A scenario-based unmanned aerial vehicle control data analysis system and method

Through the scenario-based drone control data analysis system, the problem of UAV communication signal interference during emergencies in urban environments is solved, and the uninterrupted signal link and communication quality improvement of UAV as a relay node is realized. Ensure timely data reception of the command center.

CN118071082BActive Publication Date: 2024-11-26南京海汇装备科技有限公司
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410186406.7
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-02-20
Publication Date
2024-11-26
Estimated Expiration
2044-02-20

AI Technical Summary

Technical Problem

In urban environments, drone communication signals are easily disturbed during emergencies, which makes the command center unable to receive detailed data on the site in a timely manner. Especially due to the large number of communication signals caused by high-rise buildings in the city, the number of communication signals and complicated satellite line rental procedures are caused by the numerous blind spots, resulting in the Decision lags.

Method used

Adopt a scenario-based drone control data analysis system, and build a scenario-based drone emergency command platform to obtain scene historical data, extract key feature data, and form the data between the data changes of the unmanned communication relay node and the key feature data. Relationship, analyze the time information of adding unmanned communication relay nodes, build drone control strategies, make plans in advance, and ensure communication quality and distance.

Benefits of technology

In different scenario environments, using drones as relay communication nodes, uninterrupted signal links are achieved, the probability of communication interference is reduced, communication quality and distance is improved, and visual and audio information is quickly transmitted at the scene of emergencies. Go to the command center.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118071082B_ABST
    Figure CN118071082B_ABST
Patent Text Reader

Abstract

The present invention discloses a scenario-based unmanned aerial vehicle control data analysis system and method, which belongs to the field of unmanned aerial vehicle control technology. The system includes: an emergency command module, a scenario history data storage module, a communication relay module and a control analysis module; the output end of the emergency command module is connected to the input end of the scenario history data storage module; the output end of the scenario history data storage module is connected to the input end of the communication relay module; the output end of the communication relay module is connected to the input end of the control analysis module. The present invention can use unmanned aerial vehicles to monitor and handle emergency scenarios under different scenario environment backgrounds, and use unmanned aerial vehicles as relay communication nodes to solve the problem of many communication signal blind spots caused by high-rise buildings in the city. In the event of an emergency, it can provide an uninterrupted signal link to the ground, so that the command system can receive detailed data of the scene in time.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of unmanned aerial vehicle control technology, and in particular to a scenario-based unmanned aerial vehicle control data analysis system and method. Background Art

[0002] A drone is an unmanned aerial vehicle controlled by a radio remote control device and a self-contained program control device. With the development of science and technology, the application fields of drones are becoming more and more extensive, especially in the handling of emergencies in urban scenarios. Drones have become an indispensable part. The drone's onboard camera can quickly collect on-site data, quickly transmit on-site visual and audio information to the command center, track the development of events, and provide commanders with judgments and decisions.

[0003] However, in actual use, due to the high-rise buildings in the city, there are many blind spots for communication signals. In case of emergencies, communication equipment needs to rent satellite lines. However, the renting of satellite lines needs to be reported in advance, and the procedures are complicated, which often leads to the failure of signals to be transmitted to the command center in time, resulting in delayed decision-making. Although the small communication equipment carried by drones can provide uninterrupted signal links to the ground, so that the command system can receive detailed data from the scene in time, due to the continuous changes and development of the scene, the number of data ports connected to the command center often increases geometrically. The increase in data volume and the change in the source of data ports will cause interference to drone communications, resulting in the communication quality and communication distance being affected, and it is very easy to lose key information data. Summary of the invention

[0004] The purpose of the present invention is to provide a scenario-based UAV control data analysis system and method to solve the problems raised in the above background technology.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions: a scenario-based UAV control data analysis method, the method comprising the following steps:

[0006] S1. Build a scenario-based UAV emergency command platform and obtain scenario historical data based on the scenario-based UAV emergency command platform;

[0007] S2. Extract key feature data based on scene historical data to form a data relationship between unmanned communication relay node data changes and key feature data;

[0008] S3. Analyze the time information of adding unmanned communication relay nodes according to the data relationship and build the UAV control strategy under the scenario data;

[0009] S4. Feedback the formed UAV control strategy to the emergency command system and prepare contingency plans in advance.

