Low-altitude remote sensing data processing method and device based on 5G Internet of Things

Abstract

The invention provides a low-altitude remote sensing data processing method and device based on the 5G Internet of Things, and relates to the field of data processing. In the method, the number of unmanned aerial vehicles and the positions of the unmanned aerial vehicles corresponding to the unmanned aerial vehicles executing a data acquisition task are acquired, and the data acquisition task is to acquire low-altitude remote sensing data through the unmanned aerial vehicles; constructing an unmanned aerial vehicle topology network according to the number and the positions of the unmanned aerial vehicles; acquiring an acquisition state corresponding to a first unmanned aerial vehicle and acquired first acquisition data, wherein the first unmanned aerial vehicle is any one unmanned aerial vehicle in a plurality of unmanned aerial vehicles executing a data acquisition task; if it is determined that the collection state corresponding to the first unmanned aerial vehicle does not meet the preset condition, a second unmanned aerial vehicle is determined according to the unmanned aerial vehicle topology network, and the second unmanned aerial vehicle is any one unmanned aerial vehicle except the first unmanned aerial vehicle in the multiple unmanned aerial vehicles; and sending the first acquisition data to the ground station by controlling the second unmanned aerial vehicle. By implementing the technical scheme, the low-altitude remote sensing data can be accurately transmitted to the ground station.

Description

Technical Field

[0001] The present application relates to the technical field of data processing, and specifically to a method and device for processing low-altitude remote sensing data based on 5G Internet of Things. Background Art

[0002] With the development of science and technology, drones are increasingly used in low-altitude remote sensing data collection. Low-altitude remote sensing usually involves detailed observation and data collection of the environment, terrain or target area, requiring drones to be able to perform tasks efficiently in complex environments.

[0003] In the current low-altitude remote sensing data collection, a single-point transmission method is usually used, that is, the drone sends data directly to the ground station. However, since multiple drones are in motion, the communication link is easily interfered or interrupted. Especially in complex environments or large mission areas, how to ensure that the data can be accurately transmitted to the ground station is a major problem.

[0004] Therefore, there is an urgent need for a low-altitude remote sensing data processing method and device based on 5G Internet of Things. Summary of the invention

[0005] The present application provides a low-altitude remote sensing data processing method and device based on 5G Internet of Things, which facilitates the accurate transmission of low-altitude remote sensing data to the ground station.

[0006] In the first aspect of the present application, a low-altitude remote sensing data processing method based on 5G Internet of Things is provided, the method comprising: obtaining the number of drones and the positions of drones corresponding to the drones performing a data collection task, wherein the data collection task is to collect low-altitude remote sensing data through the drones; constructing a drone topology network according to the number of drones and the positions of the drones; obtaining the collection status and first collected data corresponding to a first drone, wherein the first drone is any one of the multiple drones performing the data collection task; if it is determined that the collection status corresponding to the first drone does not meet a preset condition, determining a second drone according to the drone topology network, wherein the second drone is any one of the multiple drones except the first drone; and sending the first collected data to a ground station by controlling the second drone.

[0007] By adopting the above technical solution, the number and location of drones are obtained in real time, and a dynamic topology network is constructed to achieve efficient collaboration of drone swarms. During the execution of a task, when a drone is in an abnormal state or fails, the system can quickly determine the replacement drone through the topology network, take over the task, and avoid interruption of the task. The overall ability of the drone swarm to perform tasks is enhanced to ensure the smooth completion of the task, and even if a drone fails, it will not affect the overall situation. By real-time monitoring of the drone collection status, abnormalities or interruptions in the collected data can be discovered in time, and the backup plan can be triggered. The replacement drone can receive and send the collected data to prevent data loss. The integrity and accuracy of low-altitude remote sensing data collection are guaranteed, avoiding data loss or incomplete collection caused by single point failures. The dynamic topology network enables drones to relay data through other drones in complex environments. Even if the communication link directly connected to the ground station is interrupted, data transmission can be completed through other paths. The system can intelligently select the best path or backup node according to the real-time status and topology of the drone to ensure reliable data transmission. The stability and reliability of data transmission are significantly improved to avoid affecting the mission results due to communication interruptions. Therefore, it is convenient for low-altitude remote sensing data to be accurately transmitted to the ground station.

[0008] Optionally, the obtaining of the number of drones and the positions of drones corresponding to the drones performing the data collection task specifically includes: receiving drone data sent by each of the drones, the drone data including a drone ID, longitude and latitude, and elevation, and one drone corresponds to one drone ID; preprocessing and data statistics of the drone ID, the longitude and latitude, and the elevation to determine the number of drones and the positions of the drones, the preprocessing including denoising, filtering, and normalization.

[0009] By adopting the above technical solutions, random noise that may exist in the data is eliminated, the drone position data is smoothed, and outliers that may be caused by changes in flight status or instantaneous fluctuations are filtered out. The data of different drones are unified into the same standard range to facilitate subsequent calculations and network construction. The data preprocessing step effectively improves the accuracy of position and quantity information, avoiding errors in topological network construction or task allocation caused by raw data quality problems. Each drone is identified by the drone ID to ensure that the drone information of each collection task is unique, avoiding errors in task management and topological construction caused by data confusion. The unique identification and precise positioning of drone data are achieved to avoid management difficulties caused by repeated or confused data. The raw data sent by the drone is statistically processed to quickly obtain the total number of drones and their respective positions, providing a basis for task allocation and topological construction. Through normalization processing, drone data from different sources are standardized to reduce storage and calculation complexity. Data preprocessing removes noise and redundant information, reducing the load on communication links and storage systems. The data transmission efficiency is optimized, storage space is saved, and the real-time and scalability of the system are guaranteed. By counting the number and precise location of drones, accurate input data is provided for the dynamic construction of the topological network. Accurate latitude, longitude and elevation information can ensure the reliability of node locations in the topology structure, thereby avoiding misjudgment of the network structure.

[0010] Optionally, constructing a drone topology network according to the number of drones and the positions of the drones specifically includes: broadcasting a data synchronization request among the multiple drones; receiving response data sent by a target drone, the response data being data generated by the drone in response to receiving the data synchronization request, and the drones include the target drone; deploying 5G Internet of Things in the target drones according to the response data to obtain an initial link network; evaluating the feasibility score of the communication link according to the distance between the target drones and a signal attenuation model in the environment; if it is determined that the feasibility score of the communication link is greater than a preset score, integrating a mesh structure into the initial link network to obtain the drone topology network.

