination of technical solutions does not exist and is not within the scope of protection required by this application.

[0085] Figure 1 The flowchart of a Beidou dual network channel control method based on an AI control device according to an embodiment of the present application is schematically shown. Figure 1 As shown, an embodiment of the present application provides a Beidou dual-network channel control method based on an AI control device, which is applied to the AI ​​control device. The number of AI control devices is at least two. The AI ​​control device is arranged in a water conservancy monitoring area. The water conservancy monitoring area is connected to a central control device. The method may include the following steps.

[0086] S101, in response to receiving a transmission signal sent by a central control device, determining whether a Beidou communication channel is an optimal communication channel, wherein the transmission signal is used to transmit water conservancy monitoring data;

[0087] S102. When the Beidou communication channel is not the optimal communication channel, obtain the positions of all AI control devices in each water conservancy monitoring area;

[0088] S103, constructing a water conservancy monitoring ad hoc network based on the locations of all AI control devices in each water conservancy monitoring area, wherein each AI control device is a node of the water conservancy monitoring ad hoc network;

[0089] S104, obtaining node information of the water conservancy monitoring ad hoc network;

[0090] S105, screening the communication abnormal nodes in the water conservancy monitoring ad hoc network according to the node information, and obtaining the communication coverage blind area nodes in the water conservancy monitoring ad hoc network;

[0091] S106, obtaining the node with the strongest communication signal in the water conservancy monitoring ad hoc network;

[0092] S107, networking the node in the communication blind area with the node with the strongest communication signal, and determining whether the node in the communication blind area and the node with the strongest communication signal meet the direct connection condition;

[0093] S108. If the node in the blind area of ​​communication coverage and the node with the strongest communication signal meet the direct connection condition, the node in the blind area of ​​communication coverage and the node with the strongest communication signal are directly connected to obtain the target water conservancy monitoring ad hoc network, wherein the direct connection condition is that the communication protocol of the node in the blind area of ​​communication coverage and the node with the strongest communication signal are the same;

[0094] S109, if the communication coverage blind area node and the node with the strongest communication signal do not meet the direct connection condition, obtain the relay node of the water conservancy monitoring ad hoc network;

[0095] S110, connecting the relay node to the communication coverage blind area node to obtain the target water conservancy monitoring self-organizing network.

[0096] The transmission signal sent by the central control device is received by the AI ​​control device, wherein the transmission signal is used to transmit water conservancy monitoring data. In this embodiment, the AI ​​control device can be a telemetry terminal device, which is an electronic device controlled by a microprocessor. The AI ​​control device is a key device in the water conservancy monitoring area, responsible for receiving transmission signals from the central control device, which contain the water conservancy monitoring data to be transmitted and related control instructions. After receiving the transmission signal, the AI ​​control device will immediately evaluate the current Beidou communication channel and determine whether the Beidou communication channel is the nearest communication channel. If the Beidou communication channel is determined to be the best communication channel, the AI ​​control device will directly use the channel to transmit water conservancy monitoring data. If the Beidou communication channel is not the best communication channel, the AI ​​control device will take further action to find other available communication channels, such as other satellite communication channels or ground communication networks, or build a water conservancy monitoring ad hoc network to optimize the data transmission path.

[0097] When the Beidou communication channel is not the optimal communication channel, the positions of all AI control devices in each water conservancy monitoring area are obtained. That is to say, since the Beidou communication channel may be affected by various factors, such as weather, terrain, building obstruction, etc., resulting in poor communication quality, at this time, obtaining the positions of all AI control devices in each water conservancy monitoring area can be achieved through a geographic information system. A geographic information system is a comprehensive technical system that integrates computer hardware, software and geographic data. It is used to comprehensively and systematically collect, store, process, analyze, display and describe geographic information. The water conservancy monitoring area is digitized using a geographic information system, and the location information of the AI ​​control device is marked on the map in the form of graphic elements such as points, lines, and surfaces to obtain the positions of all AI control devices in each water conservancy monitoring area.

[0098] After obtaining the locations of all AI control devices in each water conservancy monitoring area, a water conservancy monitoring ad hoc network is constructed based on the locations of the AI ​​control devices in each water conservancy monitoring area. In this embodiment, each AI control device is used as a node of the water conservancy monitoring ad hoc network. Through the location information of the AI ​​control devices in each water conservancy monitoring area, a water conservancy monitoring ad hoc network is constructed, which can collect, transmit and process water conservancy monitoring data in real time. The AI ​​control device in each water conservancy monitoring area is used as a node of the water conservancy monitoring ad hoc network, and each node is set and configured, and a unique identifier is configured, such as an IP address or MAC address, so that it can be uniquely identified in the network. Subsequently, according to the characteristics and needs of the water conservancy monitoring area, the network topology of the water conservancy monitoring ad hoc network is designed, and a suitable network topology is selected, such as a star, mesh or hybrid topology. Taking the mesh structure as an example, the embodiment of the present application provides a structural schematic diagram of a water conservancy monitoring ad hoc network, as shown in FIG. Figure 3 As shown, in Figure 3 In the figure, nodes 1, 2, 3, 4 to 6 constitute a water conservancy monitoring ad hoc network, which is used to monitor the water conditions of the water conservancy system, where each node is connected in no fixed order. After selecting a suitable topology, it is necessary to configure various parameters of the network, such as communication protocol, data transmission rate, network address, etc. According to the communication capability of the node and the characteristics of the water conservancy monitoring data, select a suitable communication protocol, such as ZigBee, LoRa, NB-IoT, etc., and configure various parameters of the communication module, such as communication frequency, transmission power, receiving sensitivity, etc. Finally, a water conservancy monitoring ad hoc network is constructed according to the location of the AI ​​control device in each water conservancy monitoring area.

[0099] After building a water conservancy monitoring ad hoc network, you can obtain the node information of each water conservancy monitoring ad hoc network and directly access the network management system of the water conservancy monitoring ad hoc network. The water conservancy monitoring ad hoc network will be equipped with a network management system. By logging into the system, you can directly query the status, configuration, data transmission and other information of each node. For some node devices, you can directly read the relevant information of the node, such as device identification, status, data, etc., through its own interface.

[0100] After obtaining the node information of each water conservancy monitoring self-organizing network, the communication abnormal nodes in the water conservancy monitoring self-organizing network are screened according to the node information to obtain the communication coverage blind area nodes in the water conservancy monitoring self-organizing network. In this embodiment, the communication coverage blind area nodes are nodes that cannot effectively receive signals from other nodes due to the obstruction of signal transmission or insufficient signal strength, thus becoming the nodes in the communication coverage blind area. That is to say, by analyzing the node communication status, such as the signal strength, communication rate, packet loss rate and other data of the node, if the signal strength of the node is lower than a certain threshold, it may indicate that the node is in the communication coverage blind area; if the communication rate of the node is much lower than the normal level, it may indicate that the node has a communication problem; if the packet loss rate of the node is too high, it may indicate that the communication link of the node is unstable; by analyzing the signal strength, communication rate, packet loss rate and other data of the node, the nodes with abnormal communication can be screened out. After screening out the abnormal communication nodes, it is necessary to further analyze the location information of these nodes to determine whether there is a communication coverage blind area. Firstly, according to the location information of the nodes, the network topology diagram of the water conservancy monitoring self-organizing network is drawn, and the nodes with communication abnormalities are marked in the network topology diagram. The distribution of the nodes with communication abnormalities is analyzed and observed. If the number of abnormal nodes in certain areas is large or they appear continuously, it may indicate that there is a communication blind spot in the area. The communication blind spot nodes in the water conservancy monitoring self-organizing network are obtained.