[0010] According to the above technical solution, the scenario-based UAV emergency command platform includes: UAV reconnaissance node, unmanned communication relay node, emergency command system, UAV control console, ground receiving station and data processing and analysis library;

[0011] Among them, the drone reconnaissance node is connected to the unmanned communication relay node, and the drone reconnaissance node feeds back the reconnaissance data to the emergency command system via the unmanned communication relay node; the drone control console is connected to the drone reconnaissance node, and the drone control console controls the drone to fly to the drone reconnaissance node; the ground receiving station is connected to the emergency command system, and the emergency command system transmits the reconnaissance data to the ground receiving station; the ground receiving station is connected to the data processing and analysis library, and calls the scene historical data in the data processing and analysis library for further processing and analysis.

[0012] According to the above technical solution, the scene history data includes:

[0013] Historical records data in different scenarios;

[0014] The different scenarios include: fire scenario, query scenario and traffic scenario; the fire scenario refers to the scenario data when a fire occurs in an urban area; the query scenario refers to the scenario data when searching for and monitoring people or objects in an urban area; the traffic scenario refers to the scenario data when a major traffic accident occurs in an urban area or when traffic is congested during peak travel;

[0015] The scene historical data includes the data source point, time range, scene diffusion radius and urban area location; the data source point refers to the initial target point when the scene data occurs; the time range refers to the time interval when the scene data occurs, each day is divided into 24 time intervals, and each interval corresponds to a full hour; the scene diffusion radius refers to the straight-line distance between the farthest point of the scene's influence and the data source point in each time period; the urban area location includes complex urban areas and simple urban areas, which are divided according to the building density in the area, and are randomly divided into several areas of the same area in the urban area. The building density in each area is calculated, and a threshold is set. Areas with building density exceeding the threshold are recorded as complex urban areas, and areas that do not exceed the threshold are recorded as simple urban areas.

[0016] According to the above technical solution, in steps S2-S3, it also includes:

[0017] The key feature data refers to the data source point, time range, scene diffusion radius and urban location; the key feature data in the emergency scene is obtained, and the training data is retrieved from the scene historical data. The retrieval method includes:

[0018] In the same scenario, based on the data source point, time range, and urban location in the key feature data of the emergency scenario and the same number in the scene historical data, the scene historical data with all the same key features are selected first, followed by the scene historical data with two identical key features, and finally the scene historical data with one identical key feature. The selection priority is that the data source point is higher than the urban location, and the urban location is higher than the time range. When the number of training data reaches the number threshold set by the system, the selection is stopped and all the selected scene historical data are output as training data;

[0019] For each set of training data, the time period, the scene diffusion radius corresponding to the time period, and the data change of the unmanned communication relay node corresponding to the scene diffusion radius are calibrated to form a data combination. , ,in, Respectively represent time period, The scene diffusion radius corresponding to the time period and the scene diffusion radius Data volume of unmanned communication relay nodes under ; Represents the diffusion radius of the data source point in the scene based on the current group of training data The number of road intersections below;

[0020] Data combination based on all training data , forming the basic data column ,in Represents the average value of the scene diffusion radius in each time period, and N represents the maximum number of time periods, where:

[0021]

[0022] in, represent In any of the above, i ranges from 1 to N, which refers to the time period sequence number; M represents the number of data sets of training data; h represents the sequence number, represents the scene diffusion radius of the hth group of training data in the i-th time period;

[0023] The basic data column is processed by gray accumulation to form a gray data column. After the gray data column is processed by adjacent mean value, the adjacent mean data column is formed. The gray data column and the adjacent mean data column are combined and the gray prediction algorithm is used to form the relationship function between the scene diffusion radius and the time period:

[0024]

[0025] Where, e represents the natural logarithm; Refers to the average value of the generated scene diffusion radius; Refers to the development coefficient and grey action in the whitening differential equation in the grey data column; the average value of the generated scene diffusion radius is fed back to the system as the predicted value of the corresponding time period.

[0026] In the above technical solution, the ever-changing scene diffusion radius is analyzed to predict the impact range in each time period, and the total amount of data communication required is gradually analyzed, which can minimize communication interference and improve the drone's ability to relay communications.