[0011] By adopting the above technical solution, the communication status and cooperation intention between multiple drones can be obtained in real time by broadcasting data synchronization requests and receiving response data from the target drone. The initial link network is dynamically constructed so that the topology structure can adapt to the real-time location and mission changes of the drone. There is no need to pre-set a fixed network structure. The system can quickly build a dynamic topology network according to the distribution of drones and mission requirements to adapt to the changing environment. By evaluating the communication distance between the target drones and the environmental signal attenuation model, the feasibility score of the link is calculated to ensure that only high-quality communication links are selected. After screening out reliable links, they are integrated into the topology structure to avoid data loss or communication interruption caused by poor link quality. The quality of the communication link is optimized to improve the stability of the topology network and the reliability of data transmission. If the feasibility score of the link meets the conditions, a redundant path is constructed by integrating the mesh structure into the initial link network. The mesh network can effectively disperse data traffic, prevent single point failures from causing the entire network to crash, and provide backup paths when the main link is interrupted. Enhance the fault tolerance and robustness of the network to ensure that data transmission can still proceed smoothly in complex environments. The constructed drone topology network is based on the actual location of the target drone and the signal transmission conditions to achieve precise collaboration. The network built with 5G technology has stronger dynamic adjustment capabilities, and can flexibly adjust the topology when the network load increases, thereby improving the communication capabilities of drone swarm missions.

[0012] Optionally, the obtaining of the collection status and the first collection data corresponding to the first UAV specifically includes: obtaining a traffic data group of the first UAV, the traffic data group including traffic duration, traffic fluctuation difference and traffic transmission rate; analyzing the traffic data group using a preset processing model to obtain a first analysis result; obtaining a first transmission path of the first UAV to the ground station; analyzing the first transmission path using the preset processing model to obtain a second analysis result; and determining the collection status corresponding to the first UAV based on the first analysis result and the second analysis result.

[0013] By adopting the above technical solution, the quality and stability of the communication link are judged by evaluating the transmission path from the first UAV to the ground station. Multi-dimensional analysis ensures that the evaluation of the collection status is more comprehensive and accurate, avoiding misjudgment that may be caused by a single indicator. The preset processing model is used to analyze the traffic data group and the transmission path, and the results can be obtained quickly without manual intervention. The data group and path analysis are automated and can adapt to dynamically changing networks and collection tasks. It reduces analysis time and improves evaluation efficiency, and is suitable for tasks with high real-time requirements. The root cause of the problem is quickly located to ensure that the system responds to collection anomalies more promptly and accurately. Through transmission path analysis, inefficient or unstable paths are identified to ensure that the collected data can be reliably transmitted to the ground station. The linkage evaluation of traffic transmission rate and path quality can dynamically adjust the priority or allocation method of collection tasks. Avoid data loss caused by poor transmission paths or traffic problems, and ensure the real-time and integrity of data transmission.

[0014] Optionally, if it is determined that the collection status corresponding to the first UAV does not meet the preset conditions, the second UAV is determined according to the UAV topology network, specifically including: within a preset first time period, judging the relationship between the frequency of occurrence of the traffic fluctuation difference and a preset frequency threshold, and judging the relationship between the traffic transmission rate and a preset rate threshold; if it is determined that the frequency of occurrence of the traffic fluctuation difference is greater than or equal to the preset frequency threshold, and the traffic transmission rate is less than the preset rate threshold, then it is determined that the collection status corresponding to the first UAV does not meet the preset conditions; matching a second transmission path with the same path loss as the first transmission path in the UAV topology network; and determining the second UAV corresponding to the second transmission path.

[0015] By adopting the above technical solution, the stability of the UAV communication quality can be reflected by monitoring the frequency of traffic fluctuation difference. The monitoring of traffic transmission rate directly reflects the efficiency and speed of data transmission. Only when the traffic fluctuation frequency is abnormal and the transmission rate is insufficient, it is determined that the collection state does not meet the conditions. It avoids the misjudgment that may be caused by a single condition evaluation, improves the accuracy of the collection state evaluation, and ensures that the switching decision is based on the judgment of the real problem. Find a second transmission path with the same path loss as the first transmission path in the topological network to ensure that the network performance after switching is close to the original path. Avoid the degradation of communication link quality or transmission failure caused by path switching. Realize seamless switching of collection tasks, maintain task continuity, and avoid task interruption due to collection status problems. Selecting an alternative UAV through path loss matching instead of random selection can effectively avoid adding unnecessary communication burden. The reasonable selection of the second transmission path can balance the load of the topological network and reduce the pressure of high-frequency tasks on the main link. Realize task collaborative allocation among UAVs to ensure that the task load is reasonably distributed in the UAV group. The path matching mechanism analyzes the path loss and selects a second transmission path with the same quality as the original path to reduce the uncertainty in the switching process. Even if the first UAV has a problem, the mission can be quickly switched to the backup UAV to ensure the stable operation of the network. This enhances the fault tolerance and robustness of the network and adapts to complex mission environments and dynamically changing network conditions.

[0016] Optionally, the method also includes: generating data to be transmitted based on the first collected data; monitoring the change speed of the data to be transmitted when the second UAV transmits the data to be transmitted to the ground station; within a preset second time period, if it is determined that the change speed is greater than a preset change speed threshold, determining difference data, the difference data being different data generated between the data to be transmitted and the first collected data within the preset second time period; sending the difference data to a third UAV for backup, the third UAV being any one of the multiple UAVs except the first UAV and the second UAV.

[0017] By adopting the above technical solutions, the data changes can be evaluated in real time, especially in the scenario where the data collection changes dynamically, to ensure that the transmission task always follows the latest data status. The data change trend can be discovered in time to provide support for the subsequent adjustment of the transmission and backup strategies, and improve the real-time performance of the system. Only the different parts of the data to be transmitted and the first collected data are extracted to reduce the amount of redundant data transmission. The load of the communication link can be reduced, especially when the bandwidth of the drone group network is limited, which can significantly improve the transmission efficiency. The full data update can be avoided through differential transmission, which greatly reduces the time and resource consumption of data transmission and improves the task efficiency. The differential data that changes too fast is sent to the third drone for backup to avoid data loss due to transmission link interruption or error. The backup tasks are dynamically allocated in the group of drones to prevent single point failures from affecting task execution. The robustness and fault tolerance of the system are enhanced by backing up differential data to ensure the continuity of the task and data integrity. When the change rate exceeds the preset threshold, the differential backup is triggered to meet the real-time data processing requirements in scenes such as video stream acquisition and fast motion. Temporary backup of differential data is performed through the third drone to avoid transmitting all differential data directly to the ground station. The backup mechanism can restore data in an orderly manner when requested by the ground station, reducing its processing pressure.

[0018] Optionally, the method also includes: processing historical traffic data to obtain multiple feature values; taking a feature value greater than a preset threshold among the multiple feature values ​​as a representative feature value; taking the historical traffic data corresponding to the representative feature value as a training sample; inputting the training sample into the input layer of the neural network, and performing supervised training on the corresponding comparison result to the output layer of the neural network to obtain an initial processing model; performing accuracy detection on the initial processing model, and selecting a model whose accuracy meets the preset accuracy as the preset processing model.

