A multi-source data driven low-altitude operation intelligent scheduling method and system

Abstract

The application relates to the technical field of big data analysis, and discloses a multi-source data driven low-altitude operation intelligent scheduling method and system, the method comprising the following steps: firstly, a system acquires multi-source heterogeneous data, and carries out standardization processing to form a unified multi-source data set. On this basis, dynamic identification and density evaluation are carried out to generate a traffic density distribution map. Then, clustering analysis is carried out on the distribution map, the boundary range of a key area is extracted, and the fence boundary is updated according to the boundary range to generate new fence constraint conditions. The system corrects flight parameters according to the constraint conditions, obtains an adjusted operation state, carries out data collection in combination with traffic judgment, and forms higher-precision regional traffic dynamic data. Finally, the system executes load balancing scheduling and abnormal dynamic updating based on the data to form the latest low-altitude traffic management state. The method can solve the problem of static scheduling of edge resources.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of big data analysis, and particularly relates to a multi-source data driven low-altitude operation intelligent scheduling method and system. BACKGROUND

[0002] The present application relates to the technical field of big data analysis. Big data analysis refers to a key technology for collecting, processing, fusing and modeling analysis of structured and unstructured massive heterogeneous data to mine potential correlation patterns and support intelligent decision-making. With the development of infrastructure such as the Internet of Things, cloud computing and edge computing, big data analysis technology has been widely applied in many fields such as finance, medical treatment, transportation, security and energy, and has promoted the transformation from static rule-driven to data-driven management mode. This technology emphasizes the efficient processing capability of real-time, spatial and multi-dimensional dynamic information, and shows significant potential in scenarios that require rapid perception and response to complex environmental changes.

[0003] In the existing low-altitude operation management technology, regional resource scheduling generally adopts a static allocation mechanism based on preset rules, and edge computing tasks are fixedly mapped to each node according to geographical regions or node performance, lacking dynamic perception and response to real-time data state. Since the existing technology does not collect the real-time running pressure of the current node, nor analyzes the fluctuation trend of traffic density, it is difficult to meet the actual needs of flexible scheduling of edge nodes in high-density task scenarios.

[0004] In summary, the existing technology has the problem of static edge resource scheduling. SUMMARY

[0005] The present application provides a multi-source data driven low-altitude operation intelligent scheduling method and system to solve the problem of static edge resource scheduling.

[0006] In a first aspect, to solve the above technical problems, the present application provides a multi-source data driven low-altitude operation intelligent scheduling method, comprising:

[0007] acquiring multi-source heterogeneous data;

[0008] performing data standardization processing according to the multi-source heterogeneous data to obtain a multi-source data set;

[0009] performing dynamic identification and density evaluation according to the multi-source data set to obtain a traffic density distribution map;

[0010] performing cluster identification analysis according to the traffic density distribution map to obtain a boundary range of a key region;

[0011] performing fence boundary updating according to the boundary range of the key region to obtain an updated fence constraint condition;

[0012] According to the updated fence constraint condition, flight parameter correction is performed to obtain an adjusted operating state;

[0013] According to the adjusted operating state, traffic determination and data collection are performed to obtain higher-precision regional traffic dynamic data;

[0014] According to the higher-precision regional traffic dynamic data, resource load balancing scheduling is performed to obtain a final resource allocation scheme;

[0015] According to the final resource allocation scheme, abnormality monitoring and dynamic adjustment are performed to obtain the latest low-altitude traffic management state.

[0016] Preferably, according to the multi-source heterogeneous data, data standardization processing is performed to obtain a multi-source data set, including:

[0017] The multi-source heterogeneous data includes unmanned aerial vehicle sensing data, ground monitoring data, and meteorological information data;

[0018] According to the unmanned aerial vehicle sensing data, field mapping and structure conversion are performed to obtain a sensor standard data group;

[0019] According to the ground monitoring data, field extraction and format regularization are performed to obtain a monitoring standard data group;

[0020] The sensor standard data group and the monitoring standard data group are integrated to obtain a multi-source data set in a unified format.

[0021] Preferably, according to the multi-source data set, dynamic identification and density evaluation are performed to obtain a traffic density distribution map, including:

[0022] According to the multi-source data set, unit division and data extraction are performed to obtain a unit-level preliminary traffic data set, wherein the unit-level preliminary traffic data set includes speed data, height data, position information, and target identification;

[0023] According to the speed data and the height data in the traffic data set, the change amplitude in each unit is calculated;

[0024] If the change amplitude in the unit is greater than or equal to a preset amplitude threshold, the corresponding unit is marked as a high-dynamic region;

[0025] If the change amplitude in the unit is less than the preset amplitude threshold, the unit is marked as a low-dynamic region;

[0026] The high-dynamic region and the low-dynamic region are integrated to generate a dynamic distribution feature map;

[0027] Based on the dynamic distribution feature map, the target identifier, and the location information, a density distribution map is generated to obtain a traffic density distribution map.

[0028] Preferably, cluster identification analysis is performed based on the traffic density distribution map to obtain the boundary range of the key area, including:

[0029] Based on the traffic density distribution map, density screening is performed to obtain a set of high-density units;

[0030] Based on the high-density unit set, clustering identification is performed to obtain a key region identifier set;

[0031] Based on the set of key region identifiers, boundary extraction and expansion are performed to obtain the boundary range of the key regions.

[0032] Preferably, based on the boundary range of the key area, the fence boundary is updated to obtain the updated fence constraints, including:

[0033] Obtain the boundary coordinate data of the key area;

[0034] Based on the boundary coordinate data of the key area, a vector fence is generated to obtain the preliminary fence boundary shape;

[0035] Based on the initial fence boundary shape, a boundary expansion process is performed to obtain the expanded fence boundary shape.

[0036] Based on the expanded fence boundary shape, boundary confirmation and synchronization are performed to obtain the updated fence constraints.

[0037] Preferably, based on the adjusted operating status, traffic determination and data collection are performed to obtain more accurate regional traffic dynamic data, including:

[0038] Based on the adjusted operating status, safety parameters are compared and passage is determined to obtain the passage determination result;

[0039] Based on the access determination result, permission mapping and allocation operations are performed to obtain valid access permissions;

[0040] Based on the valid access permissions, priority road segments are selected and nodes are planned to obtain a node deployment scheme;

[0041] Based on the node deployment scheme, data integration and frequency assessment are performed to obtain more accurate regional traffic dynamic data.

[0042] Preferably, based on the higher-precision regional traffic dynamic data, resource load balancing scheduling is performed to obtain the final resource allocation scheme, including:

[0043] According to the higher precision regional traffic dynamic data, load detection and list generation are performed to obtain a node load state list;

[0044] According to the node load state list, task migration scheduling is performed to obtain a load distribution state;

[0045] According to the load distribution state, scheme synchronous deployment is performed to obtain a final resource allocation scheme.

[0046] Preferably, according to the final resource allocation scheme, abnormal monitoring and dynamic adjustment are performed to obtain the latest low-altitude traffic management state, including:

[0047] According to the final resource allocation scheme, data acquisition and density calculation are performed to obtain the traffic density of each region;

[0048] If the traffic density is greater than or equal to a preset density threshold, an abnormal time point is recorded and corresponding regional position information is obtained, so as to obtain abnormal fluctuation initial distribution information;

[0049] If the traffic density is less than the preset density threshold, it is judged that the corresponding region is in a normal state, and fluctuation detection is continuously performed;

[0050] According to the abnormal fluctuation initial distribution information, dynamic range identification and update instruction generation are performed to obtain an updated traffic situation map and fence boundary data;

[0051] According to the updated traffic situation map and fence boundary data, execution synchronization publishing and state confirmation are performed to obtain the latest low-altitude traffic management state.