[0027] According to the above technical solution, it also includes:

[0028] Second data combination based on all training data , forming a periodic change over time and The linear fitting equation between ,in , Respectively represent the parameter term and the constant term of the fitting equation, and the fitting equation is formed by:

[0029] Take each time period ,by As the horizontal axis, As the ordinate, the scattered points of the same set of training data are formed in the coordinate system for linear fitting;

[0030] Linear fitting is performed on all training data to form M groups of fitting equation lines. According to the key feature data of the emergency scenario, the scene diffusion radius of each time period in the emergency scenario is inferred. Based on the data source points in the emergency scenario and the inferred scene diffusion radius of each time period, the number of road intersections in each time period is circled on the urban map;

[0031] Substitute the number of road intersections in each time period into the fitting equation line, calculate M fitting results, select the mode from the M fitting results as the output result, if there is no mode, calculate the average value as the output result; if there are multiple modes, calculate the average value of the multiple modes as the output result;

[0032] The output result is used as the predicted data volume of the unmanned communication relay node in each time period. Based on the data capacity threshold of the drone communication relay node under the scene data, if the predicted data volume of the unmanned communication relay node in any time period exceeds the data capacity threshold of the drone communication relay node, the previous time period is added as the time information of the unmanned communication relay node, and the new drone is controlled to establish a new unmanned communication relay node before the time information.

[0033] A scenario-based UAV control data analysis system, the system includes: an emergency command module, a scenario history data storage module, a communication relay module and a control analysis module;

[0034] The emergency command module is used to build a scenario-based UAV emergency command platform, mobilize and command the scenario-based UAV emergency command platform when facing an emergency scenario, and build UAV reconnaissance, communication and control; the scenario history data storage module is used to store scenario history data; the communication relay module is used to extract key feature data based on scenario history data, and form a data relationship between the data change of the unmanned communication relay node and the key feature data; at the same time, according to the data relationship, analyze the time information of adding the unmanned communication relay node, and build the UAV control strategy under the scenario data; the control analysis module is used to feed back the formed UAV control strategy to the emergency command system, and make plan processing in advance;

[0035] The output end of the emergency command module is connected to the input end of the scene history data storage module; the output end of the scene history data storage module is connected to the input end of the communication relay module; the output end of the communication relay module is connected to the input end of the control analysis module.

[0036] According to the above technical solution, the emergency command module includes a scenario-based UAV emergency command unit and an emergency scenario scheduling unit;

[0037] The scenario-based UAV emergency command unit constructs a scenario-based UAV emergency command platform; the emergency scenario dispatching unit is used to mobilize and command the scenario-based UAV emergency command platform when facing an emergency scenario, and construct the reconnaissance, communication and control of the UAV;

[0038] The output end of the scenario-based UAV emergency command unit is connected to the input end of the emergency scenario scheduling unit.

[0039] According to the above technical solution, the communication relay module includes a feature data processing unit and a strategy unit;

[0040] The feature data processing unit is used to extract key feature data according to the scene historical data, and form a data relationship between the data change of the unmanned communication relay node and the key feature data; the strategy unit is used to analyze the time information of adding the unmanned communication relay node according to the data relationship, and construct the drone control strategy under the scene data;

[0041] The output end of the feature data processing unit is connected to the input end of the strategy unit.

[0042] According to the above technical solution, the control analysis module includes a data feedback unit and a plan processing unit;

[0043] The data feedback unit is used to obtain the drone control strategy and feed it back to the emergency command system, and the plan processing unit is used to remind the management personnel to deploy the plan and prepare the plan in advance;

[0044] The output end of the data feedback unit is connected to the input end of the plan processing unit.