[0019] By adopting the above technical solution, multiple feature values ​​are extracted from historical traffic data to make the original data more structured. The feature values ​​greater than the preset threshold are used as representative feature values, redundant features are removed, and important information is retained. Invalid or low-related information processed by the model is reduced, and training efficiency is improved. Focus on high-value features to improve the sensitivity of the model to key traffic changes. Training samples are constructed by historical traffic data corresponding to representative feature values ​​to avoid using all historical data. Reduce the redundancy of training data and save computing resources. Enhance the pertinence of training samples and improve the adaptability of the model to the target task. By providing clear guidance signals through comparison results, the neural network can learn the effective mapping relationship between input and output. The training process is more accurate, invalid iterations are reduced, and the convergence speed is improved. The initial model is evaluated for accuracy and the model that meets the preset accuracy requirements is selected. Model versions with poor performance are eliminated and only high-quality models are retained for task processing.

[0020] In a second aspect of the present application, a low-altitude remote sensing data processing device based on 5G Internet of Things is provided, the device comprising an acquisition module and a processing module, wherein the acquisition module is used to acquire the number of drones and the position of the drones corresponding to the drones performing a data collection task, and the data collection task is to collect low-altitude remote sensing data through the drones; the processing module is used to construct a drone topology network according to the number of drones and the positions of the drones; the acquisition module is also used to acquire the collection status and first collection data corresponding to a first drone, and the first drone is any one of the multiple drones performing the data collection task; the processing module is also used to determine a second drone according to the drone topology network if it is determined that the collection status corresponding to the first drone does not meet a preset condition, and the second drone is any one of the multiple drones except the first drone; the processing module is also used to send the first collection data to the ground station by controlling the second drone.

[0021] In the third aspect of the present application, an electronic device is provided, which includes a processor, a memory, a user interface and a network interface, the memory is used to store instructions, the user interface and the network interface are both used to communicate with other devices, and the processor is used to execute the instructions stored in the memory so that the electronic device performs the method described above.

[0022] In a fourth aspect of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores instructions, and when the instructions are executed, the method described above is executed.

[0023] In summary, one or more technical solutions provided in this application have at least the following technical effects or advantages: By acquiring the number and location of drones in real time and building a dynamic topology network, efficient collaboration of drone swarms is achieved. During the execution of a task, when a drone is in an abnormal state or fails, the system can quickly determine a replacement drone through the topology network, take over the task, and avoid interruption of the task. The overall ability of the drone swarm to perform tasks is enhanced to ensure the smooth completion of the task. Even if a drone fails, it will not affect the overall situation. By monitoring the acquisition status of drones in real time, abnormalities or interruptions in the collected data can be discovered in time and backup plans can be triggered. The replacement drone can receive and send collected data to prevent data loss. The integrity and accuracy of low-altitude remote sensing data acquisition are guaranteed to avoid data loss or incomplete collection caused by single point failures. The dynamic topology network enables drones to relay data through other drones in complex environments. Even if the communication link directly connected to the ground station is interrupted, data transmission can be completed through other paths. The system can intelligently select the best path or backup node according to the real-time status and topology of the drone to ensure reliable data transmission. The stability and reliability of data transmission are significantly improved to avoid affecting the mission results due to communication interruptions. Therefore, it is convenient for low-altitude remote sensing data to be accurately transmitted to the ground station. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 A flowchart of a low-altitude remote sensing data processing method based on 5G Internet of Things provided in an embodiment of the present application; Figure 2 Another schematic diagram of a process for processing low-altitude remote sensing data based on 5G Internet of Things provided in an embodiment of the present application; Figure 3 A module schematic diagram of a low-altitude remote sensing data processing device based on 5G Internet of Things provided in an embodiment of the present application; Figure 4 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application.

[0025] Explanation of the reference numerals: 31, acquisition module; 32, processing module; 41, processor; 42, communication bus; 43, user interface; 44, network interface; 45, memory. DETAILED DESCRIPTION

[0026] In order to enable technicians in this field to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this application, not all of the embodiments.

[0027] In the description of the embodiments of the present application, words such as "for example" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "for example" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "for example" or "for example" is intended to present related concepts in a specific way.

[0028] In the description of the embodiments of the present application, the meaning of the term "multiple" refers to two or more. For example, multiple systems refer to two or more systems, and multiple screen terminals refer to two or more screen terminals. In addition, the terms "first" and "second" are used for descriptive purposes only and cannot be understood as indicating or implying relative importance or implicitly indicating the indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. The terms "include", "comprise", "have" and their variations all mean "including but not limited to", unless otherwise specifically emphasized.

[0029] With the continuous advancement of science and technology, drones are increasingly used in the field of low-altitude remote sensing data collection. Low-altitude remote sensing usually involves detailed observation and data collection of the environment, terrain or specific target areas, requiring drones to perform tasks efficiently in complex environments.

[0030] However, in the existing low-altitude remote sensing data collection process, a single transmission method is usually used, that is, the drone directly transmits the data to the ground station. However, since multiple drones are in flight, the communication link is easily interfered or interrupted, especially in complex environments or large mission areas. How to ensure that the data can be stably and accurately transmitted to the ground station has become an important challenge that needs to be solved urgently.

[0031] In order to solve the above technical problems, this application provides a low-altitude remote sensing data processing method based on 5G Internet of Things, referring to Figure 1 , Figure 1 A flowchart of a low-altitude remote sensing data processing method based on 5G Internet of Things provided in an embodiment of the present application. The method is applied to a server in a drone cluster, including steps S110 to S150, which are as follows: S110, obtaining the number of drones and the positions of drones corresponding to the drones that perform a data collection task, where the data collection task is to collect low-altitude remote sensing data through drones.

[0032] Specifically, the server is a control server for commanding data collection tasks in a drone cluster among multiple drones. The server will follow the collection task to a suitable take-off location, thereby controlling the drone to take off and perform the task. The server needs to know the specific number and location information of the drones participating in the data collection task. This is to effectively schedule resources, manage the network during the task execution, and ensure the smooth completion of the task. The number of drones refers to the number of drones that the server can identify and track in the data collection task. For example, if a low-altitude remote sensing task requires 5 drones to work at the same time, then the server needs to know the existence of all 5 drones involved in the task. The server obtains this information from the status reports of these drones or the communication network. The drone position refers to the precise position of each drone participating in the task when the task is executed, expressed in coordinates such as longitude, latitude, and altitude. The location can be obtained through different technical means, such as GPS positioning, visual positioning, or through sensor-based data fusion methods. In low-altitude remote sensing tasks, the location of drones is crucial because it helps the server understand the area covered by each drone and its relative position to other drones. Data collection tasks refer to tasks in which drones collect remote sensing data in a specified airspace or ground area. These data can include high-definition images, temperature and humidity, gas composition, terrain height, etc., and are usually obtained through sensors mounted on drones. These data are used to analyze information such as the environment, terrain, and resources. Low-altitude remote sensing data collection refers to the use of drones at lower flight altitudes, such as a few hundred meters or a few thousand meters, to observe and collect data on the ground. Compared with satellite remote sensing, low-altitude remote sensing has higher spatial resolution and flexibility, and is suitable for detailed observation of local areas or smaller areas.