[0052] In a second aspect, the present application provides a multi-source data driven low-altitude operation intelligent scheduling system, comprising:

[0053] A data acquisition module is configured to acquire multi-source heterogeneous data;

[0054] A standardization module is configured to perform data standardization processing according to the multi-source heterogeneous data to obtain a multi-source data set;

[0055] A traffic density module is configured to perform dynamic identification and density evaluation according to the multi-source data set to obtain a traffic density distribution map;

[0056] A boundary range module is configured to perform clustering identification analysis according to the traffic density distribution map to obtain a boundary range of a key region;

[0057] A constraint condition module is configured to perform fence boundary updating according to the boundary range of the key region to obtain updated fence constraint conditions;

[0058] A correction module is configured to correct flight parameters according to the updated fence constraint condition, and obtain an adjusted operation state;

[0059] A dynamic data module is configured to perform traffic judgment and data collection according to the adjusted operation state, and obtain higher-precision regional traffic dynamic data;

[0060] A distribution scheme module is configured to perform resource load balancing scheduling according to the higher-precision regional traffic dynamic data, and obtain a final resource distribution scheme;

[0061] A management state module is configured to perform abnormality monitoring and dynamic adjustment according to the final resource distribution scheme, and obtain a latest low-altitude traffic management state.

[0062] In a third aspect, the present application also provides an electronic device, comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor executes the computer program to implement the multi-source data driven low-altitude operation intelligent scheduling method according to any one of the above.

[0063] In a fourth aspect, the present application also provides a computer readable storage medium, comprising a stored computer program, wherein the computer readable storage medium controls a device where the computer readable storage medium is located to execute the multi-source data driven low-altitude operation intelligent scheduling method according to any one of the above when the computer program runs.

[0064] Compared with the prior art, the present application has the following beneficial effects:

[0065] (1) The present application can integrate unmanned aerial vehicle sensing data, ground monitoring data and meteorological information data by acquiring multi-source heterogeneous data and performing standardization processing, realize data integration with unified format and consistent structure, improve the compatibility and information integrity of downstream processing, and solve the problem of fragmented data sources and difficult unified analysis in traditional methods.

[0066] (2) The present application can accurately distinguish high-dynamic and low-dynamic regions by unit division, change amplitude calculation and density distribution map generation of the multi-source data set, generate a traffic density distribution map with spatial distribution characteristics, effectively improve the accuracy of regional target recognition and the fineness of dynamic perception, and support accurate formulation of subsequent management strategies.

[0067] (3) The present application can flexibly adjust the allocation of computing resources according to the current node state based on traffic density and operation state data, combined with real-time load information of edge nodes, perform task migration and synchronous deployment, effectively alleviate the problem of overloading of part of the nodes, and improve the overall resource utilization efficiency and response ability of the system.

[0068] (4) The application performs load detection, task migration and synchronous deployment operation based on traffic dynamic data, can dynamically adjust resource allocation structure according to the real-time load state of the edge node, breaks through the limitation of static edge resource scheduling, and improves the scheduling flexibility and processing capacity of the system in a high-concurrency or burst task scenario. BRIEF DESCRIPTION OF DRAWINGS

[0069] Figure 1 is a multi-source data driven low-altitude operation intelligent scheduling method process schematic diagram provided by the first embodiment of the application;

[0070] Figure 2 is a multi-source data driven low-altitude operation intelligent scheduling system structure schematic diagram provided by the second embodiment of the application. DETAILED DESCRIPTION

[0071] The technical solutions in the embodiments of the application will be clearly and completely described below with reference to the drawings in the embodiments of the application. Obviously, the described embodiments are only part of the embodiments of the application, rather than all the embodiments of the application. Based on the embodiments in the application, all other embodiments obtained by a person of ordinary skill in the art without creative labor fall within the protection scope of the application.

[0072] With reference to Figure 1 , the first embodiment of the application provides a multi-source data driven low-altitude operation intelligent scheduling method, comprising the following steps:

[0073] S11, acquiring multi-source heterogeneous data;

[0074] S12, performing data standardization processing according to the multi-source heterogeneous data to obtain a multi-source data set;

[0075] S13, performing dynamic identification and density evaluation according to the multi-source data set to obtain a traffic density distribution map;

[0076] S14, performing clustering identification analysis according to the traffic density distribution map to obtain a boundary range of a key area;

[0077] S15, performing fence boundary updating according to the boundary range of the key area to obtain an updated fence constraint condition;

[0078] S16, performing flight parameter correction according to the updated fence constraint condition to obtain an adjusted operation state;

[0079] S17, performing passing judgment and data collection according to the adjusted operation state to obtain higher-precision intra-regional traffic dynamic data;

[0080] S18, performing resource load balancing scheduling according to the higher-precision regional traffic dynamic data, to obtain a final resource allocation scheme;

[0081] S19, performing abnormality monitoring and dynamic adjustment according to the final resource allocation scheme, to obtain the latest low-altitude traffic management state.

[0082] In step S11, multi-source heterogeneous data is acquired;

[0083] It is worth noting that the system performs the operation of acquiring multi-source heterogeneous data, mainly including two types of data streams from the unmanned aerial vehicle platform and the ground monitoring device, namely unmanned aerial vehicle sensing data and ground monitoring data. In the unmanned aerial vehicle sensing data, the speed data is obtained through the linkage of the accelerometer and the gyroscope in the inertial navigation unit of the unmanned aerial vehicle on board, and the system continuously reads the speed change information at a fixed sampling frequency (for example, 50 Hz), and obtains the average speed in a short period through time integration; the height data is measured by a laser altimeter or a barometric altimeter, for example, when flying in the city, the vertical distance between the unmanned aerial vehicle and the ground obstacles is obtained by using the laser ranging module to mark the flight height of the unmanned aerial vehicle in the vertical direction. The ground monitoring data is obtained from image acquisition devices arranged in traffic corridors, take-off and landing points or low-altitude monitoring sentries, and the system acquires video streams through cameras with a frame rate not less than 25 frames per second. Image recognition is achieved by using an edge detection and contour matching based method. The specific process is as follows: the system first uses the ground monitoring camera to acquire continuous pictures, converts each picture into a gray picture, and extracts the image edges through the Canny algorithm; on the obtained edge map, the system further uses a contour extraction algorithm such as the findContours function in OpenCV to obtain the closed boundary region. Subsequently, for the typical shape features of the aircraft, such as the geometric structure of "rotor + fuselage", the system establishes the boundary contour template of the aircraft in advance. The template matching operation is performed on the contour result in the real-time image, and by comparing the contour area, the aspect ratio and the boundary shape and other indicators, it is judged whether there is an aircraft target in the current image, and a unique identification code is assigned as the target identification. The unique identity is used to mark a specific aircraft or ground object. The position information is obtained by connecting the device with a GNSS receiver or a fusion positioning device (such as an RTK module), and the system synchronously extracts the latitude and longitude or plane coordinates of the identified target in each frame of image according to the time stamp.

[0084] In step S12, data standardization processing is performed according to the multi-source heterogeneous data, to obtain a multi-source data set, including:

[0085] The multi-source heterogeneous data includes unmanned aerial vehicle sensing data and ground monitoring data;

[0086] According to the unmanned aerial vehicle sensing data, field mapping and structure conversion are performed to obtain a sensor standard data group;

[0087] According to the ground monitoring data, field extraction and format normalization are performed to obtain a monitoring standard data set;

[0088] The sensor standard data set and the monitoring standard data set are integrated to obtain a unified format multi-source data set.