[0101] Subsequently, the node with the strongest communication signal in the water conservancy monitoring ad hoc network can be obtained by collecting communication data, analyzing the collected communication data, especially the signal strength data, and comparing the signal strength values ​​of different nodes to find the node with the strongest signal.

[0102] After obtaining the node with the strongest communication signal in the water conservancy monitoring self-organizing network, the node in the communication blind area is networked with the node with the strongest communication signal to determine whether the node in the communication blind area and the node with the strongest communication signal meet the direct connection condition. In this embodiment, the direct connection condition is that the communication protocol between the node in the communication blind area and the node with the strongest communication signal is the same, and the direct connection condition is met. In other words, by determining whether the communication protocol between the node in the communication blind area and the node with the strongest communication signal is the same, it is determined whether the node in the communication blind area and the node with the strongest communication signal can be directly connected.

[0103] If the node in the blind area of ​​communication coverage meets the direct connection condition with the node with the strongest communication signal, that is, the communication protocol of the node in the blind area of ​​communication coverage is the same as that of the node with the strongest communication signal, the node in the blind area of ​​communication coverage is directly connected with the node with the strongest communication signal to obtain the target water conservancy monitoring self-organizing network. The consistency of the communication protocol is the key to ensure that the two nodes can communicate normally. After the node in the blind area of ​​communication coverage is directly connected with the node with the strongest communication signal, the architecture of the water conservancy monitoring self-organizing network needs to be designed according to actual needs to obtain the target water conservancy monitoring self-organizing network.

[0104] If the communication coverage blind area node and the node with the strongest communication signal do not meet the direct connection conditions, obtain the relay node of the water conservancy monitoring self-organizing network, that is, when the communication protocol of the communication coverage blind area node and the node with the strongest communication signal is different, for example, due to compatibility issues, the communication protocol is different, and some devices may not support specific communication protocol versions or functions, resulting in the inability to communicate with other devices. Obtain the relay node, and deploy the relay node near the location of the communication coverage blind area node by considering factors such as the relay node's location, communication range, transmission power, receiving sensitivity, and compatibility with other nodes to ensure the communication stability of the relay node.

[0105] Connect the relay nodes with the nodes in the communication blind area to obtain the target water conservancy monitoring self-organizing network. Use appropriate communication technology and equipment to connect the relay nodes with the nodes in the communication blind area, such as Wi-Fi, microwave, satellite communication and other technologies. Connect the relay nodes with the nodes in the communication blind area through wireless connection to obtain the target water conservancy monitoring self-organizing network.

[0106] By judging whether the Beidou communication channel is the best communication channel and building a water conservancy monitoring ad hoc network under non-optimal conditions, this method can dynamically adjust the communication path to ensure the real-time and stable transmission of water conservancy monitoring data, which helps to reduce communication delays and packet loss rates and improve overall communication efficiency. By identifying nodes in communication coverage blind areas and connecting them to nodes with the strongest communication signals or relay nodes, this method can significantly optimize the network coverage of the water conservancy monitoring area. This ensures stable data transmission even in remote or weak signal areas, improving the reliability and comprehensiveness of the monitoring system. In the process of building an ad hoc network, this method enhances the security of the network by screening abnormal communication nodes and ensuring the consistency of communication protocols. This helps prevent data leakage and illegal access, and protects the security and integrity of water conservancy monitoring data. Combining AI technology and Beidou communication technology, the intelligent management of the water conservancy monitoring system is realized. By real-time monitoring and analysis of network status, the AI ​​control device can automatically adjust the communication strategy to improve the response speed and decision-making ability of the monitoring system.

[0107] In one implementation of this embodiment, the method further includes:

[0108] S210, when the Beidou communication channel is the best communication channel, converting the water conservancy monitoring data into a water conservancy monitoring digital signal;

[0109] S220, transmit the water conservancy monitoring digital signal to the Beidou satellite using the AI ​​control device;

[0110] S230, obtaining a target area covered by Beidou satellite signals, and determining a central control device in the target area;

[0111] S240, transmitting the water conservancy monitoring digital signal to the central control device;

[0112] S250. Decode the water conservancy monitoring digital signal transmitted by the Beidou satellite through the central control equipment to obtain readable water conservancy monitoring data.

[0113] When the Beidou communication channel is determined as the best communication channel, the water conservancy monitoring data is converted from analog signals to digital signals. This can be achieved through an analog-to-digital converter, which can convert continuous analog signals into discrete digital signals. During the conversion process, it is necessary to select a suitable sampling rate and resolution to ensure that the digital signal can accurately reflect the characteristics of the original analog signal.

[0114] After obtaining the water conservancy monitoring digital signal, the water conservancy monitoring digital signal is transmitted to the Beidou satellite using the AI ​​control device. First, it is necessary to establish a stable connection between the AI ​​control device and the water conservancy monitoring digital signal, and establish a connection between the AI ​​control device and the water conservancy monitoring digital signal through antenna alignment, signal capture and other steps. Subsequently, in order to ensure the integrity and security of the data during transmission, the AI ​​control device will encode and package the water conservancy monitoring digital signal. The encoding process may involve measures such as data compression and encryption; the packaging process usually includes adding data packet headers, checksums and other information. After establishing the connection and completing data encoding and packaging, the AI ​​control device will transmit the data packet to the designated receiving end through the Beidou satellite communication system. During this process, it is necessary to ensure that key indicators such as data transmission rate and bit error rate meet the requirements.

[0115] After the water conservancy monitoring digital signal is transmitted to the Beidou satellite using the AI ​​control device, the target area covered by the Beidou satellite signal is obtained, and the central control equipment in the target area is determined. That is to say, first, the target area covered by the Beidou satellite navigation system's signal is determined. Among them, in the target area covered by the Beidou satellite signal, the central control equipment is a key part to ensure the normal operation and data processing of the Beidou satellite navigation system. The central control equipment in the target area is determined. In this embodiment, the central control equipment can be a data processing center, a device that processes and analyzes the received data. The central control equipment can be a telemetry terminal device. The telemetry terminal device is a multi-functional device that can collect data from various sensors and devices, and transmit the data to a control center or data center for analysis and processing.

[0116] After determining the central control equipment in the target area, the water conservancy monitoring digital signal is transmitted to the central control equipment using Beidou satellites and other communication satellites. The Beidou satellite navigation system is a global satellite navigation system that can provide a high-precision positioning and navigation basic system.

[0117] When the central control device receives the water conservancy monitoring digital signal from the Beidou satellite, it may be encoded and compressed in order to save bandwidth and improve efficiency during transmission. First, the received signal is preprocessed, including signal amplification, filtering, denoising, etc., to improve the signal quality and readability. Subsequently, the received signal needs to be further decoded to be converted into readable water conservancy monitoring data. According to the signal format and encoding method transmitted by the Beidou satellite, the corresponding decoding algorithm is selected, such as binary phase shift keying, orthogonal phase shift keying, etc. The preprocessed signal is decoded by the decoding algorithm to extract the original water conservancy monitoring digital signal and obtain readable water conservancy monitoring data.

[0118] By using Beidou satellites to transmit water conservancy monitoring digital signals to the central control equipment, not only can efficient and reliable transmission of water conservancy monitoring data be achieved, but it can also promote the intelligent development of water conservancy management systems and provide strong support for the rational development and utilization of water resources.