[0033] In a possible implementation, obtaining the number of drones and the positions of drones corresponding to the drones performing the data collection task specifically includes: receiving drone data sent by each drone, the drone data includes a drone ID, longitude and latitude, and elevation, and one drone corresponds to one drone ID; preprocessing and data statistics of the drone ID, longitude and latitude, and elevation to determine the number of drones and the positions of drones, the preprocessing includes denoising, filtering, and normalization.

[0034] Specifically, first, the server needs to receive data from each drone. The drone ID is a unique identifier for each drone, which can be used to distinguish different drones. The longitude and latitude are the geographic coordinates of the drone, indicating the location of the drone on the surface of the earth. The elevation indicates the flight altitude of the drone, usually in meters, which is used to indicate the vertical distance of the drone from the ground. This information is sent from the drone to the server via a wireless communication network such as 5G or other wireless protocols. By receiving this information, the server can track the real-time location and status of each drone. The received data needs to be preprocessed before statistical analysis to remove irrelevant or noise information to ensure the accuracy and reliability of the data.

[0035] Among them, denoising refers to removing useless information introduced into the data due to communication interference, sensor errors or other reasons. For example, during the transmission of data by drones, the position data may fluctuate slightly due to signal attenuation or multipath effects. Denoising operations can eliminate these fluctuations through algorithms such as median filtering and Kalman filtering, retaining valid position information. Filtering is the process of further cleaning up the data to eliminate the influence of system errors or external interference generated during the acquisition process. For example, if the GPS signal of the drone is temporarily lost or strongly interfered with, it may cause abnormal position data, such as sudden large-scale jumps. Through filtering technology, these abnormal data can be smoothed to make the position changes more coherent. Normalization is to standardize the data, usually by converting the values ​​into a unified range for subsequent analysis. For drone data, it may include converting the latitude, longitude and elevation data to a unified numerical scale, for example, to between 0 and 1, or a relatively standard range, to avoid analysis deviations caused by inconsistent dimensions between data. Through the preprocessed data, the server can accurately count the number and location of drones currently participating in the mission. The number of drones is the number of unique IDs received, while the location is derived from the pre-processed latitude, longitude and elevation data.

[0036] S120: construct a drone topology network according to the number of drones and the locations of the drones.

[0037] Specifically, first, the server has obtained the number and location of the drones participating in the data collection task through the received drone data. The process of building a drone topological network means that the server establishes a network structure representing the connection relationship between each drone based on the number and location of the drones. In this topological network, each drone is a node in the network, and the connection between nodes indicates that these drones can communicate directly. The construction of the topological network involves the following aspects: Node: Each drone is a node in the topological network; Edge: The existence of the connection depends on factors such as the distance, communication capability and signal strength between drones. Only when the distance is close or the signal is strong, can the drones communicate directly; Network type: According to the specific task requirements, the topological network can be different types such as star network, mesh network, tree network, etc. Specifically, the purpose of building a drone topological network is to ensure that each drone can communicate with each other through a suitable path to ensure smooth data transmission of the task.

[0038] In one possible implementation, a drone topology network is constructed based on the number of drones and the locations of the drones, specifically including: broadcasting a data synchronization request among multiple drones; receiving response data sent by a target drone, the response data being data generated by the drone in response to receiving the data synchronization request, and the drones include a target drone; deploying a 5G Internet of Things in the target drones based on the response data to obtain an initial link network; evaluating the feasibility score of the communication link based on the distance between the target drones and the signal attenuation model in the environment; if it is determined that the feasibility score of the communication link is greater than a preset score, integrating a mesh structure into the initial link network to obtain a drone topology network.

[0039] Specifically, first, the server will control all drones to broadcast "data synchronization requests" to each other. This means that each drone will send a synchronization signal to other nearby drones in order to establish a communication connection between each other and ensure that their clocks and data transmission and reception are synchronized. Suppose there are 5 drones: A, B, C, D and E. Each drone will broadcast a synchronization signal to inform other drones that it is ready to start communication. After sending the synchronization request, other drones will receive the request and respond. The response data contains the status information of the drones, especially their communication capabilities and reception capabilities. The purpose of this process is to let each drone know which target drones can receive the data they send. Drone A sends a data synchronization request to B, C, D and E, among which drones B and C respond and confirm that they can receive data, while D and E may not respond due to the long distance or weak signal. When the target drone responds to the request, 5G Internet of Things technology is deployed in these drones. 5G Internet of Things will provide high-speed, low-latency communication capabilities for each drone and establish a preliminary communication link network. This initial link network is a preliminary communication connection structure that can support information transmission between drones. For example, drones B and C both start to deploy 5G network modules after responding to A's synchronization request. A preliminary communication link is established between them, i.e. A→B→C.

[0040] Next, the feasibility scores of these communication links are evaluated based on the distance between each pair of target drones and the signal attenuation model. The feasibility of the communication link is calculated based on the actual physical distance, signal strength, and interference in the environment. The signal attenuation model takes into account factors such as obstacles, weather, and terrain to predict whether the drones can maintain stable communication. For example, if the distance between drones A and B is 500 meters, the signal attenuation is small, and the signal strength is high, the feasibility score of the link may be high. If the distance between drones A and E is 3 kilometers, and there are buildings or other obstacles in between, the signal attenuation is large, and the feasibility score of the link may be low. If the feasibility score of the communication link is greater than the preset score threshold, it means that the communication link is stable and reliable, and the network structure can be further optimized. At this stage, the initial link network will be integrated into a mesh structure, that is, each drone can not only communicate directly with the drones around it, but also forward data through multiple paths, thereby enhancing the robustness and redundancy of the network. For example, suppose that the distance between drone A and B, C, and D is relatively close, and the link feasibility is high. At this time, a mesh structure can be formed between these drones. For example, A can communicate directly with B, or transmit data through C or D. Through the mesh network structure, even if a link is interrupted, data can be transmitted through other paths to ensure that communication is not affected. Finally, after the above steps, the entire drone group forms a complex drone topology network. This network connects drone nodes through multiple communication links, supports efficient data transmission, and can automatically switch paths when the communication link is unstable to ensure stable execution of the task.