[0089] It is worth noting that the system first performs field mapping and structure conversion processing on the obtained unmanned aerial vehicle sensor data to form a unified standard sensor standard data set. The unmanned aerial vehicle sensor data is generally reported in the form of raw data packets, and the data structure contains multiple irregular fields, such as V x , V y , and Z alt , as well as other physical quantities with units or different naming formats. In order to achieve data consistency and readability, the system pre-establishes a field mapping table to map these raw fields to standard field names, such as combining "V x " and "V y " to calculate the total speed field "speed". The calculation method is to square and square root the sum of the two direction speeds, i.e. speed equals the square root of the sum of the squares of V x and V y . For the "Z alt " field, it is directly mapped to the unified altitude field "altitude" and unit conversion is performed, such as converting feet to meters. The structure conversion part is to integrate the scattered timestamps, position numbers and sensor numbers in the original data into a unified data record line, with time as the main index, and each record line contains the corresponding time speed, height, sensor number and data source label. For example, when the unmanned aerial vehicle numbered U01 reports a speed of 15 meters per second and a height of 120 meters at 10:20 on May 1, 2024, the system converts this data into a structured record line, with fields including: time 202405011020, number U01, speed 15, altitude 120.

[0090] The system first performs field extraction and format normalization processing on the received ground monitoring data to construct a structured monitoring standard data set. The ground monitoring data comes from fixed cameras, radars and image sensing devices, and the original records contain time-indexed position information and target identification information. In order to ensure data structure clarity, the system needs to first parse the metadata attached in the monitoring image frames. For example, the original position information field format is "gps x " and "gps y ", and the target identification is "track id, but the naming and format of these fields are not uniform. The system will establish a field mapping table to merge and convert “gps x ” and “gps y ” into a uniform two-dimensional coordinate field “position” in the format of a floating-point array such as [120.154234, 30.245678]. At the same time, the “track id ” field is renamed to “target id ”, ensuring that all monitoring objects have unique identifiers within the entire data set. Subsequently, the system aligns each record by a uniform timestamp, such as sampling once per second, and organizes it into a standard structured record containing collection time, position coordinates, and target number.

[0091] Finally, the system aligns the sensor standard data set and the monitoring standard data set by the timestamp field, matches the data records of the same time point by traversal, and merges the speed, height, position, and target number into one row to generate a structured and consistent unified format data set.

[0092] In step S13, according to the multi-source data set, dynamic identification and density evaluation are performed to obtain a traffic density distribution map, including:

[0093] According to the multi-source data set, unit division and data extraction are performed to obtain a unit-level preliminary traffic data set, wherein the unit-level preliminary traffic data set includes speed data, height data, position information, and target identification;

[0094] According to the speed data and height data in the traffic data set, the change amplitude in each unit is calculated;

[0095] If the change amplitude in the unit is greater than or equal to a preset amplitude threshold, the corresponding unit is marked as a high dynamic area;

[0096] If the change amplitude in the unit is less than the preset amplitude threshold, the unit is marked as a low dynamic area;

[0097] The high dynamic area and the low dynamic area are integrated to generate a dynamic distribution feature map;

[0098] According to the dynamic distribution feature map, the target identification, and the position information, a density distribution map is generated to obtain a traffic density distribution map.

[0099] It is worth mentioning that the system first divides the monitoring area into a two-dimensional grid according to the geographical space range, and constructs a regular cell set. The division granularity is generally a square with a side length of 100 meters, which ensures that each cell can cover multiple target points but not too large to cause ambiguity. After the division is completed, the system takes each cell as a search area, traverses all records in the multi-source data set, and extracts records falling into the cell according to the location information field. Each record contains a speed value, a height value, a target number, and corresponding latitude and longitude coordinates.

[0100] Subsequently, the system needs to calculate the change amplitude in each cell. First, calculate the speed change and height change:

[0101]

[0102] ΔV is the speed change, ΔH is the height change, is the speed value at time point t1, is the speed value at time point t2, is the height value at time point t1, is the height value at time point t2.

[0103] The normalized weighted average method is used to calculate the change amplitude:

[0104]

[0105] where Δ u nit is the change amplitude, α and β are weight coefficients, α = 0.7, β = 0.3, V max is the maximum speed value of all targets in all cells in the current evaluation period, V min is the minimum speed value of all targets in all cells in the current evaluation period; H max is the maximum height value appearing in the same period, H min is the minimum height value appearing in the same period. The two maximum values and the two minimum values are obtained by traversing each record in the traffic data set and comparing the fields speed and altitude, which can effectively reflect the global speed and height upper limit in the current period.

[0106] And the α and β weight settings are that the speed change directly reflects the propulsion state and maneuvering behavior of the aircraft, such as acceleration, deceleration, or sudden turning, etc., which changes with control instructions or path adjustment, so it is more sensitive to judging the dynamics of the flight area. The height change is limited by airspace regulation and terrain constraints in most low-altitude operating environments, with a smaller range of variation, which is often used to assist in judging flight trends rather than directly reflecting dynamic behavior.

[0107] The preset amplitude threshold value set here is 0.1, which can effectively distinguish the flight state of the high change flatness and the speed sharp fluctuation. When the change amplitude is greater than or equal to 0.1, the system marks the unit as a high dynamic region, considering that the region exists sharp motion behavior, and on the contrary, if less than 0.1, the unit is considered as a low dynamic region, and the motion characteristics are stable.

[0108] The system uniformly marks all the units that have completed the change amplitude calculation, and respectively gives "high dynamic" and "low dynamic" marks, and then the marking information of the high dynamic and low dynamic units is summarized, so as to obtain the dynamic distribution feature map.

[0109] In order to further identify the traffic gathering situation, the system takes the unit marked as high dynamic in the dynamic distribution map as the key statistical area, and performs target gathering analysis with a fixed time window.

[0110] In specific operation, the system extracts all target identifiers falling into each marked dynamic unit in the time period of 10:00:00 to 10:00:10, and filters out duplicate values to count the number of active targets in the unit. For example, if target_id A101, A102, A103, A104, A105 are recorded in a certain block, the number of active targets in the unit in this time period is 5, which is the initial density value of the unit.

[0111] Subsequently, the system performs a unified spatial mapping operation in combination with the position coordinate information attached to each target identifier. The two-dimensional region is divided into equal amplitude grid units with a preset spatial grid step (such as 50 meters), and the number of target identifiers falling into each unit is counted. The statistical value is the traffic density value, and the higher the density represents the higher the target gathering degree in the region, and the more complex the traffic state.

[0112] In step S14, according to the traffic density distribution map, clustering recognition analysis is performed to obtain the boundary range of the key region, including:

[0113] According to the traffic density distribution map, density screening is performed to obtain a high-density unit set;

[0114] According to the high-density unit set, clustering recognition is performed to obtain a key region identifier set;

[0115] According to the key region identifier set, boundary extraction and expansion are performed to obtain the boundary range of the key region.

[0116] It is worth mentioning that the system first performs a density screening operation on all cells in the traffic density distribution map to identify high-density areas and provide input basis for subsequent clustering analysis. The specific operation process is as follows: the system traverses all cells in the density distribution map, extracts the corresponding density value, and records it as a density sequence. Then, based on the density sequence, the average density and standard deviation of all cells are calculated. The average density represents the overall level of traffic activity in the whole map, and the standard deviation describes the dispersion degree of the density of each cell. The system sets the density screening threshold based on this, which is set to the average density plus one standard deviation, which is used to define the "high-density" interval. This screening condition can effectively eliminate cells within the normal fluctuation range, ensuring that the remaining cells have significant density characteristics in a statistical sense.