[0119] In one implementation of this embodiment, determining whether the Beidou communication channel is the best communication channel includes:

[0120] S310, determining the communication scenario of each water conservancy monitoring area through the geographical location information;

[0121] S320, dividing the water conservancy monitoring area into multiple target monitoring areas through the communication scenario;

[0122] S330, obtaining signal strength change data and data volume change values ​​of water conservancy monitoring data transmitted in each target monitoring area within a preset time period;

[0123] S340, determining a communication stability threshold of each target monitoring area through signal strength change data and signal data volume change data within a preset time period;

[0124] S350, obtaining communication parameters of each target monitoring area;

[0125] S360, inputting the communication parameters into the pre-trained model to obtain the current communication stability value of each target monitoring area;

[0126] S370, comparing the communication stability value corresponding to each communication scenario with the communication stability threshold, and marking the number of communication scenarios whose communication stability values ​​are greater than the communication stability threshold;

[0127] S380: If the number is greater than a preset threshold, determining the Beidou communication channel as the best communication channel;

[0128] S390: If the number is less than the preset threshold, it is determined that the Beidou communication channel is not the best communication channel.

[0129] Determine whether the Beidou communication channel is the best communication channel. Specifically, first, determine the communication scenario of each water conservancy monitoring area through the geographic location information. In this embodiment, the communication scenario can be the foot of a mountain in a remote mountainous area, the riverside with a vast water area, and other scenes. Determine the communication environment of each water conservancy monitoring area through the geographic information system. Determine the communication environment based on the geographic location information to determine the impact of terrain on signal propagation, the impact of climate characteristics on communication stability, and whether there are other interference factors such as electromagnetic interference, building obstruction and other interference.

[0130] After determining the communication scenario of each water conservancy monitoring area, the water conservancy monitoring area is divided into multiple target monitoring areas according to the communication scenario. In this embodiment, the target monitoring area is the monitoring area divided according to the communication scenario. That is to say, each water conservancy monitoring area is divided into target monitoring areas according to the communication scenario of each water conservancy monitoring area obtained before. For example, the communication scenario of some water conservancy monitoring areas is a riverside with a vast water area, and there are no mountains around the water conservancy monitoring areas to affect the communication environment. These communication scenarios are divided into the same type of target monitoring areas.

[0131] After determining the target monitoring area, the signal strength change data and data volume change values ​​of each target monitoring area transmitting water conservancy monitoring data within the preset time period can be obtained through the telemetry terminal device. The telemetry terminal device is a microprocessor-controlled device that integrates data acquisition, transmission, and storage functions. It can collect data from various sensors and devices and transmit the data to the control center or data center for analysis and processing. The preset time period can be determined according to the actual situation. Through the signal strength change data and data volume change values ​​of each target monitoring area transmitting water conservancy monitoring data within the preset time period, the communication stability threshold of each target monitoring area can be determined.

[0132] Subsequently, the communication stability threshold of each target monitoring area is determined. In this embodiment, the communication stability threshold refers to the critical value or limit of the communication system's ability to maintain stable communication under specific conditions by measuring the signal strength and the signal transmission rate. Specifically, first, a preset recognition algorithm is used to identify the data with a signal-to-noise ratio less than a preset noise ratio threshold and the data with a signal-to-noise ratio greater than the preset noise ratio threshold in the signal strength change data of each target monitoring area, as well as the data with a signal packet loss rate less than a preset packet loss rate threshold and the data with a signal packet loss rate greater than the preset packet loss rate threshold in the signal data volume change data of each target monitoring area. In this embodiment, the preset packet loss rate threshold and the preset noise ratio threshold can be determined according to actual conditions. The preset recognition algorithm can be a machine learning algorithm, such as a support vector machine or a decision tree, which learns the patterns and features in the data through training to determine whether the data exceeds the preset threshold. Subsequently, the data with a signal-to-noise ratio less than the preset threshold and the data with a signal packet loss rate less than the preset threshold are marked as true stability cases, and the data with a signal-to-noise ratio greater than the preset threshold and the data with a signal packet loss rate greater than the preset threshold are marked as false stability cases. The true stable examples and false stable examples are input into the trained binary classification algorithm, and true positive examples and false positive examples, true negative examples and false negative examples are output. In this embodiment, the true stable example refers to the data with a signal-to-noise ratio less than a preset threshold and the data with a signal packet loss rate less than a preset threshold, and the false stable example refers to the data with a signal-to-noise ratio greater than a preset threshold and the data with a signal packet loss rate greater than a preset threshold; the true positive example indicates a data point predicted to be a positive sample and actually a positive sample; the false positive example indicates a data point predicted to be a positive sample but actually a negative sample; the false negative example indicates a data point predicted to be a negative sample but actually a positive sample; the true negative example indicates a data point predicted to be a negative sample and actually a negative sample.

[0133] After obtaining true positive examples and false positive examples, true negative examples and false negative examples, the true stability rate is calculated through the true positive examples and false negative examples, and the true stability rate can be calculated through the preset true stability rate; the false stability rate is calculated through the false positive examples and true negative examples, and the false stability rate can be calculated through the preset false stability rate formula; and the false stability rate is used as the horizontal axis and the true stability rate as the vertical axis to draw the communication stability threshold curve of each target monitoring area, and then the threshold boundary point of the communication stability threshold curve of each target monitoring area is determined by the preset optimal threshold discrimination formula. The preset optimal threshold can use the statistical method of the maximum inter-class variance method to calculate the stability index of the data point. This method finds a threshold value so that the inter-class variance between the stable channel and the unstable channel is maximized, and the threshold boundary point of the communication stability threshold curve is obtained, thereby obtaining the communication stability threshold of each target monitoring area.

[0134] After determining the communication stability threshold of each target monitoring area, the communication parameters of each target monitoring area are obtained. Through network monitoring, network monitoring equipment or software can be deployed to obtain data such as signal strength, bit error rate, signal-to-noise ratio, jitter, delay, and packet loss rate.

[0135] After obtaining the communication parameters, the communication parameters are input into the pre-trained model to obtain the current communication stability value of each target monitoring area. The pre-trained model refers to a trained model that can predict communication stability based on the communication parameters. It can be a model based on machine learning or deep learning, such as a regression model, a neural network, etc. The communication parameters of each target monitoring area are input into the regression model, and the current communication stability value of each target monitoring area is output. The communication stability value is an indicator used to quantify the ability of a communication network or device to maintain stable communication under specific conditions.

[0136] Subsequently, the communication stability value corresponding to each communication scenario is compared with the communication stability threshold, and the number of communication scenarios whose communication stability values ​​are greater than the communication stability threshold is marked. That is to say, the communication stability value corresponding to each communication scenario is compared with the communication stability threshold. For example, the communication scenario is a river with a vast water area, and the corresponding communication stability value is 0.7, and the communication stability threshold is 0.6. This communication scenario is marked. In the same way, the communication stability value corresponding to each communication scenario is compared with the communication stability threshold, and the number of communication scenarios greater than the communication stability threshold is counted. If the number is greater than the preset threshold, the Beidou communication channel is determined to be the best communication channel. If the number is less than the preset threshold, it is determined that the Beidou communication channel is not the best communication channel. The preset threshold can be determined according to actual conditions.

[0137] By judging whether the Beidou communication channel is the best communication channel, it is possible to accurately evaluate whether the Beidou communication channel is the best communication channel in the water conservancy monitoring area, which helps to improve monitoring efficiency and accuracy and ensure the reliability and integrity of water conservancy monitoring data.