[0041] For example, suppose that in a mission, all five drones eventually form a mesh structure, and each drone can communicate directly or indirectly with other drones. For example, A→B→C→D→E constitutes a primary data transmission link, while A→D→C and B→E→D can serve as backup links.

[0042] S130: Acquire a collection state and first collected data corresponding to a first drone, where the first drone is any one of a plurality of drones that perform a data collection task.

[0043] Specifically, first, the server needs to select one of the multiple drones that perform low-altitude remote sensing data collection tasks as the first drone. This first drone refers to any drone that is currently performing a data collection task. The server will obtain the collection status and collected data of this drone. The collection status refers to the current status of the drone during the data collection process. For example, whether data is being collected normally, whether there is a fault, whether the collection is completed, etc. The collected data refers to the specific data that the drone has collected, which may be environmental or target information collected by sensors, cameras, radars and other equipment, such as ground temperature, humidity, images, location information, etc. The core of this process is that the server obtains data from the drone through the communication protocol, monitors the collection process, and ensures that the task can be completed smoothly. Drone A sends its collection status to the server: "Collecting data, mission in progress", as well as the image data it has collected, such as a high-definition image of an area, and temperature data, such as 25°C. Based on the received data, the server knows that the drone is in good condition and the current collection data already includes part of the ground temperature information.

[0044] In a possible implementation, obtaining the collection status and first collection data corresponding to the first UAV specifically includes: obtaining a traffic data group of the first UAV, the traffic data group including traffic duration, traffic fluctuation difference, and traffic transmission rate; analyzing the traffic data group using a preset processing model to obtain a first analysis result; obtaining a first transmission path of the first UAV to the ground station; analyzing the first transmission path using a preset processing model to obtain a second analysis result; and determining the collection status corresponding to the first UAV based on the first analysis result and the second analysis result.

[0045] Specifically, first, the server needs to obtain a traffic data group from the first drone. The traffic data group includes three key elements: traffic duration refers to the duration of the drone continuously transmitting data within a period of time. It reflects the continuity of the data flow. Traffic fluctuation difference refers to the fluctuation amplitude of the data flow during the transmission process, that is, the difference in the change of the data transmission rate within a period of time. A large fluctuation difference may mean that the communication is unstable or the network is interfered. Traffic transmission rate refers to the speed at which the drone transmits data within a specific time, that is, the amount of data transmitted per unit time. The server uses a preset processing model to analyze these traffic data and obtain a first analysis result. The analysis result may include an evaluation of data flow stability, bandwidth requirements, delay, etc. Through this analysis, the server can know whether the data transmission is normal and whether there are abnormal fluctuations or delays. In addition to the traffic data, the server also needs to obtain the first transmission path for the first drone to send data to the ground station. The transmission path refers to the communication link that the data passes through from the first drone to the ground station, which may be a direct link or a path relayed by other drones. The quality of this path, such as delay, stability, bandwidth, etc., directly affects the reliability and efficiency of data transmission. The server also uses a preset processing model to analyze this transmission path and obtain a second analysis result. This may include analysis results on path stability, path loss, interference, path bandwidth and latency. Through this analysis, the server can determine whether the transmission path is suitable for continued use or whether it needs to switch to another path. Finally, the server combines the first analysis result with the second analysis result to comprehensively determine the collection status of the first drone.

[0046] For example, suppose there is a drone A that is performing a low-altitude remote sensing data collection mission, and the server needs to analyze its status: flow duration: 10 minutes; flow fluctuation difference: 5MB / s; flow transmission rate: 50MB / s. After analysis, the server found that the flow transmission rate and fluctuation difference were relatively normal, but a large flow fluctuation difference may indicate that the communication link of the drone is interfered and the data transmission is not stable. Assume that the transmission path used by drone A is a communication link directly established with the ground station. The server analyzed the path and found that the delay of this path is 300ms, the bandwidth is 100MB / s, and the stability is average. The first analysis result shows that the flow fluctuation difference is large, and there may be unstable transmission. The second analysis result shows that although the transmission path has a high bandwidth, the delay is large, which may affect the real-time performance of the data. Combining these two analysis results, the server may conclude that the current collection status of drone A does not meet the preset conditions, and it may be necessary to reallocate tasks or switch transmission paths.

[0047] S140: If it is determined that the collection state corresponding to the first drone does not meet the preset condition, determine a second drone according to the drone topology network, where the second drone is any drone among the multiple drones except the first drone.

[0048] Specifically, first, the server will analyze the status of the first drone, such as the stability of data collection, transmission quality, etc. If it is found that the collection status of the drone does not meet the preset standards, such as data transmission delays or interruptions, or excessive traffic fluctuations, the collection status of the drone is considered abnormal. For example, the server detects that the traffic transmission rate of the first drone is lower than the preset standard, or its transmission path has a high packet loss rate, resulting in failure to meet the real-time and reliability requirements of the task. The drone topology network is the connection relationship in space between all drones participating in the task, that is, the communication and coordination method between drones. The topology network can show the relative position and communication capabilities between drones, and help determine the flow of data and tasks. When the status of the first drone is found to be abnormal, the server will consult the drone topology network and select a replacement drone to continue the data collection task based on the location and communication status of the drone. This selection is based on existing communication paths, signal strength, geographical location and other factors. The second drone selected is any drone other than the first drone, and usually a drone that is closer to the first drone or in a suitable position is selected. This drone will undertake the data collection or data transmission task originally performed by the first drone.

[0049] In one possible implementation, if it is determined that the collection state corresponding to the first drone does not meet the preset conditions, then the second drone is determined according to the drone topology network, specifically including: within a preset first time period, determining the relationship between the frequency of occurrence of traffic fluctuation differences and a preset frequency threshold, and determining the relationship between the traffic transmission rate and a preset rate threshold; if it is determined that the frequency of occurrence of traffic fluctuation differences is greater than or equal to the preset frequency threshold, and the traffic transmission rate is less than the preset rate threshold, then determining that the collection state corresponding to the first drone does not meet the preset conditions; matching a second transmission path with the same path loss as the first transmission path in the drone topology network; and determining the second drone corresponding to the second transmission path.