[0117] For example, if the average density of the whole map is 12 and the standard deviation is 3, the screening threshold is 15. The system marks the cells with a density value greater than or equal to 15 as "high-density cells", and the remaining cells are marked as ordinary areas and excluded in the subsequent steps. All cells that meet the screening conditions are grouped into a high-density cell set, each cell in the set contains its location coordinates and actual density value in the original distribution map.

[0118] Based on the high-density cell set obtained in the previous stage, the system performs clustering identification operations to divide the area groups that are close to each other and have continuous traffic activity. The specific operation process is as follows: first, the system takes the center coordinates of each high-density cell as the basis to calculate the spatial distance with other high-density cells, and classifies the cells within a certain distance threshold as a class. The distance threshold can be determined according to the grid division scale, for example, the system uses a cell edge length of 50 meters, and sets the distance threshold of adjacent cells to 70 meters to ensure that the cells diagonally adjacent are included.

[0119] The system uses a one-by-one traversal method to retrieve other high-density cells within the adjacent range of each unmarked high-density cell, and assigns all cells that meet the conditions a cluster number. This process continues to iterate until all high-density cells are assigned to a cluster. For example, if the coordinates of cell A are (100, 100) and cell B are (130, 120), the Euclidean distance between them is 36 meters, which is less than the threshold of 70 meters, so they are classified into the same cluster. Through this operation, the system finally identifies several spatially continuous and high-density areas, and each cluster represents a key area.

[0120] Each cluster corresponds to a key area identifier, which is numbered as Z1, Z2, Z3, etc., and records the range of cell coordinates it contains. This key area identifier set provides a clear geographical range basis for subsequent boundary extraction and scheduling decisions.

[0121] The system identifies the boundary of each key area based on the identified key area label set, and performs boundary extraction and expansion processing on the cell set in each key area to determine the boundary range of the key area in space. Specifically, the system first reads the coordinate data of all member cells of each key area, and uses the minimum bounding rectangle method to construct its boundary. This method determines a closed rectangular frame by finding the minimum horizontal and vertical coordinate values and the maximum horizontal and vertical coordinate values that contain all the cells, for example, the horizontal coordinate range of the cells in a key area is 100 to 150, and the vertical coordinate range is 200 to 240, then the initial boundary frame is defined as the upper left corner of the rectangle (100, 240), and the lower right corner (150, 200).

[0122] Subsequently, the system performs expansion processing on the boundary range. The expansion operation means extending a certain distance outward on the basis of the original minimum bounding rectangle to cover the interference cells or critical cells that may exist at the edge of the area, so as to avoid the situation that the recognition range of the area is too narrow due to instantaneous fluctuations in density. For example, if the expansion boundary is set to 10 meters, then the rectangle is expanded by one cell width to the left, right, top and bottom respectively. After expansion, the boundary range of the key area is updated to horizontal coordinate 90 to 160 and vertical coordinate 190 to 250.

[0123] Finally, each key area is defined as a closed area with a clear coordinate range, and the system records and numbers the boundary range in the form of a coordinate set, such as the boundary range of key area Z1 is horizontal 90 to 160 and vertical 190 to 250.

[0124] In step S15, according to the boundary range of the key area, the fence boundary is updated to obtain the updated fence constraint condition, including:

[0125] Obtaining the boundary range coordinate data of the key area;

[0126] According to the boundary range coordinate data of the key area, vector fence generation is performed to obtain the preliminary fence boundary shape;

[0127] According to the preliminary fence boundary shape, boundary expansion processing is performed to obtain the expanded fence boundary shape;

[0128] According to the expanded fence boundary shape, boundary confirmation synchronization is performed to obtain the updated fence constraint condition.

[0129] It is worth mentioning that the system retrieves the corresponding cell position coordinates one by one according to the key area identifier set extracted in the previous step, and combines to form the boundary range coordinate data. The boundary range of the key area refers to a closed area composed of multiple adjacent high-density cells, and its spatial distribution is described by the coordinate points of the outermost cells. The system first extracts the two-dimensional position index information of each key area cell, such as represented as an X and Y coordinate pair in the form of grid top-left corner coordinates. Then, the system sequentially connects the set of coordinate points to obtain the boundary coordinate point set. Taking a key area containing five adjacent cells as an example, its boundary coordinate points are [(100, 200), (100, 250), (150, 250), (150, 200)] in turn, and this data set is the boundary range coordinate data of the current key area.

[0130] In order to convert the boundary range coordinate data into a continuous closed boundary line, the system calls the contour stitching algorithm to sequentially connect the coordinate points to form one or more closed polygons. This algorithm will determine the connection relationship between adjacent points according to the arrangement order of the coordinate points, and construct a polygon path when the first and last closed conditions are met.

[0131] After construction, the system stores the obtained boundary line data in the fence boundary array, and each boundary line is recorded in the form of a line segment sequence, representing the preliminary physical blocking range of the area. For example, if the boundary coordinate point set is [(100, 200), (100, 250), (150, 250), (150, 200)], the system generates a rectangular boundary line frame, and the corresponding preliminary fence shape is a preliminary fence boundary shape with a width of 50 meters and a height of 50 meters.

[0132] The system performs boundary expansion processing based on the generated preliminary fence boundary shape, with the purpose of reserving safety redundancy for the key area to prevent traffic fluctuations near the boundary from exceeding the original boundary. The operation logic of the expansion processing is: the system first reads all the boundary coordinate points of the preliminary fence, and sequentially performs buffer calculation on each coordinate point. Buffer calculation refers to moving each point outward in its normal direction by a certain distance to form a new outwardly expanded edge point. The expansion distance is preset by the system and set to ten meters according to task requirements.

[0133] Subsequently, the system reconnects all the expanded points to form a closed path, and merges the area between the original boundary polygon and the expanded path through a geometric Boolean operation to form a new polygon boundary, referred to as the expanded fence boundary shape. For example, if the original boundary is a rectangle with four corner points A, B, C, and D, the system will translate each of the four points outward by ten meters to obtain A', B', C', and D', and then reconstruct the expanded boundary frame with the new points. The expansion result spatially covers the initial key area and leaves a buffer zone, effectively improving the containment and control ability of the fence against sudden traffic expansion. The final output of the expanded boundary is still a sequence of polygon coordinate points.

[0134] After completing the extraction and organization of the fence area historical data, the system calculates and sets specific running thresholds for each expanded fence boundary area. Thresholds are important reference benchmarks for limiting the running behavior of targets in the area, including speed threshold and height threshold. The system first extracts the running speed and flight height of each target in the area according to all historical trajectory records, and normalizes each record to ensure consistent data structure. Then, the system uses statistical analysis methods to sort all speed data, and selects the ninth decile of the speed value as the maximum speed threshold, ensuring that the threshold covers most normal running targets but excludes extreme outliers.

[0135] For example, in a certain area, if the extracted speed data is an array containing three hundred records, the 270th speed value after sorting is 13.6 meters per second, then the speed threshold of the area is set to 13.6 meters per second. Similarly, the system performs the same processing on the height data and sets the height threshold to the ninth decile of the height value of the target in the past time, for example, one hundred and fifteen meters. This method ensures that the obtained threshold has statistical reasonableness and running safety, avoiding excessive restriction or excessive leniency. Finally, each updated fence constraint condition binds the complete control structure of the speed threshold and the height threshold.

[0136] In step S16, according to the updated fence constraint condition, the flight parameter correction is performed to obtain an adjusted running state, including:

[0137] Obtaining the speed parameter and the height parameter of the sensor standard data set;

[0138] The updated fence constraint condition includes a speed threshold and a height threshold;

[0139] According to the speed parameter and the height parameter, and the speed threshold and the height threshold, respectively, parameter comparison analysis and instruction generation are performed to obtain an aircraft control instruction;

[0140] According to the aircraft control instruction, parameter issuance and running correction are performed to obtain an adjusted running state.