[0138] In one implementation of this embodiment, determining the communication stability threshold of each target monitoring area by using the signal strength change data and the signal data volume change data within a preset time period includes:

[0139] S401, using a preset recognition algorithm, identifying data whose signal-to-noise ratio is less than a preset noise ratio threshold and data whose signal-to-noise ratio is greater than a preset noise ratio threshold in the signal strength change data of each target monitoring area;

[0140] S402, using a preset recognition algorithm, identifying data whose signal packet loss rate is less than a preset packet loss rate threshold and data whose signal packet loss rate is greater than a preset packet loss rate threshold in the signal data volume change data of each target monitoring area;

[0141] S403, marking data with a signal-to-noise ratio less than a preset noise ratio threshold and data with a signal packet loss rate less than a preset packet loss rate threshold as true stable cases;

[0142] S404, marking data with a signal-to-noise ratio greater than a preset noise ratio threshold and data with a signal packet loss rate greater than a preset packet loss rate threshold as false stable cases;

[0143] S405, inputting the true stable examples into the trained binary classification algorithm, and outputting true positive examples and false positive examples;

[0144] S406, inputting the false stable examples into a binary classification algorithm, and outputting true negative examples and false negative examples;

[0145] S407, calculating the true stability rate through true positive examples and false negative examples;

[0146] S408, calculating the false stability rate through false positive examples and true negative examples;

[0147] S409, using the false stability rate as the horizontal axis and the true stability rate as the vertical axis, drawing a communication stability threshold curve for each target monitoring area;

[0148] S410, determining the threshold boundary point of the communication stability threshold curve of each target monitoring area by a preset optimal threshold judgment formula;

[0149] S411. Determine the communication stability threshold of each target monitoring area through the threshold boundary point.

[0150] First, a preset recognition algorithm is used to identify data with a signal-to-noise ratio less than a preset noise ratio threshold and data with a signal-to-noise ratio greater than a preset noise ratio threshold in the signal strength change data of each target monitoring area. The signal-to-noise ratio is the ratio of signal power to noise power. In this embodiment, the preset recognition algorithm can be a machine learning algorithm, such as a support vector machine, a decision tree, etc., which learns patterns and features in the data through training to determine whether the data exceeds the preset threshold. In other words, the signal strength change data of each target monitoring area can be processed by the support vector machine algorithm to determine the signal-to-noise ratio of each data point, and the obtained signal-to-noise ratio is compared with the preset noise ratio threshold to respectively identify data with a signal-to-noise ratio less than the preset noise ratio threshold and data with a signal-to-noise ratio greater than the preset noise ratio threshold in the signal strength change data.

[0151] Using a preset recognition algorithm, data with a signal packet loss rate less than a preset packet loss rate threshold and data with a signal packet loss rate greater than a preset packet loss rate threshold in the signal data volume change data of each target monitoring area are identified. The signal packet loss rate refers to the proportion of data packets lost during data transmission. In this embodiment, the preset recognition algorithm can be a machine learning algorithm, such as a support vector machine or a decision tree, which learns the patterns and features in the data through training to determine whether the data exceeds the preset threshold. In other words, the signal packet loss rate data of each target monitoring area is processed by the support vector machine algorithm to determine the signal packet loss rate of each data point, and the obtained signal packet loss rate ratio is compared with the preset packet loss rate threshold to respectively identify the data with a signal packet loss rate less than the preset packet loss rate threshold and the data with a signal packet loss rate greater than the preset packet loss rate threshold in the signal data volume change data of each target monitoring area. Among them, the preset recognition algorithm can be the same algorithm or different algorithms.

[0152] Secondly, the data whose signal-to-noise ratio is less than the preset threshold and the data whose signal packet loss rate is less than the preset packet loss rate threshold are marked as true stable cases. In this embodiment, the true stable cases refer to the data whose signal-to-noise ratio is less than the preset signal-to-noise threshold and the data whose signal packet loss rate is less than the preset signal packet loss threshold. That is to say, by traversing all signal data and comparing the signal-to-noise ratio of each data with the preset noise ratio threshold, if the signal-to-noise ratio is less than the preset noise ratio threshold and the signal packet loss rate is less than the preset signal packet loss threshold, the data is marked as a true stable case. Similarly, the data whose signal-to-noise ratio is greater than the preset noise ratio threshold and the data whose signal packet loss rate is greater than the preset packet loss rate threshold are marked as false stable cases. In this embodiment, the false stable cases refer to the data whose signal-to-noise ratio is greater than the preset threshold and the data whose signal packet loss rate is greater than the preset threshold. That is to say, by traversing all signal data and comparing the signal-to-noise ratio of each data with the preset noise ratio threshold, if the signal-to-noise ratio is greater than the preset noise ratio threshold and the signal packet loss rate is greater than the preset threshold, the data is marked as a false stable case.

[0153] After obtaining the true stable examples and the false stable examples, the true stable examples are input into the trained binary classification algorithm to output the true positive examples and the false positive examples, and the false stable examples are input into the binary classification algorithm to output the true negative examples and the false negative examples. The trained binary classification algorithm can be based on traditional machine learning methods, such as logistic regression, support vector machine, decision tree, random forest and other algorithms. In this embodiment, the true positive example refers to the data point predicted as a positive sample and actually a positive sample. That is to say, by inputting the true stable example into the trained binary classification algorithm, the output sample is also data less than the preset noise ratio threshold and the preset packet loss rate threshold; the false positive example indicates that the sample is predicted to be a positive sample. That is to say, when the true stable example is input into the trained binary classification algorithm, the output sample is data greater than the preset noise ratio threshold and the preset packet loss rate threshold; the false negative example represents the data point predicted to be a negative sample, but is actually a positive sample, that is to say, when the false stable example is input into the trained binary classification algorithm, the output sample is data less than the preset noise ratio threshold and the preset packet loss rate threshold; the true negative example represents the data point predicted to be a negative sample, but is actually a negative sample, that is to say, when the false stable example is input into the trained binary classification algorithm, the output sample is data greater than the preset noise ratio threshold and the preset packet loss rate threshold.

[0154] After obtaining the true positive examples and false positive examples, true negative examples and false negative examples, the true stability rate is calculated through the true positive examples and false negative examples, and the false stability rate is calculated through the false positive examples and true negative examples. The true stability rate can be calculated by the preset true stability rate formula, which is as follows:

[0155]

[0156] The false stability rate can be calculated using a preset false stability rate formula, which is as follows:

[0157]

[0158] After obtaining the true stability rate and the false stability rate, the false stability rate is used as the horizontal axis and the true stability rate is used as the vertical axis to draw the communication stability threshold curve of each target monitoring area. In other words, the true stability rate and the false stability rate of each target monitoring area are obtained, and the true stability rate and the false stability rate in the preset time period are respectively plotted to obtain the communication stability threshold curve. The values ​​of the true stability rate and the false stability rate per minute in the preset time period are used to draw the communication stability threshold curve in the manner of using the false stability rate as the horizontal axis and the true stability rate as the vertical axis. In this embodiment, the communication stability threshold curve is a threshold curve for evaluating the stability of the communication system.

[0159] Subsequently, the threshold cutoff point of the communication stability threshold curve of each target monitoring area is determined by a preset optimal threshold discrimination formula. The preset optimal threshold can use the statistical method of the maximum inter-class variance method to calculate the stability index of the data point. This method finds a threshold value so that the inter-class variance between the stable channel and the unstable channel is the largest, and obtains the threshold cutoff point of the communication stability threshold curve. After obtaining the threshold cutoff point, the threshold cutoff point is used as the communication stability threshold of each target monitoring area, thereby obtaining the communication stability threshold of each target monitoring area.