[0050] Specifically, the drone checks the frequency of the traffic fluctuation difference and compares it with the preset frequency threshold. If the fluctuation frequency exceeds the threshold, it may mean that there is a continuous instability in the communication connection of the drone. The drone also checks the traffic transmission rate of the drone and compares it with the preset rate threshold. If the rate is lower than the threshold, it may mean that the transmission efficiency is insufficient and cannot meet the requirements of real-time data transmission. If the traffic fluctuation difference frequency is greater than or equal to the preset frequency threshold, and the traffic transmission rate is less than the preset rate threshold, the drone considers that the collection status of the first drone does not meet the preset conditions. The drone checks the transmission path of the first drone, evaluates the path loss, and then looks for another transmission path with similar path loss. The similarity of path loss helps maintain the stability and reliability of data transmission and avoids a sharp drop in performance due to large path differences. Assume that the transmission path loss of the first drone is 3dB. The drone will look for another path in the topological network with a path loss close to 3dB to ensure communication quality. After finding a matching second transmission path, the drone will confirm the second drone corresponding to the path. The second drone will take on the data collection and transmission tasks and replace the first drone. Assume that both drone B and drone C have transmission paths that can replace A, and their path losses meet the requirements. The drones finally choose drone B as the second drone to continue the mission.

[0051] S150: Send the first collected data to the ground station by controlling the second UAV.

[0052] Specifically, the server will select and control the second drone according to the current drone topology network and mission requirements. The second drone may be a drone that is temporarily not involved in the data transmission task during the collection process, or a drone that is idle in other tasks. The way to control the second drone includes controlling the flight path, position adjustment, data transmission, etc. of the drone through wireless communication instructions. The server will ensure that the second drone has the ability to perform the data transmission task. The first drone has completed data collection, but because its collection status does not meet the standard, it cannot continue to transmit data to the ground station. Therefore, the server forwards the data collected by the first drone by controlling the second drone. This is done through the 5G IoT communication link to ensure that the data can be safely transmitted to the ground station with high bandwidth and low latency. After receiving the data, the ground station can process and analyze the data.

[0053] In a possible implementation, data to be transmitted is generated based on the first collected data; when the second UAV transmits the data to be transmitted to the ground station, the change speed of the data to be transmitted is monitored; within a preset second time period, if it is determined that the change speed is greater than a preset change speed threshold, difference data is determined, and the difference data is different data generated by the data to be transmitted compared with the first collected data within the preset second time period; the difference data is sent to a third UAV for backup, and the third UAV is any one of the multiple UAVs except the first UAV and the second UAV.

[0054] Specifically, the data to be transmitted is generated according to the original data collected by the first drone, that is, the first collected data. The data to be transmitted may be data after compression, processing, and screening of the first collected data, and is ready to be transmitted to the ground station. When the second drone starts to transmit the data to be transmitted to the ground station, the server monitors the change rate of the transmitted data. The change rate refers to the amount of change in the data content within a specific time. This change rate may be related to environmental changes, task requirements or other factors. Within a preset time period, the server will determine whether the data change rate is greater than a preset threshold. If the change rate exceeds the threshold, it means that the data has changed significantly. For example, in a remote sensing mission, the sensor may produce large data fluctuations due to environmental changes. Or, data loss occurs due to fluctuations in network quality. If the data change rate is fast, it may indicate that the new information collected needs to be urgently backed up or processed in time. If the change rate of the data to be transmitted and the first collected data within the preset time period exceeds the threshold, the server will calculate the difference data. The difference data refers to the different data parts generated by the data to be transmitted compared with the first collected data within a specified time period. This means that the difference data contains new information or updated data compared with the first collected data. For example, if a drone detects a new target or significant changes in the acquisition area, this new or changed content is the difference data. Once the difference data is determined, the server will select a third drone for data backup. The task of the third drone is to receive this difference data and store it in its internal server to prevent the original data from being lost or problems during transmission. The purpose of backup is to improve the reliability and redundancy of the data in case the second drone fails during transmission and ensure that the data can be saved.

[0055] In one possible implementation, refer to Figure 2 , Figure 2Another flow chart of a low-altitude remote sensing data processing method based on 5G Internet of Things provided in an embodiment of the present application. It includes steps S210 to S250, and the above steps are as follows: S210, process the historical traffic data to obtain multiple feature values; S220, take the feature value greater than the preset threshold value among the multiple feature values ​​as the representative feature value; S230, take the historical traffic data corresponding to the representative feature value as the training sample; S240, input the training sample to the input layer of the neural network, and the corresponding comparison result to the output layer of the neural network for supervised training to obtain the initial processing model; S250, perform accuracy detection on the initial processing model, and select the model whose accuracy meets the preset accuracy as the preset processing model.

[0056] Specifically, historical traffic data contains multiple parameters such as time, transmission rate, delay, packet loss rate, etc. Through data processing, such as feature extraction, data cleaning, etc., multiple feature values ​​can be extracted from these raw data. For example, features such as traffic fluctuation, maximum value, minimum value, and average value can be extracted from network traffic data. Assume that historical traffic data contains hourly network traffic. From these data, the mean value of traffic, maximum fluctuation, time period of frequent fluctuations, etc. can be calculated. After extracting multiple feature values, the next step is to filter out those features that are greater than the preset threshold. These features greater than the threshold are considered to be the most critical for model training and represent important information in the data. For example, a threshold is set: data points with a traffic fluctuation difference greater than 10% are considered important features. Data with a traffic fluctuation greater than 10% will be selected as representative feature values, reflecting the drastic changes in network traffic. The selected representative feature values ​​correspond to certain specific historical traffic data. These data will be used as samples for neural network training and further used for model training.

[0057] For example, suppose that in the historical traffic data, certain features, such as traffic fluctuations greater than 10%, appear in a specific time period, such as network peak hours, and these data are selected as training samples. In the neural network, the input layer receives the training samples, and the output layer returns the results predicted by the model. These training samples are input into the network together with the correct comparison results for training, adjusting the weights of the neural network and optimizing the model. Assume that the input samples are features such as traffic fluctuations and rates, and the goal is to predict network quality or whether network congestion will occur. During the training process, the neural network adjusts its parameters by inputting these feature data so that it can correctly predict the network status. The initial model after training needs to be tested for accuracy through the validation set. Test the accuracy of the model to ensure that it can provide correct results in actual applications. If the accuracy of the model meets the preset standards, it can be selected as the final processing model. The trained model will be evaluated on a set of test data. If the accuracy of the model is higher than the preset accuracy, such as 95%, it means that it can effectively predict the network traffic status, and the model can be used as a processing model in actual applications.

[0058] This application also provides a low-altitude remote sensing data processing device based on 5G Internet of Things, referring to Figure 3 , Figure 3 A module schematic diagram of a low-altitude remote sensing data processing device based on 5G Internet of Things provided in an embodiment of the present application. The low-altitude remote sensing data processing device is a server, and the server includes an acquisition module 31 and a processing module 32, wherein the acquisition module 31 acquires the number of drones and the position of drones corresponding to the drones performing the data collection task, and the data collection task is to collect low-altitude remote sensing data through drones; the processing module 32 constructs a drone topology network according to the number of drones and the positions of drones; the acquisition module 31 acquires the collection state and the first collection data corresponding to the first drone, and the first drone is any one of the multiple drones performing the data collection task; if the processing module 32 determines that the collection state corresponding to the first drone does not meet the preset conditions, the second drone is determined according to the drone topology network, and the second drone is any one of the multiple drones except the first drone; the processing module 32 sends the first collection data to the ground station by controlling the second drone.