[0045] Compared with the prior art, the beneficial effects achieved by the present invention are: in different scene environments, drones are used to monitor and handle emergency scenes, and drones are used as relay communication nodes to solve the problem of many communication signal blind spots caused by high-rise buildings in cities. In the event of an emergency, an uninterrupted signal link can be provided to the ground, so that the command system can receive detailed data of the scene in time; at the same time, based on the constantly changing data volume, the plan processing is done in advance, which can reduce the probability of interference with drone communications, improve communication quality and communication distance, and quickly transmit the visual and audio information of the scene to the command center, track the development trend of the incident, and provide the commander with judgment and decision-making. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0047] Figure 1 It is a flow chart of a scenario-based UAV control data analysis method of the present invention. DETAILED DESCRIPTION

[0048] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0049] See also Figure 1 , in the first embodiment: a scenario-based UAV control data analysis method is provided, the method comprising: constructing a scenario-based UAV emergency command platform, and acquiring scenario historical data based on the scenario-based UAV emergency command platform;

[0050] The scenario-based UAV emergency command platform includes: UAV reconnaissance nodes, unmanned communication relay nodes, emergency command systems, UAV control consoles, ground receiving stations, and data processing and analysis libraries;

[0051] Among them, the drone reconnaissance node is connected to the unmanned communication relay node, and the drone reconnaissance node feeds back the reconnaissance data to the emergency command system via the unmanned communication relay node; the drone control console is connected to the drone reconnaissance node, and the drone control console controls the drone to fly to the drone reconnaissance node; the ground receiving station is connected to the emergency command system, and the emergency command system transmits the reconnaissance data to the ground receiving station; the ground receiving station is connected to the data processing and analysis library, and calls the scene historical data in the data processing and analysis library for further processing and analysis.

[0052] Extract key feature data based on scene historical data to form a data relationship between unmanned communication relay node data changes and key feature data;

[0053] The scene history data includes:

[0054] Historical records data in different scenarios;

[0055] The different scenarios include: fire scenario, query scenario and traffic scenario; the fire scenario refers to the scenario data when a fire occurs in an urban area; the query scenario refers to the scenario data when searching for and monitoring people or objects in an urban area; the traffic scenario refers to the scenario data when a major traffic accident occurs in an urban area or when traffic is congested during peak travel;

[0056] The scene historical data includes the data source point, time range, scene diffusion radius and urban area location; the data source point refers to the initial target point when the scene data occurs; the time range refers to the time interval when the scene data occurs, each day is divided into 24 time intervals, and each interval corresponds to a full hour; the scene diffusion radius refers to the straight-line distance between the farthest point of the scene's influence and the data source point in each time period; the urban area location includes complex urban areas and simple urban areas, which are divided according to the building density in the area, and are randomly divided into several areas of the same area in the urban area. The building density in each area is calculated, and a threshold is set. Areas with building density exceeding the threshold are recorded as complex urban areas, and areas that do not exceed the threshold are recorded as simple urban areas.

[0057] The key feature data refers to the data source point, time range, scene diffusion radius and urban location; the key feature data in the emergency scene is obtained, and the training data is retrieved from the scene historical data. The retrieval method includes:

[0058] In the same scenario, based on the data source point, time range, and urban location in the key feature data of the emergency scenario and the same number in the scene historical data, the scene historical data with all the same key features are selected first, followed by the scene historical data with two identical key features, and finally the scene historical data with one identical key feature. The selection priority is that the data source point is higher than the urban location, and the urban location is higher than the time range. When the number of training data reaches the number threshold set by the system, the selection is stopped and all the selected scene historical data are output as training data;

[0059] For each set of training data, the time period, the scene diffusion radius corresponding to the time period, and the data change of the unmanned communication relay node corresponding to the scene diffusion radius are calibrated to form a data combination. , ,in, Respectively represent time period, The scene diffusion radius corresponding to the time period and the scene diffusion radius Data volume of unmanned communication relay nodes under ; Represents the diffusion radius of the data source point in the scene based on the current group of training data The number of road intersections below;

[0060] For example, if the time period is 30 seconds, the first time period is the first 30 seconds. Taking fire as an example, the data source point of the fire alarm refers to the fire point. When calculating the scene diffusion radius, the farthest point affected by the fire is taken as the point on the circumference to calculate the scene diffusion radius. After calculating the scene diffusion radius, take the data source point as the center of the circle and form an area according to the scene diffusion radius. The number of road intersections in the area is recorded as At this time, each road intersection should be dispatched to monitor the drone, and the total amount of communication feedback data generated by each drone is recorded as ;

[0061] Data combination based on all training data , forming the basic data column ,in Represents the average value of the scene diffusion radius in each time period, and N represents the maximum number of time periods, where:

[0062]