[0141] It is worth mentioning that the system first extracts the current speed parameter and height parameter of the aircraft from the sensor standard data set, which is generally provided by the inertial measurement unit and barometric altimeter on the unmanned aerial vehicle, with a sampling frequency of once per second and data fields of speed and altitude. The real-time data obtained will serve as the basis for the current operating state of the aircraft.

[0142] Subsequently, the system calls in the fence constraint condition generated in the previous stage of boundary confirmation synchronization, which contains the corresponding speed threshold and height threshold in a specific area. For example, the speed threshold for a certain fence area is 15 meters per second, and the height threshold is 120 meters.

[0143] Next, the system performs numerical comparison and analysis on the current speed and height parameters. If the current speed is greater than the threshold, it indicates that the aircraft may have a rapid crossing risk, and the system will generate a "reduce speed" control instruction. If the speed is below the threshold, no adjustment is needed. If the current height is greater than the set threshold, it indicates that the aircraft is flying too high and has the potential risk of airspace overrun, and the system will generate a "lower height" instruction. If the height is below the threshold, it may also enter a dangerous area due to flying too low, and a "raise height" instruction is also generated.

[0144] Finally, the system generates aircraft control instructions based on the above judgment results, for example: if the speed is 18 meters per second and the altitude is 130 meters, both thresholds are exceeded, the system will issue a speed reduction and height reduction instruction to correct the flight state and return it to a safe operating range.

[0145] The running correction process has a feedback loop, and the system monitors the speed and height changes of the aircraft in real time to determine whether the control effect meets the target state. For example, within one second after issuing the instruction, the system detects that the speed has decreased from eighteen meters per second to fourteen point eight meters per second, and the height has decreased from one hundred thirty meters to one hundred twenty-one meters, indicating that the flight state has been effectively corrected.

[0146] The adjusted operating state means that the parameters of the aircraft are within the fence set range, specifically, the speed does not exceed fifteen meters per second, the height is stable below one hundred twenty meters, and there is no sudden change trend.

[0147] In step S17, according to the adjusted operating state, traffic determination and data collection are performed to obtain higher-precision regional traffic dynamic data, including:

[0148] According to the adjusted operating state, safety parameter comparison and traffic determination are performed to obtain a traffic determination result;

[0149] According to the passage judgment result, a permission mapping and distribution operation is performed to obtain an effective passage permission;

[0150] According to the effective passage permission, a priority section screening and node planning is performed to obtain a node deployment scheme;

[0151] According to the node deployment scheme, data integration and frequency evaluation are performed to obtain higher-precision regional traffic dynamic data.

[0152] It is worth noting that the system verifies the safety of the current speed, height and other key operating parameters of the aircraft based on the adjusted operating state obtained in the previous stage, and judges whether it has the condition to continue to pass. Specifically, the system first retrieves the speed threshold and height threshold set in the fence area where each aircraft is currently located, and compares them with the real-time speed value and height value reported by the aircraft sensor one by one. The comparison process is carried out in a difference judgment manner: if the current speed is less than the set upper speed limit and the height is within the allowed height interval, the system will preliminarily determine that the operating state is "passable". Otherwise, if any parameter exceeds the preset amplitude threshold, the system will mark it as "need to limit passage".

[0153] For example, if the current speed of a certain aircraft is 12 meters per second, and the speed upper limit set in the fence area is 15 meters per second, the speed parameter meets the passage condition. If at the same time its height is 90 meters, and the height interval set in this area is 80 to 100 meters, it also meets the height requirement, and the system will generate a passage judgment result of "pass". Conversely, if the height exceeds the upper limit or the speed is too fast, the result will be "prohibited passage".

[0154] The system performs permission mapping and distribution operations according to the passage judgment result generated in the previous stage to ensure that each aircraft has legal path access qualification in actual operation. The passage judgment result is a Boolean type of judgment information, represented by "allow passage" or "prohibit passage" two labels, which is the system's conclusion on whether the current operating state of the aircraft meets the dynamic control conditions of the fence area.

[0155] The specific operation process is as follows: the system first reads the passage judgment result and establishes a mapping relationship between the judgment result and the permission level. If the judgment result is "allow passage", the system will assign the aircraft to "first-level passage permission" and allow it to execute tasks according to the default path or scheduling strategy in the current area. If the judgment is "prohibit passage", the system will downgrade its permission to "limit passage" or "pending scheduling", and restrict its access to some sensitive nodes or high-density areas at the task level to prevent resource conflicts or flight risk spread.

[0156] In the permission mapping process, the system generates a permission mapping table indexed by the aircraft ID, and assigns specific access ranges in combination with the current fence position, flight time period, and task category. For example, if aircraft U01 is determined to be allowed to access a certain area, it is assigned valid access permission within "key_area_A, 10:00-10:10". This permission information is recorded synchronously in the task scheduling table and edge node cache for subsequent path planning and data reporting processing.

[0157] In the priority section screening process, the system performs multi-dimensional index calculation on each grid channel in the access area, mainly including three core indicators: historical access frequency, node density, and task concentration. First, the system counts the number of target passes in each grid within a set time window to obtain the access frequency parameter, with higher frequency indicating a mature and stable access capacity. Second, the system calculates the number of perception and communication nodes in the coverage area of each channel, and uses the ratio of node number to coverage area as the node density indicator, reflecting its support capacity. Third, the system counts the number of scheduled tasks in each grid within the current period to form the task concentration, which describes the task space aggregation.

[0158] After obtaining the above parameters, the system integrates the indicators of each grid crossed by the candidate path, and calculates the average access frequency, average node density, and total task concentration. Then, the system normalizes and fuses the three indicators with a set weight, outputting the comprehensive access load value of the path. At the same time, the system analyzes the congestion record frequency and density of the grids in the path based on historical trajectory records, and calculates the congestion probability of the path. Finally, the system selects the top few paths with low load, balanced node distribution, and reasonable task concentration as the priority access channels based on the load value and congestion probability.

[0159] Taking aircraft U01 as an example, if it is authorized to access area R5, the system will prioritize selecting paths in R5 with low historical congestion rate, high task target concentration, and small path overlap rate, such as paths R5-A1, R5-A3, and R5-B2, to construct an optimized flight route with low interference and high access efficiency.

[0160] Node planning is to set physical nodes for data collection, state synchronization, or communication relay for each optimized path. The system calculates the minimum number of nodes required to cover the entire path based on path length and aircraft communication radius, and deploys them evenly based on geographic coordinates. For example, for a 300-meter-long section, if the aircraft communication radius is 60 meters, the system will deploy 5 communication nodes along the section to ensure uninterrupted information transmission.

[0161] The final output node deployment scheme is a binding relationship between a set of paths and node numbers, in the form of: {path: R5-A1, node: [N21, N22, N23]}, which provides key support for subsequent data collection scheduling and communication coordination.

[0162] The system integrates and processes the data collected by each node according to the node deployment scheme generated in the preamble, and performs traffic frequency analysis in combination with the sampling frequency. The goal is to obtain more fine-grained, shorter update cycle, and more complete spatial coverage of regional traffic dynamic data. Each monitoring node included in the node deployment scheme has clear location information and collection range, and will continuously collect target trajectory, speed, orientation, and identification tag information within the region after deployment. The system first unifies the structure of these data, including field format standardization, timestamp alignment, and multi-source data merging processing, to form a clear structure and continuous time data stream set.