[0059] In a possible implementation, the acquisition module 31 acquires the number of drones and the positions of drones corresponding to the drones performing the data collection task, specifically including: the acquisition module 31 receives the drone data sent by each drone, the drone data includes the drone ID, longitude and latitude, and elevation, and one drone corresponds to one drone ID; the processing module 32 pre-processes and performs data statistics on the drone ID, longitude and latitude, and elevation to determine the number of drones and the positions of drones, and the pre-processing includes denoising, filtering, and normalization.

[0060] In a possible implementation, the processing module 32 constructs a drone topology network according to the number of drones and the positions of the drones, specifically including: the processing module 32 broadcasts a data synchronization request among multiple drones; the acquisition module 31 receives response data sent by the target drone, the response data is data generated by the drone in response to receiving the data synchronization request, and the drone includes the target drone; the processing module 32 deploys 5G Internet of Things in the target drone according to the response data to obtain an initial link network; the processing module 32 evaluates the feasibility score of the communication link according to the distance between the target drones and the signal attenuation model in the environment; if the processing module 32 determines that the feasibility score of the communication link is greater than the preset score, the mesh structure is integrated into the initial link network to obtain a drone topology network.

[0061] In a possible implementation, the acquisition module 31 acquires the collection status and the first collection data corresponding to the first UAV, specifically including: the acquisition module 31 acquires the traffic data group of the first UAV, the traffic data group includes the traffic duration, the traffic fluctuation difference and the traffic transmission rate; the processing module 32 uses a preset processing model to analyze the traffic data group to obtain a first analysis result; the acquisition module 31 acquires the first transmission path of the first UAV to the ground station; the processing module 32 uses a preset processing model to analyze the first transmission path to obtain a second analysis result; the processing module 32 determines the collection status corresponding to the first UAV based on the first analysis result and the second analysis result.

[0062] In a possible implementation, if the processing module 32 determines that the collection state corresponding to the first UAV does not meet the preset conditions, then the second UAV is determined according to the UAV topology network, specifically including: the processing module 32 determines the relationship between the frequency of occurrence of the traffic fluctuation difference and the preset frequency threshold within the preset first time period, and determines the relationship between the traffic transmission rate and the preset rate threshold; if the processing module 32 determines that the frequency of occurrence of the traffic fluctuation difference is greater than or equal to the preset frequency threshold, and the traffic transmission rate is less than the preset rate threshold, then it is determined that the collection state corresponding to the first UAV does not meet the preset conditions; the processing module 32 matches a second transmission path with the same path loss as the first transmission path in the UAV topology network; the processing module 32 determines the second UAV corresponding to the second transmission path.

[0063] In a possible implementation, the processing module 32 generates data to be transmitted based on the first collected data; the processing module 32 monitors the change speed of the data to be transmitted when the second UAV transmits the data to be transmitted to the ground station; the processing module 32 determines difference data within a preset second time period if it is determined that the change speed is greater than a preset change speed threshold, where the difference data is different data generated between the data to be transmitted and the first collected data within the preset second time period; the processing module 32 sends the difference data to a third UAV for backup, and the third UAV is any one of the multiple UAVs except the first UAV and the second UAV.

[0064] In one possible implementation, the processing module 32 processes the historical traffic data to obtain multiple feature values; the processing module 32 uses the feature value that is greater than a preset threshold among the multiple feature values ​​as a representative feature value; the processing module 32 uses the historical traffic data corresponding to the representative feature value as a training sample; the processing module 32 inputs the training sample to the input layer of the neural network, and performs supervised training on the corresponding comparison results to the output layer of the neural network to obtain an initial processing model; the processing module 32 performs accuracy detection on the initial processing model, and selects a model whose accuracy meets the preset accuracy as the preset processing model.

[0065] It should be noted that: when the device provided in the above embodiment realizes its function, only the division of the above functional modules is used as an example. In actual application, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the device and method embodiments provided in the above embodiment belong to the same concept, and the specific implementation process is detailed in the method embodiment, which will not be repeated here.

[0066] The present application also provides an electronic device, referring to Figure 4 , Figure 4 The electronic device may include: at least one processor 41 , at least one network interface 44 , a user interface 43 , a memory 45 , and at least one communication bus 42 .

[0067] The communication bus 42 is used to realize the connection and communication between these components.

[0068] The user interface 43 may include a display screen (Display) and a camera (Camera). Optionally, the user interface 43 may also include a standard wired interface and a wireless interface.

[0069] The network interface 44 may optionally include a standard wired interface or a wireless interface (such as a WI-FI interface).

[0070] Among them, the processor 41 may include one or more processing cores. The processor 41 uses various interfaces and lines to connect various parts in the entire server, and executes various functions of the server and processes data by running or executing instructions, programs, code sets or instruction sets stored in the memory 45, and calling data stored in the memory 45. Optionally, the processor 41 can be implemented in at least one hardware form of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), and programmable logic array (Programmable Logic Array, PLA). The processor 41 can integrate one or a combination of a central processing unit (Central Processing Unit, CPU), a graphics processing unit (Graphics Processing Unit, GPU) and a modem. Among them, the CPU mainly processes the operating system, user interface and application programs; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 41, and it can be implemented separately through a chip.

[0071] Among them, the memory 45 may include a random access memory (RAM) or a read-only memory (Read-Only Memory). Optionally, the memory 45 includes a non-transitory computer-readable storage medium. The memory 45 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 45 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned method embodiments, etc.; the data storage area may store data involved in the above-mentioned method embodiments, etc. The memory 45 may also be optionally at least one storage device located away from the aforementioned processor 41. As Figure 4 As shown, the memory 45 as a computer storage medium may include an operating system, a network communication module, a user interface module, and an application program for a low-altitude remote sensing data processing method based on 5G Internet of Things.

[0072] exist Figure 4In the electronic device shown, the user interface 43 is mainly used to provide an input interface for the user and obtain data input by the user; and the processor 41 can be used to call an application program stored in the memory 45 for a low-altitude remote sensing data processing method based on the 5G Internet of Things. When executed by one or more processors, the electronic device executes one or more methods in the above-mentioned embodiments.

[0073] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the order of the actions described, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required for the present application.

[0074] The present application also provides a computer-readable storage medium, which stores instructions. When executed by one or more processors, the electronic device executes one or more of the methods described in the above embodiments.