[0063] in, represent In any of the above, i ranges from 1 to N, which refers to the time period sequence number; M represents the number of data sets of training data; h represents the sequence number, represents the scene diffusion radius of the hth group of training data in the i-th time period;

[0064] The basic data column is processed by gray accumulation to form a gray data column. After the gray data column is processed by adjacent mean value, the adjacent mean data column is formed. The gray data column and the adjacent mean data column are combined and the gray prediction algorithm is used to form the relationship function between the scene diffusion radius and the time period:

[0065]

[0066] Where, e represents the natural logarithm; Refers to the average value of the generated scene diffusion radius; Refers to the development coefficient and grey action in the whitening differential equation in the grey data column; the average value of the generated scene diffusion radius is fed back to the system as the predicted value of the corresponding time period.

[0067] Second data combination based on all training data , forming a periodic change over time and The linear fitting equation between ,in , Respectively represent the parameter term and the constant term of the fitting equation, and the fitting equation is formed by:

[0068] Take each time period ,by As the horizontal axis, As the ordinate, the scattered points of the same set of training data are formed in the coordinate system for linear fitting;

[0069] Linear fitting is performed on all training data to form M groups of fitting equation lines. According to the key feature data of the emergency scenario, the scene diffusion radius of each time period in the emergency scenario is inferred. Based on the data source points in the emergency scenario and the inferred scene diffusion radius of each time period, the number of road intersections in each time period is circled on the urban map;

[0070] Substitute the number of road intersections in each time period into the fitting equation line, calculate M fitting results, select the mode from the M fitting results as the output result, if there is no mode, calculate the average value as the output result; if there are multiple modes, calculate the average value of the multiple modes as the output result;

[0071] The output result is used as the predicted data volume of the unmanned communication relay node in each time period. Based on the data capacity threshold of the drone communication relay node under the scene data, if the predicted data volume of the unmanned communication relay node in any time period exceeds the data capacity threshold of the drone communication relay node, the previous time period is added as the time information of the unmanned communication relay node, and the new drone is controlled to establish a new unmanned communication relay node before the time information.

[0072] In the second embodiment, a scenario-based UAV control data analysis system is provided, which includes: an emergency command module, a scenario history data storage module, a communication relay module, and a control analysis module;

[0073] The emergency command module is used to build a scenario-based UAV emergency command platform, mobilize and command the scenario-based UAV emergency command platform when facing an emergency scenario, and build UAV reconnaissance, communication and control; the scenario history data storage module is used to store scenario history data; the communication relay module is used to extract key feature data based on scenario history data, and form a data relationship between the data change of the unmanned communication relay node and the key feature data; at the same time, according to the data relationship, analyze the time information of adding the unmanned communication relay node, and build the UAV control strategy under the scenario data; the control analysis module is used to feed back the formed UAV control strategy to the emergency command system, and make plan processing in advance;

[0074] The output end of the emergency command module is connected to the input end of the scene history data storage module; the output end of the scene history data storage module is connected to the input end of the communication relay module; the output end of the communication relay module is connected to the input end of the control analysis module.

[0075] The emergency command module includes a scenario-based UAV emergency command unit and an emergency scenario dispatch unit;

[0076] The scenario-based UAV emergency command unit constructs a scenario-based UAV emergency command platform; the emergency scenario dispatching unit is used to mobilize and command the scenario-based UAV emergency command platform when facing an emergency scenario, and construct the reconnaissance, communication and control of the UAV;

[0077] The output end of the scenario-based UAV emergency command unit is connected to the input end of the emergency scenario scheduling unit.

[0078] The communication relay module includes a feature data processing unit and a strategy unit;

[0079] The feature data processing unit is used to extract key feature data according to the scene historical data, and form a data relationship between the data change of the unmanned communication relay node and the key feature data; the strategy unit is used to analyze the time information of adding the unmanned communication relay node according to the data relationship, and construct the drone control strategy under the scene data;

[0080] The output end of the feature data processing unit is connected to the input end of the strategy unit.

[0081] The control and analysis module includes a data feedback unit and a plan processing unit;

[0082] The data feedback unit is used to obtain the drone control strategy and feed it back to the emergency command system, and the plan processing unit is used to remind the management personnel to deploy the plan and prepare the plan in advance;

[0083] The output end of the data feedback unit is connected to the input end of the plan processing unit.