[0160] By determining the communication stability threshold of each target monitoring area, it is possible to improve communication quality, optimize resource allocation, enhance user experience, and help build a more stable, efficient, and intelligent communication network.

[0161] In one implementation of this embodiment, the communication abnormal nodes in the water conservancy monitoring ad hoc network are screened according to the node information to obtain the communication coverage blind area nodes in the water conservancy monitoring ad hoc network, including:

[0162] S510, obtaining the total number of times each node sends data and the number of times the data is successfully sent from the node information;

[0163] S520, calculating the communication success rate of each node by the total number of times data is sent and the number of times data is successfully sent;

[0164] S530, calculating the correlation coefficient between any two nodes according to the communication success rate;

[0165] S540, performing cluster analysis on the correlation coefficients to obtain nodes with abnormal correlation coefficients;

[0166] S550, determining the target monitoring area where the node with abnormal correlation coefficient is located, and obtaining the abnormal target detection area;

[0167] S560, obtaining all node information in the abnormal target detection area;

[0168] S570, obtaining a topological structure of the abnormal target detection area, and extracting topological structure features;

[0169] S580, inputting the topological structure features and all node information in the abnormal target detection area into the trained communication connection effect level model, and outputting the target connection effect of the abnormal target detection area;

[0170] S590: Compare the target connection effect with the preset standard connection effect. If the target connection effect is less than the pre-calculated standard connection effect, obtain the communication coverage blind area node in the water conservancy monitoring ad hoc network.

[0171] Figure 2A flowchart of determining a candidate relay node is provided in an embodiment of the present application, such as Figure 2 As shown, for the process of determining candidate relay nodes, first, all node information is exchanged arbitrarily, and the node information is preliminarily matched to obtain candidate relay nodes; then, the hash value of the candidate relay node and the communication coverage blind spot node is calculated, and it is determined whether the hash value is less than a preset threshold value. When the hash value is less than the preset threshold value, the communication coverage blind spot node sends a connection request to the candidate relay node; next, the information of the candidate relay node is matched again with the information of the communication coverage blind spot node, and it is determined whether the matching degree of the rematch is greater than the preset matching degree threshold. When the matching degree of the rematch is greater than the preset matching degree threshold, the candidate relay node replies to the connection request of the communication coverage blind spot node and connects with the communication coverage blind spot node to obtain the target water conservancy monitoring self-organizing network; when the matching degree of the rematch is less than the preset matching degree threshold, the step of iteratively screening candidate relay nodes will be executed.

[0172] According to the node information, the communication abnormal nodes in the water conservancy monitoring self-organizing network are screened to obtain the communication coverage blind area nodes in the water conservancy monitoring self-organizing network. Specifically, first, in the node information, the total number of times each node sends data and the number of times the data is successfully sent are obtained, that is, the total number of times each node sends data is counted. The total number of times the node sends data can be obtained through the system or database that records the node communication activities. At the same time, the number of times each node successfully sends data can also be counted through the system or database that records the node communication activities. Subsequently, the communication success rate of each node is calculated by the total number of times data is sent and the number of times data is successfully sent. In other words, the communication success rate of each node is obtained by dividing the number of successful data transmissions by the total number of data transmissions.

[0173] After obtaining the communication success rate of each node, calculate the correlation coefficient between any two nodes. By calculating the correlation coefficient between any two nodes, that is, when the communication success rate of one node increases, the communication success rate of the other node also increases. It can be judged whether the communication success rate between any two nodes has a certain correlation change trend. If the correlation between the communication success rates of any two nodes is small, it means that there is an abnormality in the communication stability between the two nodes, that is, when the communication success rate of one node increases, the communication success rate of the other node decreases. The correlation coefficient between any two nodes can be calculated by the Pearson correlation coefficient formula, which is as follows:

[0174]

[0175] Among them, r is the Pearson correlation coefficient, n is the number of samples; x i and i represents the i-th observation value of variables X and Y; and represent the sample means of X and Y respectively;

[0176] After obtaining the correlation coefficient between any two nodes, cluster analysis is performed on the correlation coefficient to obtain nodes with abnormal correlation coefficients. K-means clustering can be used for cluster analysis. K-means clustering is a widely used unsupervised learning algorithm that is used to divide data points into K clusters. By iteratively minimizing the sum of the squares of the distances from each data point to the center of the cluster to which it belongs, the K clusters in the data set are found. In other words, cluster analysis of the correlation coefficient between any two nodes can identify nodes with a smaller correlation coefficient between any two nodes, indicating that there is abnormal communication between the two nodes. Therefore, nodes with abnormal correlation coefficients are obtained.

[0177] After the node with abnormal correlation coefficient is determined, the target monitoring area where the node with abnormal correlation coefficient is located is determined. In this embodiment, the number of target monitoring areas is at least one. In this embodiment, the target monitoring area is a monitoring area divided according to the communication scenario. According to the communication scenario of each water conservancy monitoring area obtained before, each water conservancy monitoring area is divided into a target monitoring area. In other words, the area of ​​the communication scenario where the node with abnormal correlation coefficient is located is determined, and this area is used as the abnormal target detection area.

[0178] After determining the abnormal target detection area, obtain all node information in the abnormal target detection area, that is, collect relevant data of all nodes from the monitoring system of the abnormal target detection area, including node identifiers, attributes, status data, such as location, type, function, etc., status information, status code, alarm information and other information.

[0179] Subsequently, the topological structure of the abnormal target detection area is obtained, and the topological structure features are extracted. That is to say, through the supervision system of the abnormal target detection area, the topological structure of the abnormal target detection area is obtained, and the topological structure features are extracted, including basic features and connectivity features. The basic feature extraction includes the number of nodes, the number of edges, and the average degree. The connectivity features include the connected components, the diameter, and the average path length.

[0180] After obtaining the topological structure features, the topological structure features and all node information in the abnormal target detection area are input into the trained communication connection effect level model, and the target connection effect of the abnormal target detection area is output. In this embodiment, the trained communication connection effect level model can be a deep learning model. That is to say, the topological structure of the abnormal target detection area where the nodes with abnormal correlation coefficients are located, and all node information in the abnormal target detection area, such as the node identifier, attributes, status data, such as location, type, function, etc., status information, status code, alarm information and other information, are input into the deep learning model, and the target connection effect of this abnormal target detection area can be obtained. In this embodiment, the target connection effect refers to the effect of the stability of communication between nodes. The model will make predictions based on the input data and output the target connection effect level of the abnormal target detection area, such as outputting target connection effects such as "excellent", "good", "general", "poor", and "extremely poor".

[0181] Subsequently, the target connection effect is compared with the preset standard connection effect. If the target connection effect is less than the pre-calculated standard connection effect, the communication coverage blind spot node in the water conservancy monitoring self-organizing network is obtained. Specifically, a standard connection effect threshold can be set according to the specific business needs of water conservancy monitoring. If the target connection effect of a node is lower than the preset standard connection effect threshold and the duration exceeds a certain threshold, such as several consecutive hours or days, it will be marked as a communication coverage blind spot node.