[0075] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0076] In the several embodiments provided in this application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some service interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0077] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0078] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0079] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a memory and includes several instructions for a computer device (which can be a personal computer, server or network device, etc.) to execute all or part of the steps of the various embodiments of the present application. The aforementioned memory includes: various media that can store program codes, such as USB flash drives, mobile hard drives, magnetic disks or optical disks.

[0080] The above is only an exemplary embodiment of the present disclosure, and the scope of the present disclosure cannot be limited thereto. That is, any equivalent changes and modifications made according to the teachings of the present disclosure are still within the scope of the present disclosure. After considering the disclosure of the specification and the truth of practice, it will be easy for those skilled in the art to think of other embodiments of the present disclosure. This application is intended to cover any modification, use or adaptation of the present disclosure, which follows the general principles of the present disclosure and includes common knowledge or customary technical means in the technical field that are not recorded in the present disclosure. The description and examples are regarded as exemplary only, and the scope and spirit of the present disclosure are defined by the claims.

Claims

1. A low-altitude remote sensing data processing method based on 5G Internet of Things, characterized in that: The method comprises: Obtaining the number of drones and the positions of drones corresponding to the drones that perform a data collection task, wherein the data collection task is to collect low-altitude remote sensing data through the drones; Constructing a drone topology network according to the number of drones and the locations of the drones; Acquire a collection state and first collected data corresponding to a first drone, where the first drone is any one of the plurality of drones that perform the data collection task; If it is determined that the collection state corresponding to the first drone does not meet the preset condition, determining a second drone according to the drone topology network, where the second drone is any one of the multiple drones except the first drone; The first collected data is sent to a ground station by controlling the second UAV.

2. The low-altitude remote sensing data processing method based on 5G Internet of Things according to claim 1 is characterized in that: The obtaining of the number of drones and the positions of drones corresponding to the drones performing the data collection task specifically includes: Receiving drone data sent by each drone, the drone data including drone ID, latitude, longitude and elevation, one drone corresponding to one drone ID; The drone ID, the longitude and latitude, and the altitude are preprocessed and data statistics are performed to determine the number of drones and the positions of the drones, wherein the preprocessing includes denoising, filtering, and normalization processing.

3. The low-altitude remote sensing data processing method based on 5G Internet of Things according to claim 1 is characterized in that: The step of constructing a drone topology network according to the number of drones and the positions of the drones specifically includes: Broadcasting a data synchronization request among the plurality of drones; Receiving response data sent by a target UAV, wherein the response data is data generated by the UAV in response to receiving the data synchronization request, and the UAV includes the target UAV; According to the response data, a 5G Internet of Things is deployed in the target UAV to obtain an initial link network; evaluating a feasibility score of a communication link based on a distance between the target UAVs and a signal attenuation model in an environment; If it is determined that the feasibility score of the communication link is greater than a preset score, a mesh structure is integrated into the initial link network to obtain the drone topology network.

4. The low-altitude remote sensing data processing method based on 5G Internet of Things according to claim 1 is characterized in that: The obtaining of the collection state corresponding to the first drone and the collected first collection data specifically includes: Acquire a flow data group of the first UAV, wherein the flow data group includes flow duration, flow fluctuation difference, and flow transmission rate; Analyzing the flow data group using a preset processing model to obtain a first analysis result; Acquire a first transmission path of the first UAV to the ground station; Analyzing the first transmission path using the preset processing model to obtain a second analysis result; Based on the first analysis result and the second analysis result, a collection state corresponding to the first drone is determined.

5. The low-altitude remote sensing data processing method based on 5G Internet of Things according to claim 4 is characterized in that: If it is determined that the collection state corresponding to the first drone does not meet the preset condition, determining a second drone according to the drone topology network specifically includes: In a preset first time period, determining the magnitude relationship between the frequency of occurrence of the flow fluctuation difference and a preset frequency threshold, and determining the magnitude relationship between the flow transmission rate and a preset rate threshold; If it is determined that the frequency of occurrence of the traffic fluctuation difference is greater than or equal to the preset frequency threshold, and the traffic transmission rate is less than the preset rate threshold, it is determined that the collection state corresponding to the first UAV does not meet the preset condition; Matching a second transmission path having the same path loss as the first transmission path in the drone topology network; Determine the second drone corresponding to the second transmission path.

6. The low-altitude remote sensing data processing method based on 5G Internet of Things according to claim 1 is characterized in that: The method further comprises: generating data to be transmitted according to the first collected data; When the second UAV transmits the data to be transmitted to the ground station, monitoring a change speed of the data to be transmitted; If it is determined that the change speed is greater than a preset change speed threshold within a preset second time period, difference data is determined, where the difference data is different data generated between the data to be transmitted and the first collected data within the preset second time period; The difference data is sent to a third drone for backup, where the third drone is any one of the multiple drones except the first drone and the second drone.

7. The low-altitude remote sensing data processing method based on 5G Internet of Things according to claim 4 is characterized in that: The method further comprises: Process the historical traffic data to obtain multiple characteristic values; Taking a characteristic value greater than a preset threshold value among the plurality of characteristic values ​​as a representative characteristic value; Using the historical traffic data corresponding to the representative characteristic value as a training sample; Inputting the training samples into the input layer of the neural network, and sending the corresponding comparison results to the output layer of the neural network for supervised training to obtain an initial processing model; The initial processing model is tested for accuracy, and a model whose accuracy meets a preset accuracy is selected as the preset processing model.

8. A low-altitude remote sensing data processing device based on 5G Internet of Things, characterized in that: The device comprises an acquisition module (31) and a processing module (32), wherein: The acquisition module (31) is used to acquire the number of drones and the position of the drones corresponding to the drones that perform the data collection task, wherein the data collection task is to collect low-altitude remote sensing data through the drones; The processing module (32) is used to construct a drone topology network according to the number of drones and the positions of the drones; The acquisition module (31) is further used to acquire a collection state corresponding to a first drone and first collected data, wherein the first drone is any one of the plurality of drones that perform the data collection task; The processing module (32) is further configured to determine a second drone according to the drone topology network if it is determined that the collection state corresponding to the first drone does not meet a preset condition, wherein the second drone is any one of the plurality of drones except the first drone; The processing module (32) is further used to send the first collected data to a ground station by controlling the second unmanned aerial vehicle.

9. An electronic device, characterized in that: The electronic device comprises a processor (41), a memory (45), a user interface (43) and a network interface (44), wherein the memory (45) is used to store instructions, the user interface (43) and the network interface (44) are both used to communicate with other devices, and the processor (41) is used to execute the instructions stored in the memory (45) so that the electronic device executes the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores instructions, and when the instructions are executed, the method according to any one of claims 1 to 7 is performed.

Images