[0084] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0085] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A scenario-based UAV control data analysis method, characterized by: The method comprises the following steps: S1. Build a scenario-based UAV emergency command platform and obtain scenario historical data based on the scenario-based UAV emergency command platform; S2. Extract key feature data based on scene historical data to form a data relationship between unmanned communication relay node data changes and key feature data; S3. Analyze the time information of adding unmanned communication relay nodes according to the data relationship and build the UAV control strategy under the scenario data; S4. Feedback the formed UAV control strategy to the emergency command system and prepare the emergency plan in advance; The scenario-based UAV emergency command platform includes: UAV reconnaissance nodes, unmanned communication relay nodes, emergency command systems, UAV control consoles, ground receiving stations, and data processing and analysis libraries; Among them, the drone reconnaissance node is connected to the unmanned communication relay node, and the drone reconnaissance node feeds back the reconnaissance data to the emergency command system via the unmanned communication relay node; the drone control console is connected to the drone reconnaissance node, and the drone control console controls the drone to fly to the drone reconnaissance node; the ground receiving station is connected to the emergency command system, and the emergency command system transmits the reconnaissance data to the ground receiving station; the ground receiving station is connected to the data processing and analysis library, and calls the scene history data in the data processing and analysis library for further processing and analysis; The scene history data includes: Historical records data in different scenarios; The different scenarios include: fire scenario, query scenario and traffic scenario; the fire scenario refers to the scenario data when a fire occurs in an urban area; the query scenario refers to the scenario data when searching for and monitoring people or objects in an urban area; the traffic scenario refers to the scenario data when a major traffic accident occurs in an urban area or when traffic is congested during peak travel; The scene history data includes data source point, time range, scene diffusion radius and urban area location; the data source point refers to the initial target point when the scene data occurs; the time range refers to the time interval when the scene data occurs, each day is divided into 24 time intervals, each interval corresponds to a full hour; the scene diffusion radius refers to the straight-line distance between the farthest point of the scene influence and the data source point in each time period; the urban area location includes complex urban areas and simple urban areas, which are divided according to the building density in the area, and are randomly divided into several areas of the same area in the urban area. The building density in each area is calculated, and a threshold is set. The building density exceeding the threshold is recorded as a complex urban area, and the building density not exceeding the threshold is recorded as a simple urban area; In steps S2-S3, it also includes: The key feature data refers to the data source point, time range, scene diffusion radius and urban location; the key feature data in the emergency scene is obtained, and the training data is retrieved from the scene historical data. The retrieval method includes: In the same scenario, based on the data source point, time range, and urban location in the key feature data of the emergency scenario and the same number in the scene historical data, the scene historical data with all the same key features are selected first, followed by the scene historical data with two identical key features, and finally the scene historical data with one identical key feature. The selection priority is that the data source point is higher than the urban location, and the urban location is higher than the time range. When the number of training data reaches the number threshold set by the system, the selection is stopped and all the selected scene historical data are output as training data; For each set of training data, the time period, the scene diffusion radius corresponding to the time period, and the data change of the unmanned communication relay node corresponding to the scene diffusion radius are calibrated to form a data combination [t0, R0], [W0, S0], where t0, R0 and S0 represent the t0th time period, the scene diffusion radius corresponding to the t0th time period, and the amount of unmanned communication relay node data S0 under the scene diffusion radius R0, respectively; W0 represents the number of road intersections under the scene diffusion radius R0 of the data source point based on the current set of training data; Based on the data combination [t0, R0] of all training data, the basic data column [Y1, Y2, ..., Y N ], where Y1, Y2, …, Y N Represents the average value of the scene diffusion radius in each time period, and N represents the maximum number of time periods, where: Among them, Y i represents Y1, Y2, ..., Y N In any of the above, i ranges from 1 to N, which refers to the time period sequence number; M represents the number of training data sets; h represents the sequence number, R h represents the scene diffusion radius of the hth group of training data in the i-th time period; The basic data column is processed by gray accumulation to form a gray data column. After the gray data column is processed by adjacent mean value, the adjacent mean data column is formed. The gray data column and the adjacent mean data column are combined and the gray prediction algorithm is used to form the relationship function between the scene diffusion radius and the time period: Where, e represents the natural logarithm; Y N+1 Refers to the average value of the generated scene diffusion radius; μ and σ refer to the development coefficient and gray action in the whitening differential equation in the gray data column; the average value of the generated scene diffusion radius is used as the prediction value for the corresponding time period and fed back to the system.