[0163] In the frequency evaluation process, the system counts the number of target detections of each node within a set time window (e.g., 1 second or 2 seconds), and further calculates the frequency and duration of target appearance within the node's perception range, to reflect the local traffic density fluctuations. For example, if a node continuously captures target trajectories 20 times from 10:00:00 to 10:00:10, and each time interval is less than 1 second, it indicates that the node is in a high traffic active state, and its data has high timeliness and high representativeness. The system further integrates the statistical results of adjacent nodes, fills in the coverage blind area or sampling gap based on location interpolation and time interpolation methods, and generates continuous and complete dynamic data grid.

[0164] The "higher precision regional traffic dynamic data" obtained finally refers to grid traffic situation data with a sampling period of seconds and a spatial resolution of fifty meters. It not only includes the number of targets, speed average, and location center of gravity in each time slice, but also includes path distribution density and movement direction trend.

[0165] In step S18, according to the higher precision regional traffic dynamic data, resource load balancing scheduling is performed to obtain the final resource allocation scheme, including:

[0166] According to the higher precision regional traffic dynamic data, load detection and list generation are performed to obtain a node load state list;

[0167] According to the node load state list, task migration scheduling is performed to obtain a load distribution state;

[0168] According to the load distribution state, scheme synchronization deployment is performed to obtain the final resource allocation scheme.

[0169] It is worth mentioning that the system performs load detection and list generation operations based on the obtained higher precision regional traffic dynamic data, aiming to identify the current load intensity state of each running node, providing a basis for subsequent task scheduling. Higher precision traffic dynamic data refers to the grid target state data obtained by sampling at a second level and with a spatial resolution of fifty meters, covering the target quantity, average speed, concentration, and path direction in each time slice. The system first takes the spatial grid covered by each node as the analysis unit, extracts the target appearance frequency, average residence time, and task accumulation index of the node in the current time window. Then, the system normalizes the extracted data, standardizing each index to the interval of 0 to 1, and then performs weighted fusion according to the preset weight values. Specifically, the system sets the target quantity weight to 0.5, the residence time weight to 0.3, and the task density weight to 0.2, representing the contribution degree of different dimensions to the node load. The weighted fusion operation is to multiply the standardized three indexes by their corresponding weights and sum them up to calculate the comprehensive load score of the node. The higher the score, the more tasks the node is currently carrying, the higher the target aggregation degree, and the heavier the load. Finally, the system sets the grading threshold according to the score value, divides all running nodes into high load, medium load, and low load, and generates a structured node load state list. The list explicitly shows the number, spatial position, load level, and score value of each node, guiding the subsequent task migration and resource allocation operations. For example, node N105 receives 12 independent targets in 60 seconds, with an average residence time of 35 seconds and a task density index higher than 0.8, the system identifies it as a high load node and records its detailed indicators and location coordinates in the list.

[0170] The system selects multiple candidate target nodes within a distance radius range around the source node based on the node location information and task attributes recorded in the list, with the selection rule prioritizing nodes with lower current load, while evaluating whether the communication distance is acceptable and whether it has the resource capability to receive the corresponding task type. For each pair of task source node and target node combination, the system performs preliminary matching of tasks according to the task shortest path priority principle and the remaining receiving capacity of the node, updates the task list of each node, and obtains the load distribution state.

[0171] When the scheme synchronization deployment is performed, the system first reads the task receiving records of all target nodes in the state table, and generates scheduling instructions according to the scheduling strategy of each path. The instructions include the task source node number, the target node number, the task content summary and the planned execution time. Subsequently, the system sends these scheduling instructions to the node control unit in the order of task scheduling time and path order, to realize the synchronization deployment operation. The finally generated resource allocation scheme includes the following specific contents: the task number, the source path, the expected execution time period and the required resource amount of each node.

[0172] In step S19, according to the final resource allocation scheme, abnormal monitoring and dynamic adjustment are performed to obtain the latest low-altitude traffic management state, including:

[0173] According to the final resource allocation scheme, data collection and density calculation are performed to obtain the traffic density of each region;

[0174] If the traffic density is greater than or equal to the preset density threshold, the abnormal time point is recorded and the corresponding region position information is obtained, so as to obtain the initial distribution information of abnormal fluctuations;

[0175] If the traffic density is less than the preset density threshold, it is judged that the corresponding region is in a normal state, and the fluctuation detection is continuously performed;

[0176] According to the initial distribution information of abnormal fluctuations, dynamic range identification and update instruction generation are performed to obtain the updated traffic situation map and fence boundary data;

[0177] According to the updated traffic situation map and fence boundary data, execution synchronization publishing and state confirmation are performed to obtain the latest low-altitude traffic management state.

[0178] It is worth noting that the data collection focuses on collecting the number of occurrences of targets in each region within a unit time period, target position information and corresponding spatial grid number. The collection frequency is performed in seconds, and the grid resolution is fifty meters. The number of targets appearing in each grid is counted once every second. The system accumulates the occurrence frequency of targets in each grid within the current time period, and records the statistical time period and grid area.

[0179] The traffic density is calculated by the following formula:

[0180]

[0181] Wherein, p is the traffic density, the unit is target / square kilometer / minute, N is the cumulative number of occurrences of targets, A is the spatial area of the corresponding grid, the unit is square meter, and T is the length of the statistical period, the unit is second.

[0182] Taking the R3 area as an example, if the area is 2500 square meters, and 2 targets are monitored in a continuous 5-second statistical time period, the traffic density of the area is about 9600 / km2·min according to the calculation. In order to effectively identify the abnormal traffic gathering area, the system sets the traffic density judgment threshold value to 8000 / km2·min. This threshold value is based on the average traffic density level of the typical route dense area in the peak period of the task, which has high representativeness and practicality. When the density value of a certain area is greater than or equal to the threshold value, the system determines it as a traffic density area, and automatically triggers the subsequent dynamic identification, boundary extraction and fence updating process; on the contrary, if the density value is lower than the threshold value, the area is considered to be in a stable traffic state, and no adjustment operation is performed. 2 ·min. This threshold value is based on the average traffic density level of the typical route dense area in the peak period of the task, which has high representativeness and practicality. When the density value of a certain area is greater than or equal to the threshold value, the system determines it as a traffic density area, and automatically triggers the subsequent dynamic identification, boundary extraction and fence updating process; on the contrary, if the density value is lower than the threshold value, the area is considered to be in a stable traffic state, and no adjustment operation is performed.

[0183] When the traffic density value of a certain area is greater than or equal to the threshold value, the system immediately records the time point of the abnormal occurrence, and extracts the two-dimensional spatial coordinates corresponding to the grid. Through the spatial index structure, the system can quickly locate the specific position of the area in the entire low-altitude grid. Subsequently, the system combines the time point with the corresponding position information to form an initial distribution record of abnormal fluctuations, which is used as the input basis for subsequent dynamic identification and boundary updating. This information is the "initial distribution information of abnormal fluctuations", which includes the unique number of the abnormal area, the occurrence time, the traffic density value and the spatial position coordinates.

[0184] If the traffic density value of a certain area is less than the preset density threshold value, it means that the current traffic state of the area is in the normal range. The system does not immediately adjust the boundary or resource redistribution of the area, but continues to detect the traffic density change with a sampling period of 5 seconds. If the fluctuation threshold value is not reached in a plurality of consecutive sampling periods, the area always maintains the "normal area" label to avoid misjudgment caused by short-term accidental changes.