[0182] By screening the communication abnormal nodes in the water conservancy monitoring self-organizing network, the communication blind area nodes in the water conservancy monitoring self-organizing network can be obtained. The communication blind area nodes in the water conservancy monitoring self-organizing network can be accurately identified, which not only improves the reliability and stability of the network, but also provides strong support for subsequent network optimization and resource allocation.

[0183] In one implementation of this embodiment, a relay node of a water conservancy monitoring ad hoc network is obtained, and the relay node is connected to a node in a communication coverage blind area to obtain a target water conservancy monitoring ad hoc network, including:

[0184] S610, arbitrarily exchanging all node information among all nodes of the water conservancy monitoring ad hoc network through a preset communication protocol;

[0185] S620, performing preliminary matching on the node information through the received arbitrary node information to obtain a candidate relay node;

[0186] S630, calculating the hash values ​​of the candidate relay node and the communication coverage blind area node by a preset hash value calculation algorithm, wherein, when the hash value is less than a preset threshold, the communication coverage blind area node is used to send a connection request to the candidate relay node;

[0187] S640, in response to the connection request, rematching the information of the candidate relay node with the information of the node in the communication coverage blind area;

[0188] S650, wherein, when the re-matching degree is greater than the preset matching degree threshold, the candidate relay node replies to the connection request of the communication coverage blind spot node, and connects with the communication coverage blind spot node to obtain the target water conservancy monitoring self-organizing network. When the matching degree is less than the preset matching degree threshold, the candidate relay node does not reply to the connection request of the communication coverage blind spot node, and the communication coverage blind spot node will repeat the steps of performing preliminary matching on the node information through any node information received to obtain the candidate relay node.

[0189] Obtain the relay node of the water conservancy monitoring self-organizing network, connect the relay node with the node in the communication blind area, and obtain the target water conservancy monitoring self-organizing network. Specifically, first, all node information is arbitrarily exchanged among all nodes of the water conservancy monitoring self-organizing network through a preset communication protocol. The preset communication protocol can be TCP / IP, UDP, Zigbee, LoRa and other communication protocols. The information that each node needs to collect and prepare to be exchanged, including monitoring data, node status, location information, etc., is encapsulated and packaged according to a preset format, and the encapsulated information is sent to other nodes in the water conservancy monitoring self-organizing network in a broadcast manner through the preset communication protocol.

[0190] Through the received arbitrary node information, the node information is preliminarily matched to obtain candidate relay nodes. That is to say, when other nodes receive the broadcast information, they parse and process the received information, and preliminarily match the node information according to the type and content of the information. The matching conditions can be set according to the needs of the network and the actual application scenarios. The conditions for screening candidate relay nodes can be matched according to the link quality, geographical location, remaining energy and other conditions between nodes. When the preliminary matching of the node information is successful, the candidate relay node is obtained. In this embodiment, the candidate relay node refers to a candidate object that is considered likely to be selected as a relay node in the communication network after preliminary screening and evaluation. Relay nodes play an important role in the network. They can forward, amplify or regenerate signals, thereby expanding the coverage of the network and improving the transmission quality and reliability of the signal.

[0191] After obtaining the candidate relay nodes, the hash values ​​of the candidate relay nodes and the nodes in the communication coverage blind area are calculated through the preset hash value calculation algorithm. The preset hash value calculation algorithm can be the MD5 algorithm. The MD5 algorithm takes data of any length as input and outputs a 128-bit hash value. Specifically, the node can store specific information in the distributed hash table and mark itself as a candidate relay node. The specific information can be the node's geographical location, communication capability and other information. This information can be used as a keyword in the distributed hash table. The node can inform other nodes of its existence and willingness to serve as a candidate relay node through broadcast messages. Other nodes can find and discover these candidate relay nodes through the query mechanism of the distributed hash table. After determining the candidate relay nodes, the hash values ​​of the candidate relay nodes and the nodes in the communication coverage blind area are calculated through the MD5 algorithm.

[0192] When the hash value is less than the preset threshold, the communication coverage blind area node is used to send a connection request to the candidate relay node. The preset threshold should be set according to the specific conditions of the network, such as node distribution, communication requirements, etc. In other words, when the hash value between nodes is smaller, the information between nodes is more matched. When the hash value is less than the preset threshold, it means that the two nodes can be connected to each other. Therefore, the communication coverage blind area node is used to send a connection request to the candidate relay node.

[0193] In response to the connection request, the information of the candidate relay node is matched again with the information of the node in the communication blind spot. Specifically, when the candidate relay node receives a connection request from the node in the communication blind spot, the candidate relay node parses the connection request, and the candidate relay node evaluates its own information, including geographical location, communication capability, remaining bandwidth, etc., to determine whether it meets the communication needs of the node in the communication blind spot. When the matching degree of the re-match is greater than the preset matching degree threshold, that is, the candidate relay node evaluates that its own information meets the needs of the node in the communication blind spot, the candidate relay node will reply to the connection request of the node in the communication blind spot, and connect with the node in the communication blind spot to obtain the target water conservancy monitoring self-organizing network.

[0194] When a candidate relay node evaluates that its own information does not meet the requirements of a node in a communication blind spot, the candidate relay node does not reply to the connection request of the node in the communication blind spot. The node in the communication blind spot will perform a preliminary match of the node information received through any node information to obtain the candidate relay node, and then search for the candidate relay node for a secondary match until the node in the communication blind spot successfully matches the candidate relay node.

[0195] By obtaining the relay nodes of the water conservancy monitoring self-organizing network and connecting the relay nodes with the nodes in the blind area of ​​communication coverage, the target water conservancy monitoring self-organizing network can be obtained. This can significantly improve the coverage and reliability of the network, optimize the node selection and connection efficiency, improve the network performance and scalability, and reduce the operation and maintenance costs and difficulty.

[0196] In one implementation of this embodiment, after the candidate relay node replies to the connection request of the communication coverage blind area node and connects with the communication coverage blind area node to obtain the target water conservancy monitoring self-organizing network, it also includes:

[0197] S710, obtaining a first transmission performance of the water conservancy monitoring ad hoc network that meets the direct connection condition and a first node transmission performance between each AI control device;

[0198] S720, obtaining the second transmission performance of the target water conservancy monitoring ad hoc network and the second node transmission performance between each AI control device and the relay node;

[0199] S730, comparing the first transmission performance with the second transmission performance, and comparing the first node transmission performance with the second node transmission performance;

[0200] S740: If the first transmission performance is less than or equal to the second transmission performance, and the first node transmission performance is less than or equal to the second node transmission performance, the target water conservancy monitoring ad hoc network is obtained after the communication coverage blind area node is connected to the candidate relay node.

[0201] The first transmission performance of the water conservancy monitoring self-organizing network that meets the direct connection condition and the first node transmission performance between each AI control device are obtained. In this embodiment, the first transmission performance refers to the transmission performance of the water conservancy monitoring self-organizing network, and the first node transmission performance refers to the transmission performance between each AI control device. The first transmission performance of the water conservancy monitoring self-organizing network that meets the direct connection condition and the first node transmission performance between each AI control device can be obtained through professional testing tools and software, such as network performance testers, throughput testers, etc., which can directly measure key performance indicators such as data transmission rate, delay, packet loss rate, etc. between two nodes under direct connection conditions.