2. The scenario-based UAV control data analysis method according to claim 1, characterized in that: Also includes: Based on the second data combination [W0, S0] of all training data, a linear fitting equation between W0 and S0 that changes with the time period is formed, S0=k0*W0+b0, where k0 and b0 represent the parameter term and the constant term of the fitting equation respectively, and the fitting equation formation includes: Take [W0, S0] in each time period, use W0 as the horizontal coordinate and S0 as the vertical coordinate, and form scattered points of the same group of training data in the coordinate system for linear fitting; Linear fitting is performed on all training data to form M groups of fitting equation lines. According to the key feature data of the emergency scenario, the scene diffusion radius of each time period in the emergency scenario is inferred. Based on the data source points in the emergency scenario and the inferred scene diffusion radius of each time period, the number of road intersections in each time period is circled on the urban map; Substitute the number of road intersections in each time period into the fitting equation line, calculate M fitting results, select the mode from the M fitting results as the output result, if there is no mode, calculate the average value as the output result; if there are multiple modes, calculate the average value of the multiple modes as the output result; The output result is used as the predicted data volume of the unmanned communication relay node in each time period. Based on the data capacity threshold of the drone communication relay node under the scene data, if the predicted data volume of the unmanned communication relay node in any time period exceeds the data capacity threshold of the drone communication relay node, the previous time period is added as the time information of the unmanned communication relay node, and the new drone is controlled to establish a new unmanned communication relay node before the time information.

3. A scenario-based UAV control data analysis system, used to implement the scenario-based UAV control data analysis method according to claim 1, characterized in that: The system includes: an emergency command module, a scene history data storage module, a communication relay module and a control analysis module; The emergency command module is used to build a scenario-based UAV emergency command platform, mobilize and command the scenario-based UAV emergency command platform when facing an emergency scenario, and build UAV reconnaissance, communication and control; the scenario history data storage module is used to store scenario history data; the communication relay module is used to extract key feature data based on scenario history data, and form a data relationship between the data change of the unmanned communication relay node and the key feature data; at the same time, according to the data relationship, analyze the time information of adding the unmanned communication relay node, and build the UAV control strategy under the scenario data; the control analysis module is used to feed back the formed UAV control strategy to the emergency command system, and make plan processing in advance; The output end of the emergency command module is connected to the input end of the scene history data storage module; the output end of the scene history data storage module is connected to the input end of the communication relay module; the output end of the communication relay module is connected to the input end of the control analysis module.

4. The scenario-based UAV control data analysis system according to claim 3 is characterized by: The emergency command module includes a scenario-based UAV emergency command unit and an emergency scenario dispatch unit; The scenario-based UAV emergency command unit constructs a scenario-based UAV emergency command platform; the emergency scenario dispatching unit is used to mobilize and command the scenario-based UAV emergency command platform when facing an emergency scenario, and construct the reconnaissance, communication and control of the UAV; The output end of the scenario-based UAV emergency command unit is connected to the input end of the emergency scenario scheduling unit.

5. The scenario-based UAV control data analysis system according to claim 3 is characterized by: The communication relay module includes a feature data processing unit and a strategy unit; The feature data processing unit is used to extract key feature data according to the scene historical data, and form a data relationship between the data change of the unmanned communication relay node and the key feature data; the strategy unit is used to analyze the time information of adding the unmanned communication relay node according to the data relationship, and construct the drone control strategy under the scene data; The output end of the feature data processing unit is connected to the input end of the strategy unit.

6. The scenario-based UAV control data analysis system according to claim 3 is characterized by: The control and analysis module includes a data feedback unit and a plan processing unit; The data feedback unit is used to obtain the drone control strategy and feed it back to the emergency command system, and the plan processing unit is used to remind the management personnel to deploy the plan and prepare the plan in advance; The output end of the data feedback unit is connected to the input end of the plan processing unit.