[0185] After the system reads the initial distribution information of abnormal fluctuations, it first constructs an analysis window around the abnormal area, sets the spatial buffer range to 50-100 meters, and retrieves the adjacent grid nodes in this range. Then, the traffic density of each adjacent grid is reviewed to determine whether it has reached or approached the fluctuation threshold value in the same time window. For example, taking a certain area R7 as the initial point of abnormality, the system will sequentially detect its eight adjacent grids R6, R8, R12, etc. If there is a grid node with a density value greater than 8000, it will be included in the same dynamic area, and finally form a continuous or approximately continuous abnormal area set. This set is the "dynamic identification range".

[0186] In the process of updating the fence boundary data, the system performs closed contour detection on the edge grid of the dynamically identified area through the contour extraction algorithm. The specific operation includes three steps: first, the system constructs a binary matrix based on the identified high-density abnormal grid set, marking the abnormal area as 1 and other areas as 0; second, starting from the top left corner, scan each row to find the boundary grid, and traverse the adjacent grid point by point in a clockwise direction, recording the boundary intersection coordinates; third, when returning to the starting point and the trajectory forms a complete closed loop, output the coordinate sequence of the boundary grid, which completes the contour extraction.

[0187] The coordinate sequence generated by the contour extraction operation will be the core component of the "fence boundary data". Its data content includes: first, the two-dimensional spatial coordinates of the boundary grid points, with the top left corner as the origin and the unit in meters; second, the boundary trend information, which is used to represent the topological continuity of the fence boundary, facilitating subsequent regional closure processing; third, the unique identification code of the abnormal area, such as Zone_202405_T103, which is used to mark the source and timestamp of the abnormal detection corresponding to the fence.

[0188] In the process of generating the latest traffic situation map, the system performs grid-level situation fusion and layer rendering operations based on the initial distribution information of abnormal fluctuations and the updated traffic density data. First, the system integrates the target number, average speed, and moving direction of each grid in the latest time slice, and covers the information of the corresponding grid in the update history map, where the high-density area is represented by color gradient deepening, the moving direction is marked by an arrow, and the abnormal fluctuation area is highlighted by a red frame. Subsequently, the system completes layer rendering through the map service interface, superimposes the fused traffic density matrix and fence boundary, and displays it according to the layer structure, which is divided into geographic base map, regular situation layer, and abnormal area annotation layer. The final generated traffic situation map is connected to the user end in the form of a web page, providing dispatch personnel with real-time viewing of the traffic conditions, abnormal changes, and fence adjustment results in each area.

[0189] After the update of the traffic situation map and the fence boundary data is completed, the system immediately performs a synchronous release and state confirmation operation to ensure that the latest low-altitude control information is timely pushed and adopted. First, the system will package the updated traffic situation map and the corresponding fence boundary data into a structured configuration file, which includes the grid number, real-time traffic density value, fence boundary coordinate point sequence, and fluctuation area identification field. Subsequently, the system pushes the configuration file to the dispatch terminal, command terminal, and task execution equipment through the data distribution interface, and each node analyzes and completes local strategy replacement. In the state confirmation stage, the system will collect the confirmation signals and configuration verification values of each device to determine whether they have completed the loading and validation of new data. If there are inconsistent configurations or delayed responses from the nodes, a secondary synchronization instruction will be triggered. For example, if a UAV execution device does not return configuration update confirmation information within the set five seconds, the system will automatically switch to a backup channel to resend the fence coordinates and situation data for the task area. Finally, the system confirms that the current full-area operating environment has been updated based on the feedback status of all nodes, thereby obtaining the latest low-altitude traffic management state. This state refers to the unified operating configuration adapted by all flight equipment, monitoring nodes, and dispatch strategies in the system, ensuring the consistency of command distribution, fence restriction, and traffic strategy.

[0190] Referring to Figure 2 The second embodiment of the present application provides a multi-source data-driven low-altitude operation intelligent scheduling system, comprising:

[0191] A data acquisition module for acquiring multi-source heterogeneous data;

[0192] A standardization module for performing data standardization processing based on the multi-source heterogeneous data to obtain a multi-source data set;

[0193] A traffic density module for performing dynamic identification and density evaluation based on the multi-source data set to obtain a traffic density distribution map;

[0194] A boundary range module for performing clustering identification analysis based on the traffic density distribution map to obtain a boundary range of a key area;

[0195] A constraint condition module for performing fence boundary update based on the boundary range of the key area to obtain updated fence constraint conditions;

[0196] A correction module for performing flight parameter correction based on the updated fence constraint conditions to obtain an adjusted operating state;

[0197] A dynamic data module for performing traffic determination and data collection based on the adjusted operating state to obtain higher-precision regional traffic dynamic data;

[0198] The allocation scheme module is configured to perform resource load balancing scheduling according to the traffic dynamic data in the region with higher precision, and obtain a final resource allocation scheme.

[0199] The management state module is configured to perform abnormality monitoring and dynamic adjustment according to the final resource allocation scheme, and obtain a latest low-altitude traffic management state.

[0200] It should be noted that the low-altitude operation intelligent scheduling system provided by the embodiments of the present application is used to execute all process steps of the low-altitude operation intelligent scheduling method provided by the embodiments, and the working principles and advantages of the two are one-to-one correspondence, thus not being repeated.

[0201] The embodiments of the present application further provide an electronic device. The electronic device comprises a processor, a memory, and a computer program stored in the memory and executable on the processor, for example, a management state program. The processor executes the computer program to implement the steps in the above-mentioned various low-altitude operation intelligent scheduling method embodiments, for example Figure 1 The processor executes the computer program to implement the functions of the modules / units in the above-mentioned various device embodiments, for example, a management state module.

[0202] For example, the computer program can be divided into one or more modules / units, which are stored in the memory and executed by the processor to complete the present application. The one or more modules / units can be a series of computer program instruction segments capable of completing a specific function, which are used to describe the execution process of the computer program in the electronic device.

[0203] The electronic device can be a desktop computer, a notebook computer, a palm computer, a smart tablet and the like. The electronic device can include, but is not limited to, a processor, a memory. Those skilled in the art can understand that the above components are only examples of the electronic device, and do not constitute a limitation on the electronic device, and can include more or less components than the above, or combine certain components, or different components, for example, the electronic device can also include an input / output device, a network access device, a bus and the like.

[0204] The processor can be a central processing unit (CPU), and can also be other general-purpose processors, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor. The processor is a control center of the electronic device, and connects various parts of the electronic device through various interfaces and lines.

[0205] The memory can be used to store the computer program and / or modules, and the processor realizes various functions of the electronic device by running or executing the computer program and / or modules stored in the memory, and calling data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, at least one application program required by a function (such as a sound playing function, an image playing function, etc.), etc.; and the data storage area can store data created according to the use of the mobile phone (such as audio data, a phone book, etc.), etc. In addition, the memory can include a high-speed random access memory, and can also include a nonvolatile memory, for example, a hard disk, a memory, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, at least one disk storage device, a flash memory device, or other volatile solid-state memory device.

[0206] The modules / units integrated in the electronic device, if realized in the form of software function units and sold or used as independent products, can be stored in a computer readable storage medium. Based on such understanding, all or part of the processes in the above-mentioned embodiment methods can also be completed by a computer program instructing related hardware, and the computer program can be stored in a computer readable storage medium. The computer program can implement the steps of each method embodiment when executed by a processor. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or some intermediate forms, etc. The computer readable medium can include any entity or device, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium, etc. that can carry the computer program code. It should be noted that the contents included in the computer readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction, for example, in some jurisdictions, according to legislation and patent practice, the computer readable medium does not include electrical carrier signals and telecommunication signals.

[0207] It should be noted that the above-described device embodiments are only schematic, and the units described as separate components can or can not be physically separated, and the components shown as units can or can not be physical units, that is, they can be located in one place, or distributed on multiple network units. Part or all of the modules can be selected according to actual needs to achieve the purpose of the embodiment. In addition, the connection relationship between the modules in the device embodiment provided by the present application indicates that there is a communication connection between them, which can be realized as one or more communication buses or signal lines. Those skilled in the art can understand and implement it without creative labor.