[0202] Subsequently, the second transmission performance of the target water conservancy monitoring self-organizing network and the second node transmission performance between each AI control device and the relay node are obtained. In this embodiment, the second transmission performance refers to the transmission performance of the target water conservancy monitoring self-organizing network, that is, the transmission performance of the water conservancy monitoring self-organizing network with relay nodes. The second node transmission performance refers to the transmission performance between each AI control device and the relay node. The second transmission performance of the target water conservancy monitoring self-organizing network and the second node transmission performance between each AI control device and the relay node can be obtained through professional testing tools and software, such as network performance testers, throughput testers, etc., which can directly measure key performance indicators such as data transmission rate, delay, packet loss rate, etc. between two nodes under direct connection conditions.

[0203] By comparing the first transmission performance with the second transmission performance, and comparing the first node transmission performance with the second node transmission performance, the transmission speed, transmission stability and transmission efficiency in the first transmission performance and the second transmission performance can be compared; similarly, the transmission speed, transmission stability and transmission efficiency in the first node transmission performance and the second node transmission performance can be compared; transmission stability can be manifested by whether packet loss, delay and the like occur during data transmission, and transmission efficiency can be manifested by the amount of data successfully transmitted per unit time.

[0204] When the first transmission performance is less than or equal to the second transmission performance, and the first node transmission performance is less than or equal to the second node transmission performance, the target water conservancy monitoring self-organizing network after the communication coverage blind spot node is connected to the candidate relay node is obtained. That is to say, when the transmission speed, transmission stability and transmission efficiency of the water conservancy monitoring self-organizing network are less than the transmission speed, transmission stability and transmission efficiency of the target water conservancy monitoring self-organizing network, and the transmission speed, transmission stability and transmission efficiency between each AI control device are less than the transmission speed, transmission stability and transmission efficiency between each AI control device and the relay node, it indicates that the overall communication performance of the current target water conservancy monitoring self-organizing network and each AI control device and relay node is not affected, and stable communication can be carried out. Therefore, the target water conservancy monitoring self-organizing network after the communication coverage blind spot node is connected to the candidate relay node is obtained.

[0205] By evaluating the communication performance of the target water conservancy monitoring self-organizing network after the communication coverage blind spot nodes are connected to the candidate relay nodes, the effectiveness of the relay nodes can be verified, and the reliability and stability of the network can be improved, which also provides convenience and efficiency for subsequent maintenance and optimization work.

[0206] In one implementation of this embodiment, the method further includes:

[0207] S810, obtaining climate monitoring data of each water conservancy monitoring area in real time;

[0208] S820, inputting the climate monitoring data into the prediction model to obtain climate prediction information for each water conservancy monitoring area;

[0209] S830, collects water monitoring data of each water conservancy monitoring area in real time through AI control device;

[0210] S840, obtaining water regime change data for each water conservancy monitoring area within the future trend through water regime monitoring data and climate forecast information;

[0211] S850. Generate a water control plan for each water monitoring area based on the water situation change data of each water monitoring area within the future trend.

[0212] Real-time acquisition of climate monitoring data for each water conservancy monitoring area can be obtained through data from meteorological stations, such as rainfall and other data. After obtaining the climate monitoring data, the climate monitoring data is input into the prediction model to obtain climate prediction information for each water conservancy monitoring area. The prediction model can be a neural network model. Key climate parameters such as temperature, precipitation, wind speed, wind direction, and humidity are input into the neural network model to obtain climate prediction information for each water conservancy monitoring area in the future time period, such as whether it will rain in the water conservancy monitoring area in the future time period. Among them, the neural network model is a pre-trained model.

[0213] Through the AI ​​control device, the water situation monitoring data of each water conservancy monitoring area is collected in real time, that is, the water level and flow data of each water conservancy monitoring area are collected in real time through the AI ​​control device; through the water situation monitoring data and climate forecast information, the water situation change data of each water conservancy monitoring area in the future trend is obtained, that is, through the rainfall in each water conservancy monitoring area in the future time period, and the water level and flow data of each water conservancy monitoring area, the water situation change data of each water conservancy monitoring area in the future trend can be obtained. For example, based on the rainfall, water level and flow data, it is judged whether the water level of each water conservancy monitoring area will exceed the standard and a flood warning will occur.

[0214] By using the water situation change data of each water conservancy monitoring area within the future trend, a water conservancy regulation plan is generated for each water conservancy monitoring area. In other words, the water situation of each water conservancy monitoring area is regulated according to the water situation change data of each water conservancy monitoring area. For example, floods may occur in the upstream water conservancy monitoring area, and flood warnings need to be issued for the downstream water conservancy monitoring area. Based on the water level data of the downstream water conservancy monitoring area, it is determined whether to open the gates to discharge floodwater, as well as the water level conditions of each downstream water conservancy monitoring area, to determine which water conservancy monitoring areas downstream can open the gates to discharge floodwater.

[0215] By generating a water control plan for each water monitoring area based on the water situation change data in each water monitoring area within the future trend, we can improve the real-time and accuracy of water monitoring, enhance climate forecasting capabilities, optimize water control plans, ensure water safety, and help achieve sustainable utilization of water resources and healthy development of the water industry.

[0216] An embodiment of the present application also provides a machine-readable storage medium, on which instructions are stored, and the instructions are used to enable a machine to execute a Beidou dual-network channel control method based on an AI control device.

[0217] The present application also provides a Beidou dual-network channel control system based on an AI control device, comprising:

[0218] a memory configured to store instructions; and

[0219] The processor is configured to call instructions from a memory and implement a Beidou dual-network channel control method based on an AI control device when executing the instructions.

[0220] In this embodiment, the electronic device can be a tablet computer, a desktop computer, a laptop computer, a handheld computer, a wearable device, a notebook computer, an ultra-mobile personal computer (UMPC), a netbook, or other device with a processor. Of course, the electronic device can also be a server. The embodiment of the present application does not impose any special restrictions on the specific form of the electronic device.

[0221] 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 on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0222] 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 embodiments of 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 generate 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 1A device that provides the functions specified in a block or multiple blocks.

[0223] 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 including 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.

[0224] 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 in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0225] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0226] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0227] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0228] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0229] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A Beidou dual-network channel control method based on an AI control device, characterized in that: Applied to an AI control device, the number of the AI ​​control devices is at least two, the AI ​​control device is arranged in a water conservancy monitoring area, the water conservancy monitoring area is connected to a central control device, and the method includes: In response to receiving a transmission signal sent by the central control device, determining whether the Beidou communication channel is the best communication channel, wherein the transmission signal is used to transmit water conservancy monitoring data; When the Beidou communication channel is not the optimal communication channel, obtaining the positions of all the AI ​​control devices in each of the water conservancy monitoring areas; Building a water conservancy monitoring ad hoc network based on the locations of all the AI ​​control devices in each of the water conservancy monitoring areas, wherein each of the AI ​​control devices is a node of the water conservancy monitoring ad hoc network; Obtaining node information of the water conservancy monitoring ad hoc network; According to the node information, the communication abnormal nodes in the water conservancy monitoring ad hoc network are screened to obtain the communication coverage blind area nodes in the water conservancy monitoring ad hoc network; Obtaining the node with the strongest communication signal in the water conservancy monitoring ad hoc network; Networking the node in the communication blind area with the node with the strongest communication signal, and determining whether the node in the communication blind area and the node with the strongest communication signal meet direct connection conditions; If the communication coverage blind area node and the node with the strongest communication signal meet the direct connection condition, the communication coverage blind area node and the node with the strongest communication signal are directly connected to obtain the target water conservancy monitoring ad hoc network, wherein the direct connection condition is that the communication protocol of the communication coverage blind area node and the node with the strongest communication signal is the same; If the communication coverage blind area node and the node with the strongest communication signal do not meet the direct connection condition, obtain the relay node of the water conservancy monitoring ad hoc network; The relay node is connected to the communication coverage blind area node to obtain a target water conservancy monitoring self-organizing network.

2. The method according to claim 1, characterized in that The method further comprises: When the Beidou communication channel is the best communication channel, converting the water conservancy monitoring data into a water conservancy monitoring digital signal; Transmitting the water conservancy monitoring digital signal to the Beidou satellite using the AI ​​control device; Acquire a target area covered by the signal of the Beidou satellite, and determine the central control device in the target area; Transmitting the water conservancy monitoring digital signal to the central control device; The water conservancy monitoring digital signal transmitted by the Beidou satellite is decoded by the central control device to obtain readable water conservancy monitoring data.

3. The method according to claim 1, characterized in that The determining whether the Beidou communication channel is the best communication channel comprises: Determining the communication scenario of each of the water conservancy monitoring areas through the geographical location information; By means of the communication scenario, the water conservancy monitoring area is divided into a plurality of target monitoring areas; Obtaining signal strength change data and data volume change values ​​of the water conservancy monitoring data transmitted by each target monitoring area within a preset time period; Determine the communication stability threshold of each target monitoring area by using the signal strength change data and the signal data volume change data within a preset time period; Acquiring communication parameters of each target monitoring area; Inputting the communication parameters into the pre-trained model to obtain the current communication stability value of each target monitoring area; Comparing the communication stability value corresponding to each of the communication scenarios with the communication stability threshold, and marking the number of the communication scenarios whose communication stability value is greater than the communication stability threshold; If the number is greater than a preset threshold, determining that the Beidou communication channel is the best communication channel; If the number is less than a preset threshold, it is determined that the Beidou communication channel is not the best communication channel.

4. The method according to claim 3, characterized in that: Determining the communication stability threshold of each target monitoring area by using the signal strength change data and the signal data volume change data within a preset time period includes: Using a preset recognition algorithm, identifying data whose signal-to-noise ratio is less than a preset noise ratio threshold and data whose signal-to-noise ratio is greater than a preset noise ratio threshold in the signal strength change data of each target monitoring area; Using a preset recognition algorithm, identifying data whose signal packet loss rate is less than a preset packet loss rate threshold and data whose signal packet loss rate is greater than a preset packet loss rate threshold in the signal data volume change data of each target monitoring area; Marking the data whose signal-to-noise ratio is less than a preset noise ratio threshold and the data whose signal packet loss rate is less than a preset packet loss rate threshold as true stable cases; Marking the data whose signal-to-noise ratio is greater than a preset noise ratio threshold and the data whose signal packet loss rate is greater than a preset packet loss rate threshold as false stable cases; Inputting the true stable examples into the trained binary classification algorithm, and outputting true positive examples and false positive examples; Inputting the false stable example into the binary classification algorithm, and outputting true negative examples and false negative examples; Calculating a true stability rate through the true positive examples and the false negative examples; Calculating a false stability rate through the false positive examples and the true negative examples; Using the false stability rate as the horizontal axis and the true stability rate as the vertical axis, a communication stability threshold curve of each target monitoring area is drawn; Determine the threshold boundary point of the communication stability threshold curve of each target monitoring area by a preset optimal threshold judgment formula; The communication stability threshold of each target monitoring area is determined by the threshold boundary point.

5. The method according to claim 3, characterized in that: The step of screening the communication abnormal nodes in the water conservancy monitoring ad hoc network according to the node information to obtain the communication coverage blind area nodes in the water conservancy monitoring ad hoc network includes: In the node information, the total number of times each node sends data and the number of times the data is successfully sent are obtained; Calculate the communication success rate of each node according to the total number of times the data is sent and the number of times the data is successfully sent; Calculate the correlation coefficient between any two nodes according to the communication success rate; Performing cluster analysis on the correlation coefficients to obtain nodes with abnormal correlation coefficients; Determine the target monitoring area where the node with abnormal correlation coefficient is located, and obtain the abnormal target detection area; Obtaining all node information within the abnormal target detection area; Acquire the topological structure of the abnormal target detection area and extract the topological structure features; Inputting the topological structure features and all node information in the abnormal target detection area into the trained communication connection effect level model, and outputting the target connection effect of the abnormal target detection area; The target connection effect is compared with a preset standard connection effect. If the target connection effect is less than the pre-calculated standard connection effect, a communication coverage blind area node in the water conservancy monitoring ad hoc network is obtained.

6. The method according to claim 1, characterized in that The step of obtaining the relay node of the water conservancy monitoring ad hoc network, connecting the relay node with the communication coverage blind area node, and obtaining the target water conservancy monitoring ad hoc network includes: All the node information is exchanged arbitrarily among all the nodes in the water conservancy monitoring ad hoc network through a preset communication protocol; By using any node information received, a preliminary match is performed on the node information to obtain a candidate relay node; Calculate the hash value of the candidate relay node and the communication coverage blind area node by using a preset hash value calculation algorithm, wherein, when the hash value is less than a preset threshold, the communication coverage blind area node is used to send a connection request to the candidate relay node; In response to the connection request, matching the information of the candidate relay node with the information of the communication coverage blind area node again; Among them, when the matching degree of the re-matching is greater than the preset matching degree threshold, the candidate relay node replies to the connection request of the communication coverage blind spot node and connects with the communication coverage blind spot node to obtain the target water conservancy monitoring self-organizing network. When the matching degree is less than the preset matching degree threshold, the candidate relay node does not reply to the connection request of the communication coverage blind spot node, and the communication coverage blind spot node will repeat the step of performing preliminary matching on the node information received through any node information to obtain the candidate relay node.

7. The method according to claim 6, characterized in that After the candidate relay node replies to the connection request of the communication coverage blind area node and connects with the communication coverage blind area node to obtain the target water conservancy monitoring self-organizing network, the method further includes: Obtaining the first transmission performance of the water conservancy monitoring ad hoc network that meets the direct connection condition and the first node transmission performance between each of the AI ​​control devices; Acquire the second transmission performance of the target water conservancy monitoring ad hoc network and the second node transmission performance between each of the AI ​​control devices and the relay node; comparing the first transmission performance with the second transmission performance, and comparing the first node transmission performance with the second node transmission performance; If the first transmission performance is less than or equal to the second transmission performance, and the first node transmission performance is less than or equal to the second node transmission performance, the target water conservancy monitoring ad hoc network is obtained after the communication coverage blind area node is connected to the candidate relay node.

8. The method according to claim 1, characterized in that The method further comprises: Obtain climate monitoring data for each water conservancy monitoring area in real time; Inputting the climate monitoring data into a prediction model to obtain climate prediction information for each of the water conservancy monitoring areas; Through the AI ​​control device, water condition monitoring data of each water conservancy monitoring area is collected in real time; Obtaining water regime change data for each of the water conservancy monitoring areas within future trends through the water regime monitoring data and the climate forecast information; A water control plan for each water monitoring area is generated by using the water situation change data of each water monitoring area within the future trend.

9. A machine-readable storage medium, characterized in that: The machine-readable storage medium stores instructions for enabling a machine to execute the Beidou dual-network channel control method based on an AI control device according to any one of claims 1 to 8.

10. A Beidou dual-network channel control system based on an AI control device, characterized in that: include: a memory configured to store instructions; as well as A processor is configured to call the instruction from the memory and to implement the Beidou dual-network channel control method based on the AI ​​control device according to any one of claims 1 to 8 when executing the instruction.

Images