[0208] The above-described specific embodiments further illustrate the purpose, technical solutions and beneficial effects of the present application. It should be understood that the above-described specific embodiments are only for the specific embodiments of the present application and are not used to limit the protection scope of the present application. It is particularly pointed out that any modification, equivalent replacement, improvement, etc. made by those skilled in the art within the spirit and principles of the present application should be included in the protection scope of the present application.

Claims

1. A multi-source data-driven intelligent scheduling method for low-altitude operations, characterized in that, include: Acquire multi-source heterogeneous data; Based on the aforementioned multi-source heterogeneous data, data standardization processing is performed to obtain a multi-source dataset; Based on the multi-source dataset, dynamic identification and density assessment are performed to obtain a traffic density distribution map; Based on the traffic density distribution map, cluster identification analysis is performed to obtain the boundary range of key areas; Based on the boundary range of the key area, the fence boundary is updated to obtain the updated fence constraints. Based on the updated fence constraints, the flight parameters are corrected to obtain the adjusted operating status; Based on the adjusted operating status, traffic conditions are determined and data is collected to obtain more accurate regional traffic dynamic data. Based on the higher-precision regional traffic dynamic data, resource load balancing scheduling is performed to obtain the final resource allocation scheme. Based on the final resource allocation plan, anomaly monitoring and dynamic adjustments are performed to obtain the latest low-altitude traffic management status; The step of determining traffic flow and collecting data based on the adjusted operating status to obtain more accurate regional traffic dynamic data includes: Based on the adjusted operating status, safety parameters are compared and passage is determined to obtain the passage determination result; Based on the access determination result, permission mapping and allocation operations are performed to obtain valid access permissions; Based on the valid access permissions, priority road segments are selected and nodes are planned to obtain a node deployment scheme; Based on the node deployment scheme, data integration and frequency assessment are performed to obtain more accurate regional traffic dynamic data; The step of performing resource load balancing scheduling based on the higher-precision regional traffic dynamic data to obtain the final resource allocation scheme includes: Based on the higher-precision regional traffic dynamic data, load detection and inventory generation are performed to obtain a node load status inventory. Based on the node load status list, task migration and scheduling are performed to obtain the load distribution status; Based on the load distribution status, the solution is deployed synchronously to obtain the final resource allocation solution.

2. The multi-source data-driven intelligent scheduling method for low-altitude operations according to claim 1, characterized in that, The step of performing data standardization processing on the multi-source heterogeneous data to obtain a multi-source dataset includes: The multi-source heterogeneous data includes: UAV sensor data and ground monitoring data; Based on the UAV sensor data, field mapping and structure transformation are performed to obtain the sensor standard data set; Based on the ground monitoring data, field extraction and format standardization are performed to obtain the monitoring standard data group; The sensor standard data set and the monitoring standard data set are integrated to obtain a multi-source dataset in a unified format.

3. The multi-source data-driven intelligent scheduling method for low-altitude operations according to claim 1, characterized in that, The step of performing dynamic identification and density assessment based on the multi-source dataset to obtain a traffic density distribution map includes: Based on the multi-source dataset, unit division and data extraction are performed to obtain a preliminary unit-level traffic data set, wherein the preliminary unit-level traffic data set includes speed data, altitude data, location information and target identifiers; Based on the speed and altitude data in the traffic dataset, calculate the magnitude of change within each unit; If the change within the unit is greater than or equal to a preset amplitude threshold, the corresponding unit is marked as a high dynamic region. If the change within the unit is less than a preset amplitude threshold, the unit is marked as a low dynamic region. The high-dynamic region and the low-dynamic region are integrated to generate a dynamic distribution feature map; Based on the dynamic distribution feature map, the target identifier, and the location information, a density distribution map is generated to obtain a traffic density distribution map.

4. The multi-source data-driven intelligent scheduling method for low-altitude operations according to claim 1, characterized in that, The step of performing cluster identification analysis based on the traffic density distribution map to obtain the boundary range of key areas includes: Based on the traffic density distribution map, density screening is performed to obtain a set of high-density units; Based on the high-density unit set, clustering identification is performed to obtain a key region identifier set; Based on the set of key region identifiers, boundary extraction and expansion are performed to obtain the boundary range of the key regions.

5. The multi-source data-driven intelligent scheduling method for low-altitude operations according to claim 1, characterized in that, The step of updating the fence boundary based on the boundary range of the key area to obtain the fence constraint conditions includes: Obtain the boundary coordinate data of the key area; Based on the boundary coordinate data of the key area, a vector fence is generated to obtain the preliminary fence boundary shape; Based on the initial fence boundary shape, a boundary expansion process is performed to obtain the expanded fence boundary shape. Based on the expanded fence boundary shape, boundary confirmation and synchronization are performed to obtain the updated fence constraints.

6. The multi-source data-driven intelligent scheduling method for low-altitude operations according to claim 2, characterized in that, The step of correcting flight parameters based on the updated fence constraints to obtain the adjusted operating state includes: Obtain the velocity and height parameters of the sensor's standard data set; The updated fence constraints include: a speed threshold and a height threshold; Based on the speed parameters and altitude parameters, the parameters are compared and analyzed with the speed threshold and altitude threshold respectively, and commands are generated to obtain the aircraft control commands. Based on the aircraft control commands, parameters are issued and operational corrections are made to obtain the adjusted operational status.

7. The multi-source data-driven intelligent scheduling method for low-altitude operations according to claim 1, characterized in that, The step of monitoring and dynamically adjusting for anomalies based on the final resource allocation scheme to obtain the latest low-altitude traffic management status includes: Based on the final resource allocation plan, data collection and density calculation are performed to obtain the traffic density of each area; If the traffic density is greater than or equal to a preset density threshold, the abnormal time point is recorded and the corresponding regional location information is obtained, thereby obtaining the initial distribution information of the abnormal fluctuation; If the traffic density is less than a preset density threshold, the corresponding area is determined to be in a normal state, and fluctuation detection continues. Based on the initial distribution information of the abnormal fluctuations, dynamic range identification and update instructions are generated to obtain the updated traffic situation map and fence boundary data. Based on the updated traffic situation map and fence boundary data, synchronous release and status confirmation are performed to obtain the latest low-altitude traffic management status.

8. A multi-source data-driven intelligent scheduling system for low-altitude operations, used to execute the multi-source data-driven intelligent scheduling method for low-altitude operations as described in any one of claims 1 to 7, characterized in that, The system includes: The data acquisition module is used to acquire heterogeneous data from multiple sources; The standardization module is used to perform data standardization processing on the multi-source heterogeneous data to obtain a multi-source dataset; The traffic density module is used to perform dynamic identification and density assessment based on the multi-source dataset to obtain a traffic density distribution map. The boundary range module is used to perform cluster identification analysis based on the traffic density distribution map to obtain the boundary range of key areas; The constraint condition module is used to update the fence boundary based on the boundary range of the key area to obtain the updated fence constraint conditions. The correction module is used to correct the flight parameters according to the updated fence constraints to obtain the adjusted operating status. The dynamic data module is used to determine traffic flow and collect data based on the adjusted operating status, so as to obtain more accurate dynamic traffic data within the area. The allocation scheme module is used to perform resource load balancing scheduling based on the higher-precision regional traffic dynamic data to obtain the final resource allocation scheme. The management status module is used to monitor anomalies and make dynamic adjustments based on the final resource allocation scheme to obtain the latest low-altitude traffic management status.

Images